多图像全景拼接技术研究
摘要
全景图像拼接技术是数字图像处理领域的一个重要的研究方向,在文物保护(古籍或古文字资料保护)、计算机视觉、遥感图像处理、医学图像分析、计算机图形学等领域有着重要的应用价值。
一个完整的图像拼接过程主要包括图像获取,图像配准,投影,图像融合等几个步骤,而其中的图像配准和图像融合是关键,若是多幅图像的拼接,还得考虑图像的排序。因此本文的研究也就着重于这三个方面。
在图像配准方面,本文通过对基于灰度信息与基于特征的几种配准算法进行较深入研究后,选择采用基于尺度不变特征变换(Scale Invariant Feature Transform, SIFT)的图像配准方式。针对研究中发现的问题,提出了一种改进的匹配算法,即距离、角度、随机抽样一致性(Random Sample Consensus, RANSAC)三者相结合的算法。同时将匹配阶段分为粗匹配和细匹配两个部分。在粗匹配阶段,利用SIFT的特性将距离和角度结合,利用相似性来剔除误配点。在细匹配阶段,使用RANSAC算法提纯特征点并得到图像间的单应性矩阵,完成配准。实验结果表明：该算法与其他所选方法相比,耗时相当,精度更高,是一种不错的匹配方案。
在图像融合方面,首先叙述了图像融合中的几种典型算法,接着对加权平均法,渐进渐出法和金字塔式融合分别进行了实验。实验结果表明：加权平均法运算简单,但效果最差；渐进渐出法改善了加权平均法的缺点,效果较好；基于金字塔式的融合,效果最好,没有明显的缺陷,但耗时较高。最后,根据实验结果,选择使用渐进渐出的融合算法。
在图像排序方面,利用图像配准阶段算法的特点,使用基于粗匹配阶段的相匹配特征点对数来进行排序,匹配对数量多的就可能有匹配关系,最后利用概率模型来确认这种匹配关系。
在此基础上,提出了一种自动的全景图像拼接方案,并进行了实验,其结果表明,该方案能对多幅图像进行排序,能剔除图像集合中不相关的噪声图像,拼接后的图像效果较好,速度合理,达到了预期的目的。
The panoramic image mosaic technology is an important research direction in the field of digital image processing. There has a wide range of important practical value on protection of cultural relics(ancient or ancient text data protection), computer vision, remote sensing image processing, medical image analysis, computer graphics etc.
A complete image mosaic process includes image acquisition, image registration, projection and image fusion etc. The key steps are image registration and image fusion. It has to consider the sort of image if the mosaic object is an image sequence. So, this paper focuses on these three points.
In image registration, this paper choose an image registration method based on Scale Invariant Feature Transform(SIFT) after study deeply on based on gray information and the fcature of image registration algorithm. Propose an improved matching algorithm which is a distance, angle and Random Sample Conscnsus(RANSAC) combination of the three algorithms. The matching stage is divided into coarse matching and fine matching of two parts. In the coarse matching stage, use the SIFT to combine with distance and angle and weed out mismatches points with similarity. In the fine matching stage, use the RANSAC algorithm purification feature points and obtain the homography between images to complete the registration. The experimental results show that proposed algorithm compare with other algorithm has higher accuracy and time-consuming almost equal. It's a good matching plan.
In image fusion, this paper describes several typical algorithms, and then do experiment on weighted average fusion, fading in and out fusion and pyramid fusion. These experimental results indicate that the weighted average fusion is the simplest but least effective, the fading in and out fusion improve the shortcomings of the weighted average fusion and the effect is good. The pyramid fusion is the best, no obvious defects, but time-consuming higher. Based on the experimental results, choose to use the fading in and out fusion algorithm.
In image sorting, using the feature of the image registration stage which are the number of matching points to do sorting. The most number of the matching points is the most likely to have matching relations and then use a probabilistic method to make sure this relations.
Based on these, propose an automated panoramic image mosaic program and do experiment. The results indicate that this program can sort the unsorted images automatically, and able to remove the independent images out of the sequence. After image mosaic, the result is good, the speed is reasonable, achieve the intended purpose.
