数字图像及视频修复方法研究
|
摘要
数字图像(视频)修复是通过从图像(视频)的完好区域提取有效信息,填补图像(视频)中丢失信息的过程。数字图像(视频)修复技术与复原技术不同,图像修复的目的不要求修复结果还原缺损图像的本来面目,而是要求修复结果保证良好的视觉观赏性,并且在观察者没有见过原图的情况下不能察觉出图像内容经过改动。相对图像的恢复、增强、去噪等技术,图像修复技术因为其在操作上具有高度的自由性并带有一定的娱乐性,在图像处理领域成为备受瞩目的应用技术。数字图像修复技术是数字图像处理的一个新兴领域,也是当前计算机视觉领域研究的一个热点问题。随着数字图像处理技术的不断进步,图像修复技术已经成为了文物保护、照片修复、特效制作、视频固化信息去除等应用领域中不可缺少的技术。由于图像的种类繁多,缺损区域的千差万别,所以修复的方法侧重点各有不同。相对于国外研究的蓬勃发展,国内在数字图像修复和数字视频修复领域中研究起步较晚,其理论及技术水平亟待提高。
本文在介绍数字图像修复技术研究背景,深入分析现有图像修复方法的基础上,结合目前图像处理发展的最新理论,针对图像中的固化字幕信息的检测、小面积缺损图像修复、大面积缺损图像修复和视频修复等问题提出了一系列的新方法。本文的主要研究成果如下：
1.字幕修复区域自动检测方法研究
目前的图像以及视频修复方法都需要人工指定修复区域,而在各种图像和视频修复任务中,图像和视频中的文字去除一直是备受关注的应用,而手工标定所有的图像文字区域不但费时费力而且容易出错。为了自动定位图像和视频上的文字区域作为图像修复和视频修复的目标区域。本文提出了一种基于稀疏表示分类字典和多尺度几何分析的图像文字检测方法。这种方法首先通过多尺度几何分析得到图像文字的候选边缘,然后借助基于分类字典的稀疏表示完成文字的检测。一系列的实验验证了这种文字检测方法不仅能够准确的提取照片和视频中的人工字幕,为图像和视频修复提供高质量的修复目标区域；而且还能在各种复杂环境中提取嵌入场景之中的文字,不受文字颜色、大小、纹理、语言‘和光照强度的限制,具有较好的鲁棒性和较高地准确性。
2.小面积缺损图像修复方法研究
稀疏表示是图像处理和信号处理中的重要理论和重点研究方向,受到了国内外图像处理界的广泛关注。我们在现有稀疏表示图像修复框架的基础上提出了一种基于图像源区域字典的稀疏表示图像修复方法。利用图像源区域字典生成方便,并且能够携带目标图像信息的特点有效地克服了以往固定字典修复方法和机器学习字典修复方法的不足,使得稀疏表示图像修复方法的效果有了显著增强。而后针对现有图像修复方法无法高效地修复包含纹理的小面积缺损图像的问题,本文提出了结合各向同性扩散修复和稀疏表示修复的混合图像修复方法,首先充分考虑到扩散修复和基于图像源区域稀疏表示修复的互补性,通过简单而有效地纹理分析算法将待修复区域划分为光滑部分和复杂部分。然后使用各向同性扩散的修复方法修复光滑部分,用基于稀疏表示的修复方法修复复杂部分。最后将两种修复方法的修复结果结合起来得到最终的修复结果。理论分析和实验结果表明,混合修复方法无论在修复结果的观赏性或修复方法的处理速度上都要优于现有的扩散类图像修复算法。在这一章的最后我们分析了稀疏表示图像修复的局限性,即稀疏表示图像修复方法因为其求解误差的关系不适合大面积缺损图像的修复。
3.大面积缺损图像修复方法研究
在补全大面积缺损图像的问题中,保证缺损结构的完整性和一致性是得到良好修复结果的关键。在分析了现有基于纹理合成的图像修复方法容易产生结构误差的原因以及叙述了人类视觉在感知图像缺损和自动填充的机制之后,针对大面积缺损图像的修复问题,本文提出了一种基于图像缺损结构线补全的图像修复方法。不同于现有修复算法通过修复顺序来补全图像缺损结构的做法,该方法考虑了图像结构完整的重要性,充分利用缺损结构的信息来保证修复结果结构的完整性。首先通过多尺度几何分析找出缺损的结构线,然后根据缺损结构线的颜色、纹理和曲率信息将它们配对并通过曲线拟合加以补全。这样不仅保证了图像结构的完整性而且使得修复的结构有较好的视觉效果。此外考虑到修复的结构线将缺损区域分割成了几个子区域,在进行纹理修复时可以逐个地对每个子区域进行纹理填充,这样不但加快了处理速度,而且提高了纹理填充的质量。大量的修复结果和对比实验证明本文提出基于图像缺损结构线补全的图像修复方法比现有方法更好地保证了修复结果图像的完整性,并且修复结果有很高的视觉质量。
4.视频修复方法研究
视频修复是图像修复的延续,也是图像修复技术重要的研究和应用领域。针对视频修复中的不同应用本文提出了两种视频修复算法。一个是针对视频中的台标字幕等固化修复区域的基于三维泊松方程的视频修复方法；另一个是针对视频中的物体缺损的基于前景运动目标运动周期的视频修复方法。在三维泊松方程图像修复方法中,本文首先计算所有视频帧的梯度场,然后填补梯度场中的缺失信息,最后通过求解三维泊松方程完成视频修复,这样充分保证了修复视频在时间域上的连续性。在基于前景运动目标运动周期的视频修复方法中,本文对视频修复问题提出了一个观点,即视频修复技术应该是一种遮掩视频待修复区域的技术,因此视频修复技术可以根据实际需要在满足观察者视觉感官的同时对视频的部分内容进行编排和对视频帧的数量进行适当的变更。在这一观点的指导下,我们根据视频中完好的信息提取出前景目标运动的规律,然后依照运动的规律对视频的缺损部分的运动状态进行预测,最后根据这些预测完成视频缺损部分的修复。理论分析和实验证明我们的视频修复方法不但使修复结果自然并且有良好的视觉连续性,而且消耗的处理时间也少于现有方法。
The digital image or video inpainting technique aims to fill missing pixels in unknown regions of an image or video in visually plausible way by utilizing the information from the un-missing region. Different from the image restoration, the digital inpainting technique does not request the result to reappear the original image. Its objective is to conceal the missing or damage parts of the images or videos and restore it in a unity way that is non-detectable for an observer who does not know the original image. Along with the popularity of the mobile image and video acquisition devices, the requisite for the advanced image processing technique of people is increasing dramatical. Compared with the image restoration, image enhancement and image denoising technology, the inpainting technology possesses high operating freedom and it becomes a high-profile technology in the digital image processing field. Digital image inpainting is not only an emerging technique, but also a hot issue in the image processing and computer vision research. With the development of inpainting technique, it has found broad applications in heritage conservation, photo restoration, special effects, and errors conceal in videos, disocclusion in computer in computer vision and so on. However, due to a wide variety of images and videos and missing regions, the digital inpainting methods are also varied.
This dissertation attempts to research on image inpainting and video inpainting techniques as well as their applications, according to the analysis of the traditional inpainting algorithm and the existed image processing theory. In this dissertation, a series of methods have been proposed for the detection of caption text in image and video, the small textural missing region restore of image, the large scale missing completion of image and video inpainting problem. The main contributions of this dissertation are as follows:
1. The research of superimposed text detection in images and videos
Today, more superimposed texts are embedded within images and videos. Usually some texts are unnecessary. Thus, many applications require an approach to remove the text and complete the video. Moreover, the current image and video restoration methods need to specify the inpainting target area by the human intervention. The manually marking of the superimposed text at the image or video is not only time-consuming but also unreliable. To automatically locate the superimposed text and provide the target region for the inpainting algorithm, this dissertation proposes a classification-based algorithm for text detection using a sparse representation with discriminative dictionaries. First, the edges are detected by the wavelet transform and scanned into patches by a sliding window. Then, candidate text areas are obtained by applying a classification procedure using two learned discriminative dictionaries. Finally, the adaptive run-length smoothing algorithm and projection profile analysis are used to further refine the candidate text areas. The proposed method is evaluated on a large number of images and video frames. The various experiments shows that the proposed text detection method not only accurately extracts the artificial subtitles of photos and videos as target area for the image and video inpainting but also allows robust text detection.
2. The research of small scale textural missing image inpainting
Sparse representation is a theory and research focus in the image processing and signal processing. It is a novel signal representation theory in succession to the multiresolution transforms such as wavelet and curvelet. Compared to the traditional multiresolution transforms, the sparse representation is closer to the human visual characteristics. In the image inpainting field, this dissertation first proposes an improved sparse representation inpainting approach based on source image dictionary according to the framework of the classical sparse representation inpainting method. By considering the defects of predefined or learned dictionary sparse representation inpainting, this dissertation use a source image dictionary to replace the traditional dictionary, which makes sparse representation inpainting approach more effective. Then to handle the small scale textural missing image inpainting problem, a effective inpainting method is proposed, which combines fast inpainting method and source image dictionary based sparse representation inpainting method. A texture distribution analysis algorithm divides the missing area into homogeneous region and inhomogeneous region. Then the fast inpainting method restores the homogeneous region and sparse representation inpainting method recovers the inhomogeneous region. The proposed method fully considers the complementary between the fast inpainting method and sparse representation inpainting approach. In this manner, the hybrid inpainting method inpaints the small size textural missing image more effectively than the available inpainting method.
