基于注意机制的煤矿监控图像知觉编组研究
|
摘要
现有煤矿视频监控系统监控模式简单,只是实时采集和显示系统。随着视频头增加,在众多视频中发现异常十分困难,造成漏检率高,不能满足煤矿安全监控的要求,给煤矿安全生产埋下隐患。
实现对煤矿监控视频的机器监视是煤矿视频监控系统发展的迫切要求。为了达到这个目的,首先需要检测煤矿目标。这一过程受到多种因素的制约,包括环境因素,技术理论与方法,以及实时性等方面。其中最为关键的就是缺少对煤矿领域特征和特点的总结,以至于缺乏针对煤矿的,行之有效的图像和视频处理算法。
知觉编组能用最少的领域知识形成目标假设。当目标满足格式塔准则时,知觉编组可以降低视觉过程中目标检测和识别的计算复杂度。本文引入视觉感知系统信息处理理论中的知觉编组完成煤矿目标检测。
本文分为四个部分阐述:(1)光照不均图像的编组种子提取方法;(2)交互式闭合轮廓知觉编组算法;(3)基于自底向上注意机制的知觉编组算法;(4)基于自顶向下注意机制的知觉编组算法。
(1)编组种子提取是知觉编组过程中的重要一环,一个有效的编组种子提取算法将显著降低后续知觉编组的难度,而环境因素造成煤矿图像具有光照不均现象,影响知觉编组过程中编组种子提取的准确度。为了解除环境因素的制约,本文研究了煤矿光照不均图像的编组种子提取算法。首先说明光照不均图像的边缘模型,研究了两种基于视觉非线性特性的光照不均图像边缘提取算法,最后说明如何将粗糙,不光滑且相交的边缘轮廓平滑为编组种子。本文实验表明:基于视觉非线性特性提取的编组种子,减少了光照不均图像中亮区域的边缘冗余和暗区域边缘缺失现象。
(2)在煤矿视频监控目标中,满足编组准则的目标可能有多个,此时需要多次执行编组过程,增加了运算时间,并且也未必能够检测到最终结果。本文在分析交互式和非交互式知觉编组算法异同的基础上,研究了一种基于双权重图的交互式闭合轮廓知觉编组算法。本文实验表明:交互式与非交互式知觉编组算法在算法复杂度上差距很小,但交互式编组算法的收敛速度是非交互式算法的3倍以上。
(3)交互式知觉编组算法的初始条件如果单纯依靠人手动选择,必须由了解并熟悉煤矿监控领域的专门人员操作,这降低了算法的适应性。本文采用注意机制选择初始条件,代替交互过程,提出了基于自底向上注意机制和自顶向下注意机制的煤矿复杂图像知觉编组算法。本文实验表明:自底向上的注意计算模型在视频高兴趣区域提取任务中每秒可以运行4次以上,但是存在位置偏移现象,偏移率约40%。
(4)基于自顶向下注意机制的知觉编组算法可以选择全局特征,边缘错误率和线索错误率都相对较低,在提取一条显著编组种子时,边缘错误率和线索错误率为0;随着编组种子增多,错误率逐步升高,在12条编组种子以内,两种错误率都低于40%。
作者通过实验平台对本文提出的技术方法进行了实验,平台采用Matlab和C++实现。平台任务包括:编组种子提取,局部特征和全局特征模型化,最优化过程求解,以及两种注意机制的实现。
该论文有图47幅,表4个,参考文献193篇。
The surveillance pattern of current coal-mine video surveillance systems is too simple, they are just a system for real-time information collection and transmission. In fact, as the number of camera is increasing, it’s becoming more and more difficult to capture the abnormal status, that results in high omission factor, can’t satisfy the coal-mine demand for safety, so it’s a potential trouble for coal-mine safety production.
To develop the coal-mine video surveillance system, it is necessary to apply the intelligent surveillance technique on coal-mine image and video processing. To achieve the purpose, first of all, we must detect objects out of the coal-mine videos and images. Perceptual grouping can form the object hypothesis with the least specific knowledge, and reduce the computation complexity of visual recognition. This dissertation introduces perceptual grouping of visual information processing system to detect the coal-mine objects.
But the application of perceptual grouping algorithm is restricted by some factors, such as environment condition, convergence speed, and adaption. Aiming at the three problems, this dissertation is mainly organized by three parts: (1) Extraction of grouping seed for coal-mine uneven light images; (2) Interactive closed boundary grouping based on double-weight graph; (3) Perceptual grouping algorithm of coal-mine complex image based on bottom-up attention mechanism and perceptual grouping algorithm of coal-mine complex image based on up-bottom attention mechanism.
(1) Grouping seed extraction, which will greatly reduce the difficulty of following perceptual grouping steps, is one important process of perceptual grouping. But the environment conditions result in uneven lighting phenomenon which disturbs the accuracy of grouping seed extraction of perceptual grouping. In order to unlock the restriction of environment conditions, this dissertation puts forward the grouping seed extraction algorithm for coal-mine uneven light images. Firstly, we show the edge model of uneven lighting image, and then based on nonlinear visual perception characteristic, we introduce two edge detection algorithms for uneven lighting image, at last, we explain how to transform these coarse unsmooth and intersecting edges to smooth grouping seeds. The experiments show that grouping seed extraction algorithm based on non-linear visual characteristic reduces the redundant edges at bright regions and loss of edges at dark regions.
(2) The current perceptual grouping algorithms are mostly aiming at general application. At the coal-mine field, maybe there are many objects which fulfill the grouping laws, so we must run the perceptual grouping algorithm many times to focus on the final needed object, this process costs more computation time, and will not definitely find the wanted result. This dissertation introduces an interactive closed contour grouping algorithm based on double-weight graph, we analyze the similarities and differences between interactive and non-interactive perceptual grouping algorithms. The experiments show that: the computation complexity difference between the interactive and the non-interactive algorithms is small, but convergence speed of interactive algorithm is at least 3 times faster than that of non-interactive algorithm;
(3) If the interactive process of interactive perceptual grouping algorithm completely depends on manual selection, we must ask for the professional surveillance worker to do it, this action reduces the flexibility of algorithm. Attention mechanism simulates the human’s visual process, directly locates around the most interesting object. This dissertation puts forward two attention mechanisms to subtitude the manual selection: one is based on bottom-up attention mechanism, the other is based on up- bottom attention mechanism. The experiments show that: the computation model of bottom-up attention mechanism run more than 4 times per second, but it has position deviation phenomenon which is about 40%. The perceptual grouping algorithm with specific knowledge based on up-bottom attention mechanism can select the global cue. Cue error ratio and seed error ratio are both low, when detecting only one seed, they both are zero, when below 12 seeds, they both are under the 40%.
We have designed a platform implemented by Matlab and C++ for the experiment. The tasks of the platform include: grouping seed extraction, computation of global and local cues, solution of object function, realization of two kinds of attention mechanisms.
The dissertation has 47 figures, 4 tables and 193 references.
实现对煤矿监控视频的机器监视是煤矿视频监控系统发展的迫切要求。为了达到这个目的,首先需要检测煤矿目标。这一过程受到多种因素的制约,包括环境因素,技术理论与方法,以及实时性等方面。其中最为关键的就是缺少对煤矿领域特征和特点的总结,以至于缺乏针对煤矿的,行之有效的图像和视频处理算法。
知觉编组能用最少的领域知识形成目标假设。当目标满足格式塔准则时,知觉编组可以降低视觉过程中目标检测和识别的计算复杂度。本文引入视觉感知系统信息处理理论中的知觉编组完成煤矿目标检测。
本文分为四个部分阐述:(1)光照不均图像的编组种子提取方法;(2)交互式闭合轮廓知觉编组算法;(3)基于自底向上注意机制的知觉编组算法;(4)基于自顶向下注意机制的知觉编组算法。
(1)编组种子提取是知觉编组过程中的重要一环,一个有效的编组种子提取算法将显著降低后续知觉编组的难度,而环境因素造成煤矿图像具有光照不均现象,影响知觉编组过程中编组种子提取的准确度。为了解除环境因素的制约,本文研究了煤矿光照不均图像的编组种子提取算法。首先说明光照不均图像的边缘模型,研究了两种基于视觉非线性特性的光照不均图像边缘提取算法,最后说明如何将粗糙,不光滑且相交的边缘轮廓平滑为编组种子。本文实验表明:基于视觉非线性特性提取的编组种子,减少了光照不均图像中亮区域的边缘冗余和暗区域边缘缺失现象。
(2)在煤矿视频监控目标中,满足编组准则的目标可能有多个,此时需要多次执行编组过程,增加了运算时间,并且也未必能够检测到最终结果。本文在分析交互式和非交互式知觉编组算法异同的基础上,研究了一种基于双权重图的交互式闭合轮廓知觉编组算法。本文实验表明:交互式与非交互式知觉编组算法在算法复杂度上差距很小,但交互式编组算法的收敛速度是非交互式算法的3倍以上。
(3)交互式知觉编组算法的初始条件如果单纯依靠人手动选择,必须由了解并熟悉煤矿监控领域的专门人员操作,这降低了算法的适应性。本文采用注意机制选择初始条件,代替交互过程,提出了基于自底向上注意机制和自顶向下注意机制的煤矿复杂图像知觉编组算法。本文实验表明:自底向上的注意计算模型在视频高兴趣区域提取任务中每秒可以运行4次以上,但是存在位置偏移现象,偏移率约40%。
(4)基于自顶向下注意机制的知觉编组算法可以选择全局特征,边缘错误率和线索错误率都相对较低,在提取一条显著编组种子时,边缘错误率和线索错误率为0;随着编组种子增多,错误率逐步升高,在12条编组种子以内,两种错误率都低于40%。
作者通过实验平台对本文提出的技术方法进行了实验,平台采用Matlab和C++实现。平台任务包括:编组种子提取,局部特征和全局特征模型化,最优化过程求解,以及两种注意机制的实现。
该论文有图47幅,表4个,参考文献193篇。
The surveillance pattern of current coal-mine video surveillance systems is too simple, they are just a system for real-time information collection and transmission. In fact, as the number of camera is increasing, it’s becoming more and more difficult to capture the abnormal status, that results in high omission factor, can’t satisfy the coal-mine demand for safety, so it’s a potential trouble for coal-mine safety production.
