全局显著信息指导下的轮廓编组计算模型研究
|
摘要
知觉组织作为人类视觉感知系统的重要组成部分,近年来受到从事神经科学、认知心理学和计算机科学等多领域研究人员的高度关注。知觉组织的过程为自然界中的光信号和感知目标之间架起一道桥梁,是人类进行图像识别、注意分配以及记忆存储等高级加工过程的基础。轮廓编组作为以图像边缘为编组对象的一种知觉组织,是知觉组织研究中不可或缺的一部分。轮廓编组模型能够发现图像中的显著结构,是定义和获取感知目标的重要工具,为实现基于目标的注意模型、目标检测和目标识别等模型提供保障。因此研究知觉组织的认知和神经机制,建立符合人类感知特性的高效的轮廓编组模型,是当前视觉感知系统信息处理理论研究中一个非常重要的问题。
将认知心理学和神经科学中有关知觉组织的研究成果应用到计算模型中,是建立符合人类感知特性的轮廓编组模型的关键。本文以心理学中格式塔的知觉组织规则为依据,将心理学和神经科学中的研究成果作为理论基础,从统计学的角度出发,强调注意对知觉组织过程的影响作用,提出了符合自然图像统计特性的格式塔编组线索量化模型,并构建了全局显著信息指导下的轮廓编组模型。
本文的研究内容依据建立轮廓编组模型的三个步骤可分为三大部分。第一部分从优化轮廓编组输入的角度出发,设计实现了适合于轮廓编组的自然图像中的边缘检测算法。第二部分通过分析人类所接受的外部信息的统计特性,建立了边缘间格式塔编组线索的量化模型。第三部分确定轮廓编组算法的优化目标和优化过程,从中体现出注意对知觉组织的作用,实现对自然图像的轮廓编组。本文的主要创新点有：
第一,提出了一种基于全局显著信息的多尺度边缘检测算法。与其它边缘检测算法相比,该算法能够获得较好的边缘检测结果,更符合轮廓编组的输入要求。算法采用非线性的方法将多种特征下的边缘检测结果进行融合,保证边缘的准确和完整；以图像中显著区域的边界位置作为边缘检测的空间先验知识,有效去除噪声和细节边缘；将空间位置相邻的边缘点连接成具有一定长度的边,确保检测结果的稳定性和对轮廓编组算法的适用性；最后在多尺度的变化中不断更新空间先验知识和追踪每条边缘的演化过程,用每条边从出现到消亡过程中的能量总和来度量其显著性。
第二,提出了轮廓编组中新的边缘相似性度量方法-有向边区域度量。利用自行开发的交互式的图形化标注工具,人工标注得到了规范且准确的有向边缘数据集,并在此数据集上,以正则化方差准则为依据,具体讨论了影响有向边相似性度量的几个关键因素,明确给出了有向边区域度量的最佳参数。有向边区域度量的边缘相似性度量方法克服了边缘连接方式的不确定性,能够有效提高相似性线索在轮廓编组中的重要性。在有向边缘数据集上的统计信息显示,有向边区域度量明显优于已有的其它边缘相似性度量方法。
第三,建立了轮廓编组中生成式的编组线索合并模型。结合认知心理学中有关格式塔规则的研究,将邻近性作为轮廓编组中的主导线索,讨论了在不同的邻近性条件下连续性和相似性线索的联合分布情况。用生成式的编组线索合并模型,拟合了连续性和相似性线索在人工标注数据集上具有特殊形式的联合分布,准确地描述了编组线索之间的相关性。此模型摒除了以往判别式模型中对于线索不相关的假设,更准确的拟合了由自然图像统计得到的格式塔编组线索的统计特性,是更为精确的格式塔线索合并模型。
第四,提出了全局显著信息指导下的轮廓编组算法,并通过对轮廓编组算法的层次化实现了基于目标的注意。该轮廓编组算法以心理学中有关注意对知觉组织作用的研究成果为依据,用全局显著信息来指导轮廓编组的过程,实现对自然图像中显著感知目标的轮廓编组。模拟注意中的同物效果和禁止返回机制,将轮廓编组算法层次化,实现了注意在感知目标中的层次化转移。在自然图像上的实验结果表明,该轮廓编组算法能够编组得到图像中的显著感知目标,在绝大多数情况下获得了比其它算法更好的编组结果。在此基础上实现的基于目标的注意,其注意焦点转移路径更加规整,也更加符合人类的视觉感知。
Perceptual organization is an important mechanism of human visual perception system. It attracts many researchers who employ themselves in neurophysiology, cognitive psychology, computer science and other fields in recent years. The process of perceptual organization is a link between the optical signals in natural world and the perceptual objects. It is also the basis of many high level visual tasks, such as image recognition, attention assignment, memory storage and so on. Contour grouping, which takes image edges as grouping elements, is an important part of perceptual organization. The contour grouping model can find salient structures in images, and is an important tool for the definition and obtainment of perceptual objects. It can be seemed as the foundation of constructing object-based attention model, object detection model and object recognition model. Researching the cogni-tive and neural mechanism of perceptual organization to design a contour grouping model with high efficiency which accords with human perception system is indis-pensable in the study of visual perception system inspired information processing theory.
Applying the research results about perceptual organization in cognitive psy-chology and neurophysiology into computational models is the key of constructing contour grouping models which accord with human perception characteristics. In this dissertation, we propose the quantized model of Gestalt grouping cues and con-struct a contour grouping model guided by global saliency information. All of these studies are based on the Gestalt grouping rules and the research results in psychol-ogy and neurophysiology, take Statistic as the tool, and mainly emphasize the role of attention in perceptual organization.
According to the three stage of constructing a contour grouping model, the study of this dissertation can be divided into three parts. The first part aims at improving the input quality of contour grouping. In this part, we design and realize the natural image edge detection algorithm which is suitable for contour grouping. The second part analyses the statistical properties of the natural images, and give a reasonable definition and quantization of gestalt grouping cues between directed tangents. The third part defines the grouping cost based on the role of attention in perceptual organization, gives the optimization of the grouping cost, and finally realizes the contour grouping in natural images. The main innovative points of the dissertation are as follows:
First, we propose a multi-scale boundary detection algorithm based on global saliency information. Compared with other algorithms, our algorithm can get better detection results, which are more proper for contour grouping. Nonlinear combina-tion of the edge detection results in multiple features can ensure the accuracy and integrity of the edges. The spatial prior getting from the boundaries of salient re-gions can remove noises and trivial edges effectively. Linking neighbor edge pixels to form edges with a certain length can make the detection results more steady and proper for contour grouping. We update the spatial prior and trace each edge across multiple scales, and evaluate the saliency of each edge according to the edge energy existing in its whole life.
Second, we propose a new similarity measurement for directed tangents in con-tour grouping, which is called directed edge region measurement. We develop a graphic interactive tangent label tool, and by which we construct a standard and accurate human labeled directed tangents set. We discuss the key factors which impact the similarity measurement and give the best parameters according to nor-malized variation standard for similarity measurement on labeled directed tangents set. The directed edge region measurement for tangent similarity measurement over-comes the indefiniteness of tangent groups, which can improve the importance of similarity cue in contour grouping. Comparison with other similarity measurements on the tangents set shows that the directed edge region measurement is much more accurate.