3. The research of large scale missing image inpainting
In the large scale missing image inpainting field, ensuring the integrity and consistency of damaged structure is the key to obtain good results of inpainting. At the beginning of Chapters4, this dissertation analyzes the defect of existing texture synthesis based image inpainting method and the human visual perception in image missing detection and filling. Then the idea of large scale inpainting method is proposed.
Inspired by human visual characteristics, a new image inpainting approach which includes salient structure completion and texture propagation is introduced. In the salient structure completion step, incomplete salient structures are detected using wavelet transform, and completion order is determined through color texture and curvature features around the incomplete salient structures. Afterwards, curve fitting and extension are used to complete the incomplete salient structures. In the texture propagation step, the completed salient structures divide the target area into several sub-regions. The texture propagation is used to synthesize the texture information with samples from the corresponding adjacent sub-regions. This reduces the running-time and offers more precise texture information. A number of examples on real and synthetic images demonstrate the effectiveness of our algorithm in removing occluding objects. The experimental results compare favorably to those obtained by existing inpainting techniques.
4. The research of video inpainting method
Video inpainting is a continuation of the image inpainting technique. It is an important part and application of inpainting technique. To deal with the main issues of video inpainting:fixed information removing and motion object repairing, this dissertation proposes two different video inpainting methods. One is the video inpainting based on three-dimensional Poisson equation to remove the fixed information of videos. The other is foreground replacement based video inpainting via motion cycle detection method to handle the motion object repairing problem.
In the three-dimensional Poisson equation video inpainting method, firstly, the gradient fields of video frame are extracted. Then, the target area of every gradient field is filled through patch-by-patch inpainting method. Afterwards, to repair the video, a three-dimensional Poisson equation is built and solved in the gradient field of the target area. The experimental results show that the three-dimensional Poisson equation video inpainting method can achieve desired results and perform better than existed methods in the colors, light and shade consistency.
In the motion object repairing issue, the challenge of video inpainting is how to complete the damaged moving foreground objects in the spatiotemporal domain. Therefore, this dissertation presents a novel foreground-background inpainting method for completing missing information based on object motion analysis. In the foreground replacement based video inpainting via motion cycle detection method, the foreground in the video is firstly separated from the background. As for background inpainting, we use spatiotemporal copy method. In the foreground inpainting stage, a motion cycle of the moving object is detected using skeleton similarity. After that the damaged foreground object is directly replaced by corresponding undamaged foreground in the motion cycle. The proposed method is useful for a variety of tasks, including, static and translation camera motion and large object movement, moving target region and variation background.
Finally, the dissertation summarizes the main contribution, innovative research achievements and the future work.
本文在介绍数字图像修复技术研究背景,深入分析现有图像修复方法的基础上,结合目前图像处理发展的最新理论,针对图像中的固化字幕信息的检测、小面积缺损图像修复、大面积缺损图像修复和视频修复等问题提出了一系列的新方法。本文的主要研究成果如下：
1.字幕修复区域自动检测方法研究
目前的图像以及视频修复方法都需要人工指定修复区域,而在各种图像和视频修复任务中,图像和视频中的文字去除一直是备受关注的应用,而手工标定所有的图像文字区域不但费时费力而且容易出错。为了自动定位图像和视频上的文字区域作为图像修复和视频修复的目标区域。本文提出了一种基于稀疏表示分类字典和多尺度几何分析的图像文字检测方法。这种方法首先通过多尺度几何分析得到图像文字的候选边缘,然后借助基于分类字典的稀疏表示完成文字的检测。一系列的实验验证了这种文字检测方法不仅能够准确的提取照片和视频中的人工字幕,为图像和视频修复提供高质量的修复目标区域；而且还能在各种复杂环境中提取嵌入场景之中的文字,不受文字颜色、大小、纹理、语言‘和光照强度的限制,具有较好的鲁棒性和较高地准确性。
2.小面积缺损图像修复方法研究
稀疏表示是图像处理和信号处理中的重要理论和重点研究方向,受到了国内外图像处理界的广泛关注。我们在现有稀疏表示图像修复框架的基础上提出了一种基于图像源区域字典的稀疏表示图像修复方法。利用图像源区域字典生成方便,并且能够携带目标图像信息的特点有效地克服了以往固定字典修复方法和机器学习字典修复方法的不足,使得稀疏表示图像修复方法的效果有了显著增强。而后针对现有图像修复方法无法高效地修复包含纹理的小面积缺损图像的问题,本文提出了结合各向同性扩散修复和稀疏表示修复的混合图像修复方法,首先充分考虑到扩散修复和基于图像源区域稀疏表示修复的互补性,通过简单而有效地纹理分析算法将待修复区域划分为光滑部分和复杂部分。然后使用各向同性扩散的修复方法修复光滑部分,用基于稀疏表示的修复方法修复复杂部分。最后将两种修复方法的修复结果结合起来得到最终的修复结果。理论分析和实验结果表明,混合修复方法无论在修复结果的观赏性或修复方法的处理速度上都要优于现有的扩散类图像修复算法。在这一章的最后我们分析了稀疏表示图像修复的局限性,即稀疏表示图像修复方法因为其求解误差的关系不适合大面积缺损图像的修复。
3.大面积缺损图像修复方法研究
在补全大面积缺损图像的问题中,保证缺损结构的完整性和一致性是得到良好修复结果的关键。在分析了现有基于纹理合成的图像修复方法容易产生结构误差的原因以及叙述了人类视觉在感知图像缺损和自动填充的机制之后,针对大面积缺损图像的修复问题,本文提出了一种基于图像缺损结构线补全的图像修复方法。不同于现有修复算法通过修复顺序来补全图像缺损结构的做法,该方法考虑了图像结构完整的重要性,充分利用缺损结构的信息来保证修复结果结构的完整性。首先通过多尺度几何分析找出缺损的结构线,然后根据缺损结构线的颜色、纹理和曲率信息将它们配对并通过曲线拟合加以补全。这样不仅保证了图像结构的完整性而且使得修复的结构有较好的视觉效果。此外考虑到修复的结构线将缺损区域分割成了几个子区域,在进行纹理修复时可以逐个地对每个子区域进行纹理填充,这样不但加快了处理速度,而且提高了纹理填充的质量。大量的修复结果和对比实验证明本文提出基于图像缺损结构线补全的图像修复方法比现有方法更好地保证了修复结果图像的完整性,并且修复结果有很高的视觉质量。
4.视频修复方法研究
视频修复是图像修复的延续,也是图像修复技术重要的研究和应用领域。针对视频修复中的不同应用本文提出了两种视频修复算法。一个是针对视频中的台标字幕等固化修复区域的基于三维泊松方程的视频修复方法；另一个是针对视频中的物体缺损的基于前景运动目标运动周期的视频修复方法。在三维泊松方程图像修复方法中,本文首先计算所有视频帧的梯度场,然后填补梯度场中的缺失信息,最后通过求解三维泊松方程完成视频修复,这样充分保证了修复视频在时间域上的连续性。在基于前景运动目标运动周期的视频修复方法中,本文对视频修复问题提出了一个观点,即视频修复技术应该是一种遮掩视频待修复区域的技术,因此视频修复技术可以根据实际需要在满足观察者视觉感官的同时对视频的部分内容进行编排和对视频帧的数量进行适当的变更。在这一观点的指导下,我们根据视频中完好的信息提取出前景目标运动的规律,然后依照运动的规律对视频的缺损部分的运动状态进行预测,最后根据这些预测完成视频缺损部分的修复。理论分析和实验证明我们的视频修复方法不但使修复结果自然并且有良好的视觉连续性,而且消耗的处理时间也少于现有方法。
The digital image or video inpainting technique aims to fill missing pixels in unknown regions of an image or video in visually plausible way by utilizing the information from the un-missing region. Different from the image restoration, the digital inpainting technique does not request the result to reappear the original image. Its objective is to conceal the missing or damage parts of the images or videos and restore it in a unity way that is non-detectable for an observer who does not know the original image. Along with the popularity of the mobile image and video acquisition devices, the requisite for the advanced image processing technique of people is increasing dramatical. Compared with the image restoration, image enhancement and image denoising technology, the inpainting technology possesses high operating freedom and it becomes a high-profile technology in the digital image processing field. Digital image inpainting is not only an emerging technique, but also a hot issue in the image processing and computer vision research. With the development of inpainting technique, it has found broad applications in heritage conservation, photo restoration, special effects, and errors conceal in videos, disocclusion in computer in computer vision and so on. However, due to a wide variety of images and videos and missing regions, the digital inpainting methods are also varied.
This dissertation attempts to research on image inpainting and video inpainting techniques as well as their applications, according to the analysis of the traditional inpainting algorithm and the existed image processing theory. In this dissertation, a series of methods have been proposed for the detection of caption text in image and video, the small textural missing region restore of image, the large scale missing completion of image and video inpainting problem. The main contributions of this dissertation are as follows:
1. The research of superimposed text detection in images and videos
Today, more superimposed texts are embedded within images and videos. Usually some texts are unnecessary. Thus, many applications require an approach to remove the text and complete the video. Moreover, the current image and video restoration methods need to specify the inpainting target area by the human intervention. The manually marking of the superimposed text at the image or video is not only time-consuming but also unreliable. To automatically locate the superimposed text and provide the target region for the inpainting algorithm, this dissertation proposes a classification-based algorithm for text detection using a sparse representation with discriminative dictionaries. First, the edges are detected by the wavelet transform and scanned into patches by a sliding window. Then, candidate text areas are obtained by applying a classification procedure using two learned discriminative dictionaries. Finally, the adaptive run-length smoothing algorithm and projection profile analysis are used to further refine the candidate text areas. The proposed method is evaluated on a large number of images and video frames. The various experiments shows that the proposed text detection method not only accurately extracts the artificial subtitles of photos and videos as target area for the image and video inpainting but also allows robust text detection.