一个完整的图像拼接过程主要包括图像获取,图像配准,投影,图像融合等几个步骤,而其中的图像配准和图像融合是关键,若是多幅图像的拼接,还得考虑图像的排序。因此本文的研究也就着重于这三个方面。
在图像配准方面,本文通过对基于灰度信息与基于特征的几种配准算法进行较深入研究后,选择采用基于尺度不变特征变换(Scale Invariant Feature Transform, SIFT)的图像配准方式。针对研究中发现的问题,提出了一种改进的匹配算法,即距离、角度、随机抽样一致性(Random Sample Consensus, RANSAC)三者相结合的算法。同时将匹配阶段分为粗匹配和细匹配两个部分。在粗匹配阶段,利用SIFT的特性将距离和角度结合,利用相似性来剔除误配点。在细匹配阶段,使用RANSAC算法提纯特征点并得到图像间的单应性矩阵,完成配准。实验结果表明：该算法与其他所选方法相比,耗时相当,精度更高,是一种不错的匹配方案。
在图像融合方面,首先叙述了图像融合中的几种典型算法,接着对加权平均法,渐进渐出法和金字塔式融合分别进行了实验。实验结果表明：加权平均法运算简单,但效果最差；渐进渐出法改善了加权平均法的缺点,效果较好；基于金字塔式的融合,效果最好,没有明显的缺陷,但耗时较高。最后,根据实验结果,选择使用渐进渐出的融合算法。
在图像排序方面,利用图像配准阶段算法的特点,使用基于粗匹配阶段的相匹配特征点对数来进行排序,匹配对数量多的就可能有匹配关系,最后利用概率模型来确认这种匹配关系。
在此基础上,提出了一种自动的全景图像拼接方案,并进行了实验,其结果表明,该方案能对多幅图像进行排序,能剔除图像集合中不相关的噪声图像,拼接后的图像效果较好,速度合理,达到了预期的目的。
The panoramic image mosaic technology is an important research direction in the field of digital image processing. There has a wide range of important practical value on protection of cultural relics(ancient or ancient text data protection), computer vision, remote sensing image processing, medical image analysis, computer graphics etc.
A complete image mosaic process includes image acquisition, image registration, projection and image fusion etc. The key steps are image registration and image fusion. It has to consider the sort of image if the mosaic object is an image sequence. So, this paper focuses on these three points.
In image registration, this paper choose an image registration method based on Scale Invariant Feature Transform(SIFT) after study deeply on based on gray information and the fcature of image registration algorithm. Propose an improved matching algorithm which is a distance, angle and Random Sample Conscnsus(RANSAC) combination of the three algorithms. The matching stage is divided into coarse matching and fine matching of two parts. In the coarse matching stage, use the SIFT to combine with distance and angle and weed out mismatches points with similarity. In the fine matching stage, use the RANSAC algorithm purification feature points and obtain the homography between images to complete the registration. The experimental results show that proposed algorithm compare with other algorithm has higher accuracy and time-consuming almost equal. It's a good matching plan.
In image fusion, this paper describes several typical algorithms, and then do experiment on weighted average fusion, fading in and out fusion and pyramid fusion. These experimental results indicate that the weighted average fusion is the simplest but least effective, the fading in and out fusion improve the shortcomings of the weighted average fusion and the effect is good. The pyramid fusion is the best, no obvious defects, but time-consuming higher. Based on the experimental results, choose to use the fading in and out fusion algorithm.
In image sorting, using the feature of the image registration stage which are the number of matching points to do sorting. The most number of the matching points is the most likely to have matching relations and then use a probabilistic method to make sure this relations.
Based on these, propose an automated panoramic image mosaic program and do experiment. The results indicate that this program can sort the unsorted images automatically, and able to remove the independent images out of the sequence. After image mosaic, the result is good, the speed is reasonable, achieve the intended purpose.
引文
[1]解凯,郭恒业,张田文.图像Mosaics技术综述[J].电子学报,2004,4(4)：630-634.
[2]陈佃苹.基于特征向量的图像配准算法分析及其在医学超声图像中的应用[D].山东：山东大学,2009.
[3]Liu, J.&L. Li. A Brief Introduction of Reconstruction Technology of Distant Medical Consultation for Large Image[J]. china Contemporary medicine,2000,6(10):62-64.
[4]聂生东,司京玉.医学显微图像自动拼接的算法研究[J].中国生物医学工程学报,2005,24(2)：143-177.
[5]蔡毅,胡旭.短波红外成像技术及其军事应用[J].红外与激光工程,2006,35(6)：643-647
[6]温红艳.遥感图像拼接算法研究[D].湖北：华中科技大学,2009.
[7]xiong Y, Turkowski. Creating image-based VR using a self-calibration fisheye lens[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1997:237-243.