Third, we construct a generative grouping cue combination model for contour grouping. This model makes no assumptions of the independence of grouping cues like other discriminative models, which can lead to a more satisfying description of the statistic properties of gestalt grouping cues. The generative model is a more exact gestalt cue combination model than other models. We use the proximity as a key grouping cue, and discuss the joint probability distribution of continuity and similarity in different proximity conditions. Using the generative cue combination model, we fit the joint probability distribution of continuity and similarity on human labeled set which has a special form, and give a more accurate description of the correlation of gestalt cues.
Forth, we propose a contour grouping algorithm guided by global saliency infor-mation, and realize the object-based attention model based on the hierarchical con-tour grouping algorithm. We use the global saliency information to guide the process of contour grouping on the basis of the research achievements about the attention role in perceptual organization in psychology, and obtain the contour grouping of salient perceptual objects in natural images. We consider both the same object ef-fect and inhibition of return in attention, and realize the hierarchical attention shift among perceptual objects using hierarchical contour grouping model. The experi-mental results on natural color images show that our contour grouping algorithm can group the salient perceptual objects and is more effective than other grouping algorithms in most images. Also, the attention shifts of object-based attention are hierarchical and are agreed with human visual perception.
将认知心理学和神经科学中有关知觉组织的研究成果应用到计算模型中,是建立符合人类感知特性的轮廓编组模型的关键。本文以心理学中格式塔的知觉组织规则为依据,将心理学和神经科学中的研究成果作为理论基础,从统计学的角度出发,强调注意对知觉组织过程的影响作用,提出了符合自然图像统计特性的格式塔编组线索量化模型,并构建了全局显著信息指导下的轮廓编组模型。
本文的研究内容依据建立轮廓编组模型的三个步骤可分为三大部分。第一部分从优化轮廓编组输入的角度出发,设计实现了适合于轮廓编组的自然图像中的边缘检测算法。第二部分通过分析人类所接受的外部信息的统计特性,建立了边缘间格式塔编组线索的量化模型。第三部分确定轮廓编组算法的优化目标和优化过程,从中体现出注意对知觉组织的作用,实现对自然图像的轮廓编组。本文的主要创新点有：
第一,提出了一种基于全局显著信息的多尺度边缘检测算法。与其它边缘检测算法相比,该算法能够获得较好的边缘检测结果,更符合轮廓编组的输入要求。算法采用非线性的方法将多种特征下的边缘检测结果进行融合,保证边缘的准确和完整；以图像中显著区域的边界位置作为边缘检测的空间先验知识,有效去除噪声和细节边缘；将空间位置相邻的边缘点连接成具有一定长度的边,确保检测结果的稳定性和对轮廓编组算法的适用性；最后在多尺度的变化中不断更新空间先验知识和追踪每条边缘的演化过程,用每条边从出现到消亡过程中的能量总和来度量其显著性。
第二,提出了轮廓编组中新的边缘相似性度量方法-有向边区域度量。利用自行开发的交互式的图形化标注工具,人工标注得到了规范且准确的有向边缘数据集,并在此数据集上,以正则化方差准则为依据,具体讨论了影响有向边相似性度量的几个关键因素,明确给出了有向边区域度量的最佳参数。有向边区域度量的边缘相似性度量方法克服了边缘连接方式的不确定性,能够有效提高相似性线索在轮廓编组中的重要性。在有向边缘数据集上的统计信息显示,有向边区域度量明显优于已有的其它边缘相似性度量方法。
第三,建立了轮廓编组中生成式的编组线索合并模型。结合认知心理学中有关格式塔规则的研究,将邻近性作为轮廓编组中的主导线索,讨论了在不同的邻近性条件下连续性和相似性线索的联合分布情况。用生成式的编组线索合并模型,拟合了连续性和相似性线索在人工标注数据集上具有特殊形式的联合分布,准确地描述了编组线索之间的相关性。此模型摒除了以往判别式模型中对于线索不相关的假设,更准确的拟合了由自然图像统计得到的格式塔编组线索的统计特性,是更为精确的格式塔线索合并模型。
第四,提出了全局显著信息指导下的轮廓编组算法,并通过对轮廓编组算法的层次化实现了基于目标的注意。该轮廓编组算法以心理学中有关注意对知觉组织作用的研究成果为依据,用全局显著信息来指导轮廓编组的过程,实现对自然图像中显著感知目标的轮廓编组。模拟注意中的同物效果和禁止返回机制,将轮廓编组算法层次化,实现了注意在感知目标中的层次化转移。在自然图像上的实验结果表明,该轮廓编组算法能够编组得到图像中的显著感知目标,在绝大多数情况下获得了比其它算法更好的编组结果。在此基础上实现的基于目标的注意,其注意焦点转移路径更加规整,也更加符合人类的视觉感知。
Perceptual organization is an important mechanism of human visual perception system. It attracts many researchers who employ themselves in neurophysiology, cognitive psychology, computer science and other fields in recent years. The process of perceptual organization is a link between the optical signals in natural world and the perceptual objects. It is also the basis of many high level visual tasks, such as image recognition, attention assignment, memory storage and so on. Contour grouping, which takes image edges as grouping elements, is an important part of perceptual organization. The contour grouping model can find salient structures in images, and is an important tool for the definition and obtainment of perceptual objects. It can be seemed as the foundation of constructing object-based attention model, object detection model and object recognition model. Researching the cogni-tive and neural mechanism of perceptual organization to design a contour grouping model with high efficiency which accords with human perception system is indis-pensable in the study of visual perception system inspired information processing theory.
Applying the research results about perceptual organization in cognitive psy-chology and neurophysiology into computational models is the key of constructing contour grouping models which accord with human perception characteristics. In this dissertation, we propose the quantized model of Gestalt grouping cues and con-struct a contour grouping model guided by global saliency information. All of these studies are based on the Gestalt grouping rules and the research results in psychol-ogy and neurophysiology, take Statistic as the tool, and mainly emphasize the role of attention in perceptual organization.
According to the three stage of constructing a contour grouping model, the study of this dissertation can be divided into three parts. The first part aims at improving the input quality of contour grouping. In this part, we design and realize the natural image edge detection algorithm which is suitable for contour grouping. The second part analyses the statistical properties of the natural images, and give a reasonable definition and quantization of gestalt grouping cues between directed tangents. The third part defines the grouping cost based on the role of attention in perceptual organization, gives the optimization of the grouping cost, and finally realizes the contour grouping in natural images. The main innovative points of the dissertation are as follows:
First, we propose a multi-scale boundary detection algorithm based on global saliency information. Compared with other algorithms, our algorithm can get better detection results, which are more proper for contour grouping. Nonlinear combina-tion of the edge detection results in multiple features can ensure the accuracy and integrity of the edges. The spatial prior getting from the boundaries of salient re-gions can remove noises and trivial edges effectively. Linking neighbor edge pixels to form edges with a certain length can make the detection results more steady and proper for contour grouping. We update the spatial prior and trace each edge across multiple scales, and evaluate the saliency of each edge according to the edge energy existing in its whole life.
