基于内容的不良图像识别研究
|
摘要
随着信息技术及互联网技术的飞速发展,网络信息成为一种人们熟知的便捷信息来源和休闲生活方式,但网络上大量的色情淫秽等不良信息已经严重干扰了正常的网络生活,严重毒害着青少年的身心健康,网络空间的色情传播已在全球引起了关注,如何净化网络环境,增加对网络活动的监控手段,提高信息识别的能力便成为一种强烈的需求,作为其技术支持,基于内容的不良信息识别技术日益引起人们的重视。基于内容的不良图像的识别和检测技术近来已引起人们的极大兴趣,同时它也是基于内容的网络过滤系统所面临的一个重要且亟待解决的研究课题。色情图像的识别问题实际上是一个图像分类问题,我们使用基于内容的方法对图像进行研究,采用统计分类方法实现对色情图像的识别,采用的关键技术有:肤色检测、目标区域的提取、图像特征的提取、分类器的设计。
肤色检测在基于内容的不良图像信息识别研究中具有重要地位,是统计分类方法中特征提取的基础。通过对肤色特征、肤色检测过程中颜色空间的选择、多种肤色模型的比较进行研究后,我们综合利用YUV和YIQ颜色空间进行肤色检测,并在此结果的基础上使用基于直方图的大津法从检出区域再次甄别肤色区域,从而得到满意的肤色检测结果。实验表明,使用这种方法能够有效地检测出图像的皮肤区域。根据误检为肤色区域以及皮肤区域本身的特点,本文使用纹理分析的方法来消除误检的皮肤区域。
特征提取是统计分类方法的基础,选择合适的特征也是实现对不良图像的识别的关键,我们对图像上主要的特征提取方法进行了描述,包括颜色特征、纹理特征、边界形状特征、区域形状特征等。通过利用前面提到的肤色检测方法,我们可以得到一个肤色目标区域,如果没有得到目标区域,则我们就可以认为该图片是正常的,否则我们对肤色区域提取肤色的颜色特征;由于目标区域的形状可以通过其质心的不同圆周上的分布来描述,因此我们提出了一种基于分布的形状特征描述子,在该目标区域内进行不良图像区域特征的提取;同时结合傅里叶变换提取不良图像区域的低频图像特征,也就是我们所说的纹理特征,从而更有利于不良图像的识别。
分类器设计是统计分类方法的关键。不良图像识别问题是一个小样本问题,支持向量机具有极好的学习性能,对解决小样本、非线性和高维模式分类问题具有很大优势。我们首先对SVM的原理进行了介绍,明确了特征向量的构造方法:我们把得到的形状特征向量、颜色分布特征向量和纹理特征向量组合到一起就可以形成一个具有205个元素的特征向量。然后对核函数的选择与训练方法、基于SVM的不良图像识别算法的基本框架进行了描述。通过实验,我们提供的这种基于内容的不良图像识别方案的查全率为82.67%,达到了比较好的效果,达到了我们预期的研究目标,该课题的研究可以为打击色情图像的传播提供技术支持。
With the speedy development in information techniques and Internets, The network information becomes a kind of convenient information source and recreational way that be familiar with. But large numbers of smuttiness information and erotica has already seriously interfered the normal network living, harmed the teenager's mind and the body’s health. The spread of erotica and smuttiness information has caused the concern in the world. How to purify the network environment, increase supervises and control the means to the network activity, improving the ability that information identify has became a kind of strong need. As its techniques supports, bad information identification techniques based on content have caused people’s recognition increasingly. According to the adult’s picture of the contents identify and examine, the techniques recently have caused people biggest interest. It is a research lesson in network percolation system base on the contents, an importance for facing and need the solution at the same time. In fact, the adults picture identification is a image classification. We research in this area adopting the covariance classification method to identify the adult’s picture. The key techniques: Skin Detection, Target District Pick up, Picture Character Pick up, The Design of the Classification Machine.
The skin color detection is placed in the important position in adults picture identification based on contents. It is the foundation of character pick up to process in design with classified method in statistics. We studied the skin character, color-space chooses in process of skin detection and compared different skin color models. We use YUV and YIQ color-space to detected skin district. And in this district, we use OTSU to pick up the skin again. The experiment shows that it can examine the skin district effectively. According to the characteristic of fails detected skin district and the true skin district, we use the method of veins analysis to eliminate the mistake in skin detection.