2. The research of small scale textural missing image inpainting
Sparse representation is a theory and research focus in the image processing and signal processing. It is a novel signal representation theory in succession to the multiresolution transforms such as wavelet and curvelet. Compared to the traditional multiresolution transforms, the sparse representation is closer to the human visual characteristics. In the image inpainting field, this dissertation first proposes an improved sparse representation inpainting approach based on source image dictionary according to the framework of the classical sparse representation inpainting method. By considering the defects of predefined or learned dictionary sparse representation inpainting, this dissertation use a source image dictionary to replace the traditional dictionary, which makes sparse representation inpainting approach more effective. Then to handle the small scale textural missing image inpainting problem, a effective inpainting method is proposed, which combines fast inpainting method and source image dictionary based sparse representation inpainting method. A texture distribution analysis algorithm divides the missing area into homogeneous region and inhomogeneous region. Then the fast inpainting method restores the homogeneous region and sparse representation inpainting method recovers the inhomogeneous region. The proposed method fully considers the complementary between the fast inpainting method and sparse representation inpainting approach. In this manner, the hybrid inpainting method inpaints the small size textural missing image more effectively than the available inpainting method.
3. The research of large scale missing image inpainting
In the large scale missing image inpainting field, ensuring the integrity and consistency of damaged structure is the key to obtain good results of inpainting. At the beginning of Chapters4, this dissertation analyzes the defect of existing texture synthesis based image inpainting method and the human visual perception in image missing detection and filling. Then the idea of large scale inpainting method is proposed.
Inspired by human visual characteristics, a new image inpainting approach which includes salient structure completion and texture propagation is introduced. In the salient structure completion step, incomplete salient structures are detected using wavelet transform, and completion order is determined through color texture and curvature features around the incomplete salient structures. Afterwards, curve fitting and extension are used to complete the incomplete salient structures. In the texture propagation step, the completed salient structures divide the target area into several sub-regions. The texture propagation is used to synthesize the texture information with samples from the corresponding adjacent sub-regions. This reduces the running-time and offers more precise texture information. A number of examples on real and synthetic images demonstrate the effectiveness of our algorithm in removing occluding objects. The experimental results compare favorably to those obtained by existing inpainting techniques.
4. The research of video inpainting method
Video inpainting is a continuation of the image inpainting technique. It is an important part and application of inpainting technique. To deal with the main issues of video inpainting:fixed information removing and motion object repairing, this dissertation proposes two different video inpainting methods. One is the video inpainting based on three-dimensional Poisson equation to remove the fixed information of videos. The other is foreground replacement based video inpainting via motion cycle detection method to handle the motion object repairing problem.
In the three-dimensional Poisson equation video inpainting method, firstly, the gradient fields of video frame are extracted. Then, the target area of every gradient field is filled through patch-by-patch inpainting method. Afterwards, to repair the video, a three-dimensional Poisson equation is built and solved in the gradient field of the target area. The experimental results show that the three-dimensional Poisson equation video inpainting method can achieve desired results and perform better than existed methods in the colors, light and shade consistency.
In the motion object repairing issue, the challenge of video inpainting is how to complete the damaged moving foreground objects in the spatiotemporal domain. Therefore, this dissertation presents a novel foreground-background inpainting method for completing missing information based on object motion analysis. In the foreground replacement based video inpainting via motion cycle detection method, the foreground in the video is firstly separated from the background. As for background inpainting, we use spatiotemporal copy method. In the foreground inpainting stage, a motion cycle of the moving object is detected using skeleton similarity. After that the damaged foreground object is directly replaced by corresponding undamaged foreground in the motion cycle. The proposed method is useful for a variety of tasks, including, static and translation camera motion and large object movement, moving target region and variation background.
Finally, the dissertation summarizes the main contribution, innovative research achievements and the future work.
引文
[1]Forsyth D A, Ponce J. Computer vision:a modern approach. Prentice Hall Professional Technical Reference,2002
[2]Gonzalez R C, Woods R E. Digital image processing. Hall Professional Technical Reference,2002
[3]Granlund G H, Knutsson H. Signal processing for computer vision. Kluwer Academic Pub,1995
[4]张红英,彭启琮.数字图像修复技术综述.中国图像图形学报,2007,12(1)：1-10
[5]周廷方,汤锋,王进,王章野,彭群生.基于径向基函数的图像修复技术.中国图像图形学报,2004,9(10)：1-11
[6]Walden S. The ravished image. St.Martin's Press, New York,1985
[7]Emile-Male G. The restorer's handbook of easel painting. Van Nostrand Reinhold, New York,1976
[8]Bertalmio M, Sapiro G, Caselles V, Ballester C. Image inpainting. In:Proc of SIGGRAPH'00,2000,417-424
[9]卢小宝,王维兰.基于样本块的破损唐卡图像修复算法的改进.计算机应用,2010,22(4)：32-36
[10]鲁东明,潘云鹤,陈任.敦煌石窟虚拟重现与壁画修复模拟.测绘学报,2002,31(1)：12-16
[11]Tauber Z, Li Z N, Drew M S. Review and preview:disocclusion by inpainting for image-based rendering. IEEE Transatcion on Systems, Man, and Cybernetics, Part C:Applications and Reviews,2007,37(4):527-540
[12]King D. The commissar vanishes. Henry Holt and Company,1997
[13]Chan T F, Shen J. Mathematical models for local nontexture inpaintings. SIAM Journal on Applied Mathematics,2001,62(3):1019-1043
[14]Chan T F, and Shen J. Non-texture inpainting by curvature driven diffusion. Journal of Visual Communication and Image Representation,2001, 12(4):436-449
[15]Ballester C, Bertalmio M, Caselles V, Sapiro G, Verdera J. Fillingin by join interpolation of vector fields and grey levels. IEEE Transatcion on Image Processing,2001,10(8):1200-1211
[16]Ambrosio L, Fusco N, Pallara D. Functions of bounded variations and free discontinuity problems. Oxford, U.K. Clarendon,2000
[17]Tsai A, Yezzi J A, Willsky A S. Curve evolution implementation of the Mumford-Shah functional for image segmentation, denoising, interpolation and magnification. IEEE Transatcion on Image Processing,2001,10(8):1169-1186
[18]Esedoglu S, Shen J H. Digital inpainting based on the Mumford-Shah-Euler image model. European Journal on Applied Mathematics,2002,13(4):353-370
[19]Oliveira M M, Bowen B, McKenna R, Chang Y S. Fast digital inpainting. In: Proc of International Conference on Visualization, Imaging and Image Processing, Marbella, Spain,2001,261-266
[20]Masnou S, Morel J M. Level lines based disoclussion. In:Proc of International Conference on Image Processing,1998,259-263
[21]张红英,彭启琮,吴亚东.数字破损图像的非线性各向异性扩散修补算法.计算机辅助设计与图形学学报,2006,18(10)：1541-1546
[22]张红英,彭启琮,吴亚东.基于p-Laplace算子的小波域图像修复模型.自动化学报,2008,34(8)：849-856
[23]Papandreou G, Maragos P, Kokaram A. Image inpainting with a wavelet domain hidden Markov tree model. In:Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing. Nevada,2008,773-776
[24]Besag J. On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society,1986,48(3):259-302
[25]Crouse M S, Nowak R D, Baraniuk R G. Wavelet-based statistical signal processing using hidden Markov models, IEEE Transatcion on Signal Processing, 1998,46(4):886-902
[26]Wei L Y, Levoy M. Fast texture synthesis using tree-structured vector quantization. In:Proc of SIGGRAPH'00,2000,479-488
[27]Criminisi A, Perez P, Toyama K. Region filling and object removal by exemplar-based inpainting. IEEE Transatcion on Image Processing,2004, 13(9):1200-1212
[28]Efros A A, Leung T K. Texture synthesis by non-parametric sampling. In:Proc the International Conference on Computer Vision,1999, pp.1033-1038
[29]Grossauer H. A combined PDE and texture synthesis approach to inpainting. In:Proc of European Conference on Computer Vision,2004,214-224
[30]Ignacio U A, Jung C R. Block-based image inpainting in the wavelet domain. The Visual Computer,2007,23(9-11):733-741
[31]Kang S H, Chan T F, Soatto S, Landmark based inpainting from multiple views. Univsersity Caifornia at Los Angeles, Los Angeles, Technique Report,2002, TR-CAM 02-11