Second, we propose a new similarity measurement for directed tangents in con-tour grouping, which is called directed edge region measurement. We develop a graphic interactive tangent label tool, and by which we construct a standard and accurate human labeled directed tangents set. We discuss the key factors which impact the similarity measurement and give the best parameters according to nor-malized variation standard for similarity measurement on labeled directed tangents set. The directed edge region measurement for tangent similarity measurement over-comes the indefiniteness of tangent groups, which can improve the importance of similarity cue in contour grouping. Comparison with other similarity measurements on the tangents set shows that the directed edge region measurement is much more accurate.
Third, we construct a generative grouping cue combination model for contour grouping. This model makes no assumptions of the independence of grouping cues like other discriminative models, which can lead to a more satisfying description of the statistic properties of gestalt grouping cues. The generative model is a more exact gestalt cue combination model than other models. We use the proximity as a key grouping cue, and discuss the joint probability distribution of continuity and similarity in different proximity conditions. Using the generative cue combination model, we fit the joint probability distribution of continuity and similarity on human labeled set which has a special form, and give a more accurate description of the correlation of gestalt cues.
Forth, we propose a contour grouping algorithm guided by global saliency infor-mation, and realize the object-based attention model based on the hierarchical con-tour grouping algorithm. We use the global saliency information to guide the process of contour grouping on the basis of the research achievements about the attention role in perceptual organization in psychology, and obtain the contour grouping of salient perceptual objects in natural images. We consider both the same object ef-fect and inhibition of return in attention, and realize the hierarchical attention shift among perceptual objects using hierarchical contour grouping model. The experi-mental results on natural color images show that our contour grouping algorithm can group the salient perceptual objects and is more effective than other grouping algorithms in most images. Also, the attention shifts of object-based attention are hierarchical and are agreed with human visual perception.
引文
[1]J. Duncan, G. Humphreys. Visual search and stimulus similarity. Psychological Review,1989.96:433-458.
[2]D. Marr. Vision. San Francisco:W. H. Freeman,1982.
[3]陈锋,韩世辉,朱滢.视知觉组织及其神经机制.心理科学,2003.26(2)：312-314.
[4]K. Koffka. Principles of Gestalt Psychology. New York:Brace,1923.
[5]S. Palmer. Common region:A new principle of perceptual grouping. Cognitive Psychology,1992.24:436-447.
[6]C. M. Moore, H. Egeth. Perception without attention:Evidence of grouping under conditions of inattention. Journal of Experimental Psychology:Human Perception and Performance,1997.23:339-352.
[7]韩世辉,G. W. Humphreys,李清阳.注意与非注意位置的知觉组织.中国科学C辑生命科学,2004.34(5)：471-480.
[8]M. I. Posner, C. R. R. Snyder, B. J. Davidson. Attention and the detection of signals. Journal of Experimental Psychology General,1980.109(1):160-174.
[9]邹琪.轮廓编组的计算模型和注意模型研究[博士学位论文].北京：北京交通大学,2006.
[10]C. P. Papageorgiou, M. Oren, T. Poggio. A general framework for object detection. IEEE International Conference on Computer Vision,1998. pp. 555-562.
[11]J. Shotton, A. Blake, R. Cipolla. Contour-based learning for object detection. IEEE International Conference on Computer Vision,2005.1:503-510.
[12]Q. Iqbal, J. K. Aggarwal. Applying perceptual grouping to content-based im-age retrieval:Building images. IEEE International Conference on Computer Vision and Pattern Recognition,1999.1:42-48.
[13]T. L. Wu, et al. Efficient shape matching for content-based image retrieval using perceptual grouping. International MultiConference of Engineers and Computer Scientists,2007. pp.2003-2008.
[14]J. H. Elder, A. Krupnik, L. A. Johnston. Contour grouping with prior mod-els. IEEE Transaction on Pattern Analysis and Machine Intelligence,2003. 25(6):661-674.
[15]T. Kadir, M. Brady. Scale, saliency and image description. International Journal of Computer Vision,2001.45(2):83-105.
[16]M. K. Kapadia, et al. Improvement in visual sensitivity by changes in lo-cal contex:parallel studies in human observers and in v1 of alert monkeys. Neuron,1995.15:843-856.
[17]U. Polat, et al. Collinear stimuli regulate visual responses depending on cell's contrast threshold. Nature,1998.391:580-584.
[18]Y. Sugita. Grouping of image fragments in primary visual cortex. Nature, 1999.401:269-272.
[19]A. Giersch, et al. The computation of occluded contours in visual agnosia:ev-idence for early computation prior to shape binding and figure-ground coding. Cognitive Neuropsychology,2002.17(8):731-759.
[20]S. H. Han, et al. Neural substrate for visual perceptual grouping in humans. Psychophysiology,2001.38:926-935.
[21]S. H. Han, Y. L. Ding, Y. Song. Heural mechanisms of perceptual grouping in humans as revealed by high density event related potentials. Neuroscience Letters,2002.319:29-32.
[22]陈霖.拓扑性质知觉——计算理论的一朵可能的乌云.关于思维科学,1986.pp.250-301.
[23]P. T. Quinlan, R. N. Wilton. Grouping by proximity or similarity? competi-tion between the gestalt principles in vision. Perception,1998.27:417-430.
[24]韩世辉,陈霖.注意对拓扑性质和局部几何性质检测的不同影响.心理学报,1994.26(3)：272-278.
[25]M. Gilbert, et al. Interactions between attention, context and learning in primary visual cortex. Vision Research,2000.40:1217-1226.
[26]B. Wang, et al. Global topological dominance in the left hemisphere. PNAS, 2007.104(52):21014-21019.
[27]J. Signorini. A computational model for perceptual grouping. International Workshop on Industrial Applications of Machine Intelligence and Vision, 1989. pp.315-320.
[28]V. Murino, G. L. Forestil, C. S. Regazzonil. A markovian model for perceptual grouping of different shape primitives. Lecture Notes in Computer Science: Intelligent Perceptual Systems,1993. pp.161-180.
[29]D. Domijan. Neural network for perceptual grouping and lightness perception. Perception 28 ECVP Abstract Supplement,1999.
[30]R. Miikkulainen, et al. Pglissom:A perceptual grouping model. Computa-tional Maps in the Visual Cortex,2005. pp.241-255.
[31]A. Treisman. The perception of features and objects. Oxford:Oxford Uni-versity Press,1993.
[32]J. Duncan. Selective attention and the organization of visual information. Journal of Experimental Psychology:General,1984.113:501-517.
[33]J. Duncan, G. Humphreys, R. Ward. Competitive brain activity in visual attention. Current Opinion in Neurobiology,1997.7:255-261.
[34]C. Koch, S. Ullman. Shifts in selective visual attention:towards the underlying neural circuitry. Hum Neurobiol,1985.4:219-227.
[35]A. M. Treisman, G. Gelade. A feature-integration theory of attention. Cogni-tive Psychology,1980.12(1):97-136.
[36]J. Triesch, et al. What you see is what you need. Journal of Vision,2003. 3:86-94.
[37]P. J. Burt. Smart sensing within a pyramid vision machine. Proceedings of the IEEE,1988.76:1006-1015.
[38]P. A. Sandon. Simulating visual attention. Journal of Cognitive Neuroscience, 1990.2(3):213-231.
[39]I. A. Rybak, et al. A model of attention-guided visual perception and recog-nition. Vision Research,1998.38:2387-2400.
[40]L. Itti, C. Koch, E. Niebur. A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998.20(11):1254-1259.