To develop the coal-mine video surveillance system, it is necessary to apply the intelligent surveillance technique on coal-mine image and video processing. To achieve the purpose, first of all, we must detect objects out of the coal-mine videos and images. Perceptual grouping can form the object hypothesis with the least specific knowledge, and reduce the computation complexity of visual recognition. This dissertation introduces perceptual grouping of visual information processing system to detect the coal-mine objects.
But the application of perceptual grouping algorithm is restricted by some factors, such as environment condition, convergence speed, and adaption. Aiming at the three problems, this dissertation is mainly organized by three parts: (1) Extraction of grouping seed for coal-mine uneven light images; (2) Interactive closed boundary grouping based on double-weight graph; (3) Perceptual grouping algorithm of coal-mine complex image based on bottom-up attention mechanism and perceptual grouping algorithm of coal-mine complex image based on up-bottom attention mechanism.
(1) Grouping seed extraction, which will greatly reduce the difficulty of following perceptual grouping steps, is one important process of perceptual grouping. But the environment conditions result in uneven lighting phenomenon which disturbs the accuracy of grouping seed extraction of perceptual grouping. In order to unlock the restriction of environment conditions, this dissertation puts forward the grouping seed extraction algorithm for coal-mine uneven light images. Firstly, we show the edge model of uneven lighting image, and then based on nonlinear visual perception characteristic, we introduce two edge detection algorithms for uneven lighting image, at last, we explain how to transform these coarse unsmooth and intersecting edges to smooth grouping seeds. The experiments show that grouping seed extraction algorithm based on non-linear visual characteristic reduces the redundant edges at bright regions and loss of edges at dark regions.
(2) The current perceptual grouping algorithms are mostly aiming at general application. At the coal-mine field, maybe there are many objects which fulfill the grouping laws, so we must run the perceptual grouping algorithm many times to focus on the final needed object, this process costs more computation time, and will not definitely find the wanted result. This dissertation introduces an interactive closed contour grouping algorithm based on double-weight graph, we analyze the similarities and differences between interactive and non-interactive perceptual grouping algorithms. The experiments show that: the computation complexity difference between the interactive and the non-interactive algorithms is small, but convergence speed of interactive algorithm is at least 3 times faster than that of non-interactive algorithm;
(3) If the interactive process of interactive perceptual grouping algorithm completely depends on manual selection, we must ask for the professional surveillance worker to do it, this action reduces the flexibility of algorithm. Attention mechanism simulates the human’s visual process, directly locates around the most interesting object. This dissertation puts forward two attention mechanisms to subtitude the manual selection: one is based on bottom-up attention mechanism, the other is based on up- bottom attention mechanism. The experiments show that: the computation model of bottom-up attention mechanism run more than 4 times per second, but it has position deviation phenomenon which is about 40%. The perceptual grouping algorithm with specific knowledge based on up-bottom attention mechanism can select the global cue. Cue error ratio and seed error ratio are both low, when detecting only one seed, they both are zero, when below 12 seeds, they both are under the 40%.
We have designed a platform implemented by Matlab and C++ for the experiment. The tasks of the platform include: grouping seed extraction, computation of global and local cues, solution of object function, realization of two kinds of attention mechanisms.
The dissertation has 47 figures, 4 tables and 193 references.
引文
[1]尹洪胜.煤矿瓦斯时间序列分析方法与预警应用研究[D].江苏徐州:中国矿业大学图书馆.2010.
[2]李贞.基于计算机视觉的驾驶员安全驾驶状态监控系统[D].陕西西安:西北工业大学图书馆. 2007.
[3]章琉晋.图像分割[M].北京:科学出版社,2001:1-10.
[4]蔡利梅,基于模糊理论的煤矿井下图像增强算法[J].煤炭科学技术, 2009(08): p. 94-96.
[5]陈力军,于洪珍.煤矿多媒体安全监视系统中基于IFS的图象压缩方法探讨[J].煤矿自动化, 1997(04): 100-104
[6]陈伟,丁世飞,夏士雄.煤矿监控图像中脸肤色和模板检测[J].计算机科学, 2010(08): 280-282
[7]陈伟,丁世飞,许新征.基于YCbCr模型的巷道监控中矿工脸部图像识别[J].煤炭科学技术, 2009(09): 79-82+85.
[8]刘富强.煤矿多媒体监测监控系统及其关键技术研究[J].煤炭学报, 1998(04): 105-109.
[9]刘富强.煤矿多媒体图像通信网的设计[J].电信科学, 2000(02): 36-38.
[10]刘富强.基于图像处理与识别技术的煤矿矸石自动分选[J].煤炭学报, 2000(05): 534-537.
[11]刘富强,沈荣,陈治国.煤矿智能化调度室多媒体图像图形系统研究[J].中国矿业大学学报, 1999(03): 185-189
[12]孟倩,周延,于洪珍.煤矿安全监视图像数据库系统研究[J].计算机应用, 1999(09): 17-18+22.
[13]孙继平.煤矿监控关键科学技术问题[J].神华科技, 2009(03): 3-5.
[14]孙继平,宋姝.煤矿井下自燃火灾的图像识别及综合判据系统[J].中国安全科学学报, 2005(12): p. 110-112+137.
[15]王艳芬,张申,狄京.煤矿井下图象信号的窄带传输[J].煤矿自动化, 1996(02): 55-60.
[16]魏连云.图像增强技术在煤矿岩层监视系统中的应用研究[J].科技资讯, 2009(35): 23-24.
[17]袁小平.基于小波变换模极大值的煤矿岩层图像边缘检测处理[J].计算机工程与设计, 2008(17): 4504-4506.
[18]袁小平.直方图修正法增强煤矿工业电视图象的研究[J].中国图象图形学报, 1998(09): 1305-1309.
[19]袁小平,童敏明,许金林.图像处理在煤矿工业电视图像报警中的应用研究[J].计算机工程与设计, 2008(18): 4833-4835.
[20]袁小平,于洪珍.基于小波变换的煤矿井下岩层图像增强处理.东南大学学报(自然科学版), 2004(S1): 211-214.
[21]郑蕾,唐飞,郝继飞.煤矿机器人视觉BMP图像显示[J].计算机与现代化, 2004(01):
[22] Stahl, J.S. and W. Song, Edge Grouping Combining Boundary and Region Information[J]. Image Processing, IEEE Transactions on, 2007. 16(10): 2590-2606.
[23]罗四维,视觉感知系统信息处理理论[M].北京.电子工业出版社. 2006: 70-77.
[24] Brunswik E, J Kamiya. Ecological cue-validity of proximity and of other gestalt factors[J]. American Journal of Psychology. 1953, 66(1): 20-32.
[25]董鸿燕,沈振康,罗军,等.感知编组综述[J].计算机工程与应用. 2007 (14): 9-13.
[26] Sergei Gepshtein, J.H. Elder, and L.T. Maloney, Perceptual organization and neural computation[J]. Journal of Vision, 2008. 8(9): 1-4.
[27] Kanizsa, G. Organization in Vision[M]. New York: Praeger. 1979: 1-8.
[28] Sarkar, S. and K. L. Boyer . Perceptual organization in computer vision: a review and a proposal for a classificatory structure[J]. Systems, Man and Cybernetics, IEEE Transactions on. 1993, 23(2): 382-399.
[29] Sayim, B., G. Westheimer, et al. Gestalt factors modulate basic spatial vision[J]. Psychological Science. 2010, 21(5): 641-644.
[30] Gdalyahu, Y., D. Weinshall, and M. Werman, Self-organization in vision: Stochastic clustering for image segmentation, perceptual grouping, and image database organization[J]. Ieee Transactions on Pattern Analysis and Machine Intelligence, 2001. 23(10): 1053-1074.
[31] Mordohai P, Medioni G. Stereo using monocular cues within the tensor voting framework[J]. IEEE Trans on PAMI. 2006, 28 ( 6) : 968- 982.
[32] Pugeault N,Worgotter F, Kruger N. Multi-modal scene reconstruction using perceptual grouping constraints[C]. Conference on Computer Vision and Pattern Recognition Workshop. 2006: 195- 203.
[33] Hirogaki Y, Sohmura T, Hiroshi S, et al. Complete 3-D reconstruction of dental cast shape using perceptual grouping[J]. IEEE Trans on Medical Imaging, 2001, 20(10) : 1093- 1101.
[34] Bigand A, Evrard L, Dubus J P. A new perceptual organization approach to 3D measuring system based on the fuzzy integral[J]. Image and Vision Computing, 2006(24): 381- 393.
[35] Gao Q, Parslow A, Tan M. Object motion detection based on perceptual edge tracking[C] . Proceedings Second International Workshop on Digital and Computational Video, 2001: 78- 85.