[8]蔡勇,刘学慧,吴恩华.基于图像绘制的虚拟现实系统环境[J].软件学报.1997,8(10)：721-728.
[9]陈永强,王启付.虚拟环境中变形图像拼接技术研究[J].华中科技大学学报.2001,29(1)：14-16.
[10]Chen S E. QuickTime VR-An image-based approach to virtual environment. In:Proceedings of the SIGGRAPH'95. Los Angeles. LA, USA,1995.29-38.
[11]Brown L.G. A survey of image registration techniques[J]. ACM Surveys, vol.24, no.4:325-376,1992.
[12]Zitova B, Flusser J. Image registration methods:a survey[J]. Image and Vision Computing, vol.21, no.11:977-1000,2003.
[13]FONSECA Leila M G, COSTA M H M. Automatic registration of satellite images[A]. IEEE Brazilian Symposium on Computer Graphics and Image Processing[C]. Campos do Jordo, BRAZIL:IEEE,219-226,1997.
[14]HSIEH J W, LIAO H Y M, FAN K C.eta. Image registration using a new edge-based approach[J]. Computer Vision and Image Understanding, vol.67,no.2:112-130,1997.
[15]钮永胜.可见光与热红外图像配准技术研究博十后出站报告[R].北京理工大学光电工程系,1999.
[16]赵向阳,杜利民,一种全自动稳健的图像拼接融合算法[J].中国图象图形学报,9(4)：417422,2004.
[17]周鹏,谭勇,徐守时.基予角点检测图像配准的一种新算法[J].中国科学技术大学学报,32(4)：455-461,2002.
[18]I1-Kyun Jung, Lacroix S. A robust interest points matching algotithm[A]. Proceedings of Eoghth IEEE international Conference on Computer Vision[C]. Vancouver, BC, Canada:IEEE, vol.2:538-543,2001.
[19]HUI Li, MANJUNATH B S. A contour-based approach to multisensor image registration[J]. IEEE Transactions on Image Processing, vol.4, no.3:320-334,1995.
[20]Maciej ZASUWA, Marcin ZUGAJ, Ryszard VOGT. System Identyfikacji I Pozpoznawania Celow Dla Mozdzierzowego Pocisku Sterowanego[J]. Instytut Techniki Lotniczej I Mechaniki Stosowanej:133-140,2004.
[21]F. Javier Varas, Francisco J. Busto, Manrico Fedi. An Heterogeneous, multi-source data fusion(MSDF) system based on a blaceboard/multi-agent architecture applied to the tasks of landmine detection and minefield delineation[C]. Prceedings of the 10th Mediterranean Conference on Control and Automation-MED2002, Lisbon, Portugal,2002.
[22]TON J, JAIN A K. Registering Landsat images by point matching[J]. IEEE Trasactions on Geoscience and Remote Sensing, vol.27,no.5:642-651,1989.
[23]XIE Zhi-yong. Image registration using hierarchical B-Splines[D]. USA:Arizona state university,2002.
[24]Barnea D I, Silverman H F. A class of algorithms for fast digital registration[J]. IEEE Trans. Computer, no.21:179-186,1972.
[25]KUGLIN C D, HINES D C. The phase correlation image alignment method[A]. Proceedings of 1975 IEEE International Conference on Cybernetics and Society[C]. New York, USA: IEEE:163-165,1975.
[26]王小睿,吴信才,李军.模拟退火算法的改进策略在模板匹配上的应用[J].小型微型计算机系统,18(8)：32-37,1997.
[27]AVERBUCH A, KELLER Y. FFT based image registration[A]. Proceedings of 2002 IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Orlando, USA:IEEE, vol.4:1608-3611,2002.
[28]Yao Jianchao. Image registration based on both feature and intensity matching[A]. Proceeding of 2001 IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Kauai, Hawaii, USA:IEEE, vol.3:1693-1696,2001.
[29]Richard Szeliski. Video mosaics for virtual environments[J]. Computer Graphics and Applications, IEEE, Mar 1996,16(2):22-30.
[30]Peleg S, Rousso B. Mosaicing on adaptive manifolds. IEEE Transactions on PAMI, 2000.22(10):1144-1154.
[31]S. Gumustedin R.W.Hall, Mosaic image generation on a flattened Gaussian sphere. In Proc. Of IEEE Workshop on Applications of Computer Vision, pp:50-55,1996.