[32]Cheng W H, Hsieh C W, Lin S K. Robust algorithm for exemplar-based image inpainting. In:Proc of the International Conference on Computer Graphics, Imaging Vision,2005,64-69
[33]Sun J, Yuan L, Jia J. Image completion with structure propagation. ACM Transatcion on Graphics,2005,24(3):861-868
[34]Komodakis N, Tziritas G. Image completion using efficient belief propagation via priority scheduling and dynamic pruning. IEEE Transatcion on Image Processing,2007,16 (11):2649-2661
[35]Hays J, Efros A A. Scene completion using millions of photographs. Communications of the ACM,2008,51(10):87-94
[36]Bertalmio M, Vesa L, Sapiro G, Osher S. Simultaneous structure and texture image inpainting. IEEE Transatcion on Image Processing,2003,12 (8):882-889
[37]Grossauer H. A combined PDE and texture synthesis approach to inpainting, In: Proc of European Conference on Computer Vision,2004,4,214-224
[38]Lai Y K, Hu S M, Gu D X, Martin R R. Geometry texture synthesis and transfer via geometry images. In:Proc of ACM Symposium on Solid and Physical Modeling,2005,15-26
[39]Jia J, Tang C K. Image repairing:robust image synthesis by adaptive and tensor voting. In:Proc of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2003,1,643-835
[40]Bertalmio M, Bertozzi A L, Sapiro G. Navier-stokes, fluid dynamics, and image and video inpainting. In:Proc of IEEE Computer Society Conference on Computer Vision Pattern Recognition,2001,1,355-362
[41]Yan W Q, Kankanhalli M S. Erasing video logos based on image inpainting. In: Proc of IEEE International Conference on Multimedia and Expo,2002,2, 521-524
[42]Patwardhan K A, Sapiro G, Bertalmio M. Video inpainting of occluding and occluded objects. In:Proc of IEEE International Conference of Image Processing,2005,2,69-72
[43]Kokaram A C, Godsill S J. Joint detection, interpolation, motion and parameter estimation for image sequences with missing data. In:Proc of IEEE International Conference on Image Processing,1997,2,191-194
[44]Tourapis A M, Cheong, H Y, Au O C, Liou M L. Temporal interpolation of video sequences using Zonal-based glgorithms. In:Proc of IEEE International Conference on Image Processing Greece,2001,895-898
[45]Wexler Y, Shechtman E, Irani M. Space-time completion of video, IEEE Transatcion on Pattern Analysis and Machine Intelligence,2007,29(3):463-476
[46]Jia Y T, Hu S M, Martin R R. Video completion using tracking and fragment merging. The Visual Computing,2005,21 (8):601-610
[47]Patwardhan K A, Sapiro G, Bertalmio M. Video inpainting of occluding and occluded objects. In:Proc of IEEE International Conference of Image Processing,2005,2,69-72
[48]Shih T K, Tang N C, Hwang J N. Exemplar-based video inpainting without ghost shadow artifacts by maintaining temporal continuity. IEEE Transatcion on Circuits and Systems for Video Technology,2009,19(3):347-360
[49]Shi W Z, Zhu C Q, Tian Y, Nichol J. Wavelet-based image fusion and quality assessment. International Journal of Applied Earth Observation and Geoinformation,2005,6(3-4):241-251
[50]Amano T. Correlation based image defect detection. In:Proc of International Conference on Pattern Recognition,2006,163-166
[51]Chang R C; Sie Y L; Chou S M; Shih T K. Photo defect detection for image inpainting. In:Proc of Seventh IEEE International Symposium on Multimedia, 2005,12-14
[52]王勇,郑辉,胡德文.图像和视频中的文字获取技术.中国图象图形学报,2004,9(5)：532-538
[53]王崇骏,杨育彬,陈世福.基于高层语义的图像检索算法.软件学报,2004,15(10)：1461-1469
[54]Khedekar S, Ramanaprasad V, Setlur S. Text-image separation in devanagari documents. In:Proc of the 7th International Conference on Document Analysis and Recognition,2003,1265-1269
[55]Lee K H, Choy Y C, Cho S. Geometric structure analysis of document image:a knowledge-based approach. IEEE Transatcion on Pattern Analysis and Machine Intelligence,2000,22(6):1224-1240
[56]Deng S L, Latifi H, Regentova E. Document segmentation using polynomial spline wavelets. Pattern Recognition,2001,34(12):2533-2545
[57]Jain A K. Bhattacharjee S. Text segmentation using gabor filters for automatic document processing. Machine Vision and Applications.5(3),1992:169-184
[58]Kubota K, Iwaki O, Arakawa H. Document understanding system. In:Proc of the 7th International Conference on Pattern Recognition,1984,612-614
[59]Fletcher L A, Kasturi R A. A Robust algorithm for text string separation from mixed text/graphic image. IEEE Transatcion on Pattern Recognition and Machine Intelligence,1998,10(6):910-918
[60]Byun H, Jang I, Choi Y. Text extraction in digital news video using morphology. Lecture Notes in Computer Science,2002,2423:341-352
[61]Granado I, Pina P, Muge F. Automatic feature extraction on pages of antique books through a mathematical morphology based methodology. Lecture Notes in Computer Science,2000,19(23):1-13
[62]Xiao Y, Yan H. Text extraction in document images based on delaunay triangulation. Pattern Recognition,2003,36(3):799-809
[63]Yuan Q, Tan C L. Text extraction from gray scale document images using edge information. In:Proc of the 6th International Conference on Document Analysis and Recognition,2001,302-306
[64]Wahl F M, Wong K Y, Casey R G. Block segmentation and text extraction in mixed text image documents. Computer Vision Graphics and Image Processing, 1982,2(6):375-390
[65]Strouthopoulos C, Papamarkos N, Chamazas N C. PLA using RLSA and a neural net work. Engineering Application Of Artificial Intelligence,1999, 12(2):119-138
[66]Wang D, Srihari S N. Classification of newsdissertation image blocks using texture analysis. Computer Vision. Graphics and Image Processing,1989, 47(3):327-352
[67]Viswanathan M, Nagy G. Characteristics of digitized images of technical articles. Machine Vision Applications in Character Recognition and Industrial Inspection, 1992,1661:6-17
[68]Ha J K, Haralick R M, Philips I R. Recursive X-Y cut using bounding boxes of connected components. In:Proc of 3rd International Conference on Document Analysis and Recognition,1995,952-955
[69]Ha J K, Haralick R M, Philips I R. Document page decomposition by the bounding box projection technique. In:Proc of 3rd International Conference on Document Analysis and Recognition,1995,1119-1122
[70]Cao Y, Wang S H, Li H. Skew detection and correction in document images based on straight-line fitting. Pattern Recognition Letters,2003, 24(12):1871-1879
[71]Fan K C, Wang L S. Classification of document blocks using density feature and connectivity histogram. Pattern Recognition Letters,1995,16(9):955-962
[72]Kruatrachue B, Suthaphan P. A Fast and efficient method for document segmentation for OCR. In:Proc of IEEE Region 10 International Conference on Electrical and Electronic Technology,2001,352-354
[73]林亚忠,赵晨光.纹理分割中的特征提取.中国医学物理学杂志,2001,18(4)：204-205
[74]Hua X S, Chen X R, Liu W Y. Automatic location of text in video frames. In: Proc of the 3rd International Workshop on Multimedia Information Retrieval, 2001,126-129
[75]Lyu M, Song J, Cai M. A comprehensive method for multilingual video text detection, localization and extraction. IEEE Transatcion on Circuits and Systems for Video Technology,2005,15 (2):243-255
[76]Jung C, Liu Q, Kim J. Accurate text localization in images based on SVM output scores, Image and Vision Computing,2009,27(9):1295-1301
[77]Chen D, Jean-Marc O, Herve B. Text detection and recognition in images and video frames. Pattern Recognition,2004,37(3):595-608
[78]Ye Q X, Huang Q M, Gao W, Zhao D B. Fast and robust text detection in images and video frames. Image and Vision Computing,2005,23(6):565-576.
[79]Anthimopoulos M, Gatos B, Pratikakis I. A two-stage scheme for text detection in video images. Image and Vision Computing,2010,28(9):1413-1426
[80]Shen H Y, Coughlan J, Ivanchenko V. Figure-ground segmentation using factor graphs. Image and Vision Computing,2009,27(7):854-863
[81]Lienhart R, Wernicke A. Localizing and segmenting text in images and videos. IEEE Transatcion on Circuits and Systems for Video Technology,2002, 12(4):256-268
[82]Mancas-Thillou C, Gosselin B. Color text extraction with selective metric-based clustering. Computer Vision and Image Understanding,2007,107(1-2):97-107
[83]Shivakumara P, Huang W H, Tan C L. Efficient video text detection using edge features. In:Proc of the 19th International Conference on Pattern Recognition, 2008,1-4
[84]Gllavata J. Ewerth R. B. Freisleben. Text detection in images based on unsupervised classification of high-frequency wavelet coefficients. In:Proc of the 17th International Conference on Pattern Recognition.2004.425-428
[85]Lienhart R. Automatic text recognition for video indexing. In:Proc of fourth ACM international conference on Multimedia,1996,11-20
[86]王惠锋,孙正兴,王箭.语义图像检索研究进展.计算机研究与发展,2002,39(05)：513-523
[87]Chen X, Zhang H J. Text area detection from video frames. In:Proc of Advances in Multimedia Information,2001,222-228
[88]Chang S F, Chen W, Meng H J, Sundaram H, Zhong D. VideoQ:an automatic content-based video search system using visual cues. In:Proc of the fifth ACM international conference on Multimedia,1997,313-324
[89]Mairal J, Bach F, Ponce J, Sapiro G, Zisserman A. Discriminative learned dictionaries for local image analysis. In:Proc of IEEE Conference on Computer Vision and Pattern Recognition,2008,1-8.
