Learning the best subset of local features for face recognition

We propose a novel, local feature-based face representation method based on two-stage subset selection where the first stage finds the informative regions and the second stage finds the discriminative features in those locations. The key motivation is to learn the most discriminative regions of a human face and the features in there for person identification, instead of assuming a priori any regions of saliency. We use the subset selection-based formulation and compare three variants of feature selection and genetic algorithms for this purpose. Experiments on frontal face images taken from the FERET dataset confirm the advantage of the proposed approach in terms of high accuracy and significantly reduced dimensionality.     

Analysis of variance of Gabor filter banks parameters for optimal face recognition

Gabor filter banks constitute a very robust tool to extract discriminant information from a visual scene. After the now “classical” bank with 5 frequencies and 8 orientations proposed by Lades et al. and Wiskott et al., many other parametrizations of a Gabor filter bank have appeared. In order to find the optimal parametrization for a face recognition experiment, we have performed a 6-way analysis of variance of Gabor parameters using FERET, FRAV2D, FRAV3D, FRGC and XM2VTS face databases, including frontal and turned poses, facial expressions, occlusions and changes of illumination. Considering independent criteria to find the optimal Gabor filter bank, the bank with the highest recognition rate was found to have 6 frequencies and narrower Gaussian widths in the space domain. These results were obtained with Mahalanobis distance for a k-NN classifier, with analytical and holistic Gabor feature vectors. Moreover about 20% of the banks studied here obtained in average a better performance than the classical bank. For most of the databases considered, the highest recognition rates have been achieved with analytical representations (frontal images, images with turns or occlusions), with a holistic preponderance for images with gestures or changes of illumination. The inferiority found for holistic Gabor representations versus their analytical counterparts can be explained for the intrinsic redundancy and the size of the feature vectors of this kind of representation.     

Gabor texture representation method for face recognition using the Gamma and generalized Gaussian models

A novel face recognition algorithm based on Gabor texture information is proposed in this paper. Two kinds of strategies to capture it are introduced: Gabor magnitude-based texture representation (GMTR) and Gabor phase-based texture representation (GPTR). Specifically, GMTR is characterized by using the Gamma density (Γ$\Gamma$ D) to model the Gabor magnitude distribution, while GPTR is characterized by using the generalized Gaussian density (GGD) to model the Gabor phase distribution. The estimated model parameters serve as texture representation. Experiments are performed on Yale, ORL and FERET databases to validate the feasibility of the proposed method. The results show that the proposed GMTR-based and GPTR-based NLDA both significantly outperform the widely used Gabor features-based NLDA and other existing subspace methods. In addition, the feature level fusion of these two kinds of texture representations performs better than them individually.     

基于Gabor小波的人脸检测

提出了一种新的正面人脸检测算法。该方法组合了Gabor小波变换、输入图像的Gabor特征分析和Bayes分类器来进行正面人脸检测。对训练集的平均脸作Gabor小波变换得到40个投影向量；通过计算输入图像和这40个投影向量间的内积来提取图像的Gabor特征向量；训练Bayes分类器来进行正面人脸检测。实验结果表明，该算法的计算效率和检测精度均优于特征脸方法。     

Methodological improvement on local Gabor face recognition based on feature selection and enhanced Borda count

Face recognition has a wide range of possible applications in surveillance, human computer interfaces and marketing and advertising goods for selected customers according to age and gender. Because of the high classification rate and reduced computational time, one of the best methods for face recognition is based on Gabor jet feature extraction and Borda count classification. In this paper, we propose methodological improvements to increase face recognition rate by selection of Gabor jets using entropy and genetic algorithms. This selection of jets additionally allows faster processing for real-time face recognition. We also propose improvements in the Borda count classification through a weighted Borda count and a threshold to eliminate low score jets from the voting process to increase the face recognition rate. Combinations of Gabor jet selection and Borda count improvements are also proposed. We compare our results with those published in the literature to date and find significant improvements. Our best results on the FERET database are 99.8%, 99.5%, 89.2% and 86.8% recognition rates on the subsets Fb, Fc, Dup1 and Dup2, respectively. Compared to the best results published in the literature, the total number of recognition errors decreased from 163 to 112 (31%). We also tested the proposed method under illumination changes, occlusions with sunglasses and scarves and for small pose variations. Results on two different face databases (AR and Extended Yale B) with significant illumination changes showed over 90% recognition rate. The combination EJS-BTH-BIP reached 98% and 99% recognition rate in images with sunglasses and scarves from the AR database, respectively. The proposed method reached 93.5% recognition on faces with small pose variation of 25° rotation and 98.5% with 15% rotation in the FERET database.     

基于分块Gabor特征的贝叶斯人脸识别

对贝叶斯分类中最大似然（ML）公式进行了简化,给出了一种实用的快速计算相似度的方法,在此基础上设计了基于分块Gabor特征提取的贝叶斯人脸识别算法。该算法从原始数字图像出发,先对图像矩阵进行分块,然后对分块子图像进行多分辨率的Gabor特征提取,对每一个特征块设计一个贝叶斯分类器,通过将这些分类器加权平均,得到最后的决策。在FERET人脸数据库的实验结果验证了该方法的有效性。     

基于Gabor小波和HMM的人像鉴别算法

探讨了利用Gabor小波和隐马尔可夫模型（HMM）进行人脸识别的方法,首先对人脸图像进行多分辨率的Gabor小波变换;然后在图像上放置一组网格结点,每个结点用该结点处的多尺度Gabor幅度特征描述,采用独立元分析法对每个结点进行去相关和降维;最后形成特征结,把每个特征结作为观测向量,对隐马尔可夫模型进行训练,并将优化的模型参数用于人脸识别,ORL人脸库的实验结果表明,该方法识别率高,工程上易于应用。     

基于Gabor滤波器的快速人脸识别算法

针对传统人脸识别方法中所提取特征维数高、计算量大等缺点,提出一种新的正面人脸识别算法。新算法融合了半边人脸识别方法、Gabor滤波器、基于互信息判据的Gabor特征筛选来进行人脸识别。新算法将人脸图像分为左右两个部分,计算并比较人脸图像左右半边脸的熵,选取熵值较大的半边人脸图像进行Gabor特征提取。利用二值分类器判别单个Gabor特征的分类能力,选取分类能力较强的特征（最具判决力的特征）。再利用互信息判据对Gabor特征进行第二次筛选,以减小特征之间的冗余度。最后利用最近邻判别器来进行人脸识别。实验结果表明,新算法的识别率优于传统半边脸识别方法,识别速度也优于传统的利用Gabor滤波器进行特征提取的方法。     

Gabor核函数窗的设置研究

Gabor滤波器广泛应用于模式识别等领域,但是在应用傅立叶变换进行Gabor快速卷积过程中,对Gabor核函数窗的设置研究较少.首先从理论上分析Gabor核函数窗的性质及其对特征提取的影响;其次从对称性、范围两个方面在YaleB人脸库上进行实验,研究Gabor核函数窗的不同设置对目标识别率的影响;最后给出相应的结论.     

改进Gabor加权分析方法在人脸识别中的应用

为提高Gabor对人脸结构特征和内容信息的保留能力,解决人脸识别中对表情等抗噪性差的缺点,提出一种基于改进Gabor加权分析的人脸识别算法。该方法通过对归一化的人脸进行多尺度Gabor分析,并依据相同滤波窗口参数进行归类合并,最后对该信号进行加权比对得到识别结果。实验证明,该方法很好地兼顾人脸结构特征和内容信息,具有良好的抗噪性和识别率。