[32]S. Gumustekin R.W.Hall. Image registration and mosaicking using a self calibration camera. In proc of IEEE Int. Conf. on Image Prcoessing,1998.
[33]Matthew Uyttendaele, Ashley Eden, Richard Szeliski. Eliminating ghosting and exposure artifacts in image mosaics[C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Hawaii,2001:209-516
[34]Davis J. Mosaics of scenes with moving objects[C]. Proceedings of 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Santa Barbara, CA, USA, 1998:354-360
[35]C.GHarris, M.Stephens. A combined corner and edge detector[C]. Proceedings of the 4th Alvey Vision Conference,1988:147-151.
[36]D. Lowe. Object Recognition from Local Scale-Invariant Features[J]. IJCV,1999:1150-1157.
[37]D. Lowe. Distinctive Image Features from Scale-Invariant Interest Points[J]. IJCV,2004, 60(2):91-110.
[38]Besl, P.&N. Mckay. A method for registration of 3-d shapes[J]. IEEE Trans. Pattern Anal. Mach. Intell.1992,14(2):239-256.
[39]Cheng, S. H.&F. H. Cheng &H. W. Hsu etal. Fast algorithm for point pattern matching: invariant to translations, rotations and scale changes[J]. Pattern Recognition,1997,30(2):311-320.
[40]Zhang,J.& Robert R. Korfhage. A Distance and Angle Similarity Measure Method. Journal ol the American Society for Information Science,50(9):772-778,1999
[41]L. Kitchen, A. Rosenfeld. Gray-level corner detection[J]. Pattern Recognition,1982:95-102.
[42]M. Brown, D.GLowe. Recognizing panoramas[A]. In:Proceedings of the IEEE Ninth International Conference on Computer Vision, Washington, DC, USA,2003,2:1218-1225.
[43]胡社教,葛西旺,苏菱.基于相位相关的全景图像拼接[J].合肥工业大学学.2007,30(1)：29-32.
[44]吴宪祥,郭宝龙,王娟.基于相位相关的柱面全景图像自动拼接算法[J].光学学报,2009,29(7)：1824-1829.
[45]李忠新,茅耀斌,王执铨.一种基于频域相关技术的柱面全景图生成方法[J].计算机工程与应用,2004,11：81-82.
[46]王字,王涌大,刘越.基于SIFT和小波变换的图像拼按算法[J].北京理工大学学报,2009,29(5)：423-426.
[47]苗立刚.基于手持相机的文档图像拼接算法[J].中国图象图形学报,2009,14(8)：1656-1662.
[48]邹北骥,阮鹏,向遥,贺加贝.一种精确匹配的全景图自动拼接算法[J].计算机工程与科学，2010,32(8)：60-63.
[49]阮鹏.多图像拼接算法研究[D].湖南：中南大学,2009.
[50]Graeme P. Penney, Jurgen Weese, John A. Little, Paul Desmedt, Derek L. G. Hill, and David J. Hawkes. A Comparison of Similarity Measures for Use in 2-D-3-D Medical Image Registration[J].IEEE TRANSACTIONS ON MEDICAL IMAGING,1998,17(4):586-595.
[51]Shu-Kai S.Fan, Yu-Chiang Chuang. A New Image Registration Method Using Intensity Difference Data on Overlapped Image[J]. In Proceeding of 2010 Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing,2010, pp.138-141.
[52]王勇,何晓川,刘清华,等.一种感兴趣区域寻优搜索的全自动图像拼接算法[J],电子与信息学报,2009,31(2)：261-264.
[53]冯宇平,戴明,孙立悦,张威.图像自动拼接融合的优化设计[J],光学精密工程,2010,18(2)：470-476
[54]王雷斌.基于计算机视觉的图像拼接技术研究[D].北京：首都师范大学,2008.
[55]林景亮,陈岳林.多摄像机图像拼接自动色彩均衡算法[J].计算机应用,2010,30(12)：3236-3237.
[56]David L. Milgram. Adaptive Techniques for Photomosaicking[J]. IEEE TRANSACTIONS ON COMPUTERS,1977,26(11):1175-1180.
[2]陈佃苹.基于特征向量的图像配准算法分析及其在医学超声图像中的应用[D].山东：山东大学,2009.
[3]Liu, J.&L. Li. A Brief Introduction of Reconstruction Technology of Distant Medical Consultation for Large Image[J]. china Contemporary medicine,2000,6(10):62-64.
[4]聂生东,司京玉.医学显微图像自动拼接的算法研究[J].中国生物医学工程学报,2005,24(2)：143-177.