[36] Singh V K, Maji S, Mukerjee A. Confidence based updation of motion conspicuity in dynamic scenes [C]. The 3rd Canadian Conference on Computer and Robot Vision, 2006:13- 21.
[37]邵晓芳,姚伟,孙即祥,等.基于视觉竞争合作机制的主观轮廓提取[J].中国图象图形学报, 2005, 10( 8) : 1024- 1028.
[38] Estrada F J, Jepson A D. Robust boundary detection with adaptive grouping[C]. Conference on Computer Vision and Pattern Recognition Workshop, 2006: 184- 192.
[39] Ge, F., S. Wang, and T.C. Liu, New benchmark for image segmentation evaluation[J]. Journal of Electronic Imaging, 2007. 16(3): 11-20.
[40]张志龙.基于遥感图像的重要目标特征提取与识别方法研究[D].湖南长沙:国防科技大学出版社, 2005.
[41] Jeon B K, Jang J H, Hong K S.Road detection in space borne SAR images using a genetic algorithm[J].IEEE Trans on Geoscience and Remote Sensing, 2002, 40( 1) : 22- 29.
[42] Ommer B, Sauter M, Buhmann J M.Learning top- down grouping of compositional hierarchies for recognition[C]. Conference on Computer Vision and Pattern Recognition Workshop, 2006: 194- 202.
[43] Forsyth, D. A. and J. Ponce. Computer vision: A modern aApproach[M], Prentice Hall. 2003: 50-55.
[44] Grossberg, S. and E. Mingolla. Neural dynamics of form perception - boundary completion, Illusory figures, and neon color spreading[J]. Psychological Review. 1985, 92(2): 173-211.
[45] Kovacs, I. and B. Julesz. A closed curve Is much more than an incomplete one - effect of closure in figure ground segmentation[C]. Proceedings of the National Academy of Sciences of the United States of America. 1993, 90(16): 7495-7497.
[46] Sisto, F. F., A. A. A. dos Santos, et al. Differential functioning of bender visual-motor gestalt Test items[J]. Perceptual and Motor Skills. 2010, 110(1): 313-322.
[47] Wille, R. Formal concept analysis of two-dimensional convex continuum structures[C]. Formal Concepts Analysis, Proceedings. 2010(5986): 61-71.
[48] Pelli, D. G., N. J. Majaj. Grouping in object recognition: The role of a Gestalt law in letter identification [J]. Cognitive Neuropsychology. 2009, 26(1): 36-49.
[49] Elder, J.H. and R.M. Goldberg, Ecological statistics of Gestalt laws for the perceptual organization of contours[J]. Journal of Vision, 2002. 2(4): 324-353.
[50] Elder, J.H. and S.W. Zucker. Computing contour closure[C]. Proceedings of the 4th European Conference on Computer Vision, ECCV'96. 1996, Cambridge, United kingdom.
[51] Elder, J.H., A. Krupnik, and L.A. Johnston, Contour grouping with prior models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003. 25(6): 661-674.
[52] PALMER, S.E., Modern Theories of Gestalt Perception[J]. Mind & Language, 1990. 5(4):289-323.
[53] Palmer, S.E., Common region: A new principle of perceptual grouping[J]. Cognitive Psychology, 1992. 24(3): 436-447.
[54] Atsumi, M., A Probabilistic Model of Visual Attention and Perceptual Organization for Constructive Object Recognition[C]. ISVC 2009. 2009: 778-787.
[55] Ben-Shahar, O. and S. Zucker, General Geometric Good Continuation: From Taylor to Laplace via Level Sets[J]. International Journal of Computer Vision, 2010. 86(1): 48-71.
[56] Gao, D.S., S. Han, and N. Vasconcelos, Discriminant Saliency, the Detection of Suspicious Coincidences, and Applications to Visual Recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009. 31(6): 989-1005.
[57] Gdalyahu, Y., D. Weinshall, and M. Werman, Self-organization in vision: Stochastic clustering for image segmentation, perceptual grouping, and image database organization[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001. 23(10): 1053-1074.
[58] Richardson, T. and S. Wang, Nonrigid shape correspondence using landmark sliding, insertion and deletion[C]. Medical Image Computing and Computer-Assisted Intervention - Miccai 2005, 3750: 435-442.
[59] Song, W., W. Jun, and T. Kubota. From fragments to salient closed boundaries: an in-depth study[C]. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004.
[60] Stahl, J.S., K. Oliver, and W. Song. Open boundary capable edge grouping with feature maps[C]. in Computer Vision and Pattern Recognition Workshops, 2008. IEEE Computer Society.
[61] Stahl, J.S. and W. Song. Convex grouping combining boundary and region information[C]. Tenth IEEE International Conference on Computer Vision. ICCV 2005. 2005.
[62] Stahl, J.S. and W. Song. Globally Optimal Grouping for Symmetric Boundaries[C]. in Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on. 2006.
[63] Wang, S., et al., Salient closed boundary extraction with ratio contour[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2005. 27(4): 546-561
[64] Stahl, J.S. and S. Wang, Globally optimal grouping for symmetric closed boundaries by combining boundary and region information[C]. Ieee Transactions on Pattern Analysis and Machine Intelligence, 2008. 30(3): 395-411.
[65] Temlyakov, A., et al., Two Perceptually Motivated Strategies for Shape Classification[C], in IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2010, IEEE: SanFrancisco, CA.
[66] Wang, S., T. Kubota, and J.M. Siskind, Salient Boundary Detection Using Ratio Contour[C], in Neural Information Processing Systems Conference (NIPS). 2003: Vancouver, Canada. 1571-1578.
[67] Wang, S., et al., Salient closed boundary extraction with ratio contour[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2005. 27(4): 546-561.
[68] Wang, S. and J.M. Siskind, Image segmentation with ratio cut[J]. Ieee Transactions on Pattern Analysis and Machine Intelligence, 2003. 25(6): 675-690.
[69] Wang, S., et al., Global detection of salient convex boundaries[J]. International Journal of Computer Vision, 2007. 71(3): 337-359
[70] Cox, I., S.B. Rao, and Y. Zhong, Ratio Regions: A Technique for Image Segmentation[C], in 13th International Conference on Pattern Recognition (ICPR'96). 1996: 557-564.
[71] Jermyn, I.H. and H. Ishikawa. Globally optimal regions and boundaries[C]. The Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999.
[72] Jermyn, I.H. and H. Ishikawa, Globally optimal regions and boundaries as minimum ratio weight cycles[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2001. 23(10): 1075-1088.
[73] Mahamud, S., Segmentation of multiple salient closed contours from real images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003. 25(4): 433-444.
[74] Sarkar, S. and P. Soundararajan, Supervised learning of large perceptual organization: graph spectral partitioning and learning automata [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2000. 22(5): 504-525.
[75] Soundararajan, P. and S. Sarkar, An in-depth study of graph partitioning measures for perceptual organization [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003. 25(6): 642-660.
[76] Williams, L.R. and K.K. Thornber, A comparison of measures for detecting natural shapes in cluttered backgrounds [J]. International Journal of Computer Vision, 2000. 34(2-3): 81-96
[77] Wu, Z. and R. Leahy, An optimal graph theoretic approach to data clustering: theory and its application to image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,, 1993. 15(11): 1101-1113.
[78] Wu, Z. and R. Leahy, An optimal graph theoretic approach to data clustering: theory and its application to image segmentation[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1993. 15(11): 1101-1113.
[79] Cour, T., F. Benezit, and J. Shi, Spectral Segmentation with Multiscale Graph Decomposition[C], in Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). 2005: 1124-1131.
[80] Shi, J.B. and J. Malik, Normalized cuts and image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000. 22(8): 888-905.
[81]万月亮,曹元大,李钝,基于全局约束的层次视知觉编组模型研究[J].电子与信息学报, 2008(09): 2152-2155.
[82]万月亮,曹元大,李钝,基于视觉组织的封闭轮廓编组模型研究[J].小型微型计算机系统, 2008(07): 1314-1319.
[83]李燕,邵作叶,余旭初.基于感知编组的道路网自动提取研究[J].遥感信息, 2005(01): 11-14.
[84]周昌雄,曹丰文,崔鸣,等.基于格式塔心理学原理的几何活动轮廓模型[J].中国图象图形学报, 2008(05): 924-929.
[85] Zou, Q., S. Luo, and J. Li, Selective Attention Guided Perceptual Grouping Model[C]. ICNC 2005, 2005: 867-876.
[86]邹琪,罗四维,钟晶晶,全局显著结构主导下的知觉编组算法[J].计算机学报, 2007(11): 2008-2016.
[87] H. Blum and R. N. Nagle. Shape description using weighted symmetric axis features[J]. Pattern Recognition, 1978(10): 167-180.
[88] M. J. Brady and H. Asada. Smoothed local symmetries and their implementation[R]. Technical Report AIM-757, Massachusetts Institute of Technology, February 1984.
[89] M. Leyton. Symmetry, Causality, Mind[M]. MIT Press, Cambridge, 1992: 110-102.
[90] S. C. Zhu and A. Yuille. Forms: a flexible object recognition and modelling system[C]. In ICCV, 1995: 465–472.
[91] Huttenlocher, D. and Wayner, P.. Finding convex edge groupings in an image[J]. International Journal of Computer Vision, 1992, 8(1): 7-29.
[92] Jacobs, D.. Robust and efficient detection of convex groups[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(1): 23-37.
[93] Borra, S. and Sarkar, S.. A framework for performance characterization of intermediate-level grouping modules[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(11): 1306-1312.