[41]N. M. Oliver, B. Rosario, A. Pentland. A bayesian computer vision system for modeling human interactions. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000.22(8):831-843.
[42]A. A. Salah, E. Alpaydin, L. Akarun. A selective attention-based method for visual pattern recognition with application to handwritten digit recognition and face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002.24(3):420-425.
[43]C. Soyer, H. I. Bozma, Y. Istefanopulos. Attentional sequence-based recogni-tion:Markovian and evidential reasoning. IEEE Trans. On Systems, Man, and Cybernetics-Part B:Cybernetics,2003.33(6):937-950.
[44]R. Desimone, J. Duncan. Neural mechanisms of selective visual attention. Ann. Rev. Neurosci.,1995.18:193-222.
[45]J. Duncan. Converging levels of analysis in the cognitive neuroscience of visual attention. Phil. Trans. R. Soc. Lond. B.,1998.353:1307-1317.
[46]S. Grossberg, R. Raizada. Contrast-sensitive perceptual grouping and object-based attention in the laminar circuits of primary visual cortex. Vision Re-serach,2000.40:1413-1432.
[47]Y. R. Sun, R. Fisher. Object-based visual attention for computer vision. Ar-tificial Intelligence,2003.146(1):77-123.
[48]D. Walther, C. Koch. Modeling attention to salient proto-objects. Neural Networks,2006.19:1395-1407.
[49]A. Sha'ashua, S. Ullman. Structural saliency:The detection of globally salient structures using locally connected network. Proc. Int'l Conf. Computer Vision,1988. pp.321-327.
[50]A. Amir, M. Lindenbaum. A generic grouping algorithm and its quantitative analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998.20(2):168-185.
[51]J. H. Elder, S. W. Zucker. Computing contour closure. Computer Vision (ECCV'96),1996. pp.399-412.
[52]J. Elder, R. Goldberg. Ecological statistics of gestalt laws for the perceptual organization of contours. Journal of Vision,2002.2(4):324-353.
[53]S. Wang, et al. Global detection of salient convex boundaries. International Journal of Computer Vision,2007.71(3):337-359.
[54]N. Adluru, et al. Contour grouping based on local symmetry. IEEE Interna-tional Conference on Computer Vision,2007. pp.1-8.
[55]S. Mahamud, et al. Segmentation of multiple salient closed contours from real images. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2003.25(4):433-444.
[56]S. Wang, T. Kubota, J. M. Siskind. Salient boundary detection using ratio contour. Neural Information Processing Systems Conference (NIPS),2003. pp.1571-1578.
[57]J. S. Stahl, S.Wang. Edge grouping combining boundary and region informa-tion. IEEE Transaction On Image Processing,2007.16(10):2590-2606.
[58]J. Stahl, K. Oliver, S. Wang. Openg boundary capable edge grouping with feature maps. IEEE Computer Society Workshop on Perceptual Organization in Computer Vision,2008. pp.1-8.
[59]L. Herault, R. Horaud. Figure-ground discrimination:a combinational opti-mization approach. IEEE Trans. On Pattern Analysis and Machine Intelli-gence,1993.15(9):899-914.
[60]A. Sha'ashua, S. Ullman. Grouping contours by iterated pairing network. Proceedings of the 1990 conference on Advances in neural information pro-cessing systems,1990.3:335-341.
[61]M. Tuceryan, A. Jain, N. Ahuja. Supervised classification of early percep-tual structure in dot patterns. Proceeding of the Interenational Conference of Pattern Recognition,1992. pp.88-91.
[62]Z. Wu, R. Leahy. An optimal graph theoretic approach to data clustering: Theory and application to image segmentation. IEEE Trans. On Pattern Analysis and Machine Intelligence,1993.15(11):1101-1113.
[63]S. Sarkar, P. Soundararajan. Supervised learning of large perceptual organi-zation:Graph spectral partitioning and learning automata. IEEE Trans. On Pattern Analysis and Machine Intelligence,2000.22(5):504-525.
[64]J. B. Shi, J. Malik. Normalized cuts and image segmentation. IEEE Trans. On Pattern Analysis and Machine Intelligence,2000.22(8):888-905.
[65]S. Wang, J. M. Siskind. Image segmentation with ratio cut. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003.25(6):675-690.
[66]D. Martin, et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. Proc.8th Int'l Conf. Computer Vision,2001.2:416-423.
[67]黄希庭.心理学导论(第二版).北京：人民教育出版社,2007.
[68]D. Todorovic. Gestalt principles. Scholarpedia,2008.3(12):5345.
[69]M. B. Ben-Av, D. Sagi. Perceptual grouping by similarity and proximity: Experimental results can be predicted by intensity autocorrelations. Vision Research,1995.35(6):853-866.
[70]G. Spinozzi, et al. The relative use of proximity, shape similarity and orien-tation as visual perceptual grouping cues in tufted capuchin monkeys (cebus apella) and humans (homo sapiens). Journal of Comparative Psychology,2009. 123:56-68.
[71]S. H. Han, G. W. Humphreys. Relationship between uniform connectedness and proximity in perceptual grouping. Science in China, series C,2003. 46(2):113-126.
[72]S. Palmer, I. Rock. Rethinking perceptual organization:The role of uniform connectedness. Psychonomic Bulletin and Review,1994.1:29-55.
[73]罗四维等.视觉感知系统信息处理理论.北京：电子工业出版社,2006.
[74]D. H. Hubel, T. N. Wiesel. Receptive fields, binocular interaction, and func-tional architecture in cat's visual cortex. Journal of physiology,1962.160:106-154.
[75]毛利华,et al.知觉组织在人类视觉皮层的神经机制.科学通报,2004.49(6)：544-548.
[76]S.0. Murray, P. Schrater, D. Kersten. Perceptual grouping and the interac-tions between visual cortical areas. Neural Networks,2004.17:695-705.
[77]F. Fang, D. Kersten, S.0. Murray. Perceptual grouping and inverse fmri activity patterns in human visual cortex. Journal of Vision,2008.8(7):2, 2-9.
[78]Neisser. Cognitive psychology. New York:Appleton-Century-Crofts,1967.
[79]A. Treisman. Perceptual grouping and attention in visual search for features and for objects. Journal of Experimental Psychology:Human Perception and Performance,1982.8:194-214.
[80]B. Julesz. A brief outline of the texton theory of human vision. Trends in Neurosciences,1984.7:41-45.
[81]J. Driver, et al. Segmentation, attention and phenomenal visual objects. Cog-nition,2001.80:61-95.
[82]J. T. Enns, A. Kingstone. Access to global and local properties in visual search for compound stimuli. Psychological Science,1995.6:283-291.
[83]R. Kimchi. Uniform connectedness and grouping in the perceptual organi-zation of hierarchical patterns. Journal of Experimental Psychology:Human Perception and Performance,1998.24:1105-1118.
[84]L. M. Trick, J. T. Enns. Clusters precede shapes in perceptual organization. Psychological Science,1997.8:124-129.
[85]A. Mack, et al. Perceptual organization and attention. Cognitive Psychology, 1992.24:475-501.
[86]R. Kimchi, I. Razpurker-Apfeld. Perceptual grouping and attention:Not all groupings are equal. Psychonomic bulletin and review,2004.11 (4): 687-696.