Character Pick up is the foundation of the method in classification with statistics. How to choose and choose which appropriate characteristics is the key to identify the bad picture. We described the main methods of characteristic pick up in picture; include veins analysis and border shape characteristics and region shape characteristics etc. We noticed that the shape of the target district can be described by its pixel distribute in the different circumference in its quality heart. We present a scheme based on center distributing of the region to descript shape feature and use it to pick up the shape characteristics in the targets district. Combine Fourier transform to pick up the low frequency picture characteristic of the bad picture district, we do further benefit to the bad picture identification.
The design of classification machine is the key to the method of classification in statistics. The problem of bad picture identification is a small sample problem. Support Vector Machines (SVM) has its excellent learning performance and has a very big advantage in small sample classification, not linear classification and high dimension mode classification. After introducing the theory of SVM, we described the construction of eigenvector, the choice of kernel function and its method of training, the rudimental framework of the bad picture identified method based on SVM. The experiment shows that the entire rate of this project is 82.67%. It has got a good result and come to the study target that we expect. The study of this project can provide a technologic aegis to cut erotica picture’s spread.
肤色检测在基于内容的不良图像信息识别研究中具有重要地位,是统计分类方法中特征提取的基础。通过对肤色特征、肤色检测过程中颜色空间的选择、多种肤色模型的比较进行研究后,我们综合利用YUV和YIQ颜色空间进行肤色检测,并在此结果的基础上使用基于直方图的大津法从检出区域再次甄别肤色区域,从而得到满意的肤色检测结果。实验表明,使用这种方法能够有效地检测出图像的皮肤区域。根据误检为肤色区域以及皮肤区域本身的特点,本文使用纹理分析的方法来消除误检的皮肤区域。
特征提取是统计分类方法的基础,选择合适的特征也是实现对不良图像的识别的关键,我们对图像上主要的特征提取方法进行了描述,包括颜色特征、纹理特征、边界形状特征、区域形状特征等。通过利用前面提到的肤色检测方法,我们可以得到一个肤色目标区域,如果没有得到目标区域,则我们就可以认为该图片是正常的,否则我们对肤色区域提取肤色的颜色特征;由于目标区域的形状可以通过其质心的不同圆周上的分布来描述,因此我们提出了一种基于分布的形状特征描述子,在该目标区域内进行不良图像区域特征的提取;同时结合傅里叶变换提取不良图像区域的低频图像特征,也就是我们所说的纹理特征,从而更有利于不良图像的识别。
分类器设计是统计分类方法的关键。不良图像识别问题是一个小样本问题,支持向量机具有极好的学习性能,对解决小样本、非线性和高维模式分类问题具有很大优势。我们首先对SVM的原理进行了介绍,明确了特征向量的构造方法:我们把得到的形状特征向量、颜色分布特征向量和纹理特征向量组合到一起就可以形成一个具有205个元素的特征向量。然后对核函数的选择与训练方法、基于SVM的不良图像识别算法的基本框架进行了描述。通过实验,我们提供的这种基于内容的不良图像识别方案的查全率为82.67%,达到了比较好的效果,达到了我们预期的研究目标,该课题的研究可以为打击色情图像的传播提供技术支持。
With the speedy development in information techniques and Internets, The network information becomes a kind of convenient information source and recreational way that be familiar with. But large numbers of smuttiness information and erotica has already seriously interfered the normal network living, harmed the teenager's mind and the body’s health. The spread of erotica and smuttiness information has caused the concern in the world. How to purify the network environment, increase supervises and control the means to the network activity, improving the ability that information identify has became a kind of strong need. As its techniques supports, bad information identification techniques based on content have caused people’s recognition increasingly. According to the adult’s picture of the contents identify and examine, the techniques recently have caused people biggest interest. It is a research lesson in network percolation system base on the contents, an importance for facing and need the solution at the same time. In fact, the adults picture identification is a image classification. We research in this area adopting the covariance classification method to identify the adult’s picture. The key techniques: Skin Detection, Target District Pick up, Picture Character Pick up, The Design of the Classification Machine.
The skin color detection is placed in the important position in adults picture identification based on contents. It is the foundation of character pick up to process in design with classified method in statistics. We studied the skin character, color-space chooses in process of skin detection and compared different skin color models. We use YUV and YIQ color-space to detected skin district. And in this district, we use OTSU to pick up the skin again. The experiment shows that it can examine the skin district effectively. According to the characteristic of fails detected skin district and the true skin district, we use the method of veins analysis to eliminate the mistake in skin detection.