[94] Parvin, B. and Viswanathan, S. Tracking of convex objects[C]. In Proceedings of the International Symposium on Computer Vision, 1995: 295-298.
[95] Estrada, F.J. and J.H. Elder. Multi-Scale Contour Extraction Based on Natural ImageStatistics[C]. in Computer Vision and Pattern Recognition Workshop, 2006. CVPRW '06. Conference on. 2006.
[96] Elder, J.H. and S.W. Zucker, Local scale control for edge detection and blur estimation[J]. Ieee Transactions on Pattern Analysis and Machine Intelligence, 1998. 20(7): 699-716.
[97] Estrada, F.J. and J.H. Elder. Multi-Scale Contour Extraction Based on Natural Image Statistics[C]. in Computer Vision and Pattern Recognition Workshop, 2006. CVPRW '06. Conference on. 2006.
[98] Canny, J., A Computational Approach to Edge Detection[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1986. 8(6): 679-698.
[99]陈维南,李立源,龚坚.主动型边界检测:理论与方法的研究[J].东南大学学报, 1995(4): 47-52
[100]陈燕龙,祝成虎.基于Canny算子的边缘检测改进算法[J].计算机应用与软件, 2008(08): 51-53.
[101]韩冰.视频镜头边界检测方法研究[D].陕西西安:西安电子科技大学图书馆. 2004
[102]黄剑玲,郑雪梅.一种改进的基于Canny算子的图像边缘提取算法[J].计算机工程与应用, 2008(25): 170-172.
[103]蒋爱德,扈少华.基于Canny算子的边缘检测研究[J].郑州牧业工程高等专科学校学报, 2007(02): 38-40.
[104]李华强. Canny算子中Otsu阈值分割法的运用[J].计算机工程与设计, 2008, 29(9): 2297-2299.
[105]李钰,孟祥萍.自适应双阈值Canny算子的图像边缘检测[J].长春工程学院学报(自然科学版), 2007(03): 44-46+53.
[106]龙甫荟,郑南宁,王爱群.基于非均匀采样及选择注意机制的多分辨率边缘检测[J].电子学报, 1998(05): 97-99.
[107]陆明,王润生.一种基于多尺度MRF模型的边缘检测算法[J].电子学报, 1999(08): 82-86.
[108] OTSU, N.. A Threshold Selection Method from Gray-Level Histograms[J]. Systems, Man and Cybernetics, IEEE Transactions on, 1979. 9(1): 62-66.
[109]毕胜,梁德群.基于人类视觉特性的纹理分割方法[J].计算机应用, 2006(05): 1015-1017.
[110]陈强.图像分割若干理论方法及应用研究[D].江苏南京:南京理工大学出版社. 2007.
[111]董建磊.基于生物视觉的新的计算机视觉分割模型[D].上海:东华大学出版社. 2006.
[112]何超.机器人视觉系统中的图像分割与目标检测[D].浙江杭州:浙江大学出版社. 2003.
[113]李改梅,杨润玲,周军妮.基于二维直方图与FCM相结合的图像快速分割方法[J].现代电子技术, 2007(15): 176-178.
[114]刘亮亮.基于视觉颜色模型的火灾图像分割[J].中国电力教育, 2006(S1): 258-261.
[115]刘庆祥,冉勇.基于视觉特性的图像分割技术及其应用[J].长江大学学报(自科版), 2005(07): 77-81.
[116]刘思远.基于高维视觉特征模型的目标图像检测与图像分割技术研究[D].四川成都:电子科技大学出版社. 2006.
[117]罗彤.视觉感知启发的图像分割系统研究[D].浙江杭州:浙江大学出版社. 2008.
[118]莫斌.目标图像视觉特征矩描述与检测分割技术[D].四川成都:电子科技大学出版社. 2006.
[119]朴松昊.仿人机器人视觉颜色空间的图像分割算法[J].华中科技大学学报(自然科学版), 2008(S1): 98-101.
[120]孙涛.一种基于梯度模型的MPEG压缩域的运动对象分割算法[J].中国图象图形学报, 2008(06): 1109-1114.
[121]田军,李应岐,方晓峰.一种基于Contourlet变换和视觉感知特性的图像分割方法[J].微电子学与计算机, 2008(03): 67-70.
[122]田小林,焦李成,缑水平.视觉特征方向流邻域加权PCM的SAR图像分割[J].西安电子科技大学学报, 2008(04): 624-631.
[123] Azhn C T. Graph theoretical methods for detecting and describing gestalt clusters[J]. IEEE Trans Comput, 1971(20): 68- 86.
[124] Tu Zhuo-wen. An integrated framework for image segmentation and perceptual grouping[C]. Tenth IEEE International Conference on Computer Vision, 2005: 670- 677.
[125] A.J. Sinclair and M.R. Jerrum, Approximative Counting, Uniform Generation and Rapidly Mixing Markov Chains[J], Information and Computation, 1989(82): 93-133.
[126] Medioni G, Lee M S, Tang C K. A computational framework for feature extraction and segmentation[M].New York: Elsevier, 2000.
[127] Mordohai P, Medioni G. Stereo using monocular cues within the tensor voting framework[J].IEEE Trans on PAMI, 2006, 28 ( 6) : 968- 982.
[128] Kubota, T., Contextual and non-combinatorial approach to feature extraction[C]. Energy Minimization Methods in Computer Vision and Pattern Recognition, Proceedings, 2003. 2683: 467-482.
[129] Bartels, R.H., J.C. Beatty, and B.A. Barsky, An Introduction to Splines for Use in Computer Graphics and Geometric Modeling[M]. 1987, Los Altos: Morgan Kaufmann. 476-485.
[130] Marr D. Vision一A Computational Investigation into the Human Representation AndProcessing of Visual Information [M]. W.H.Reeman,1982: 1-138.
[131] Burt, P. and E. Adelson, The Laplacian Pyramid as a Compact Image Code[J]. Communications, IEEE Transactions on, 1983. 31(4): 532-540.
[132] Lindeberg, T., Scale-Space for Discrete Signals[J]. Ieee Transactions on Pattern Analysis and Machine Intelligence, 1990. 12(3): 234-254.
[133] Lindeberg, T., Discrete Scale-Space Theory and the Scale-Space Primal Sketch[C], in Computational Vision and Active Perception Laboratory (CVAP). 1991, Royal Institute of Technology: Sweden. p. 292-297.
[134] Lindeberg, T., Discrete derivative approximations with scale-space properties: A basis for low-level feature extraction[J]. Journal of Mathematical Imaging and Vision, 1993. 3(4): p. 349-376.
[135] Lindeberg, T., Detecting Salient Blob-Like Image Structures and Their Scales with a Scale-Space Primal Sketch - a Method for Focus-of-Attention[J]. International Journal of Computer Vision, 1993. 11(3): 283-318.
[136] Lindeberg, T., Scale-space theory: a basic tool for analyzing structures at different scales[J]. Journal of Applied Statistics, 1994. 21(1): 225 - 270.
[137] Mallat, S.G., A Theory for Multiresolution Signal Decomposition - the Wavelet Representation[J]. Ieee Transactions on Pattern Analysis and Machine Intelligence, 1989. 11(7): 674-693.
[138] Simoncelli, E.P. and E.H. Adelson. Noise removal via Bayesian wavelet coring[C]. in Image Processing, 1996. Proceedings., International Conference on. 1996.
[139]冯杰,刘天佑,董建华.小波边缘检测方法确定煤田烧变岩范围[J].煤炭科学技术, 2005(11): 74-77.
[140]彭楠,何小海,汪华章.基于样条小波和Gabor小波的边缘检测[J].成都信息工程学院学报, 2007(02): 195-197.
[141]孙长峰.基于小波边缘检测的图像去噪方法研究[D].河南郑州:郑州大学出版社, 2007,
[142]万月亮,曹元大,李钝.小波边缘分布及边缘融和算法研究[J].小型微型计算机系统, 2008(07): 1308-1313.
[143]张文琴. Canny准则小波边缘检测在图像融合中的应用[J].光电工程, 2005(06): 79-82+92.
[144]张小洪.基于小波多尺度积的边缘检测算法[J].计算机科学, 2004(01): 133-135+144.
[145]钟平.小波边缘检测算子的构造与应用[D].湖南武汉:国防科学技术大学出版社, 2003.
[146] Itti, L., Models of bottom-up and top-down visual attention[D]. California Institute of Technology.2000,
[147] RYBAK I A, GUSAKOVA V I, GOLOVAN, et al. A model of attention-guided visual perception and recognition [J]. Vision Research, 1998, 38: 2387-2400.
[148] SALAH A A, ALPAYDIN E, AKARUN L. A selective attention-based method for visual pattern recognition with application to handwritten digit recognition and face recognition [J]. IEEE Trans on PAMI, 2002, 24(3): 420-425.
[149]张鹏,王润生.基于视点转移和视区追踪的图像显著区域检测[J].软件学报.2004, 15(6): 891-898.
[150] Estrada F. J., Jepson A, D, Perceptual grouping for contour extraction [C]. Proceedings of the 17th International Conference on Pattern Recognition,2004(2): 32-35
[151] Yiqun Hu, Deepu Rajan, Liang-Tien Chia. Robust subspace analysis for detecting visual attention regions in images[C]. Proceedings ACM Multimedia 2005,2005
[152] Feng Liu , Michael Gleieher. Region enhanced scale invariant salient detection[C], IEEEICME 2006. Toronto, Canada, 2006
[153] Alaa Halawani, Hans Burkhardt. Image Retrieval by Local Evaluation of Nonlinear Kernel Functions around Salient Points[C]. Proceedings of the 17th International Conference on pattern Recognition (ICpR’04).2004
[154]沈云,涛郭雷.一种基于颜色视觉敏感度的特征提取算法[J].微电子学与计算机, 2005,22(10): 40-43.