[87]F. Attneave. Some informational aspects of visual perception. Psychological Review,1954.61:183-193.
[88]H. B. Barlow. The codeing of sensory messages. Current problems in animal behavior, W. Thorpe and O. Zangwill (Eds),1961. pp.331-360.
[89]D. J. Field. Relations between the statistics of natural images and the response properties of cortical cells. Journal of the Optical Society of America A,1987. 4:2379-2394.
[90]B. A. Olshausen, D. J. Field. Emergence of simple-cell receptive field proper-ties by learning a sparse code for natural images. Nature,1996.381:607-609.
[91]E. Brunswik, J. Kamiya. Ecological cue-validity of'proximity' and of other gestalt factors. Journal of Psychology,1953.66:20-32.
[92]N. Kruger. Collinearity and parallelism are statistically signigicant second order relations of complex cell responses. Neural Processing Letters,1998. 8:117-129.
[93]M. Sigman, et al. On a common circle:Natural scenes and gestalt rules. Proceeding of the National Academy of Sciences,2001.98:1935-1940.
[94]W. S. Geisler, et al. Edge co-occurence in natural images predicts contour grouping performance. Vision Research,2001.41:711-724.
[95]J. Canny. A computational approach to edge detection. IEEE Trans. on Pattern Analysis and Machine Intelligence,1986.8:679-714.
[96]D. R. Martin, C. C. Fowlkes, J. Malik. Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans. on Pattern Analysis and Machine Intelligence,2004.26(5):530-549.
[97]季虎,et al.图像边缘提取方法及展望.计算机工程与应用,2004.14：70-73.
[98]C. H. Zhou, B. W. Bartlett. Cue combination and color edge detection in natural scenes. Journal of Vision,2008.8(4):1-25.
[99]董鸿燕.边缘检测的若干技术研究[博士学位论文].长沙：国防科学技术大学,2008.
[100]S. Mallat, S. F. Zhong. Characterization of signal from multiscale edge. IEEE Transactions on Pattern Analysis and Machine Intelligence,1992.14(7):710-732.
[101]T. Lindeberg. Edge detection and ridge detection with automatic scale selec-tion. International Journal of Computer Vision,1998.30(2):117-156.
[102]M. Tabb, N. Ahuja. Multiscale image segmentation by integrated edge and region detection. IEEE Transactions on Image Processing,1997.6(5):642-655.
[103]B. Sumengen, B. S. Manjunath. Multi-scale edge detection and image seg-mentation. European Signal Processing Conference (EUSIPCO),2005.
[104]X. F. Ren. Multi-scale improves boundary detection in natural images. Pro-ceedings of the 10th European Conference on Computer Vision,2008. pp.533-545.
[105]P. Felzenszwalb, D. McAllester. A min-cover approach for finding salient curves. Conference on Computer Vision and Pattern Recognition Workshop, 2006. p.185.
[106]D. Geman, B. Jedynak. An active testing model for tracking roads in satellite images. IEEE Trans On Pattern Analysis and Machine Intelligence,1996. 18(1):1-14.
[107]S. F. Zheng, Z. W. Tu, A. L. Yuille. Detecting object boundaries using low-mid-, and high-level information. IEEE Conference on Computer Vision and Pattern Recognition,2007. pp.1-8.
[108]P. Arbelaez. Boundary extraction in natural images using ultrametric contour maps. Conference on Computer Vision and Pattern Recognition Workshop, 2006. p.182.
[109]X. D. Hou, L. Q. Zhang. Saliency detection a spectral residual approach. IEEE Conference on Computer Vision and Pattern Recognition,2007. pp.1-8.
[110]X. D. Hou, L. Q. Zhang. Dynamic visual attention searching for coding length increments. Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems,2008. pp.681-688.
[111]田媚.模拟自顶向下视觉注意机制的感知模型研究[博士学位论文].北京：北京交通大学,2007.
[112]P. F. Felzenszwalb, D. P. Huttenlocher. Efficient graph-based image segmen-tation. International Journal of Computer Vision,2004.59(2):167-181.
[113]N.Otsu. A threshold selection method from gray-level histograms. IEEE Transaction on Systems, Man and Cybernetics,1979.9(1):62-66.
[114]廖灵芝.稀疏编码算法中的自适应问题研究[博士论文].北京：北京交通大学,2008.
[115]http://www.eecs.berkeley.edu/research/projects/cs/vision/grouping/segbench/.
[116]M. Maire, et al. Using contours to detect and localize junctions in natural images. IEEE Conference on Computer Vision and Pattern Recognition,2008. pp.1-8.
[117]P. Dollar, Z. W. Tu, S. Belongie. Supervised learning of edges and object boundaries. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2006.2:1964-1971.
[118]S. Wang, et al. Salient closed boundary extraction with ratio contour. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005.27(4):546-561.
[119]J. S. Stahl, S. Wang. Globally optimal grouping for symmetric closed bound-aries by combining boundary and region information. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008.30(3):395-411.
[120]J. Zhang, R. R. Korfhage. A distance and angle similarity measure method. Journal of the American Society for Information Science,1999.50(9):772-778.
[121]C. Carson, T. M. Blobworld. A system for region based image indexing and retrieval. IEEE Trans on pattern analysis and matching intelligence,2002. 24(8):1026-1038.
[122]赵玉凤,赵耀,朱振峰.一种新的基于区域的图像相似性计算.铁道学报,2007.29(1)：55-60.
[123]O. Maron, A. L. Ratan. Multiple-instance learning for natural scence classifica-tion. Proceedings of the 15th International Conference on Machine Learning, 1998. pp.341-349.
[124]L. Fei-Fei, P. Perona. A bayesian hierarchical model for learning natural scene categories. CVPR,2005. pp.524-531.
[125]F. Stentiford. Attention-based similarity. Pattern Recognition,2007.40:771-783.
[126]L. Gutmann. Course quantization techniques for correlation navigation. Pro-ceeding of the IEEE Conference on Decision and Control,1977. pp.1199-1202.
[127]B. A. Wandell. Foundations of vision. Sunderland:MA:Sinauer Associates, 1995.
[128]D. Mumford. Elastica and computer vision. Algebraic Geometry and Its Ap-plications,1994.
[129]K. K. Thornber, L. R. Williams. Analytic solution of stochastic completion fields. Biological Cybernetics,1996.75:141-151.
[130]L. R. Williams, D. W. Jacobs. Stochastic completion fields:A neural model of illusory contour shape and salience. Neural Computation,1997.9(4):837-858.
[131]Y. H. Liu, et al. A new model selection criterion based on information geom-etry. Proceedings of 7th International Conference on Signal Processing,2004. 2:1561-1564.
[132]A. Yuille, H. H. Biilthoff. Bayesian decision theory and psychophysics. In Perception as Bayesian inference, Cambridge University Press,1996. pp. 123-161.
[133]S. C. Zhu. Embedding gestalt laws in markov random fields. IEEE Trans. On Pattern Analysis and Machine Intelligence,1999.21(11):1170-1187.
[134]G. Medioni, M. Lee, C. Tang. A Computational Framework for Segmentation and Grouping. Elsevier Science B.V.,2000.
[135]Q. Zou, et al. Contour grouping with shape manifold and distance transform. International Conference on Pattern Recognition,2008. pp.1-4.