[5]蔡毅,胡旭.短波红外成像技术及其军事应用[J].红外与激光工程,2006,35(6)：643-647
[6]温红艳.遥感图像拼接算法研究[D].湖北：华中科技大学,2009.
[7]xiong Y, Turkowski. Creating image-based VR using a self-calibration fisheye lens[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1997:237-243.
[8]蔡勇,刘学慧,吴恩华.基于图像绘制的虚拟现实系统环境[J].软件学报.1997,8(10)：721-728.
[9]陈永强,王启付.虚拟环境中变形图像拼接技术研究[J].华中科技大学学报.2001,29(1)：14-16.
[10]Chen S E. QuickTime VR-An image-based approach to virtual environment. In:Proceedings of the SIGGRAPH'95. Los Angeles. LA, USA,1995.29-38.
[11]Brown L.G. A survey of image registration techniques[J]. ACM Surveys, vol.24, no.4:325-376,1992.
[12]Zitova B, Flusser J. Image registration methods:a survey[J]. Image and Vision Computing, vol.21, no.11:977-1000,2003.
[13]FONSECA Leila M G, COSTA M H M. Automatic registration of satellite images[A]. IEEE Brazilian Symposium on Computer Graphics and Image Processing[C]. Campos do Jordo, BRAZIL:IEEE,219-226,1997.
[14]HSIEH J W, LIAO H Y M, FAN K C.eta. Image registration using a new edge-based approach[J]. Computer Vision and Image Understanding, vol.67,no.2:112-130,1997.
[15]钮永胜.可见光与热红外图像配准技术研究博十后出站报告[R].北京理工大学光电工程系,1999.
[16]赵向阳,杜利民,一种全自动稳健的图像拼接融合算法[J].中国图象图形学报,9(4)：417422,2004.
[17]周鹏,谭勇,徐守时.基予角点检测图像配准的一种新算法[J].中国科学技术大学学报,32(4)：455-461,2002.
[18]I1-Kyun Jung, Lacroix S. A robust interest points matching algotithm[A]. Proceedings of Eoghth IEEE international Conference on Computer Vision[C]. Vancouver, BC, Canada:IEEE, vol.2:538-543,2001.
[19]HUI Li, MANJUNATH B S. A contour-based approach to multisensor image registration[J]. IEEE Transactions on Image Processing, vol.4, no.3:320-334,1995.
[20]Maciej ZASUWA, Marcin ZUGAJ, Ryszard VOGT. System Identyfikacji I Pozpoznawania Celow Dla Mozdzierzowego Pocisku Sterowanego[J]. Instytut Techniki Lotniczej I Mechaniki Stosowanej:133-140,2004.
[21]F. Javier Varas, Francisco J. Busto, Manrico Fedi. An Heterogeneous, multi-source data fusion(MSDF) system based on a blaceboard/multi-agent architecture applied to the tasks of landmine detection and minefield delineation[C]. Prceedings of the 10th Mediterranean Conference on Control and Automation-MED2002, Lisbon, Portugal,2002.
[22]TON J, JAIN A K. Registering Landsat images by point matching[J]. IEEE Trasactions on Geoscience and Remote Sensing, vol.27,no.5:642-651,1989.
[23]XIE Zhi-yong. Image registration using hierarchical B-Splines[D]. USA:Arizona state university,2002.
[24]Barnea D I, Silverman H F. A class of algorithms for fast digital registration[J]. IEEE Trans. Computer, no.21:179-186,1972.
[25]KUGLIN C D, HINES D C. The phase correlation image alignment method[A]. Proceedings of 1975 IEEE International Conference on Cybernetics and Society[C]. New York, USA: IEEE:163-165,1975.
[26]王小睿,吴信才,李军.模拟退火算法的改进策略在模板匹配上的应用[J].小型微型计算机系统,18(8)：32-37,1997.
[27]AVERBUCH A, KELLER Y. FFT based image registration[A]. Proceedings of 2002 IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Orlando, USA:IEEE, vol.4:1608-3611,2002.
[28]Yao Jianchao. Image registration based on both feature and intensity matching[A]. Proceeding of 2001 IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Kauai, Hawaii, USA:IEEE, vol.3:1693-1696,2001.
[29]Richard Szeliski. Video mosaics for virtual environments[J]. Computer Graphics and Applications, IEEE, Mar 1996,16(2):22-30.