Character Pick up is the foundation of the method in classification with statistics. How to choose and choose which appropriate characteristics is the key to identify the bad picture. We described the main methods of characteristic pick up in picture; include veins analysis and border shape characteristics and region shape characteristics etc. We noticed that the shape of the target district can be described by its pixel distribute in the different circumference in its quality heart. We present a scheme based on center distributing of the region to descript shape feature and use it to pick up the shape characteristics in the targets district. Combine Fourier transform to pick up the low frequency picture characteristic of the bad picture district, we do further benefit to the bad picture identification.
The design of classification machine is the key to the method of classification in statistics. The problem of bad picture identification is a small sample problem. Support Vector Machines (SVM) has its excellent learning performance and has a very big advantage in small sample classification, not linear classification and high dimension mode classification. After introducing the theory of SVM, we described the construction of eigenvector, the choice of kernel function and its method of training, the rudimental framework of the bad picture identified method based on SVM. The experiment shows that the entire rate of this project is 82.67%. It has got a good result and come to the study target that we expect. The study of this project can provide a technologic aegis to cut erotica picture’s spread.
引文
[1] 《第十九次中国互联网络发展状况统计报告(2007.1)》,《中国互联网络发展状况统计报告((2007.1))》
[2] http://www.ala.org/cipa/low.pdf
[3] FORSYTH D A,FLEEK M M. Identifying nude pictures [Z] . Third IEEE workshop on applications of computer vision. Sarasota, Florida,1996,103-108
[4] James Ze Wang, Gio Wiederhold, Oscar Firschein, System for Screening Objectionable Images Using Daubechies' Wavelets and Color Histograms[A].Lecture Notes in Computer Science[M]. Heidelberg: Springer,1997,20-30
[5] 王文惠,周良柱等.基于内容的图像检索技术的研究和发展.计算机工程与应用,2001,5:54-56
[6] 许强,江早,赵宏.基于图像内容过滤的智能防火墙系统研究与实现[J].计算机研究与发展,2000,37(4):458-464
[7] 杨金锋,傅周宇,谭铁牛等.一种新型的基于内容的图像识别与过滤方法[J].通信学报,2004,25(7):93-105
[8] 尹显东,唐丹,邓君等.基于内容的特定图像过滤方法[J].计算机测量与控制,2004,12(3):283-286
[9] 刘继敏,史忠植.一种基于形状的图像信息检索方法[J].软件学报,2000.11(1):110-115
[10]马跃先,胡晓改,秦晋渊.二值商标图像检索系统[J].山西大学学报,1998,21(2):137-143
[11]李向阳,庄越挺,潘云鹤.基于内容的图像检索技术与系统[J].计算机研究与发展,2001,38(3):344-354
[12]陈跃峰,肖自美,杨灿.基于内容检索的图像系统的关键技术及其实现[J].计算机工程与应用,2000,10:17-19
[13]方艳梅,杨灿等.支持基于内容检索的图像数据模型的设计[J].计算机应用,2001,21(7):23-26
[14]李国辉,曹莉华等.基于内容的多媒体数据查询和检索[J].小型微型计算机系统,1998,19(4):1-8
[15]许强,江早,赵宏.一种新颖的智能网络图像内容监测系统模型[J].软件学报,2002,13(3):424-432
[16]陶霖密,徐光佑.机器视觉中的颜色问题及应用[J].科学通报,2001,46(3):178-190
[17]吴相豪.基于肤色检测的敏感图像过滤器的研究与实现[D].硕士论文.2003.2:19-22
[18]HUNKE M H. Locating and Tracing of Human Faces with Neural network [R].Technical Report, CMU-CS-94-155. Pittsburgh; school of computer Science, Carnegia Mellon University,1994
[19]JEBARA T,PENTLAND A..Parameterized Structure Motion for 3D Adaptive Feedback Tracing of Faces[R]. Perceptual computing Technical Report,401.Cambridge:MIT Media Lab,1996
[20]Elli Angelopoulou. Understanding the Color of Human Skin. In Proceedings of the SPIE Conference on Human version and Electronic Imaging VI (SPIE) 2001.SPIE Vo1.4229,SPIE Press,2001:243-251