[155]王向阳,杨红颖,胡峰丽.基于感兴趣区的小波域彩色图像检索新方法[J].中国图象图形学报. 2006, 11(2): 175-179.
[156]周明荣,张淑佳,朱保林.基于小波显著特征点的图像检索技术[J].浙江工业大学学报. 2004, 32(5): 597-601.
[157] Wang Z, Bovik A.C. Bitplane-by-Bitplane Shift (BbBShift) - A Suggestion for JPEG2000 Regions of internet Image Coding [J].IEEE Signal Processing Letters. 2002,9(5):160-162.
[158] Liu L., Fan G. A New JPEG2O00 Region-of-Interest Images Code Method: Partial Significant BitPlanes Shift[C]. IEEE Signal Proeessing Letters.2003, 10(2): 35-39.
[159] Francesca Gasparini, Silvia Corchs, Rahnondo Schettini. Adaptive edge enhancement using a neurodynalineal model of visual attention[C]. IEEE. 2005.
[160] Yusuo Hu,Xing Xie,Zonghai Chen,Wei-Ying Ma. Attention model based progressive image transmission[C].2004 IEEE Illternational Conference on Multimedia and EXPO(ICME04). 2004: 1079-1082
[161]王璐,蔡自兴.未知环境中基于视觉显著性的自然路标检测[J].模式识别与人工智能.2006, 10(1): 100-105
[162] Adrian J. Chung, Fani Dellgianni, Xiao-Peng Hu, Guang-Zhong Yang. Visual Feature Extraction via Eye Tracking for Saliency Driven 2D3D Registration[J]. Image and Vision Computing. 2005,23: 999-1008.
[163] Shutao Li,James Tin-Yau Kwok,Ivor Wai-Hung Tsang,Yaonan Wang. Fusing Images With Dlfferent Focuses Using Support Vector Machines[J]. IEEE Transaetions on Neural Networks. 2004, 15(6):1555-1561.
[164] Dumont R, F. Pellaeii. Perceptually-driven decision theory for interactive realistic rendering[J]. ACM Transaction on Graphics. 2003, 22(2).
[165] Ross Brown, Luke CooPer, Binh Pham. Visual Attention-based Polygon Level of Detail Management.2003
[166] Antonios Oikonomopoulos, Ioannis Patras , Maja Pantic. Spatiotemporl Salient Points for Visual Recognition of Human Actions[J]. IEEE trans on Systems,Man and Cybernetics, 2006,36(3): 710-719
[167] YeeH,Pattanaik S N,and Greenbelg D P..Spatiotempoal sensitivity and visual attention for effieient rendering of dynamic Environments[J].ACMT Trans. On Graphics,2001 ,20(1) 39-65.
[168]田媚,罗四维,廖灵芝.基于what和where信息的目标检测方法[J].电子学报, 2007(11): 2055-2061.
[169]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[J].电子学报, 2006(03): 559-562.
[170]田媚.模拟自顶向下视觉注意机制的感知模型研究[D].北京:北京交通大学出版社. 2007.
[171]田媚.基于局部复杂度和初级视觉特征的自底向上注意信息提取算法[J].计算机研究与发展, 2008(10): 1739-1746.
[172]窦燕,孔令富.一种基于视觉注意机制的刀具检测方法[J].中国机械工程, 2008(17): 2024-2027.
[173] Williams L R, Jacobs D W. Stochastic completion fields:A neural model of illusory contour shape and salience[J]. Neural Computation, 1997, 9(4):837-858
[174] Soyer C, Bozma Hl, Istefanopulos Y. Attentional sequence-based recognition: Markovian and Evidential Reasoning[J]. IEEE Trans.on Systems, Man, And Cyberneties-PartB: Cybernetics 2003
[175] Buchsbaum, G., An Analytical Derivation of Visual Nonlinearity[J]. Biomedical Engineering, IEEE Transactions on, 1980. BME-27(5): 237-242.
[176] Wen-Nung, L. and C. Li Chun. Data hiding in images with adaptive numbers of least significant bits based on the human visual system[C]. in Image Processing, 1999. ICIP 99. Proceedings. 1999 International Conference on. 1999.
[177]邓述移.人眼调制传递函数[J].兵工学报, 1982(02): 24-33.
[178]杨俊.图像数据的视觉显著性检测技术及其应用[D].湖南武汉:国防科学技术大学出版社. 2007,
[179]姚军财,申静,王剑华.阴极射线管显示器亮度范围内对人眼视觉特性的实验研究[J].物理学报, 2008(07): 4034-4041.
[180]姚军财.人眼对比度敏感视觉特性及模型研究[J].光学技术, 2009,197(03): 334-337.
[181]張宜庭.基於人眼視覺和抵抗隱藏偵測之最佳化品質影像秘密資料嵌入技術[M],台湾台北:國立中正大學图书馆: 1995.
[182]周燕,金伟其.人眼视觉的传递特性及模型[J].光学技术, 2002(01): 57-59+62.
[183]李牧.基于类内方差最小化及模糊控制算法的小波边缘检测技术[J].电子学报, 2008(09): 1741-1745.
[184] Cook, W. and A. Rohe, Computing minimum-weight perfect matchings[J]. Informs Journal on Computing, 1999. 11(2): 138-148.
[185] Edmonds, J., Paths, tree, and flowers[J]. Canadian Journal of Mathematics, 1965(17): 449-467.
[186] Kolmogorov, V., Blossom V: a new implementation of a minimum cost perfect matching algorithm[J]. Mathematical Programming Computation, 2009. 1(1): 43-67.
[187] Manthey, B., Minimum-Weight Cycle Covers and Their Approximability[J]. 2007. 178-189.
[188] Mehlhorn, K. and G. Sch?fer, Implementation of O(nmlogn) Weighted Matchings in General Graphs[J]. The Power of Data Structures. 2001: 23-38.
[189] Arkin, E.M. and C.H. Papadimitriou, On negative cycles in mixed graphs[J]. Operations Research Letters, 1985. 4(3): 113-116.
[190] Cherkassky, B. and A. Goldberg, Negative-cycle detection algorithms[C], in Algorithms - ESA '96. 1996: 349-363.
[191] Gu, X., et al., Improved Algorithms for Detecting Negative Cost Cycles in Undirected Graphs[J], in Frontiers in Algorithmics. 2009: 40-50.
[192] Wong, C.-H. and Y.-C. Tam, Negative Cycle Detection Problem[C], in Algorithms - ESA 2005. 2005: 652-663
[193] NIMROD MEGIDDO, Combinatorial optimization with rational objective functions[C], Mathematics of Operations Research. 1979(4): 414-424.
[2]李贞.基于计算机视觉的驾驶员安全驾驶状态监控系统[D].陕西西安:西北工业大学图书馆. 2007.
[3]章琉晋.图像分割[M].北京:科学出版社,2001:1-10.
[4]蔡利梅,基于模糊理论的煤矿井下图像增强算法[J].煤炭科学技术, 2009(08): p. 94-96.
[5]陈力军,于洪珍.煤矿多媒体安全监视系统中基于IFS的图象压缩方法探讨[J].煤矿自动化, 1997(04): 100-104
[6]陈伟,丁世飞,夏士雄.煤矿监控图像中脸肤色和模板检测[J].计算机科学, 2010(08): 280-282
[7]陈伟,丁世飞,许新征.基于YCbCr模型的巷道监控中矿工脸部图像识别[J].煤炭科学技术, 2009(09): 79-82+85.
[8]刘富强.煤矿多媒体监测监控系统及其关键技术研究[J].煤炭学报, 1998(04): 105-109.
[9]刘富强.煤矿多媒体图像通信网的设计[J].电信科学, 2000(02): 36-38.
[10]刘富强.基于图像处理与识别技术的煤矿矸石自动分选[J].煤炭学报, 2000(05): 534-537.
[11]刘富强,沈荣,陈治国.煤矿智能化调度室多媒体图像图形系统研究[J].中国矿业大学学报, 1999(03): 185-189
[12]孟倩,周延,于洪珍.煤矿安全监视图像数据库系统研究[J].计算机应用, 1999(09): 17-18+22.
[13]孙继平.煤矿监控关键科学技术问题[J].神华科技, 2009(03): 3-5.
[14]孙继平,宋姝.煤矿井下自燃火灾的图像识别及综合判据系统[J].中国安全科学学报, 2005(12): p. 110-112+137.
[15]王艳芬,张申,狄京.煤矿井下图象信号的窄带传输[J].煤矿自动化, 1996(02): 55-60.
[16]魏连云.图像增强技术在煤矿岩层监视系统中的应用研究[J].科技资讯, 2009(35): 23-24.
[17]袁小平.基于小波变换模极大值的煤矿岩层图像边缘检测处理[J].计算机工程与设计, 2008(17): 4504-4506.
[18]袁小平.直方图修正法增强煤矿工业电视图象的研究[J].中国图象图形学报, 1998(09): 1305-1309.
[19]袁小平,童敏明,许金林.图像处理在煤矿工业电视图像报警中的应用研究[J].计算机工程与设计, 2008(18): 4833-4835.
[20]袁小平,于洪珍.基于小波变换的煤矿井下岩层图像增强处理.东南大学学报(自然科学版), 2004(S1): 211-214.