[136]L. R. Williams, K. K. Thornber. Orientation, scale and discontinuity as emergent properties of illusory contour shape. Neural Computation,2001. 13(8):1683-1711.
[137]R. K. Ahuja, T. L. Magnanti, J. B. Orlin. Network Flows:Theory, Algorithms, & Applications. Englewood Cliffs:Prentice Hall,1993.
[138]L. Itti, C. Koch. A saliency-based search mechanism for overt and covert shifts of visual attention. Vision Research,2000.40(10-12):1489-1506.
[139]邹琪,罗四维,郑宇.利用多尺度分析和编组的基于目标的注意计算模型.电子学报,2006.34(3)：559-562.
[140]X. P. Zhao, L. Wang, Z. Y. Hu. A perceptual object based attention mechanism for scene analysis. Journal of Image and Graphica,2006.11(2):281-288.
[2]D. Marr. Vision. San Francisco:W. H. Freeman,1982.
[3]陈锋,韩世辉,朱滢.视知觉组织及其神经机制.心理科学,2003.26(2)：312-314.
[4]K. Koffka. Principles of Gestalt Psychology. New York:Brace,1923.
[5]S. Palmer. Common region:A new principle of perceptual grouping. Cognitive Psychology,1992.24:436-447.
[6]C. M. Moore, H. Egeth. Perception without attention:Evidence of grouping under conditions of inattention. Journal of Experimental Psychology:Human Perception and Performance,1997.23:339-352.
[7]韩世辉,G. W. Humphreys,李清阳.注意与非注意位置的知觉组织.中国科学C辑生命科学,2004.34(5)：471-480.
[8]M. I. Posner, C. R. R. Snyder, B. J. Davidson. Attention and the detection of signals. Journal of Experimental Psychology General,1980.109(1):160-174.
[9]邹琪.轮廓编组的计算模型和注意模型研究[博士学位论文].北京：北京交通大学,2006.
[10]C. P. Papageorgiou, M. Oren, T. Poggio. A general framework for object detection. IEEE International Conference on Computer Vision,1998. pp. 555-562.
[11]J. Shotton, A. Blake, R. Cipolla. Contour-based learning for object detection. IEEE International Conference on Computer Vision,2005.1:503-510.
[12]Q. Iqbal, J. K. Aggarwal. Applying perceptual grouping to content-based im-age retrieval:Building images. IEEE International Conference on Computer Vision and Pattern Recognition,1999.1:42-48.
[13]T. L. Wu, et al. Efficient shape matching for content-based image retrieval using perceptual grouping. International MultiConference of Engineers and Computer Scientists,2007. pp.2003-2008.
[14]J. H. Elder, A. Krupnik, L. A. Johnston. Contour grouping with prior mod-els. IEEE Transaction on Pattern Analysis and Machine Intelligence,2003. 25(6):661-674.
[15]T. Kadir, M. Brady. Scale, saliency and image description. International Journal of Computer Vision,2001.45(2):83-105.
[16]M. K. Kapadia, et al. Improvement in visual sensitivity by changes in lo-cal contex:parallel studies in human observers and in v1 of alert monkeys. Neuron,1995.15:843-856.
[17]U. Polat, et al. Collinear stimuli regulate visual responses depending on cell's contrast threshold. Nature,1998.391:580-584.
[18]Y. Sugita. Grouping of image fragments in primary visual cortex. Nature, 1999.401:269-272.
[19]A. Giersch, et al. The computation of occluded contours in visual agnosia:ev-idence for early computation prior to shape binding and figure-ground coding. Cognitive Neuropsychology,2002.17(8):731-759.
[20]S. H. Han, et al. Neural substrate for visual perceptual grouping in humans. Psychophysiology,2001.38:926-935.
[21]S. H. Han, Y. L. Ding, Y. Song. Heural mechanisms of perceptual grouping in humans as revealed by high density event related potentials. Neuroscience Letters,2002.319:29-32.
[22]陈霖.拓扑性质知觉——计算理论的一朵可能的乌云.关于思维科学,1986.pp.250-301.
[23]P. T. Quinlan, R. N. Wilton. Grouping by proximity or similarity? competi-tion between the gestalt principles in vision. Perception,1998.27:417-430.
[24]韩世辉,陈霖.注意对拓扑性质和局部几何性质检测的不同影响.心理学报,1994.26(3)：272-278.
[25]M. Gilbert, et al. Interactions between attention, context and learning in primary visual cortex. Vision Research,2000.40:1217-1226.
[26]B. Wang, et al. Global topological dominance in the left hemisphere. PNAS, 2007.104(52):21014-21019.
[27]J. Signorini. A computational model for perceptual grouping. International Workshop on Industrial Applications of Machine Intelligence and Vision, 1989. pp.315-320.
[28]V. Murino, G. L. Forestil, C. S. Regazzonil. A markovian model for perceptual grouping of different shape primitives. Lecture Notes in Computer Science: Intelligent Perceptual Systems,1993. pp.161-180.
[29]D. Domijan. Neural network for perceptual grouping and lightness perception. Perception 28 ECVP Abstract Supplement,1999.
[30]R. Miikkulainen, et al. Pglissom:A perceptual grouping model. Computa-tional Maps in the Visual Cortex,2005. pp.241-255.
[31]A. Treisman. The perception of features and objects. Oxford:Oxford Uni-versity Press,1993.
[32]J. Duncan. Selective attention and the organization of visual information. Journal of Experimental Psychology:General,1984.113:501-517.
[33]J. Duncan, G. Humphreys, R. Ward. Competitive brain activity in visual attention. Current Opinion in Neurobiology,1997.7:255-261.
[34]C. Koch, S. Ullman. Shifts in selective visual attention:towards the underlying neural circuitry. Hum Neurobiol,1985.4:219-227.
[35]A. M. Treisman, G. Gelade. A feature-integration theory of attention. Cogni-tive Psychology,1980.12(1):97-136.
[36]J. Triesch, et al. What you see is what you need. Journal of Vision,2003. 3:86-94.
[37]P. J. Burt. Smart sensing within a pyramid vision machine. Proceedings of the IEEE,1988.76:1006-1015.
[38]P. A. Sandon. Simulating visual attention. Journal of Cognitive Neuroscience, 1990.2(3):213-231.
[39]I. A. Rybak, et al. A model of attention-guided visual perception and recog-nition. Vision Research,1998.38:2387-2400.
[40]L. Itti, C. Koch, E. Niebur. A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998.20(11):1254-1259.
[41]N. M. Oliver, B. Rosario, A. Pentland. A bayesian computer vision system for modeling human interactions. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000.22(8):831-843.
[42]A. A. Salah, E. Alpaydin, L. Akarun. A selective attention-based method for visual pattern recognition with application to handwritten digit recognition and face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002.24(3):420-425.
[43]C. Soyer, H. I. Bozma, Y. Istefanopulos. Attentional sequence-based recogni-tion:Markovian and evidential reasoning. IEEE Trans. On Systems, Man, and Cybernetics-Part B:Cybernetics,2003.33(6):937-950.
[44]R. Desimone, J. Duncan. Neural mechanisms of selective visual attention. Ann. Rev. Neurosci.,1995.18:193-222.
[45]J. Duncan. Converging levels of analysis in the cognitive neuroscience of visual attention. Phil. Trans. R. Soc. Lond. B.,1998.353:1307-1317.