[21]V.Vezhnevets and V.Sazonov and A.Andreeva, A Survey on Pixel-based Skin Color Detection Techniques.Graphicon2003,13th International Conference on the Computer Graphics and Vision,2003,Moscow,Russia, September
[22]JONES, M. J., AND REHG, J. M. Statistical Color Models with Application to Skin Detection. In Proceeding of the CVPR’99,1999(1):274–280
[23]BRAND J., MASON J.A,.Comparative Assessment of Three Approaches to Pixel Level Human Skin-detection. In Proceeding of the International Conference on Pattern Recognition,2000(1):1056-1059
[24]Ford A.,Roberts A. Color Space Conversions. Technical Report, Westminster University,London,1998
[25]Yang J.,lu W.,Waibel A. Skin Color Modeling and Adaptation. In Proceedings of the 3rd Asian Conference on Computer Vision, Hong Kong, china,1998,687-694
[26]TERRILLON,J.C., SHIRAZI,M.N., FUKAMACHI,H. AND AKAMATSU,S. Comparative Performance of Different Skin Chrominance Models and Chrominance Spaces for the Automatic Detection of Human Faces in Color Images. In Proceeding of the International Conference on Face and Gesture Recognition,2000:54–61
[27]Chair D., Ngan K.N.. Locating Facial Region of a Head and Shoulders Color Image. In Proceedings of the 3rd International Conference on Automatic Face and Gesture Recognition Nara,Japan,1998,124-129
[28]雷明,张军英,董济扬.一种可变光照条件下的肤色检测算法[J].计算机工程与应用,2002,38(24):123-125
[29]HsuR.L., Abdel-Mattaleb M.,Jain A.. Face Detection in Color Images. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):696-706
[30]张洪明,赵德斌,高文.基于肤色模型神经网络和人脸结构模型的平面旋转人脸检测[J].计算机学报,2002, 25(11):1250-1256
[31]姚鸿勋,刘明宝,高文,范旭彤,张洪明,吕雅娟等.基于彩色图像的色系坐标变换的面部定位与跟踪法[J].计算机学报,2000,23(2):158-165
[32]陈锻生,刘政凯.彩色图像人脸高光区域的自动检测与校正方法[J].软件学报,2003,14(11):1900-1906
[33]MENSER, B., AND WIEN, M. 2000. Segmentation and Tracking of Facial Regions in Color Image Sequences. In Proceeding SPIE Visual Communications and Image Processing,2000,731-740
[34]YANG, M.H. AND AHUJ A, N. Detecting Human Faces in Color Images. In International Conference on Image Processing (ICIP),1998(1):127-130
[35]Lee J.Y., Yoo S.I. An Elliptical Boundary Model for Skin Color Detection. In Proceedings of the 2002 International Conference on Imaging Science, Systems and Technology,2002,579-584
[36]Jayaram S.,Schmugge S.,Shin M.et al.. Effect of Color-Space Transformation,the illuminance component, and color modeling on skin detection. In Proceedings of the IEEE Computer Society Conference on ComputerVision and Pattern Recognition(CVPR.04),Washington,DC,USA,2004,813-818
[37]Gomez G..On Selecting Color Components for Skin Detection. In Proceedings of the 16th International Conference on Pattern Recognition,Quebec,Canada,2002,II:961-964
[38]Shin M.C.,Chang K.I.,TsapL.V..Does Color Space Transformation Make Any Difference on Skin Detection? In Proceedings of the 6th Workshop on Applications of Computer Vision,Orlando,FL,USA,2002,275-279
[39]Phung S.L.,Bouzerdoum A.,Chai D.. Skin Segmentation Using Color Pixel Classification, Analysis and Comparison[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(1):149-154
[40]Albiol A.,Torres L.,Delp E.J.. Optimum Color Space for Skin Detection. In Proceedings of the International Conference on Image Processing, The ssaloniki,Greece,2001,I:122-124