[90]Pan W, Bui T D, Suen C Y. Text detection from scene images using sparse representation. In:Proc of the 19th International Conference on Pattern Recognition,2008,1-5
[91]Canny J F. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(6):679-698
[92]Mallat S G, Zhong S. Characterization of signals from multiscale edges. IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,11 (7):710-732
[93]Chaudhuri A, Chaudhuri S. Robust detection of skew in document images. IEEE Transatcion on Image processing,1997,6(2):344-349
[94]Li S T, Shen Q H, Sun J. Skew detection using wavelet decomposition and projection profile analysis. Pattern Recognition Letters,2007,28(5):555-562
[95]Wong K, Casey R G, Wahl M. Document analysis system. IBM journal of research and development,1982,26(6):647-656
[96]Nikolaou N, Makridis M, Gatos B, Stamatopoulos N, Papamarkos N. Segmentation of historical machine-printed documents using adaptive run length smoothing and skeleton segmentation paths. Image and Vision Computing,2010, 28(4):590-604
[97]Hua X S, Liu W Y, Zhang H J. An automatic performance evaluation protocol for video text detection algorithms. IEEE Transatcion on Circuits and Systems for Video Technology,2004,14(4):498-507
[98]The ICDAR 2003 competitions. http://algoval.essex.ac.uk/icdar/Competitions. html
[99]OLshausen B A, Field D J. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature,1996,381(6583):607-609
[100]Mallat S, Zhang Z. Matching pursuit with time-frequency dictionaries. IEEE Transatcion on Signal Processing,1993,41(12):3397-3415
[101]Geiger D, Liu T, Donahue M J. Sparse representations for image decompositions. International Journal of Computer Vision,1999,33(2):139-156
[102]Aharon M, Elad M, Bruckstein A. The K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transatcion on Signal Processing,2006,54(11):4311-4322
[103]Gorodnitsky I F, Rao B D. Sparse signal reconstruction from limited data using FOCUSS:A re-weighted norm minimization algorithm. IEEE Transatcion on Signal Processing,1997,45(11):600-616
[104]Elad M, Aharon M. Image denoising via sparse and redundant representations over learned dictionaries. IEEE Transatcion on Image Processing,2006, 15(12):3736-3745
[105]Chen S, Donoho D, Saunders M. Atomic decomposition by basis pursuit. SIAM Review,2001,43(1):129-159
[106]Mitianoudis N, Stathaki T. Joint fusion and blind restoration for multiple image scenarios with missing data. The Computer Journal,2007,50(6):660-673
[107]Wright J, Ma Y, Mairal J, Sapiro G, Huang T S, Yan S. Sparse representation for computer vision and pattern recognition, IEEE Transatcion on Pattern Analysis and Machine Intelligence,2010,98(6):1031-104
[108]Huang K, Aviyente S. Sparse representation for signal classification. In:Proc of Advances in Neural Information Processing Systems,2007,19,609-615
[109]Wright J, Ganesh S, Yang A, et al. Robust face recognition via sparse representation. IEEE Transatcion on Pattern Analysis and Machine Intelligence, 2007,31(2):210-227
[110]Bryt O, Elad M. Compression of facial images using the K-SVD algorithm. Journal of Visual Communication and Image Representation,2008, 19(4):270-282
[11 l]Yang J, Wright J, Ma Y, et al. Image super-resolution as sparse representation of raw image patches. In:Proc of IEEE International Conference on Computer Vision and Pattern Recognition, Anchorage,2008,1-8
[112]Pati Y C, Rezaiifar R, Krishnaprasad P S. Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition. In:Proc of 27th Asilomar Confernce Signals, Systems and Computers,1993.1: 40-44
[113]Davis G, Mallat S, Avellaneda M. Adaptive greedy approximation. Journal of Constructive Approximation,1997,13(1):57-98
[114]Chen S S, Donoho D L, Saunders M A. Atomic decomposition by basis pursuit. SIAM Journal on Scientific Computing,2001,43(1):129-159
[115]Wipf D, Rao B. Sparse Bayesian learning for basis selection. IEEE Transatcion on Signal Processing,2004,52(8):2153-2164
[116]Chartrand R. Exact reconstruction of sparse signals via nonconvex minimization. IEEE Signal Processing Letters,2007,14(10):707-710
[117]Miller A J. Subset Selection in Regression,2nd edition London:Chapman and Hall,2002.
[118]Mairal J, Elad M, Sapiro G. Sparse representation for color image restoration. IEEE Transatcion on Image Processing,2008,17(1):53-69
[119]Elad M, Aharon M. Image Denoising via sparse and redundant representations over learned dictionaries. IEEE Transatcion on Image Processing,2006, 15(12):3736-3745
[120]Kanizsa G. Seeing and thinking. Acta Psychologica,1985,59(1):23-33
[121]Pessoa L, Thompson E, Noe A. Find out about filling-in a guide to perceptual completion for visual science and the philosophy of perception. Behavioral and Brain Sciences,1998,21(6):723-802
[122]Nill, B., Bouzas, B.,1992. Objective image quality measure derived from digital image power spectra. Optical Engineering,31 (44):813-825.
[123]Chen J, Pappas T N, Mojsilovic A, Rogowitz B E. Adaptive perceptual color-texture image segmentation. IEEE Transatcion on Image Processing,2005, 14(10):1524-1536
[124]Varma M, Zisserman A. Statistical approach to material classification using image patch Exemplars. IEEE Transatcion on Pattern Analysis and Machine Intelligence,2009,13(11):2032-2047
[125]Illingworth J, Kittler J. A survey of the Hough transform. Computer Vision, Graphics, and Image Processing,1988,44(1):87-116
[126]Wang Y, Ostermann J, Zhang Y Q著.侯正信,杨喜,王文全译.视频处理与通信.北京：电子工业出版社.2003.
[127]C. Braverman. Photoshop retouching handbook. IDG Books Worldwide,1998.
[128]Perez P, Gngnet M, Blake A. Poisson image editing. ACM Transatcion on Graphics,2003,22(3):313-318
[129]Jeschke S, Cline D, Wonka P. A GPU laplacian solver for diffusion curves and Poisson image editing. ACM Transatcion on Graphics,2009,28(5):116-121
[130]Shih T K, Tang N C, Hwang J N. Exemplar-based video inpainting without ghost shadow artifacts by maintaining temporal continuity. IEEE Transatcion on Circuits and Systems for Video Technology,2009,13(3):347-360
[131]Banham M R, Katsaggelos A K. Digital image restoration. IEEE Signal Processing Magazine,1997,14(2):24-41
[132]Buisson O, Besserer B, Boukir S, Helt F. Deterioration detection for digital film restoration. In:Proc of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1997,78-84
[133]Black M J, Anandan P. The robust estimation of multiple motions:parametric and piecewise-smooth flow fields. Computer Vision and Image Understanding, 1996,63(1):75-104
[134]Mittal A, Paragios N. Motion-based background subtraction using adaptive kernel density estimation. In:Proc of IEEE Computer Computer Society Conference on Computer Vision and Pattern Recognition,2004,2,302-309
[135]Ren Y, Chua C S, Ho Y K. Statistical background modeling for non-stationary camera. Pattern Recognition Letters,2003,24(1-3):2003.
[136]Wang J, Adelson E. Layered representation for motion analysis. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1993, 361-366.
[137]Murray D, Basu A. Motion tracking with an active camera. IEEE Transatcion on Pattern Analysis and Machine Intelligence,1994,16(5):449-459
[138]Welch G, Foxlin E. Motion tracking:No silver bullet, but a respectable arsenal. Computer Graphics and Applications,2002,26(6):24-38
[139]Herda L, Fua P, Plankers R, Boulic R, Thalmann D. Skeleton-based motion capture for robust reconstruction of human motion. In:Proc of the Computer Animation,2000,77-85.
[140]Theobalt C, Magnor M, Schuler H P.. Combining 2D feature tracking and volume reconstruction for online video-based human motion capture. In:Proc of 10th Pacific Conference on Computer Graphics and Applications,2002,96-103
[141]Silaghi MCA, Plankers A, Boulic R, FUA P, Thalmann P D. Local and global skeleton fitting techniques for optical motion capture. Modelling and Motion Capture Techniques for Virtual Environments,1998:26-40
[142]Malandain G, Fernandez-Vidal S. Euclidean skeletons. Image and Vision Computing,1998,16(3):317-327
[143]Choi W P, Lam K M, Siu W C. Extraction of the euclidean skeleton based on a connectivity criterion. Pattern Recognition,2003,36(8):721-729
[144]Shaken D, Bruckstein A M. Pruning medial axes. Computer Vision and Image Understanding,1998,69(2):156-169
[145]Bai X, Latecki L J, Liu W Y. Skeleton pruning by contour partitioning with discrete curve evolution. IEEE Transatcion on Pattern Analysis and Machine Intelligence,2007,29(3):449-462
[146]Bai X, Latecki L J:Path Similarity skeleton graph matching, IEEE Transatcion on Pattern Analysis and Machine Intelligence,2008,30(7):1282-1292
[147]Chuang Y Y, Curless B, Salesin D H. A bayesian approach to digital matting. In: IEEE Computer Society's Computer Vision and Pattern Reconition,2001: 264-271
[148]Lin S Y, Shi J Y. Fast natural inage matting in perceptual color space. Computers and Graphics,2005,29:403-411.
[149]Tropp J A, Wright S J. Computational methods for sparse solution of linear inverse problems. Proceedings of the IEEE,2010,98(6):948-958.
[150]葛永斌,田振夫,马红磊.三维泊松方程的高精度多重网格解法.应用数学,2006.2：313-318
[151]ITU-R Rec. Methodology for the Subjective Assessment of the Quality for Television Pictures. BT.500-11,2002.
[152]Wang Z, Bovik A C. A universal image quality index. IEEE Signal Processing Letters,2002,9(3):81-84.
