基于广义判别分析方法的人脸识别

提出基于广义判别分析的人脸识别方法,通过非线性核函数把样本映射到高维线性空间,然后在高维空间运用线性判决算法,从而获得输入空间非线性判决特征,可以很好地适应人脸图像中的光照、表情以及姿态等复杂的变化。实验证明该方法用较少的特征向量能获得比特征脸算法、Fisherfaces算法更高的分类准确率。     

基于Gabor、Fisher脸多特征提取及集成SVM的人脸表情识别*

针对于静态的灰度图像表情库,提出了基于多种脸部表情特征多级分类的表情识别算法。首先在选取的人脸特征点上做局部的Gabor小波变换,为了提高特征提取速度,利用改进的弹性图匹配算法来提取图像中的人脸有效区域,在提取的人脸区域中提取几何特征,并通过Fisher脸法提取统计特征,利用几何特征与建立的相应一级集成SVM来进行初次分类,最后利用Fisher特征与建立的相应二级集成SVM进行最终分类。通过在JAFFE与Cohn-Kanade表情库中实验,证明本文方法同单个特征相比较,具有更高的表情识别率以及更强的鲁棒性     

Two-dimensional discriminant transform for face recognition

This paper develops a new image feature extraction and recognition method coined two-dimensional linear discriminant analysis (2DLDA). 2DLDA provides a sequentially optimal image compression mechanism, making the discriminant information compact into the up-left corner of the image. Also, 2DLDA suggests a feature selection strategy to select the most discriminative features from the corner. 2DLDA is tested and evaluated using the AT&T face database. The experimental results show 2DLDA is more effective and computationally more efficient than the current LDA algorithms for face feature extraction and recognition.     

基于LDA算法的人脸识别方法的比较研究

线性判别分析（LDA）是一种较为普遍的用于特征提取的线性分类方法。但是将LDA直接用于人脸识别会遇到维数问题和“小样本”问题。人们经过研究，通过多种途径解决了这两个问题并实现了基于LDA的人脸识别。文章对几种基于LDA的人脸识别方法做了理论上的比较和实验数据的支持，这些方法包括Eigenfaces、Fisherfaces、DLDA、VDLDA及VDFLDA。实验结果表明VDFLDA是其中最好的一种方法。     

基于Fihserfaces算法的人脸识别

Fisher鉴别是一种有监督的特征提取技术,因其计算简单、分类效果良好而得到广泛应用。文中使用基于Fisher鉴别数值分析技术,对人脸数据进行特征提取,再使用最小距离分类器进行分类识别。该算法在ORL和YALE人脸库进行了实验,根据统计对ORL人脸库和YALEA人脸库的识别率分别为94.00%和89.33%。实验结果表明,Fisherfaces算法对于人脸库中的图像有较高的识别率。     

多模态人脸识别融合方法比较研究

比较研究了多模态人脸识别中的5种匹配得分级融合方法。首先用局部二值模式（Local Binary Pattern,LBP）算子分别提取人脸灰度图像和深度图像的区域LBP直方图序列（LBP Histogram Sequence,LBPHS）,采用Fisherfaces分别构建相应的线性子空间,用余弦相似度计算投影向量的匹配得分,再采用5种方法对匹配得分进行融合。在FRGC数据库上的实验结果表明,除最小匹配得分外,其他融合方法的识别性能都要优于单一模态的方法。     

基于复小波和Gabor小波的人脸识别

针对双树复小波变换(DT-CWT)不能直接提取水平和垂直2个方向特征的不足,提出一种结合DT-CWT和Gabor小波的人脸识别方法。将Gabor小波提取的0°和90°特征与DT-CWT提取的6个方向特征连接起来共同构成人脸特征向量,采用Fisherfaces方法构建特征向量的线性子空间,应用基于欧氏距离的分类器实现分类。在ORL数据库上的实验结果证明了该方法的有效性。     

融合LTP与Fisherfaces的分块人脸识别

提出一种融合局部三值模式(LTP)和Fisherfaces进行人脸识别的方法,运用LTP算子提取分块人脸灰度图像的LTP直方图序列,采用Fisherfaces方法对采样后的特征进行特征选择,根据最近邻原则进行识别。该算法不仅能提取人脸纹理信息,大幅降低训练数据量,而且数据量的维数与原始图像大小无关。在ORL和YALE标准人脸数据库上的实验结果表明,该方法具有较高的识别率。     