[30]Peleg S, Rousso B. Mosaicing on adaptive manifolds. IEEE Transactions on PAMI, 2000.22(10):1144-1154.
[31]S. Gumustedin R.W.Hall, Mosaic image generation on a flattened Gaussian sphere. In Proc. Of IEEE Workshop on Applications of Computer Vision, pp:50-55,1996.
[32]S. Gumustekin R.W.Hall. Image registration and mosaicking using a self calibration camera. In proc of IEEE Int. Conf. on Image Prcoessing,1998.
[33]Matthew Uyttendaele, Ashley Eden, Richard Szeliski. Eliminating ghosting and exposure artifacts in image mosaics[C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Hawaii,2001:209-516
[34]Davis J. Mosaics of scenes with moving objects[C]. Proceedings of 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Santa Barbara, CA, USA, 1998:354-360
[35]C.GHarris, M.Stephens. A combined corner and edge detector[C]. Proceedings of the 4th Alvey Vision Conference,1988:147-151.
[36]D. Lowe. Object Recognition from Local Scale-Invariant Features[J]. IJCV,1999:1150-1157.
[37]D. Lowe. Distinctive Image Features from Scale-Invariant Interest Points[J]. IJCV,2004, 60(2):91-110.
[38]Besl, P.&N. Mckay. A method for registration of 3-d shapes[J]. IEEE Trans. Pattern Anal. Mach. Intell.1992,14(2):239-256.
[39]Cheng, S. H.&F. H. Cheng &H. W. Hsu etal. Fast algorithm for point pattern matching: invariant to translations, rotations and scale changes[J]. Pattern Recognition,1997,30(2):311-320.
[40]Zhang,J.& Robert R. Korfhage. A Distance and Angle Similarity Measure Method. Journal ol the American Society for Information Science,50(9):772-778,1999
[41]L. Kitchen, A. Rosenfeld. Gray-level corner detection[J]. Pattern Recognition,1982:95-102.
[42]M. Brown, D.GLowe. Recognizing panoramas[A]. In:Proceedings of the IEEE Ninth International Conference on Computer Vision, Washington, DC, USA,2003,2:1218-1225.
[43]胡社教,葛西旺,苏菱.基于相位相关的全景图像拼接[J].合肥工业大学学.2007,30(1)：29-32.
[44]吴宪祥,郭宝龙,王娟.基于相位相关的柱面全景图像自动拼接算法[J].光学学报,2009,29(7)：1824-1829.
[45]李忠新,茅耀斌,王执铨.一种基于频域相关技术的柱面全景图生成方法[J].计算机工程与应用,2004,11：81-82.
[46]王字,王涌大,刘越.基于SIFT和小波变换的图像拼按算法[J].北京理工大学学报,2009,29(5)：423-426.
[47]苗立刚.基于手持相机的文档图像拼接算法[J].中国图象图形学报,2009,14(8)：1656-1662.
[48]邹北骥,阮鹏,向遥,贺加贝.一种精确匹配的全景图自动拼接算法[J].计算机工程与科学，2010,32(8)：60-63.
[49]阮鹏.多图像拼接算法研究[D].湖南：中南大学,2009.
[50]Graeme P. Penney, Jurgen Weese, John A. Little, Paul Desmedt, Derek L. G. Hill, and David J. Hawkes. A Comparison of Similarity Measures for Use in 2-D-3-D Medical Image Registration[J].IEEE TRANSACTIONS ON MEDICAL IMAGING,1998,17(4):586-595.
[51]Shu-Kai S.Fan, Yu-Chiang Chuang. A New Image Registration Method Using Intensity Difference Data on Overlapped Image[J]. In Proceeding of 2010 Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing,2010, pp.138-141.
[52]王勇,何晓川,刘清华,等.一种感兴趣区域寻优搜索的全自动图像拼接算法[J],电子与信息学报,2009,31(2)：261-264.
[53]冯宇平,戴明,孙立悦,张威.图像自动拼接融合的优化设计[J],光学精密工程,2010,18(2)：470-476
[54]王雷斌.基于计算机视觉的图像拼接技术研究[D].北京：首都师范大学,2008.
[55]林景亮,陈岳林.多摄像机图像拼接自动色彩均衡算法[J].计算机应用,2010,30(12)：3236-3237.
[56]David L. Milgram. Adaptive Techniques for Photomosaicking[J]. IEEE TRANSACTIONS ON COMPUTERS,1977,26(11):1175-1180.