[21]郑蕾,唐飞,郝继飞.煤矿机器人视觉BMP图像显示[J].计算机与现代化, 2004(01):
[22] Stahl, J.S. and W. Song, Edge Grouping Combining Boundary and Region Information[J]. Image Processing, IEEE Transactions on, 2007. 16(10): 2590-2606.
[23]罗四维,视觉感知系统信息处理理论[M].北京.电子工业出版社. 2006: 70-77.
[24] Brunswik E, J Kamiya. Ecological cue-validity of proximity and of other gestalt factors[J]. American Journal of Psychology. 1953, 66(1): 20-32.
[25]董鸿燕,沈振康,罗军,等.感知编组综述[J].计算机工程与应用. 2007 (14): 9-13.
[26] Sergei Gepshtein, J.H. Elder, and L.T. Maloney, Perceptual organization and neural computation[J]. Journal of Vision, 2008. 8(9): 1-4.
[27] Kanizsa, G. Organization in Vision[M]. New York: Praeger. 1979: 1-8.
[28] Sarkar, S. and K. L. Boyer . Perceptual organization in computer vision: a review and a proposal for a classificatory structure[J]. Systems, Man and Cybernetics, IEEE Transactions on. 1993, 23(2): 382-399.
[29] Sayim, B., G. Westheimer, et al. Gestalt factors modulate basic spatial vision[J]. Psychological Science. 2010, 21(5): 641-644.
[30] Gdalyahu, Y., D. Weinshall, and M. Werman, Self-organization in vision: Stochastic clustering for image segmentation, perceptual grouping, and image database organization[J]. Ieee Transactions on Pattern Analysis and Machine Intelligence, 2001. 23(10): 1053-1074.
[31] Mordohai P, Medioni G. Stereo using monocular cues within the tensor voting framework[J]. IEEE Trans on PAMI. 2006, 28 ( 6) : 968- 982.
[32] Pugeault N,Worgotter F, Kruger N. Multi-modal scene reconstruction using perceptual grouping constraints[C]. Conference on Computer Vision and Pattern Recognition Workshop. 2006: 195- 203.
[33] Hirogaki Y, Sohmura T, Hiroshi S, et al. Complete 3-D reconstruction of dental cast shape using perceptual grouping[J]. IEEE Trans on Medical Imaging, 2001, 20(10) : 1093- 1101.
[34] Bigand A, Evrard L, Dubus J P. A new perceptual organization approach to 3D measuring system based on the fuzzy integral[J]. Image and Vision Computing, 2006(24): 381- 393.
[35] Gao Q, Parslow A, Tan M. Object motion detection based on perceptual edge tracking[C] . Proceedings Second International Workshop on Digital and Computational Video, 2001: 78- 85.
[36] Singh V K, Maji S, Mukerjee A. Confidence based updation of motion conspicuity in dynamic scenes [C]. The 3rd Canadian Conference on Computer and Robot Vision, 2006:13- 21.
[37]邵晓芳,姚伟,孙即祥,等.基于视觉竞争合作机制的主观轮廓提取[J].中国图象图形学报, 2005, 10( 8) : 1024- 1028.
[38] Estrada F J, Jepson A D. Robust boundary detection with adaptive grouping[C]. Conference on Computer Vision and Pattern Recognition Workshop, 2006: 184- 192.
[39] Ge, F., S. Wang, and T.C. Liu, New benchmark for image segmentation evaluation[J]. Journal of Electronic Imaging, 2007. 16(3): 11-20.
[40]张志龙.基于遥感图像的重要目标特征提取与识别方法研究[D].湖南长沙:国防科技大学出版社, 2005.
[41] Jeon B K, Jang J H, Hong K S.Road detection in space borne SAR images using a genetic algorithm[J].IEEE Trans on Geoscience and Remote Sensing, 2002, 40( 1) : 22- 29.
[42] Ommer B, Sauter M, Buhmann J M.Learning top- down grouping of compositional hierarchies for recognition[C]. Conference on Computer Vision and Pattern Recognition Workshop, 2006: 194- 202.
[43] Forsyth, D. A. and J. Ponce. Computer vision: A modern aApproach[M], Prentice Hall. 2003: 50-55.
[44] Grossberg, S. and E. Mingolla. Neural dynamics of form perception - boundary completion, Illusory figures, and neon color spreading[J]. Psychological Review. 1985, 92(2): 173-211.
[45] Kovacs, I. and B. Julesz. A closed curve Is much more than an incomplete one - effect of closure in figure ground segmentation[C]. Proceedings of the National Academy of Sciences of the United States of America. 1993, 90(16): 7495-7497.
[46] Sisto, F. F., A. A. A. dos Santos, et al. Differential functioning of bender visual-motor gestalt Test items[J]. Perceptual and Motor Skills. 2010, 110(1): 313-322.
[47] Wille, R. Formal concept analysis of two-dimensional convex continuum structures[C]. Formal Concepts Analysis, Proceedings. 2010(5986): 61-71.
[48] Pelli, D. G., N. J. Majaj. Grouping in object recognition: The role of a Gestalt law in letter identification [J]. Cognitive Neuropsychology. 2009, 26(1): 36-49.
[49] Elder, J.H. and R.M. Goldberg, Ecological statistics of Gestalt laws for the perceptual organization of contours[J]. Journal of Vision, 2002. 2(4): 324-353.
[50] Elder, J.H. and S.W. Zucker. Computing contour closure[C]. Proceedings of the 4th European Conference on Computer Vision, ECCV'96. 1996, Cambridge, United kingdom.
[51] Elder, J.H., A. Krupnik, and L.A. Johnston, Contour grouping with prior models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003. 25(6): 661-674.
[52] PALMER, S.E., Modern Theories of Gestalt Perception[J]. Mind & Language, 1990. 5(4):289-323.
[53] Palmer, S.E., Common region: A new principle of perceptual grouping[J]. Cognitive Psychology, 1992. 24(3): 436-447.
[54] Atsumi, M., A Probabilistic Model of Visual Attention and Perceptual Organization for Constructive Object Recognition[C]. ISVC 2009. 2009: 778-787.
[55] Ben-Shahar, O. and S. Zucker, General Geometric Good Continuation: From Taylor to Laplace via Level Sets[J]. International Journal of Computer Vision, 2010. 86(1): 48-71.
[56] Gao, D.S., S. Han, and N. Vasconcelos, Discriminant Saliency, the Detection of Suspicious Coincidences, and Applications to Visual Recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009. 31(6): 989-1005.
[57] Gdalyahu, Y., D. Weinshall, and M. Werman, Self-organization in vision: Stochastic clustering for image segmentation, perceptual grouping, and image database organization[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001. 23(10): 1053-1074.
[58] Richardson, T. and S. Wang, Nonrigid shape correspondence using landmark sliding, insertion and deletion[C]. Medical Image Computing and Computer-Assisted Intervention - Miccai 2005, 3750: 435-442.
[59] Song, W., W. Jun, and T. Kubota. From fragments to salient closed boundaries: an in-depth study[C]. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004.
[60] Stahl, J.S., K. Oliver, and W. Song. Open boundary capable edge grouping with feature maps[C]. in Computer Vision and Pattern Recognition Workshops, 2008. IEEE Computer Society.
[61] Stahl, J.S. and W. Song. Convex grouping combining boundary and region information[C]. Tenth IEEE International Conference on Computer Vision. ICCV 2005. 2005.
[62] Stahl, J.S. and W. Song. Globally Optimal Grouping for Symmetric Boundaries[C]. in Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on. 2006.
[63] Wang, S., et al., Salient closed boundary extraction with ratio contour[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2005. 27(4): 546-561
[64] Stahl, J.S. and S. Wang, Globally optimal grouping for symmetric closed boundaries by combining boundary and region information[C]. Ieee Transactions on Pattern Analysis and Machine Intelligence, 2008. 30(3): 395-411.
[65] Temlyakov, A., et al., Two Perceptually Motivated Strategies for Shape Classification[C], in IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2010, IEEE: SanFrancisco, CA.
[66] Wang, S., T. Kubota, and J.M. Siskind, Salient Boundary Detection Using Ratio Contour[C], in Neural Information Processing Systems Conference (NIPS). 2003: Vancouver, Canada. 1571-1578.
[67] Wang, S., et al., Salient closed boundary extraction with ratio contour[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2005. 27(4): 546-561.
[68] Wang, S. and J.M. Siskind, Image segmentation with ratio cut[J]. Ieee Transactions on Pattern Analysis and Machine Intelligence, 2003. 25(6): 675-690.
[69] Wang, S., et al., Global detection of salient convex boundaries[J]. International Journal of Computer Vision, 2007. 71(3): 337-359
[70] Cox, I., S.B. Rao, and Y. Zhong, Ratio Regions: A Technique for Image Segmentation[C], in 13th International Conference on Pattern Recognition (ICPR'96). 1996: 557-564.
[71] Jermyn, I.H. and H. Ishikawa. Globally optimal regions and boundaries[C]. The Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999.
[72] Jermyn, I.H. and H. Ishikawa, Globally optimal regions and boundaries as minimum ratio weight cycles[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2001. 23(10): 1075-1088.
[73] Mahamud, S., Segmentation of multiple salient closed contours from real images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003. 25(4): 433-444.
[74] Sarkar, S. and P. Soundararajan, Supervised learning of large perceptual organization: graph spectral partitioning and learning automata [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2000. 22(5): 504-525.
[75] Soundararajan, P. and S. Sarkar, An in-depth study of graph partitioning measures for perceptual organization [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003. 25(6): 642-660.