Deterioration of visual information in face classification using Eigenfaces and Fisherfaces

In the area of biometrics, face classification becomes one of the most appealing and commonly used approaches for personal identification. There has been an ongoing quest for designing systems that exhibit high classification rates and portray significant robustness. This feature becomes of paramount relevance when dealing with noisy and uncertain images. The design of face recognition classifiers capable of operating in presence of deteriorated (noise affected) face images requires a careful quantification of deterioration of the existing approaches vis-à-vis anticipated form and levels of image distortion. The objective of this experimental study is to reveal some general relationships characterizing the performance of two commonly used face classifiers (that is Eigenfaces and Fisherfaces) in presence of deteriorated visual information. The findings obtained in our study are crucial to identify at which levels of noise the face classifiers can still be considered valid. Prior knowledge helps us develop adequate face recognition systems. We investigate several typical models of image distortion such as Gaussian noise, salt and pepper, and blurring effect and demonstrate their impact on the performance of the two main types of the classifiers. Several distance models derived from the Minkowski family of distances are investigated with respect to the produced classification rates. The experimental environment concerns a well-known standard in this area of face biometrics such as the FERET database. The study reports on the performance of the classifiers, which is based on a comprehensive suite of experiments and delivers several design hints supporting further developments of face classifiers. Gabriel Jarillo Alvarado obtained his B.Sc. degree in Biomedical Engineering from the Universidad Iberoamericana, Mexico. In 2003 he obtained his M.Sc. degree from the University of Alberta at the Department of Electrical and Computer Engineering, he is currently enrolled in the Ph.D. program at the same University. His research interests involve machine learning, pattern recognition, and evolutionary computation with particular interest to biometrics for personal identification. Witold Pedrycz is a Professor and Canada Research Chair (CRC) in Computational Intelligence) in the Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada. His research interests involve Computational Intelligence, fuzzy modeling, knowledge discovery and data mining, fuzzy control including fuzzy controllers, pattern recognition, knowledge-based neural networks, relational computing, and Software Engineering. He has published numerous papers in this area. He is also an author of 9 research monographs. Witold Pedrycz has been a member of numerous program committees of conferences in the area of fuzzy sets and neurocomputing. He currently serves on editorial board of numereous journals including IEEE Transactions on Systems Man and Cybernetics, Pattern Recognition Letters, IEEE Transactions on Fuzzy Systems, Fuzzy Sets & Systems, and IEEE Transactions on Neural Networks. He is an Editor-in-Chief of Information Sciences. Marek Reformat received his M.Sc. degree from Technical University of Poznan, Poland, and his Ph.D. from University of Manitoba, Canada. His interests were related to simulation and modeling in time-domain, as well as evolutionary computing and its application to optimization problems For three years he worked for the Manitoba HVDC Research Centre, Canada, where he was a member of a simulation software development team. Currently, Marek Reformat is with the Department of Electrical and Computer Engineering at University of Alberta. His research interests lay in the areas of application of Computational Intelligence techniques, such as neuro-fuzzy systems and evolutionary computing, as well as probabilistic and evidence theories to intelligent data analysis leading to translating data into knowledge. He applies these methods to conduct research in the areas of Software and Knowledge Engineering. He has been a member of program committees of several conferences related to Computational Intelligence and evolutionary computing. Keun-Chang Kwak received B.Sc., M.Sc., and Ph.D. degrees in the Department of Electrical Engineering from Chungbuk National University, Cheongju, South Korea, in 1996, 1998, and 2002, respectively. During 2002–2003, he worked as a researcher in the Brain Korea 21 Project Group, Chungbuk National University. His research interests include biometrics, computational intelligence, pattern recognition, and intelligent control.     

基于LBP和Fisherfaces的多模态人脸识别

提出一种结合局部二值模式（LBP）和Fisherfaces的多模态人脸识别方法。用LBP算子提取人脸灰度图像和深度图像的区域LBP直方图序列（LBPHS）,再采用Fisherfaces分别构建相应的线性子空间,用余弦相似度作为投影向量的相似度量,用加权求和规则进行信息融合。在FRGC数据库上的实验结果表明,该方法要明显优于LBPHS与直方图交及Fisherfaces与余弦相似度的融合,等错误率仅为0．33％。