[46]S. Grossberg, R. Raizada. Contrast-sensitive perceptual grouping and object-based attention in the laminar circuits of primary visual cortex. Vision Re-serach,2000.40:1413-1432.
[47]Y. R. Sun, R. Fisher. Object-based visual attention for computer vision. Ar-tificial Intelligence,2003.146(1):77-123.
[48]D. Walther, C. Koch. Modeling attention to salient proto-objects. Neural Networks,2006.19:1395-1407.
[49]A. Sha'ashua, S. Ullman. Structural saliency:The detection of globally salient structures using locally connected network. Proc. Int'l Conf. Computer Vision,1988. pp.321-327.
[50]A. Amir, M. Lindenbaum. A generic grouping algorithm and its quantitative analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998.20(2):168-185.
[51]J. H. Elder, S. W. Zucker. Computing contour closure. Computer Vision (ECCV'96),1996. pp.399-412.
[52]J. Elder, R. Goldberg. Ecological statistics of gestalt laws for the perceptual organization of contours. Journal of Vision,2002.2(4):324-353.
[53]S. Wang, et al. Global detection of salient convex boundaries. International Journal of Computer Vision,2007.71(3):337-359.
[54]N. Adluru, et al. Contour grouping based on local symmetry. IEEE Interna-tional Conference on Computer Vision,2007. pp.1-8.
[55]S. Mahamud, et al. Segmentation of multiple salient closed contours from real images. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2003.25(4):433-444.
[56]S. Wang, T. Kubota, J. M. Siskind. Salient boundary detection using ratio contour. Neural Information Processing Systems Conference (NIPS),2003. pp.1571-1578.
[57]J. S. Stahl, S.Wang. Edge grouping combining boundary and region informa-tion. IEEE Transaction On Image Processing,2007.16(10):2590-2606.
[58]J. Stahl, K. Oliver, S. Wang. Openg boundary capable edge grouping with feature maps. IEEE Computer Society Workshop on Perceptual Organization in Computer Vision,2008. pp.1-8.
[59]L. Herault, R. Horaud. Figure-ground discrimination:a combinational opti-mization approach. IEEE Trans. On Pattern Analysis and Machine Intelli-gence,1993.15(9):899-914.
[60]A. Sha'ashua, S. Ullman. Grouping contours by iterated pairing network. Proceedings of the 1990 conference on Advances in neural information pro-cessing systems,1990.3:335-341.
[61]M. Tuceryan, A. Jain, N. Ahuja. Supervised classification of early percep-tual structure in dot patterns. Proceeding of the Interenational Conference of Pattern Recognition,1992. pp.88-91.
[62]Z. Wu, R. Leahy. An optimal graph theoretic approach to data clustering: Theory and application to image segmentation. IEEE Trans. On Pattern Analysis and Machine Intelligence,1993.15(11):1101-1113.
[63]S. Sarkar, P. Soundararajan. Supervised learning of large perceptual organi-zation:Graph spectral partitioning and learning automata. IEEE Trans. On Pattern Analysis and Machine Intelligence,2000.22(5):504-525.
[64]J. B. Shi, J. Malik. Normalized cuts and image segmentation. IEEE Trans. On Pattern Analysis and Machine Intelligence,2000.22(8):888-905.
[65]S. Wang, J. M. Siskind. Image segmentation with ratio cut. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003.25(6):675-690.
[66]D. Martin, et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. Proc.8th Int'l Conf. Computer Vision,2001.2:416-423.
[67]黄希庭.心理学导论(第二版).北京：人民教育出版社,2007.
[68]D. Todorovic. Gestalt principles. Scholarpedia,2008.3(12):5345.
[69]M. B. Ben-Av, D. Sagi. Perceptual grouping by similarity and proximity: Experimental results can be predicted by intensity autocorrelations. Vision Research,1995.35(6):853-866.
[70]G. Spinozzi, et al. The relative use of proximity, shape similarity and orien-tation as visual perceptual grouping cues in tufted capuchin monkeys (cebus apella) and humans (homo sapiens). Journal of Comparative Psychology,2009. 123:56-68.
[71]S. H. Han, G. W. Humphreys. Relationship between uniform connectedness and proximity in perceptual grouping. Science in China, series C,2003. 46(2):113-126.
[72]S. Palmer, I. Rock. Rethinking perceptual organization:The role of uniform connectedness. Psychonomic Bulletin and Review,1994.1:29-55.
[73]罗四维等.视觉感知系统信息处理理论.北京：电子工业出版社,2006.
[74]D. H. Hubel, T. N. Wiesel. Receptive fields, binocular interaction, and func-tional architecture in cat's visual cortex. Journal of physiology,1962.160:106-154.
[75]毛利华,et al.知觉组织在人类视觉皮层的神经机制.科学通报,2004.49(6)：544-548.
[76]S.0. Murray, P. Schrater, D. Kersten. Perceptual grouping and the interac-tions between visual cortical areas. Neural Networks,2004.17:695-705.
[77]F. Fang, D. Kersten, S.0. Murray. Perceptual grouping and inverse fmri activity patterns in human visual cortex. Journal of Vision,2008.8(7):2, 2-9.
[78]Neisser. Cognitive psychology. New York:Appleton-Century-Crofts,1967.
[79]A. Treisman. Perceptual grouping and attention in visual search for features and for objects. Journal of Experimental Psychology:Human Perception and Performance,1982.8:194-214.
[80]B. Julesz. A brief outline of the texton theory of human vision. Trends in Neurosciences,1984.7:41-45.
[81]J. Driver, et al. Segmentation, attention and phenomenal visual objects. Cog-nition,2001.80:61-95.
[82]J. T. Enns, A. Kingstone. Access to global and local properties in visual search for compound stimuli. Psychological Science,1995.6:283-291.
[83]R. Kimchi. Uniform connectedness and grouping in the perceptual organi-zation of hierarchical patterns. Journal of Experimental Psychology:Human Perception and Performance,1998.24:1105-1118.
[84]L. M. Trick, J. T. Enns. Clusters precede shapes in perceptual organization. Psychological Science,1997.8:124-129.
[85]A. Mack, et al. Perceptual organization and attention. Cognitive Psychology, 1992.24:475-501.
[86]R. Kimchi, I. Razpurker-Apfeld. Perceptual grouping and attention:Not all groupings are equal. Psychonomic bulletin and review,2004.11 (4): 687-696.
[87]F. Attneave. Some informational aspects of visual perception. Psychological Review,1954.61:183-193.
[88]H. B. Barlow. The codeing of sensory messages. Current problems in animal behavior, W. Thorpe and O. Zangwill (Eds),1961. pp.331-360.
[89]D. J. Field. Relations between the statistics of natural images and the response properties of cortical cells. Journal of the Optical Society of America A,1987. 4:2379-2394.
[90]B. A. Olshausen, D. J. Field. Emergence of simple-cell receptive field proper-ties by learning a sparse code for natural images. Nature,1996.381:607-609.
[91]E. Brunswik, J. Kamiya. Ecological cue-validity of'proximity' and of other gestalt factors. Journal of Psychology,1953.66:20-32.
[92]N. Kruger. Collinearity and parallelism are statistically signigicant second order relations of complex cell responses. Neural Processing Letters,1998. 8:117-129.