[76] Williams, L.R. and K.K. Thornber, A comparison of measures for detecting natural shapes in cluttered backgrounds [J]. International Journal of Computer Vision, 2000. 34(2-3): 81-96
[77] Wu, Z. and R. Leahy, An optimal graph theoretic approach to data clustering: theory and its application to image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,, 1993. 15(11): 1101-1113.
[78] Wu, Z. and R. Leahy, An optimal graph theoretic approach to data clustering: theory and its application to image segmentation[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1993. 15(11): 1101-1113.
[79] Cour, T., F. Benezit, and J. Shi, Spectral Segmentation with Multiscale Graph Decomposition[C], in Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). 2005: 1124-1131.
[80] Shi, J.B. and J. Malik, Normalized cuts and image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000. 22(8): 888-905.
[81]万月亮,曹元大,李钝,基于全局约束的层次视知觉编组模型研究[J].电子与信息学报, 2008(09): 2152-2155.
[82]万月亮,曹元大,李钝,基于视觉组织的封闭轮廓编组模型研究[J].小型微型计算机系统, 2008(07): 1314-1319.
[83]李燕,邵作叶,余旭初.基于感知编组的道路网自动提取研究[J].遥感信息, 2005(01): 11-14.
[84]周昌雄,曹丰文,崔鸣,等.基于格式塔心理学原理的几何活动轮廓模型[J].中国图象图形学报, 2008(05): 924-929.
[85] Zou, Q., S. Luo, and J. Li, Selective Attention Guided Perceptual Grouping Model[C]. ICNC 2005, 2005: 867-876.
[86]邹琪,罗四维,钟晶晶,全局显著结构主导下的知觉编组算法[J].计算机学报, 2007(11): 2008-2016.
[87] H. Blum and R. N. Nagle. Shape description using weighted symmetric axis features[J]. Pattern Recognition, 1978(10): 167-180.
[88] M. J. Brady and H. Asada. Smoothed local symmetries and their implementation[R]. Technical Report AIM-757, Massachusetts Institute of Technology, February 1984.
[89] M. Leyton. Symmetry, Causality, Mind[M]. MIT Press, Cambridge, 1992: 110-102.
[90] S. C. Zhu and A. Yuille. Forms: a flexible object recognition and modelling system[C]. In ICCV, 1995: 465–472.
[91] Huttenlocher, D. and Wayner, P.. Finding convex edge groupings in an image[J]. International Journal of Computer Vision, 1992, 8(1): 7-29.
[92] Jacobs, D.. Robust and efficient detection of convex groups[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(1): 23-37.
[93] Borra, S. and Sarkar, S.. A framework for performance characterization of intermediate-level grouping modules[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(11): 1306-1312.
[94] Parvin, B. and Viswanathan, S. Tracking of convex objects[C]. In Proceedings of the International Symposium on Computer Vision, 1995: 295-298.
[95] Estrada, F.J. and J.H. Elder. Multi-Scale Contour Extraction Based on Natural ImageStatistics[C]. in Computer Vision and Pattern Recognition Workshop, 2006. CVPRW '06. Conference on. 2006.
[96] Elder, J.H. and S.W. Zucker, Local scale control for edge detection and blur estimation[J]. Ieee Transactions on Pattern Analysis and Machine Intelligence, 1998. 20(7): 699-716.
[97] Estrada, F.J. and J.H. Elder. Multi-Scale Contour Extraction Based on Natural Image Statistics[C]. in Computer Vision and Pattern Recognition Workshop, 2006. CVPRW '06. Conference on. 2006.
[98] Canny, J., A Computational Approach to Edge Detection[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1986. 8(6): 679-698.
[99]陈维南,李立源,龚坚.主动型边界检测:理论与方法的研究[J].东南大学学报, 1995(4): 47-52
[100]陈燕龙,祝成虎.基于Canny算子的边缘检测改进算法[J].计算机应用与软件, 2008(08): 51-53.
[101]韩冰.视频镜头边界检测方法研究[D].陕西西安:西安电子科技大学图书馆. 2004
[102]黄剑玲,郑雪梅.一种改进的基于Canny算子的图像边缘提取算法[J].计算机工程与应用, 2008(25): 170-172.
[103]蒋爱德,扈少华.基于Canny算子的边缘检测研究[J].郑州牧业工程高等专科学校学报, 2007(02): 38-40.
[104]李华强. Canny算子中Otsu阈值分割法的运用[J].计算机工程与设计, 2008, 29(9): 2297-2299.
[105]李钰,孟祥萍.自适应双阈值Canny算子的图像边缘检测[J].长春工程学院学报(自然科学版), 2007(03): 44-46+53.
[106]龙甫荟,郑南宁,王爱群.基于非均匀采样及选择注意机制的多分辨率边缘检测[J].电子学报, 1998(05): 97-99.
[107]陆明,王润生.一种基于多尺度MRF模型的边缘检测算法[J].电子学报, 1999(08): 82-86.
[108] OTSU, N.. A Threshold Selection Method from Gray-Level Histograms[J]. Systems, Man and Cybernetics, IEEE Transactions on, 1979. 9(1): 62-66.
[109]毕胜,梁德群.基于人类视觉特性的纹理分割方法[J].计算机应用, 2006(05): 1015-1017.
[110]陈强.图像分割若干理论方法及应用研究[D].江苏南京:南京理工大学出版社. 2007.
[111]董建磊.基于生物视觉的新的计算机视觉分割模型[D].上海:东华大学出版社. 2006.
[112]何超.机器人视觉系统中的图像分割与目标检测[D].浙江杭州:浙江大学出版社. 2003.
[113]李改梅,杨润玲,周军妮.基于二维直方图与FCM相结合的图像快速分割方法[J].现代电子技术, 2007(15): 176-178.
[114]刘亮亮.基于视觉颜色模型的火灾图像分割[J].中国电力教育, 2006(S1): 258-261.
[115]刘庆祥,冉勇.基于视觉特性的图像分割技术及其应用[J].长江大学学报(自科版), 2005(07): 77-81.
[116]刘思远.基于高维视觉特征模型的目标图像检测与图像分割技术研究[D].四川成都:电子科技大学出版社. 2006.
[117]罗彤.视觉感知启发的图像分割系统研究[D].浙江杭州:浙江大学出版社. 2008.
[118]莫斌.目标图像视觉特征矩描述与检测分割技术[D].四川成都:电子科技大学出版社. 2006.
[119]朴松昊.仿人机器人视觉颜色空间的图像分割算法[J].华中科技大学学报(自然科学版), 2008(S1): 98-101.
[120]孙涛.一种基于梯度模型的MPEG压缩域的运动对象分割算法[J].中国图象图形学报, 2008(06): 1109-1114.
[121]田军,李应岐,方晓峰.一种基于Contourlet变换和视觉感知特性的图像分割方法[J].微电子学与计算机, 2008(03): 67-70.
[122]田小林,焦李成,缑水平.视觉特征方向流邻域加权PCM的SAR图像分割[J].西安电子科技大学学报, 2008(04): 624-631.
[123] Azhn C T. Graph theoretical methods for detecting and describing gestalt clusters[J]. IEEE Trans Comput, 1971(20): 68- 86.
[124] Tu Zhuo-wen. An integrated framework for image segmentation and perceptual grouping[C]. Tenth IEEE International Conference on Computer Vision, 2005: 670- 677.
[125] A.J. Sinclair and M.R. Jerrum, Approximative Counting, Uniform Generation and Rapidly Mixing Markov Chains[J], Information and Computation, 1989(82): 93-133.
[126] Medioni G, Lee M S, Tang C K. A computational framework for feature extraction and segmentation[M].New York: Elsevier, 2000.
[127] Mordohai P, Medioni G. Stereo using monocular cues within the tensor voting framework[J].IEEE Trans on PAMI, 2006, 28 ( 6) : 968- 982.
[128] Kubota, T., Contextual and non-combinatorial approach to feature extraction[C]. Energy Minimization Methods in Computer Vision and Pattern Recognition, Proceedings, 2003. 2683: 467-482.
[129] Bartels, R.H., J.C. Beatty, and B.A. Barsky, An Introduction to Splines for Use in Computer Graphics and Geometric Modeling[M]. 1987, Los Altos: Morgan Kaufmann. 476-485.
[130] Marr D. Vision一A Computational Investigation into the Human Representation AndProcessing of Visual Information [M]. W.H.Reeman,1982: 1-138.
[131] Burt, P. and E. Adelson, The Laplacian Pyramid as a Compact Image Code[J]. Communications, IEEE Transactions on, 1983. 31(4): 532-540.
[132] Lindeberg, T., Scale-Space for Discrete Signals[J]. Ieee Transactions on Pattern Analysis and Machine Intelligence, 1990. 12(3): 234-254.
[133] Lindeberg, T., Discrete Scale-Space Theory and the Scale-Space Primal Sketch[C], in Computational Vision and Active Perception Laboratory (CVAP). 1991, Royal Institute of Technology: Sweden. p. 292-297.
[134] Lindeberg, T., Discrete derivative approximations with scale-space properties: A basis for low-level feature extraction[J]. Journal of Mathematical Imaging and Vision, 1993. 3(4): p. 349-376.
[135] Lindeberg, T., Detecting Salient Blob-Like Image Structures and Their Scales with a Scale-Space Primal Sketch - a Method for Focus-of-Attention[J]. International Journal of Computer Vision, 1993. 11(3): 283-318.
[136] Lindeberg, T., Scale-space theory: a basic tool for analyzing structures at different scales[J]. Journal of Applied Statistics, 1994. 21(1): 225 - 270.