[153]Nill N B, Bouzas B. Objective image quality measure derived from digital image power spectra. Optical Engineering,1992,31 (04):813-825
[154]Van Roosmalen P M B, Lagendijk R L, Biemond J. Correction of intensity flicker in old film sequences. IEEE Transatcion on Circuits and Systems for Video Technology,1999,9(7):1013-1019
[155]Saito T, Komatsu T. Ohuchi T, Seto T. Image processing for restoration of heavily-corrupted old film sequences. In:Proc of 15th International Conference on Pattern Recognition,2000,3,13-16
[156]Squire D M G, Muller W, Muller H, Pun T. Content-based query of image databases:inspirations from text retrieval. Pattern Recognition Letters,2000, 21(13-14):1193-1198
[157]Jiang Y G, Ngo C W, Yang J. Towards optimal bag-of-features for object categorization and semantic video retrieval. In:Proc of the 6th ACM International Conference on Image and video retrieval,2007,494-501
[158]Eiron N, McCurley K S. Analysis of anchor text for web search. In:Proc of the 26th Annual International ACM SIGIR Conference on Research and Development in Informaion Retrieval,2003,459-460
[159]Berg E, Friedlander M P. Probing the pareto frontier for basis pursuit solutions. SIAM Journal Science Computer,2008,31(2):890-912
[160]Mallat S, Zhang Z. Matching pursuits with time-frequency dictionaries. IEEE Transatcion on Signal Processing,1993,41 (12):3397-3415
[161]Schniter P, Potter L C, Ziniel J. Fast Bayesian matching pursuit. In:Proc of Information Theory and Applications Workshop,2008,326-383
[162]Chartrand R. Exact reconstruction of sparse signals via nonconvex minimization. IEEE Signal Processing Letters,2007,14(10):707-710
[163]Baron D, Sarvotham S, Baraniuk R G. Bayesian compressive sensing via belief propagation. IEEE Transatcion on Signal Processing,2010,58(1):269-280
[164]Migliore D A, Matteucci M, Naccari M. A revaluation of frame difference in fast and robust motion detection. In:Proc of the 4th ACM International Workshop on Video Surveillance and Sensor Networks,2006,215-218
[165]Burt P J, Adelson E H. A multiresolution spline with application to image mosaics. ACM Transatcion on Graphics,1983,2(4):217-236
[166]Su M S, Hwang W L, Cheng K Y. Analysis on multiresolution mosaic images. IEEE Transatcion on image processing,2004,13(7):952-959
[167]Szeliski R, Shum H Y. Creating full view panoramic image mosaics and environment maps. In:Proc of the 24th Annual Conference on Computer Graphics and Interactive Techniques,1997,251-258
[2]Gonzalez R C, Woods R E. Digital image processing. Hall Professional Technical Reference,2002
[3]Granlund G H, Knutsson H. Signal processing for computer vision. Kluwer Academic Pub,1995
[4]张红英,彭启琮.数字图像修复技术综述.中国图像图形学报,2007,12(1)：1-10
[5]周廷方,汤锋,王进,王章野,彭群生.基于径向基函数的图像修复技术.中国图像图形学报,2004,9(10)：1-11
[6]Walden S. The ravished image. St.Martin's Press, New York,1985
[7]Emile-Male G. The restorer's handbook of easel painting. Van Nostrand Reinhold, New York,1976
[8]Bertalmio M, Sapiro G, Caselles V, Ballester C. Image inpainting. In:Proc of SIGGRAPH'00,2000,417-424
[9]卢小宝,王维兰.基于样本块的破损唐卡图像修复算法的改进.计算机应用,2010,22(4)：32-36
[10]鲁东明,潘云鹤,陈任.敦煌石窟虚拟重现与壁画修复模拟.测绘学报,2002,31(1)：12-16
[11]Tauber Z, Li Z N, Drew M S. Review and preview:disocclusion by inpainting for image-based rendering. IEEE Transatcion on Systems, Man, and Cybernetics, Part C:Applications and Reviews,2007,37(4):527-540
[12]King D. The commissar vanishes. Henry Holt and Company,1997
[13]Chan T F, Shen J. Mathematical models for local nontexture inpaintings. SIAM Journal on Applied Mathematics,2001,62(3):1019-1043
[14]Chan T F, and Shen J. Non-texture inpainting by curvature driven diffusion. Journal of Visual Communication and Image Representation,2001, 12(4):436-449
[15]Ballester C, Bertalmio M, Caselles V, Sapiro G, Verdera J. Fillingin by join interpolation of vector fields and grey levels. IEEE Transatcion on Image Processing,2001,10(8):1200-1211
[16]Ambrosio L, Fusco N, Pallara D. Functions of bounded variations and free discontinuity problems. Oxford, U.K. Clarendon,2000
[17]Tsai A, Yezzi J A, Willsky A S. Curve evolution implementation of the Mumford-Shah functional for image segmentation, denoising, interpolation and magnification. IEEE Transatcion on Image Processing,2001,10(8):1169-1186
[18]Esedoglu S, Shen J H. Digital inpainting based on the Mumford-Shah-Euler image model. European Journal on Applied Mathematics,2002,13(4):353-370
[19]Oliveira M M, Bowen B, McKenna R, Chang Y S. Fast digital inpainting. In: Proc of International Conference on Visualization, Imaging and Image Processing, Marbella, Spain,2001,261-266
[20]Masnou S, Morel J M. Level lines based disoclussion. In:Proc of International Conference on Image Processing,1998,259-263
[21]张红英,彭启琮,吴亚东.数字破损图像的非线性各向异性扩散修补算法.计算机辅助设计与图形学学报,2006,18(10)：1541-1546
[22]张红英,彭启琮,吴亚东.基于p-Laplace算子的小波域图像修复模型.自动化学报,2008,34(8)：849-856
[23]Papandreou G, Maragos P, Kokaram A. Image inpainting with a wavelet domain hidden Markov tree model. In:Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing. Nevada,2008,773-776
[24]Besag J. On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society,1986,48(3):259-302
[25]Crouse M S, Nowak R D, Baraniuk R G. Wavelet-based statistical signal processing using hidden Markov models, IEEE Transatcion on Signal Processing, 1998,46(4):886-902
[26]Wei L Y, Levoy M. Fast texture synthesis using tree-structured vector quantization. In:Proc of SIGGRAPH'00,2000,479-488
[27]Criminisi A, Perez P, Toyama K. Region filling and object removal by exemplar-based inpainting. IEEE Transatcion on Image Processing,2004, 13(9):1200-1212
[28]Efros A A, Leung T K. Texture synthesis by non-parametric sampling. In:Proc the International Conference on Computer Vision,1999, pp.1033-1038
[29]Grossauer H. A combined PDE and texture synthesis approach to inpainting. In:Proc of European Conference on Computer Vision,2004,214-224
[30]Ignacio U A, Jung C R. Block-based image inpainting in the wavelet domain. The Visual Computer,2007,23(9-11):733-741
[31]Kang S H, Chan T F, Soatto S, Landmark based inpainting from multiple views. Univsersity Caifornia at Los Angeles, Los Angeles, Technique Report,2002, TR-CAM 02-11
[32]Cheng W H, Hsieh C W, Lin S K. Robust algorithm for exemplar-based image inpainting. In:Proc of the International Conference on Computer Graphics, Imaging Vision,2005,64-69
[33]Sun J, Yuan L, Jia J. Image completion with structure propagation. ACM Transatcion on Graphics,2005,24(3):861-868
[34]Komodakis N, Tziritas G. Image completion using efficient belief propagation via priority scheduling and dynamic pruning. IEEE Transatcion on Image Processing,2007,16 (11):2649-2661
[35]Hays J, Efros A A. Scene completion using millions of photographs. Communications of the ACM,2008,51(10):87-94
[36]Bertalmio M, Vesa L, Sapiro G, Osher S. Simultaneous structure and texture image inpainting. IEEE Transatcion on Image Processing,2003,12 (8):882-889
[37]Grossauer H. A combined PDE and texture synthesis approach to inpainting, In: Proc of European Conference on Computer Vision,2004,4,214-224
[38]Lai Y K, Hu S M, Gu D X, Martin R R. Geometry texture synthesis and transfer via geometry images. In:Proc of ACM Symposium on Solid and Physical Modeling,2005,15-26
[39]Jia J, Tang C K. Image repairing:robust image synthesis by adaptive and tensor voting. In:Proc of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2003,1,643-835
[40]Bertalmio M, Bertozzi A L, Sapiro G. Navier-stokes, fluid dynamics, and image and video inpainting. In:Proc of IEEE Computer Society Conference on Computer Vision Pattern Recognition,2001,1,355-362
[41]Yan W Q, Kankanhalli M S. Erasing video logos based on image inpainting. In: Proc of IEEE International Conference on Multimedia and Expo,2002,2, 521-524
[42]Patwardhan K A, Sapiro G, Bertalmio M. Video inpainting of occluding and occluded objects. In:Proc of IEEE International Conference of Image Processing,2005,2,69-72
[43]Kokaram A C, Godsill S J. Joint detection, interpolation, motion and parameter estimation for image sequences with missing data. In:Proc of IEEE International Conference on Image Processing,1997,2,191-194
[44]Tourapis A M, Cheong, H Y, Au O C, Liou M L. Temporal interpolation of video sequences using Zonal-based glgorithms. In:Proc of IEEE International Conference on Image Processing Greece,2001,895-898
[45]Wexler Y, Shechtman E, Irani M. Space-time completion of video, IEEE Transatcion on Pattern Analysis and Machine Intelligence,2007,29(3):463-476
[46]Jia Y T, Hu S M, Martin R R. Video completion using tracking and fragment merging. The Visual Computing,2005,21 (8):601-610
[47]Patwardhan K A, Sapiro G, Bertalmio M. Video inpainting of occluding and occluded objects. In:Proc of IEEE International Conference of Image Processing,2005,2,69-72
[48]Shih T K, Tang N C, Hwang J N. Exemplar-based video inpainting without ghost shadow artifacts by maintaining temporal continuity. IEEE Transatcion on Circuits and Systems for Video Technology,2009,19(3):347-360
[49]Shi W Z, Zhu C Q, Tian Y, Nichol J. Wavelet-based image fusion and quality assessment. International Journal of Applied Earth Observation and Geoinformation,2005,6(3-4):241-251
[50]Amano T. Correlation based image defect detection. In:Proc of International Conference on Pattern Recognition,2006,163-166
[51]Chang R C; Sie Y L; Chou S M; Shih T K. Photo defect detection for image inpainting. In:Proc of Seventh IEEE International Symposium on Multimedia, 2005,12-14
[52]王勇,郑辉,胡德文.图像和视频中的文字获取技术.中国图象图形学报,2004,9(5)：532-538
[53]王崇骏,杨育彬,陈世福.基于高层语义的图像检索算法.软件学报,2004,15(10)：1461-1469
[54]Khedekar S, Ramanaprasad V, Setlur S. Text-image separation in devanagari documents. In:Proc of the 7th International Conference on Document Analysis and Recognition,2003,1265-1269