[41]陈锻生,刘政凯.肤色检测技术综述[J].计算机学报,2006,29(2):194-207
[42]段立娟,崔国勤,高文.多层次特定类型图像过滤方法[J].计算机辅助设计与图形学学报,2002,14(5):409-109
[43]Elli Angelopoulou. Understanding the Color of Human Skin. In Proceedings of the SPIE Conference on Human Vision and Electronic Imaging VI (SPIE) 2001. SPIE Vol.4229, SPIE Press,2001:243-251
[44]孙兴华.基于内容的图像检索研究[D].博士论文,南京理工大学,南京,2001
[45]Mihran Tuceryan, Aril K Jain. Texture Analysis. The Handbook of Pattern Recognition and Computer Vision (2nd Edition), by C H Chen, L F Pau, P S P Wang (eds), World Scientific Publishing Co.,1998:207-248
[46]Ercan Oryildiz,Nils Krahnstover,Rajeev Sharma. Adaptive Texture and Color Segmentation for Tracking Moving Objects [J]. Pattern Recognition,2002,Vol.35,Nr.10,2013-2029
[47]K R Castleman 著,朱志刚等译.数字图像处理(第二版)[M].电子工业出反社,2003
[48]Haralick R.M., Shanmugam K. and Dinstein I.. Textural Features for Image Classification. IEEE Transaction on Systems, Man and Cybern, 1973, vol SMC-3,610-621
[49]李学龙,刘政凯,俞能海,袁媛.一种高效的语意图像分类方法[J].电路与系统学报.2002,7(2):22-25
[50]Tamura H, Mori S, Yamawaki T. Texture Features Corresponding to Visual Perception[J]. IEEE Transactions on Systems, Man and Cybcrnetics, 1978,8(6):460-473
[51]Derin H,H elliott. Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random fields. IEEE Transactions on Pattern Analysis and Machine Intelligence,PAMI-9,1987,39-55
[52]Randen T,Husoy J H. Filtering for Texture Classification:A comparative study[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(4):291-310
[53]Ohanian P P,Dubes R C.. Performance Evaluation for Four Classes of Texture Features[J]. Pattern Recognition,1992,25(8):819-833
[54]Ma W Y, Manjunath B S.A Comparison of Wavelet Transform Features for Texture Image Annotation[A]. In Proceedings of the IEEE International Conference On Image Processing[C], Washington, USA, 1995,2:256-259
[55]Freeman,H. On the Encoding of Arbitrary Geometric Configurations IEEE Trans. Elec. Computer, 1961, vol. EC-10,260-268
[56]Bribiesca,E., Guzman, A., How to Describe Pure Form and How to Measure Differences in Shape Using Shape Numbers[J]. Pattern Recognition, 1980,12(2):101-112
[57]Bribiesca,E., Arithmetic Operations Among Shapes Using Shape numbers[J]. Pattern Recognition, 1981,13(2):123-138
[58]Zahn,C. T., Roskies,R.Z., Fourier Descriptors for Plane Closed Curves. IEEE Transaction,1987, vol.C-21,No.3:269-281
[59]Persoon, E., Fu, K. S., Shape Discrimination Using Fourier Descriptors. IEEE Trans. Systems Man Cyb., 1977,vol.SMC-7,No.2:170-179
[60]Aguado, A.S., Nixon, M.S., Montiel,M.M., Motion and Time-Varying Imagery. IEEE Trans. Pattern Analysis and Machine Intelligence, Special Issue.1998,vol.PAMI-2,No.6:493-588
[61]Sonka,M., Hlavac, V., Boyle, R., Image Processing, Analysis, and Machine Vision, 2nd ed. PWS Publishing, New York,1999
[62]Reddy, B.S., Chatterji, B.N., An FFT-Based Technique for Translation, Rotation, and Scale Invariant Image Registration[J]. IEEE Trans. Image Procession,1996,5(7):1215-1220
[63]Zhang,T.Y., Suen,C.Y., A Fast Parallel Algorithm for Thinning Digital Patterns. Comm. ACM,1984, 27(3): 236-239
[64]M.M. Fleck, D.A. Forsyth, C. Bregler: Finding Naked People, Proc. European Conf. on Computer Vision, B. Buxton, R. Cipolla, Springer-Verlag, Berlin, Germany,1996,2:593-602
[65]王小玲,谢康林.一种新的基于区域的图像检索方法[J].计算机工程与应用,2005,3:80-82