[137] Mallat, S.G., A Theory for Multiresolution Signal Decomposition - the Wavelet Representation[J]. Ieee Transactions on Pattern Analysis and Machine Intelligence, 1989. 11(7): 674-693.
[138] Simoncelli, E.P. and E.H. Adelson. Noise removal via Bayesian wavelet coring[C]. in Image Processing, 1996. Proceedings., International Conference on. 1996.
[139]冯杰,刘天佑,董建华.小波边缘检测方法确定煤田烧变岩范围[J].煤炭科学技术, 2005(11): 74-77.
[140]彭楠,何小海,汪华章.基于样条小波和Gabor小波的边缘检测[J].成都信息工程学院学报, 2007(02): 195-197.
[141]孙长峰.基于小波边缘检测的图像去噪方法研究[D].河南郑州:郑州大学出版社, 2007,
[142]万月亮,曹元大,李钝.小波边缘分布及边缘融和算法研究[J].小型微型计算机系统, 2008(07): 1308-1313.
[143]张文琴. Canny准则小波边缘检测在图像融合中的应用[J].光电工程, 2005(06): 79-82+92.
[144]张小洪.基于小波多尺度积的边缘检测算法[J].计算机科学, 2004(01): 133-135+144.
[145]钟平.小波边缘检测算子的构造与应用[D].湖南武汉:国防科学技术大学出版社, 2003.
[146] Itti, L., Models of bottom-up and top-down visual attention[D]. California Institute of Technology.2000,
[147] RYBAK I A, GUSAKOVA V I, GOLOVAN, et al. A model of attention-guided visual perception and recognition [J]. Vision Research, 1998, 38: 2387-2400.
[148] SALAH A A, ALPAYDIN E, AKARUN L. A selective attention-based method for visual pattern recognition with application to handwritten digit recognition and face recognition [J]. IEEE Trans on PAMI, 2002, 24(3): 420-425.
[149]张鹏,王润生.基于视点转移和视区追踪的图像显著区域检测[J].软件学报.2004, 15(6): 891-898.
[150] Estrada F. J., Jepson A, D, Perceptual grouping for contour extraction [C]. Proceedings of the 17th International Conference on Pattern Recognition,2004(2): 32-35
[151] Yiqun Hu, Deepu Rajan, Liang-Tien Chia. Robust subspace analysis for detecting visual attention regions in images[C]. Proceedings ACM Multimedia 2005,2005
[152] Feng Liu , Michael Gleieher. Region enhanced scale invariant salient detection[C], IEEEICME 2006. Toronto, Canada, 2006
[153] Alaa Halawani, Hans Burkhardt. Image Retrieval by Local Evaluation of Nonlinear Kernel Functions around Salient Points[C]. Proceedings of the 17th International Conference on pattern Recognition (ICpR’04).2004
[154]沈云,涛郭雷.一种基于颜色视觉敏感度的特征提取算法[J].微电子学与计算机, 2005,22(10): 40-43.
[155]王向阳,杨红颖,胡峰丽.基于感兴趣区的小波域彩色图像检索新方法[J].中国图象图形学报. 2006, 11(2): 175-179.
[156]周明荣,张淑佳,朱保林.基于小波显著特征点的图像检索技术[J].浙江工业大学学报. 2004, 32(5): 597-601.
[157] Wang Z, Bovik A.C. Bitplane-by-Bitplane Shift (BbBShift) - A Suggestion for JPEG2000 Regions of internet Image Coding [J].IEEE Signal Processing Letters. 2002,9(5):160-162.
[158] Liu L., Fan G. A New JPEG2O00 Region-of-Interest Images Code Method: Partial Significant BitPlanes Shift[C]. IEEE Signal Proeessing Letters.2003, 10(2): 35-39.
[159] Francesca Gasparini, Silvia Corchs, Rahnondo Schettini. Adaptive edge enhancement using a neurodynalineal model of visual attention[C]. IEEE. 2005.
[160] Yusuo Hu,Xing Xie,Zonghai Chen,Wei-Ying Ma. Attention model based progressive image transmission[C].2004 IEEE Illternational Conference on Multimedia and EXPO(ICME04). 2004: 1079-1082
[161]王璐,蔡自兴.未知环境中基于视觉显著性的自然路标检测[J].模式识别与人工智能.2006, 10(1): 100-105
[162] Adrian J. Chung, Fani Dellgianni, Xiao-Peng Hu, Guang-Zhong Yang. Visual Feature Extraction via Eye Tracking for Saliency Driven 2D3D Registration[J]. Image and Vision Computing. 2005,23: 999-1008.
[163] Shutao Li,James Tin-Yau Kwok,Ivor Wai-Hung Tsang,Yaonan Wang. Fusing Images With Dlfferent Focuses Using Support Vector Machines[J]. IEEE Transaetions on Neural Networks. 2004, 15(6):1555-1561.
[164] Dumont R, F. Pellaeii. Perceptually-driven decision theory for interactive realistic rendering[J]. ACM Transaction on Graphics. 2003, 22(2).
[165] Ross Brown, Luke CooPer, Binh Pham. Visual Attention-based Polygon Level of Detail Management.2003
[166] Antonios Oikonomopoulos, Ioannis Patras , Maja Pantic. Spatiotemporl Salient Points for Visual Recognition of Human Actions[J]. IEEE trans on Systems,Man and Cybernetics, 2006,36(3): 710-719
[167] YeeH,Pattanaik S N,and Greenbelg D P..Spatiotempoal sensitivity and visual attention for effieient rendering of dynamic Environments[J].ACMT Trans. On Graphics,2001 ,20(1) 39-65.
[168]田媚,罗四维,廖灵芝.基于what和where信息的目标检测方法[J].电子学报, 2007(11): 2055-2061.
[169]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[J].电子学报, 2006(03): 559-562.
[170]田媚.模拟自顶向下视觉注意机制的感知模型研究[D].北京:北京交通大学出版社. 2007.
[171]田媚.基于局部复杂度和初级视觉特征的自底向上注意信息提取算法[J].计算机研究与发展, 2008(10): 1739-1746.
[172]窦燕,孔令富.一种基于视觉注意机制的刀具检测方法[J].中国机械工程, 2008(17): 2024-2027.
[173] Williams L R, Jacobs D W. Stochastic completion fields:A neural model of illusory contour shape and salience[J]. Neural Computation, 1997, 9(4):837-858
[174] Soyer C, Bozma Hl, Istefanopulos Y. Attentional sequence-based recognition: Markovian and Evidential Reasoning[J]. IEEE Trans.on Systems, Man, And Cyberneties-PartB: Cybernetics 2003
[175] Buchsbaum, G., An Analytical Derivation of Visual Nonlinearity[J]. Biomedical Engineering, IEEE Transactions on, 1980. BME-27(5): 237-242.
[176] Wen-Nung, L. and C. Li Chun. Data hiding in images with adaptive numbers of least significant bits based on the human visual system[C]. in Image Processing, 1999. ICIP 99. Proceedings. 1999 International Conference on. 1999.
[177]邓述移.人眼调制传递函数[J].兵工学报, 1982(02): 24-33.
[178]杨俊.图像数据的视觉显著性检测技术及其应用[D].湖南武汉:国防科学技术大学出版社. 2007,
[179]姚军财,申静,王剑华.阴极射线管显示器亮度范围内对人眼视觉特性的实验研究[J].物理学报, 2008(07): 4034-4041.
[180]姚军财.人眼对比度敏感视觉特性及模型研究[J].光学技术, 2009,197(03): 334-337.
[181]張宜庭.基於人眼視覺和抵抗隱藏偵測之最佳化品質影像秘密資料嵌入技術[M],台湾台北:國立中正大學图书馆: 1995.
[182]周燕,金伟其.人眼视觉的传递特性及模型[J].光学技术, 2002(01): 57-59+62.
[183]李牧.基于类内方差最小化及模糊控制算法的小波边缘检测技术[J].电子学报, 2008(09): 1741-1745.
[184] Cook, W. and A. Rohe, Computing minimum-weight perfect matchings[J]. Informs Journal on Computing, 1999. 11(2): 138-148.
[185] Edmonds, J., Paths, tree, and flowers[J]. Canadian Journal of Mathematics, 1965(17): 449-467.
[186] Kolmogorov, V., Blossom V: a new implementation of a minimum cost perfect matching algorithm[J]. Mathematical Programming Computation, 2009. 1(1): 43-67.
[187] Manthey, B., Minimum-Weight Cycle Covers and Their Approximability[J]. 2007. 178-189.
[188] Mehlhorn, K. and G. Sch?fer, Implementation of O(nmlogn) Weighted Matchings in General Graphs[J]. The Power of Data Structures. 2001: 23-38.
[189] Arkin, E.M. and C.H. Papadimitriou, On negative cycles in mixed graphs[J]. Operations Research Letters, 1985. 4(3): 113-116.
[190] Cherkassky, B. and A. Goldberg, Negative-cycle detection algorithms[C], in Algorithms - ESA '96. 1996: 349-363.
[191] Gu, X., et al., Improved Algorithms for Detecting Negative Cost Cycles in Undirected Graphs[J], in Frontiers in Algorithmics. 2009: 40-50.
[192] Wong, C.-H. and Y.-C. Tam, Negative Cycle Detection Problem[C], in Algorithms - ESA 2005. 2005: 652-663
[193] NIMROD MEGIDDO, Combinatorial optimization with rational objective functions[C], Mathematics of Operations Research. 1979(4): 414-424.