[55]Lee K H, Choy Y C, Cho S. Geometric structure analysis of document image:a knowledge-based approach. IEEE Transatcion on Pattern Analysis and Machine Intelligence,2000,22(6):1224-1240
[56]Deng S L, Latifi H, Regentova E. Document segmentation using polynomial spline wavelets. Pattern Recognition,2001,34(12):2533-2545
[57]Jain A K. Bhattacharjee S. Text segmentation using gabor filters for automatic document processing. Machine Vision and Applications.5(3),1992:169-184
[58]Kubota K, Iwaki O, Arakawa H. Document understanding system. In:Proc of the 7th International Conference on Pattern Recognition,1984,612-614
[59]Fletcher L A, Kasturi R A. A Robust algorithm for text string separation from mixed text/graphic image. IEEE Transatcion on Pattern Recognition and Machine Intelligence,1998,10(6):910-918
[60]Byun H, Jang I, Choi Y. Text extraction in digital news video using morphology. Lecture Notes in Computer Science,2002,2423:341-352
[61]Granado I, Pina P, Muge F. Automatic feature extraction on pages of antique books through a mathematical morphology based methodology. Lecture Notes in Computer Science,2000,19(23):1-13
[62]Xiao Y, Yan H. Text extraction in document images based on delaunay triangulation. Pattern Recognition,2003,36(3):799-809
[63]Yuan Q, Tan C L. Text extraction from gray scale document images using edge information. In:Proc of the 6th International Conference on Document Analysis and Recognition,2001,302-306
[64]Wahl F M, Wong K Y, Casey R G. Block segmentation and text extraction in mixed text image documents. Computer Vision Graphics and Image Processing, 1982,2(6):375-390
[65]Strouthopoulos C, Papamarkos N, Chamazas N C. PLA using RLSA and a neural net work. Engineering Application Of Artificial Intelligence,1999, 12(2):119-138
[66]Wang D, Srihari S N. Classification of newsdissertation image blocks using texture analysis. Computer Vision. Graphics and Image Processing,1989, 47(3):327-352
[67]Viswanathan M, Nagy G. Characteristics of digitized images of technical articles. Machine Vision Applications in Character Recognition and Industrial Inspection, 1992,1661:6-17
[68]Ha J K, Haralick R M, Philips I R. Recursive X-Y cut using bounding boxes of connected components. In:Proc of 3rd International Conference on Document Analysis and Recognition,1995,952-955
[69]Ha J K, Haralick R M, Philips I R. Document page decomposition by the bounding box projection technique. In:Proc of 3rd International Conference on Document Analysis and Recognition,1995,1119-1122
[70]Cao Y, Wang S H, Li H. Skew detection and correction in document images based on straight-line fitting. Pattern Recognition Letters,2003, 24(12):1871-1879
[71]Fan K C, Wang L S. Classification of document blocks using density feature and connectivity histogram. Pattern Recognition Letters,1995,16(9):955-962
[72]Kruatrachue B, Suthaphan P. A Fast and efficient method for document segmentation for OCR. In:Proc of IEEE Region 10 International Conference on Electrical and Electronic Technology,2001,352-354
[73]林亚忠,赵晨光.纹理分割中的特征提取.中国医学物理学杂志,2001,18(4)：204-205
[74]Hua X S, Chen X R, Liu W Y. Automatic location of text in video frames. In: Proc of the 3rd International Workshop on Multimedia Information Retrieval, 2001,126-129
[75]Lyu M, Song J, Cai M. A comprehensive method for multilingual video text detection, localization and extraction. IEEE Transatcion on Circuits and Systems for Video Technology,2005,15 (2):243-255
[76]Jung C, Liu Q, Kim J. Accurate text localization in images based on SVM output scores, Image and Vision Computing,2009,27(9):1295-1301
[77]Chen D, Jean-Marc O, Herve B. Text detection and recognition in images and video frames. Pattern Recognition,2004,37(3):595-608
[78]Ye Q X, Huang Q M, Gao W, Zhao D B. Fast and robust text detection in images and video frames. Image and Vision Computing,2005,23(6):565-576.
[79]Anthimopoulos M, Gatos B, Pratikakis I. A two-stage scheme for text detection in video images. Image and Vision Computing,2010,28(9):1413-1426
[80]Shen H Y, Coughlan J, Ivanchenko V. Figure-ground segmentation using factor graphs. Image and Vision Computing,2009,27(7):854-863
[81]Lienhart R, Wernicke A. Localizing and segmenting text in images and videos. IEEE Transatcion on Circuits and Systems for Video Technology,2002, 12(4):256-268
[82]Mancas-Thillou C, Gosselin B. Color text extraction with selective metric-based clustering. Computer Vision and Image Understanding,2007,107(1-2):97-107
[83]Shivakumara P, Huang W H, Tan C L. Efficient video text detection using edge features. In:Proc of the 19th International Conference on Pattern Recognition, 2008,1-4
[84]Gllavata J. Ewerth R. B. Freisleben. Text detection in images based on unsupervised classification of high-frequency wavelet coefficients. In:Proc of the 17th International Conference on Pattern Recognition.2004.425-428
[85]Lienhart R. Automatic text recognition for video indexing. In:Proc of fourth ACM international conference on Multimedia,1996,11-20
[86]王惠锋,孙正兴,王箭.语义图像检索研究进展.计算机研究与发展,2002,39(05)：513-523
[87]Chen X, Zhang H J. Text area detection from video frames. In:Proc of Advances in Multimedia Information,2001,222-228
[88]Chang S F, Chen W, Meng H J, Sundaram H, Zhong D. VideoQ:an automatic content-based video search system using visual cues. In:Proc of the fifth ACM international conference on Multimedia,1997,313-324
[89]Mairal J, Bach F, Ponce J, Sapiro G, Zisserman A. Discriminative learned dictionaries for local image analysis. In:Proc of IEEE Conference on Computer Vision and Pattern Recognition,2008,1-8.
[90]Pan W, Bui T D, Suen C Y. Text detection from scene images using sparse representation. In:Proc of the 19th International Conference on Pattern Recognition,2008,1-5
[91]Canny J F. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(6):679-698
[92]Mallat S G, Zhong S. Characterization of signals from multiscale edges. IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,11 (7):710-732
[93]Chaudhuri A, Chaudhuri S. Robust detection of skew in document images. IEEE Transatcion on Image processing,1997,6(2):344-349
[94]Li S T, Shen Q H, Sun J. Skew detection using wavelet decomposition and projection profile analysis. Pattern Recognition Letters,2007,28(5):555-562
[95]Wong K, Casey R G, Wahl M. Document analysis system. IBM journal of research and development,1982,26(6):647-656
[96]Nikolaou N, Makridis M, Gatos B, Stamatopoulos N, Papamarkos N. Segmentation of historical machine-printed documents using adaptive run length smoothing and skeleton segmentation paths. Image and Vision Computing,2010, 28(4):590-604
[97]Hua X S, Liu W Y, Zhang H J. An automatic performance evaluation protocol for video text detection algorithms. IEEE Transatcion on Circuits and Systems for Video Technology,2004,14(4):498-507
[98]The ICDAR 2003 competitions. http://algoval.essex.ac.uk/icdar/Competitions. html
[99]OLshausen B A, Field D J. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature,1996,381(6583):607-609
[100]Mallat S, Zhang Z. Matching pursuit with time-frequency dictionaries. IEEE Transatcion on Signal Processing,1993,41(12):3397-3415
[101]Geiger D, Liu T, Donahue M J. Sparse representations for image decompositions. International Journal of Computer Vision,1999,33(2):139-156
[102]Aharon M, Elad M, Bruckstein A. The K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transatcion on Signal Processing,2006,54(11):4311-4322
[103]Gorodnitsky I F, Rao B D. Sparse signal reconstruction from limited data using FOCUSS:A re-weighted norm minimization algorithm. IEEE Transatcion on Signal Processing,1997,45(11):600-616
[104]Elad M, Aharon M. Image denoising via sparse and redundant representations over learned dictionaries. IEEE Transatcion on Image Processing,2006, 15(12):3736-3745
[105]Chen S, Donoho D, Saunders M. Atomic decomposition by basis pursuit. SIAM Review,2001,43(1):129-159
[106]Mitianoudis N, Stathaki T. Joint fusion and blind restoration for multiple image scenarios with missing data. The Computer Journal,2007,50(6):660-673
[107]Wright J, Ma Y, Mairal J, Sapiro G, Huang T S, Yan S. Sparse representation for computer vision and pattern recognition, IEEE Transatcion on Pattern Analysis and Machine Intelligence,2010,98(6):1031-104
[108]Huang K, Aviyente S. Sparse representation for signal classification. In:Proc of Advances in Neural Information Processing Systems,2007,19,609-615
[109]Wright J, Ganesh S, Yang A, et al. Robust face recognition via sparse representation. IEEE Transatcion on Pattern Analysis and Machine Intelligence, 2007,31(2):210-227
[110]Bryt O, Elad M. Compression of facial images using the K-SVD algorithm. Journal of Visual Communication and Image Representation,2008, 19(4):270-282
[11 l]Yang J, Wright J, Ma Y, et al. Image super-resolution as sparse representation of raw image patches. In:Proc of IEEE International Conference on Computer Vision and Pattern Recognition, Anchorage,2008,1-8
[112]Pati Y C, Rezaiifar R, Krishnaprasad P S. Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition. In:Proc of 27th Asilomar Confernce Signals, Systems and Computers,1993.1: 40-44
[113]Davis G, Mallat S, Avellaneda M. Adaptive greedy approximation. Journal of Constructive Approximation,1997,13(1):57-98
[114]Chen S S, Donoho D L, Saunders M A. Atomic decomposition by basis pursuit. SIAM Journal on Scientific Computing,2001,43(1):129-159
[115]Wipf D, Rao B. Sparse Bayesian learning for basis selection. IEEE Transatcion on Signal Processing,2004,52(8):2153-2164
[116]Chartrand R. Exact reconstruction of sparse signals via nonconvex minimization. IEEE Signal Processing Letters,2007,14(10):707-710
[117]Miller A J. Subset Selection in Regression,2nd edition London:Chapman and Hall,2002.