[66]Hu, M.K., Visual Pattern Recognition by Moment Invariants [J]. IEEE trans Information Theory, 1962,8:179-187
[67]李宗民,刘玉杰,李振波,崔丽,李华. Bezier 矩及其在人体姿态识别中的应用[J].计算机工程,2005,24:38-40
[68]Huicheng Zheng, Mohamed Daoudi, Bruno Jedynak. Blocking Adult Images Based on Statistical Skin Detection[J]. Electronic Letters on Computer Vision and Image Analysis 2004,4(2):1-14
[69]段立娟,包振山,毛国君.多特征特定类型图像过滤方法[J].北京工业大学学报,2005,31(4):352-357
[70]Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(4):509-522
[71]章夏芬,庄越挺,鲁伟明,吴 飞.根据形状相似性的书法内容检索[J].计算机辅助设计与图形学学报, 2005,17(11):2565-2569
[72]刘江华,程君实等.支持向量机训练算法综述[J].信息与控制,2002,31(1):45-50
[73]C.J.C.Burger. A Tutorial on Support Vector Machines for Pattern Recognition[J]. Data Mining and Knowledge Discovery,1998,2(2):121-167
[74]张学工.关于统计一学习理论与支持向量机[J].自动化学报,2000,26(1):32-42
[75]杨强.支持向量机的模型及其在图像分割中的应用[D].博士学问论文,重庆大学,重庆,2004
[2] http://www.ala.org/cipa/low.pdf
[3] FORSYTH D A,FLEEK M M. Identifying nude pictures [Z] . Third IEEE workshop on applications of computer vision. Sarasota, Florida,1996,103-108
[4] James Ze Wang, Gio Wiederhold, Oscar Firschein, System for Screening Objectionable Images Using Daubechies' Wavelets and Color Histograms[A].Lecture Notes in Computer Science[M]. Heidelberg: Springer,1997,20-30
[5] 王文惠,周良柱等.基于内容的图像检索技术的研究和发展.计算机工程与应用,2001,5:54-56
[6] 许强,江早,赵宏.基于图像内容过滤的智能防火墙系统研究与实现[J].计算机研究与发展,2000,37(4):458-464
[7] 杨金锋,傅周宇,谭铁牛等.一种新型的基于内容的图像识别与过滤方法[J].通信学报,2004,25(7):93-105
[8] 尹显东,唐丹,邓君等.基于内容的特定图像过滤方法[J].计算机测量与控制,2004,12(3):283-286
[9] 刘继敏,史忠植.一种基于形状的图像信息检索方法[J].软件学报,2000.11(1):110-115
[10]马跃先,胡晓改,秦晋渊.二值商标图像检索系统[J].山西大学学报,1998,21(2):137-143
[11]李向阳,庄越挺,潘云鹤.基于内容的图像检索技术与系统[J].计算机研究与发展,2001,38(3):344-354
[12]陈跃峰,肖自美,杨灿.基于内容检索的图像系统的关键技术及其实现[J].计算机工程与应用,2000,10:17-19
[13]方艳梅,杨灿等.支持基于内容检索的图像数据模型的设计[J].计算机应用,2001,21(7):23-26
[14]李国辉,曹莉华等.基于内容的多媒体数据查询和检索[J].小型微型计算机系统,1998,19(4):1-8
[15]许强,江早,赵宏.一种新颖的智能网络图像内容监测系统模型[J].软件学报,2002,13(3):424-432
[16]陶霖密,徐光佑.机器视觉中的颜色问题及应用[J].科学通报,2001,46(3):178-190
[17]吴相豪.基于肤色检测的敏感图像过滤器的研究与实现[D].硕士论文.2003.2:19-22
[18]HUNKE M H. Locating and Tracing of Human Faces with Neural network [R].Technical Report, CMU-CS-94-155. Pittsburgh; school of computer Science, Carnegia Mellon University,1994
[19]JEBARA T,PENTLAND A..Parameterized Structure Motion for 3D Adaptive Feedback Tracing of Faces[R]. Perceptual computing Technical Report,401.Cambridge:MIT Media Lab,1996
[20]Elli Angelopoulou. Understanding the Color of Human Skin. In Proceedings of the SPIE Conference on Human version and Electronic Imaging VI (SPIE) 2001.SPIE Vo1.4229,SPIE Press,2001:243-251
[21]V.Vezhnevets and V.Sazonov and A.Andreeva, A Survey on Pixel-based Skin Color Detection Techniques.Graphicon2003,13th International Conference on the Computer Graphics and Vision,2003,Moscow,Russia, September
[22]JONES, M. J., AND REHG, J. M. Statistical Color Models with Application to Skin Detection. In Proceeding of the CVPR’99,1999(1):274–280
[23]BRAND J., MASON J.A,.Comparative Assessment of Three Approaches to Pixel Level Human Skin-detection. In Proceeding of the International Conference on Pattern Recognition,2000(1):1056-1059
[24]Ford A.,Roberts A. Color Space Conversions. Technical Report, Westminster University,London,1998
[25]Yang J.,lu W.,Waibel A. Skin Color Modeling and Adaptation. In Proceedings of the 3rd Asian Conference on Computer Vision, Hong Kong, china,1998,687-694