[93]M. Sigman, et al. On a common circle:Natural scenes and gestalt rules. Proceeding of the National Academy of Sciences,2001.98:1935-1940.
[94]W. S. Geisler, et al. Edge co-occurence in natural images predicts contour grouping performance. Vision Research,2001.41:711-724.
[95]J. Canny. A computational approach to edge detection. IEEE Trans. on Pattern Analysis and Machine Intelligence,1986.8:679-714.
[96]D. R. Martin, C. C. Fowlkes, J. Malik. Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans. on Pattern Analysis and Machine Intelligence,2004.26(5):530-549.
[97]季虎,et al.图像边缘提取方法及展望.计算机工程与应用,2004.14：70-73.
[98]C. H. Zhou, B. W. Bartlett. Cue combination and color edge detection in natural scenes. Journal of Vision,2008.8(4):1-25.
[99]董鸿燕.边缘检测的若干技术研究[博士学位论文].长沙：国防科学技术大学,2008.
[100]S. Mallat, S. F. Zhong. Characterization of signal from multiscale edge. IEEE Transactions on Pattern Analysis and Machine Intelligence,1992.14(7):710-732.
[101]T. Lindeberg. Edge detection and ridge detection with automatic scale selec-tion. International Journal of Computer Vision,1998.30(2):117-156.
[102]M. Tabb, N. Ahuja. Multiscale image segmentation by integrated edge and region detection. IEEE Transactions on Image Processing,1997.6(5):642-655.
[103]B. Sumengen, B. S. Manjunath. Multi-scale edge detection and image seg-mentation. European Signal Processing Conference (EUSIPCO),2005.
[104]X. F. Ren. Multi-scale improves boundary detection in natural images. Pro-ceedings of the 10th European Conference on Computer Vision,2008. pp.533-545.
[105]P. Felzenszwalb, D. McAllester. A min-cover approach for finding salient curves. Conference on Computer Vision and Pattern Recognition Workshop, 2006. p.185.
[106]D. Geman, B. Jedynak. An active testing model for tracking roads in satellite images. IEEE Trans On Pattern Analysis and Machine Intelligence,1996. 18(1):1-14.
[107]S. F. Zheng, Z. W. Tu, A. L. Yuille. Detecting object boundaries using low-mid-, and high-level information. IEEE Conference on Computer Vision and Pattern Recognition,2007. pp.1-8.
[108]P. Arbelaez. Boundary extraction in natural images using ultrametric contour maps. Conference on Computer Vision and Pattern Recognition Workshop, 2006. p.182.
[109]X. D. Hou, L. Q. Zhang. Saliency detection a spectral residual approach. IEEE Conference on Computer Vision and Pattern Recognition,2007. pp.1-8.
[110]X. D. Hou, L. Q. Zhang. Dynamic visual attention searching for coding length increments. Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems,2008. pp.681-688.
[111]田媚.模拟自顶向下视觉注意机制的感知模型研究[博士学位论文].北京：北京交通大学,2007.
[112]P. F. Felzenszwalb, D. P. Huttenlocher. Efficient graph-based image segmen-tation. International Journal of Computer Vision,2004.59(2):167-181.
[113]N.Otsu. A threshold selection method from gray-level histograms. IEEE Transaction on Systems, Man and Cybernetics,1979.9(1):62-66.
[114]廖灵芝.稀疏编码算法中的自适应问题研究[博士论文].北京：北京交通大学,2008.
[115]http://www.eecs.berkeley.edu/research/projects/cs/vision/grouping/segbench/.
[116]M. Maire, et al. Using contours to detect and localize junctions in natural images. IEEE Conference on Computer Vision and Pattern Recognition,2008. pp.1-8.
[117]P. Dollar, Z. W. Tu, S. Belongie. Supervised learning of edges and object boundaries. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2006.2:1964-1971.
[118]S. Wang, et al. Salient closed boundary extraction with ratio contour. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005.27(4):546-561.
[119]J. S. Stahl, S. Wang. Globally optimal grouping for symmetric closed bound-aries by combining boundary and region information. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008.30(3):395-411.
[120]J. Zhang, R. R. Korfhage. A distance and angle similarity measure method. Journal of the American Society for Information Science,1999.50(9):772-778.
[121]C. Carson, T. M. Blobworld. A system for region based image indexing and retrieval. IEEE Trans on pattern analysis and matching intelligence,2002. 24(8):1026-1038.
[122]赵玉凤,赵耀,朱振峰.一种新的基于区域的图像相似性计算.铁道学报,2007.29(1)：55-60.
[123]O. Maron, A. L. Ratan. Multiple-instance learning for natural scence classifica-tion. Proceedings of the 15th International Conference on Machine Learning, 1998. pp.341-349.
[124]L. Fei-Fei, P. Perona. A bayesian hierarchical model for learning natural scene categories. CVPR,2005. pp.524-531.
[125]F. Stentiford. Attention-based similarity. Pattern Recognition,2007.40:771-783.
[126]L. Gutmann. Course quantization techniques for correlation navigation. Pro-ceeding of the IEEE Conference on Decision and Control,1977. pp.1199-1202.
[127]B. A. Wandell. Foundations of vision. Sunderland:MA:Sinauer Associates, 1995.
[128]D. Mumford. Elastica and computer vision. Algebraic Geometry and Its Ap-plications,1994.
[129]K. K. Thornber, L. R. Williams. Analytic solution of stochastic completion fields. Biological Cybernetics,1996.75:141-151.
[130]L. R. Williams, D. W. Jacobs. Stochastic completion fields:A neural model of illusory contour shape and salience. Neural Computation,1997.9(4):837-858.
[131]Y. H. Liu, et al. A new model selection criterion based on information geom-etry. Proceedings of 7th International Conference on Signal Processing,2004. 2:1561-1564.
[132]A. Yuille, H. H. Biilthoff. Bayesian decision theory and psychophysics. In Perception as Bayesian inference, Cambridge University Press,1996. pp. 123-161.
[133]S. C. Zhu. Embedding gestalt laws in markov random fields. IEEE Trans. On Pattern Analysis and Machine Intelligence,1999.21(11):1170-1187.
[134]G. Medioni, M. Lee, C. Tang. A Computational Framework for Segmentation and Grouping. Elsevier Science B.V.,2000.
[135]Q. Zou, et al. Contour grouping with shape manifold and distance transform. International Conference on Pattern Recognition,2008. pp.1-4.
[136]L. R. Williams, K. K. Thornber. Orientation, scale and discontinuity as emergent properties of illusory contour shape. Neural Computation,2001. 13(8):1683-1711.
[137]R. K. Ahuja, T. L. Magnanti, J. B. Orlin. Network Flows:Theory, Algorithms, & Applications. Englewood Cliffs:Prentice Hall,1993.
[138]L. Itti, C. Koch. A saliency-based search mechanism for overt and covert shifts of visual attention. Vision Research,2000.40(10-12):1489-1506.
[139]邹琪,罗四维,郑宇.利用多尺度分析和编组的基于目标的注意计算模型.电子学报,2006.34(3)：559-562.
[140]X. P. Zhao, L. Wang, Z. Y. Hu. A perceptual object based attention mechanism for scene analysis. Journal of Image and Graphica,2006.11(2):281-288.