[118]Mairal J, Elad M, Sapiro G. Sparse representation for color image restoration. IEEE Transatcion on Image Processing,2008,17(1):53-69
[119]Elad M, Aharon M. Image Denoising via sparse and redundant representations over learned dictionaries. IEEE Transatcion on Image Processing,2006, 15(12):3736-3745
[120]Kanizsa G. Seeing and thinking. Acta Psychologica,1985,59(1):23-33
[121]Pessoa L, Thompson E, Noe A. Find out about filling-in a guide to perceptual completion for visual science and the philosophy of perception. Behavioral and Brain Sciences,1998,21(6):723-802
[122]Nill, B., Bouzas, B.,1992. Objective image quality measure derived from digital image power spectra. Optical Engineering,31 (44):813-825.
[123]Chen J, Pappas T N, Mojsilovic A, Rogowitz B E. Adaptive perceptual color-texture image segmentation. IEEE Transatcion on Image Processing,2005, 14(10):1524-1536
[124]Varma M, Zisserman A. Statistical approach to material classification using image patch Exemplars. IEEE Transatcion on Pattern Analysis and Machine Intelligence,2009,13(11):2032-2047
[125]Illingworth J, Kittler J. A survey of the Hough transform. Computer Vision, Graphics, and Image Processing,1988,44(1):87-116
[126]Wang Y, Ostermann J, Zhang Y Q著.侯正信,杨喜,王文全译.视频处理与通信.北京：电子工业出版社.2003.
[127]C. Braverman. Photoshop retouching handbook. IDG Books Worldwide,1998.
[128]Perez P, Gngnet M, Blake A. Poisson image editing. ACM Transatcion on Graphics,2003,22(3):313-318
[129]Jeschke S, Cline D, Wonka P. A GPU laplacian solver for diffusion curves and Poisson image editing. ACM Transatcion on Graphics,2009,28(5):116-121
[130]Shih T K, Tang N C, Hwang J N. Exemplar-based video inpainting without ghost shadow artifacts by maintaining temporal continuity. IEEE Transatcion on Circuits and Systems for Video Technology,2009,13(3):347-360
[131]Banham M R, Katsaggelos A K. Digital image restoration. IEEE Signal Processing Magazine,1997,14(2):24-41
[132]Buisson O, Besserer B, Boukir S, Helt F. Deterioration detection for digital film restoration. In:Proc of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1997,78-84
[133]Black M J, Anandan P. The robust estimation of multiple motions:parametric and piecewise-smooth flow fields. Computer Vision and Image Understanding, 1996,63(1):75-104
[134]Mittal A, Paragios N. Motion-based background subtraction using adaptive kernel density estimation. In:Proc of IEEE Computer Computer Society Conference on Computer Vision and Pattern Recognition,2004,2,302-309
[135]Ren Y, Chua C S, Ho Y K. Statistical background modeling for non-stationary camera. Pattern Recognition Letters,2003,24(1-3):2003.
[136]Wang J, Adelson E. Layered representation for motion analysis. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1993, 361-366.
[137]Murray D, Basu A. Motion tracking with an active camera. IEEE Transatcion on Pattern Analysis and Machine Intelligence,1994,16(5):449-459
[138]Welch G, Foxlin E. Motion tracking:No silver bullet, but a respectable arsenal. Computer Graphics and Applications,2002,26(6):24-38
[139]Herda L, Fua P, Plankers R, Boulic R, Thalmann D. Skeleton-based motion capture for robust reconstruction of human motion. In:Proc of the Computer Animation,2000,77-85.
[140]Theobalt C, Magnor M, Schuler H P.. Combining 2D feature tracking and volume reconstruction for online video-based human motion capture. In:Proc of 10th Pacific Conference on Computer Graphics and Applications,2002,96-103
[141]Silaghi MCA, Plankers A, Boulic R, FUA P, Thalmann P D. Local and global skeleton fitting techniques for optical motion capture. Modelling and Motion Capture Techniques for Virtual Environments,1998:26-40
[142]Malandain G, Fernandez-Vidal S. Euclidean skeletons. Image and Vision Computing,1998,16(3):317-327
[143]Choi W P, Lam K M, Siu W C. Extraction of the euclidean skeleton based on a connectivity criterion. Pattern Recognition,2003,36(8):721-729
[144]Shaken D, Bruckstein A M. Pruning medial axes. Computer Vision and Image Understanding,1998,69(2):156-169
[145]Bai X, Latecki L J, Liu W Y. Skeleton pruning by contour partitioning with discrete curve evolution. IEEE Transatcion on Pattern Analysis and Machine Intelligence,2007,29(3):449-462
[146]Bai X, Latecki L J:Path Similarity skeleton graph matching, IEEE Transatcion on Pattern Analysis and Machine Intelligence,2008,30(7):1282-1292
[147]Chuang Y Y, Curless B, Salesin D H. A bayesian approach to digital matting. In: IEEE Computer Society's Computer Vision and Pattern Reconition,2001: 264-271
[148]Lin S Y, Shi J Y. Fast natural inage matting in perceptual color space. Computers and Graphics,2005,29:403-411.
[149]Tropp J A, Wright S J. Computational methods for sparse solution of linear inverse problems. Proceedings of the IEEE,2010,98(6):948-958.
[150]葛永斌,田振夫,马红磊.三维泊松方程的高精度多重网格解法.应用数学,2006.2：313-318
[151]ITU-R Rec. Methodology for the Subjective Assessment of the Quality for Television Pictures. BT.500-11,2002.
[152]Wang Z, Bovik A C. A universal image quality index. IEEE Signal Processing Letters,2002,9(3):81-84.
[153]Nill N B, Bouzas B. Objective image quality measure derived from digital image power spectra. Optical Engineering,1992,31 (04):813-825
[154]Van Roosmalen P M B, Lagendijk R L, Biemond J. Correction of intensity flicker in old film sequences. IEEE Transatcion on Circuits and Systems for Video Technology,1999,9(7):1013-1019
[155]Saito T, Komatsu T. Ohuchi T, Seto T. Image processing for restoration of heavily-corrupted old film sequences. In:Proc of 15th International Conference on Pattern Recognition,2000,3,13-16
[156]Squire D M G, Muller W, Muller H, Pun T. Content-based query of image databases:inspirations from text retrieval. Pattern Recognition Letters,2000, 21(13-14):1193-1198
[157]Jiang Y G, Ngo C W, Yang J. Towards optimal bag-of-features for object categorization and semantic video retrieval. In:Proc of the 6th ACM International Conference on Image and video retrieval,2007,494-501
[158]Eiron N, McCurley K S. Analysis of anchor text for web search. In:Proc of the 26th Annual International ACM SIGIR Conference on Research and Development in Informaion Retrieval,2003,459-460
[159]Berg E, Friedlander M P. Probing the pareto frontier for basis pursuit solutions. SIAM Journal Science Computer,2008,31(2):890-912
[160]Mallat S, Zhang Z. Matching pursuits with time-frequency dictionaries. IEEE Transatcion on Signal Processing,1993,41 (12):3397-3415
[161]Schniter P, Potter L C, Ziniel J. Fast Bayesian matching pursuit. In:Proc of Information Theory and Applications Workshop,2008,326-383
[162]Chartrand R. Exact reconstruction of sparse signals via nonconvex minimization. IEEE Signal Processing Letters,2007,14(10):707-710
[163]Baron D, Sarvotham S, Baraniuk R G. Bayesian compressive sensing via belief propagation. IEEE Transatcion on Signal Processing,2010,58(1):269-280
[164]Migliore D A, Matteucci M, Naccari M. A revaluation of frame difference in fast and robust motion detection. In:Proc of the 4th ACM International Workshop on Video Surveillance and Sensor Networks,2006,215-218
[165]Burt P J, Adelson E H. A multiresolution spline with application to image mosaics. ACM Transatcion on Graphics,1983,2(4):217-236
[166]Su M S, Hwang W L, Cheng K Y. Analysis on multiresolution mosaic images. IEEE Transatcion on image processing,2004,13(7):952-959
[167]Szeliski R, Shum H Y. Creating full view panoramic image mosaics and environment maps. In:Proc of the 24th Annual Conference on Computer Graphics and Interactive Techniques,1997,251-258