[26]TERRILLON,J.C., SHIRAZI,M.N., FUKAMACHI,H. AND AKAMATSU,S. Comparative Performance of Different Skin Chrominance Models and Chrominance Spaces for the Automatic Detection of Human Faces in Color Images. In Proceeding of the International Conference on Face and Gesture Recognition,2000:54–61
[27]Chair D., Ngan K.N.. Locating Facial Region of a Head and Shoulders Color Image. In Proceedings of the 3rd International Conference on Automatic Face and Gesture Recognition Nara,Japan,1998,124-129
[28]雷明,张军英,董济扬.一种可变光照条件下的肤色检测算法[J].计算机工程与应用,2002,38(24):123-125
[29]HsuR.L., Abdel-Mattaleb M.,Jain A.. Face Detection in Color Images. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):696-706
[30]张洪明,赵德斌,高文.基于肤色模型神经网络和人脸结构模型的平面旋转人脸检测[J].计算机学报,2002, 25(11):1250-1256
[31]姚鸿勋,刘明宝,高文,范旭彤,张洪明,吕雅娟等.基于彩色图像的色系坐标变换的面部定位与跟踪法[J].计算机学报,2000,23(2):158-165
[32]陈锻生,刘政凯.彩色图像人脸高光区域的自动检测与校正方法[J].软件学报,2003,14(11):1900-1906
[33]MENSER, B., AND WIEN, M. 2000. Segmentation and Tracking of Facial Regions in Color Image Sequences. In Proceeding SPIE Visual Communications and Image Processing,2000,731-740
[34]YANG, M.H. AND AHUJ A, N. Detecting Human Faces in Color Images. In International Conference on Image Processing (ICIP),1998(1):127-130
[35]Lee J.Y., Yoo S.I. An Elliptical Boundary Model for Skin Color Detection. In Proceedings of the 2002 International Conference on Imaging Science, Systems and Technology,2002,579-584
[36]Jayaram S.,Schmugge S.,Shin M.et al.. Effect of Color-Space Transformation,the illuminance component, and color modeling on skin detection. In Proceedings of the IEEE Computer Society Conference on ComputerVision and Pattern Recognition(CVPR.04),Washington,DC,USA,2004,813-818
[37]Gomez G..On Selecting Color Components for Skin Detection. In Proceedings of the 16th International Conference on Pattern Recognition,Quebec,Canada,2002,II:961-964
[38]Shin M.C.,Chang K.I.,TsapL.V..Does Color Space Transformation Make Any Difference on Skin Detection? In Proceedings of the 6th Workshop on Applications of Computer Vision,Orlando,FL,USA,2002,275-279
[39]Phung S.L.,Bouzerdoum A.,Chai D.. Skin Segmentation Using Color Pixel Classification, Analysis and Comparison[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(1):149-154
[40]Albiol A.,Torres L.,Delp E.J.. Optimum Color Space for Skin Detection. In Proceedings of the International Conference on Image Processing, The ssaloniki,Greece,2001,I:122-124
[41]陈锻生,刘政凯.肤色检测技术综述[J].计算机学报,2006,29(2):194-207
[42]段立娟,崔国勤,高文.多层次特定类型图像过滤方法[J].计算机辅助设计与图形学学报,2002,14(5):409-109
[43]Elli Angelopoulou. Understanding the Color of Human Skin. In Proceedings of the SPIE Conference on Human Vision and Electronic Imaging VI (SPIE) 2001. SPIE Vol.4229, SPIE Press,2001:243-251
[44]孙兴华.基于内容的图像检索研究[D].博士论文,南京理工大学,南京,2001
[45]Mihran Tuceryan, Aril K Jain. Texture Analysis. The Handbook of Pattern Recognition and Computer Vision (2nd Edition), by C H Chen, L F Pau, P S P Wang (eds), World Scientific Publishing Co.,1998:207-248
[46]Ercan Oryildiz,Nils Krahnstover,Rajeev Sharma. Adaptive Texture and Color Segmentation for Tracking Moving Objects [J]. Pattern Recognition,2002,Vol.35,Nr.10,2013-2029
[47]K R Castleman 著,朱志刚等译.数字图像处理(第二版)[M].电子工业出反社,2003
[48]Haralick R.M., Shanmugam K. and Dinstein I.. Textural Features for Image Classification. IEEE Transaction on Systems, Man and Cybern, 1973, vol SMC-3,610-621
[49]李学龙,刘政凯,俞能海,袁媛.一种高效的语意图像分类方法[J].电路与系统学报.2002,7(2):22-25
[50]Tamura H, Mori S, Yamawaki T. Texture Features Corresponding to Visual Perception[J]. IEEE Transactions on Systems, Man and Cybcrnetics, 1978,8(6):460-473
[51]Derin H,H elliott. Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random fields. IEEE Transactions on Pattern Analysis and Machine Intelligence,PAMI-9,1987,39-55
[52]Randen T,Husoy J H. Filtering for Texture Classification:A comparative study[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(4):291-310
[53]Ohanian P P,Dubes R C.. Performance Evaluation for Four Classes of Texture Features[J]. Pattern Recognition,1992,25(8):819-833
[54]Ma W Y, Manjunath B S.A Comparison of Wavelet Transform Features for Texture Image Annotation[A]. In Proceedings of the IEEE International Conference On Image Processing[C], Washington, USA, 1995,2:256-259
[55]Freeman,H. On the Encoding of Arbitrary Geometric Configurations IEEE Trans. Elec. Computer, 1961, vol. EC-10,260-268
[56]Bribiesca,E., Guzman, A., How to Describe Pure Form and How to Measure Differences in Shape Using Shape Numbers[J]. Pattern Recognition, 1980,12(2):101-112
[57]Bribiesca,E., Arithmetic Operations Among Shapes Using Shape numbers[J]. Pattern Recognition, 1981,13(2):123-138
[58]Zahn,C. T., Roskies,R.Z., Fourier Descriptors for Plane Closed Curves. IEEE Transaction,1987, vol.C-21,No.3:269-281
[59]Persoon, E., Fu, K. S., Shape Discrimination Using Fourier Descriptors. IEEE Trans. Systems Man Cyb., 1977,vol.SMC-7,No.2:170-179
[60]Aguado, A.S., Nixon, M.S., Montiel,M.M., Motion and Time-Varying Imagery. IEEE Trans. Pattern Analysis and Machine Intelligence, Special Issue.1998,vol.PAMI-2,No.6:493-588
[61]Sonka,M., Hlavac, V., Boyle, R., Image Processing, Analysis, and Machine Vision, 2nd ed. PWS Publishing, New York,1999
[62]Reddy, B.S., Chatterji, B.N., An FFT-Based Technique for Translation, Rotation, and Scale Invariant Image Registration[J]. IEEE Trans. Image Procession,1996,5(7):1215-1220
[63]Zhang,T.Y., Suen,C.Y., A Fast Parallel Algorithm for Thinning Digital Patterns. Comm. ACM,1984, 27(3): 236-239
[64]M.M. Fleck, D.A. Forsyth, C. Bregler: Finding Naked People, Proc. European Conf. on Computer Vision, B. Buxton, R. Cipolla, Springer-Verlag, Berlin, Germany,1996,2:593-602
[65]王小玲,谢康林.一种新的基于区域的图像检索方法[J].计算机工程与应用,2005,3:80-82
[66]Hu, M.K., Visual Pattern Recognition by Moment Invariants [J]. IEEE trans Information Theory, 1962,8:179-187
[67]李宗民,刘玉杰,李振波,崔丽,李华. Bezier 矩及其在人体姿态识别中的应用[J].计算机工程,2005,24:38-40
[68]Huicheng Zheng, Mohamed Daoudi, Bruno Jedynak. Blocking Adult Images Based on Statistical Skin Detection[J]. Electronic Letters on Computer Vision and Image Analysis 2004,4(2):1-14
[69]段立娟,包振山,毛国君.多特征特定类型图像过滤方法[J].北京工业大学学报,2005,31(4):352-357
[70]Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(4):509-522
[71]章夏芬,庄越挺,鲁伟明,吴 飞.根据形状相似性的书法内容检索[J].计算机辅助设计与图形学学报, 2005,17(11):2565-2569
[72]刘江华,程君实等.支持向量机训练算法综述[J].信息与控制,2002,31(1):45-50
[73]C.J.C.Burger. A Tutorial on Support Vector Machines for Pattern Recognition[J]. Data Mining and Knowledge Discovery,1998,2(2):121-167
[74]张学工.关于统计一学习理论与支持向量机[J].自动化学报,2000,26(1):32-42
[75]杨强.支持向量机的模型及其在图像分割中的应用[D].博士学问论文,重庆大学,重庆,2004