An Improved Real-Time Face Recognition System at Low Resolution Based on Local Binary Pattern Histogram Algorithm and CLAHE

This research presents an improved real-time face recognition system at a low resolution of 15 pixels with pose and emotion and resolution variations. We have designed our datasets named LRD200 and LRD100, which have been used for training and classification. The face detection part uses the Viola-Jones algorithm, and the face recognition part receives the face image from the face detection part to process it using the Local Binary Pattern Histogram (LBPH) algorithm with preprocessing using contrast limited adaptive histogram equalization (CLAHE) and face alignment. The face database in this system can be updated via our custom-built standalone android app and automatic restarting of the training and recognition process with an updated database. Using our proposed algorithm, a real-time face recognition accuracy of 78.40% at 15 px and 98.05% at 45 px have been achieved using the LRD200 database containing 200 images per person. With 100 images per person in the database (LRD100) the achieved accuracies are 60.60% at 15 px and 95% at 45 px respectively. A facial deflection of about 30° on either side from the front face showed an average face recognition precision of 72.25%-81.85%. This face recognition system can be employed for law enforcement purposes, where the surveillance camera captures a low-resolution image because of the distance of a person from the camera. It can also be used as a surveillance system in airports, bus stations, etc., to reduce the risk of possible criminal threats.

Face Recognition on Partial and Holistic LBP Features

An algorithm for face description and recognition based on multi-resolution with multi-scale local binary pattern （multi-LBP） features is proposed. The facial image pyramid is constructed and each facial image is divided into various regions from which partial and holistic local binary patter （LBP） histograms are extracted. All LBP features of each image are concatenated to a single LBP eigenvector with different resolutions. The dimensionaUty of LBP features is then reduced by a local margin alignment （LMA） algorithm based on manifold, which can preserve the between-class variance. Support vector machine （SVM） is applied to classify facial images. Extensive experiments on ORL and CMU face databases clearly show the superiority of the proposed scheme over some existed algorithms, especially on the robustness of the method against different facial expressions and postures of the subjects.

Palmprint Recognition Based on Statistical Local Binary Orientation Code

A novel coding based method named as local binary orientation code （LBOCode） for palmprint recognition is proposed. The palmprint image is firstly convolved with a bank of Gabor filters, and then the orientation information is attained with a winner-take-all rule. Subsequently, the resulting orientation mapping array is operated by uniform local binary pattern. Accordingly, LBOCode image is achieved which contains palmprint orientation information in pixel level. Further we divide the LBOCode image into several equal-size and nonoverlapping regions, and extract the statistical code histogram from each region independently, which builds a global description of palmprint in regional level. In matching stage, the matching score between two palmprints is achieved by calculating the two spatial enhanced histograms＇ dissimilarity, which brings the benefit of computational simplicity. Experimental results demonstrate that the proposed method achieves more promising recognition performance compared with that of several state-of-the-art methods.

AN LBP-BASED MULTI-SCALE ILLUMINATION PREPROCESSING METHOD FOR FACE RECOGNITION

It is one of the major challenges for face recognition to minimize the disadvantage of il- lumination variations of face images in different scenarios. Local Binary Pattern (LBP) has been proved to be successful for face recognition. However, it is still very rare to take LBP as an illumination preprocessing approach. In this paper, we propose a new LBP-based multi-scale illumination pre- processing method. This method mainly includes three aspects: threshold adjustment, multi-scale addition and symmetry restoration/neighborhood replacement. Our experiment results show that the proposed method performs better than the existing LBP-based methods at the point of illumination preprocessing. Moreover, compared with some face image preprocessing methods, such as histogram equalization, Gamma transformation, Retinex, and simplified LBP operator, our method can effectively improve the robustness for face recognition against illumination variation, and achieve higher recog- nition rate.

Real-Time Face Detection and Recognition in Complex Background

This paper provides efficient and robust algorithms for real-time face detection and recognition in complex backgrounds. The algorithms are implemented using a series of signal processing methods including Ada Boost, cascade classifier, Local Binary Pattern (LBP), Haar-like feature, facial image pre-processing and Principal Component Analysis (PCA). The Ada Boost algorithm is implemented in a cascade classifier to train the face and eye detectors with robust detection accuracy. The LBP descriptor is utilized to extract facial features for fast face detection. The eye detection algorithm reduces the false face detection rate. The detected facial image is then processed to correct the orientation and increase the contrast, therefore, maintains high facial recognition accuracy. Finally, the PCA algorithm is used to recognize faces efficiently. Large databases with faces and non-faces images are used to train and validate face detection and facial recognition algorithms. The algorithms achieve an overall true-positive rate of 98.8% for face detection and 99.2% for correct facial recognition.

Face recognition by decision fusion of two-dimensional linear discriminant analysis and local binary pattern

To investigate the robustness of face recognition algorithms under the complicated variations of illumination, facial expression and posture, the advantages and disadvantages of seven typical algorithms on extracting global and local features are studied through the experiments respectively on the Olivetti Research Laboratory database and the other three databases （the three subsets of illumination, expression and posture that are constructed by selecting images from several existing face databases）. By taking the above experimental results into consideration, two schemes of face recognition which are based on the decision fusion of the twodimensional linear discriminant analysis （2DLDA） and local binary pattern （LBP） are proposed in this paper to heighten the recognition rates. In addition, partitioning a face nonuniformly for its LBP histograms is conducted to improve the performance. Our experimental results have shown the complementarities of the two kinds of features, the 2DLDA and LBP, and have verified the effectiveness of the proposed fusion algorithms.

基于局部Gabor变化直方图序列的人脸描述与识别

提出了一种在Gabor变换幅值域内提取局部变化模式空间直方图序列(histogramsequenceoflocalGaborbinarypatterns,简称HSLGBP)的人脸描述及其识别方法.鉴于Gabor特征对光照、表情等变化比较鲁棒,并已在人脸识别领域得到成功应用,首先对归一化的人脸图像进行多方向、多分辨率Gabor小波滤波,并提取其对应不同方向、不同尺度的多个Gabor幅值域图谱(Gabormagnitudemap,简称GMM),然后在每个GMM上采用局部二值模式(localbinarypattern,简称LBP)算子抽取局部邻域关系模式,最后由这些模式的区域直方图形成的序列来描述人脸.Gabor变换、LBP、空间区域直方图的采用使得该方法对光照变化、表情变化、误配准等具有良好的鲁棒性.而且,这种人脸建模方法不需要基于训练集合进行统计学习,因而不存在推广性问题.同时,进一步探讨了如何在分类器设计阶段与统计方法进行结合的问题,提出了统计Fisher加权的HSLGBP匹配方法.在通过FERET人脸库光照、表情和时间变化测试集上与已发表的实验结果进行对比,充分验证了该方法的有效性.

改进的HOG和Gabor,LBP性能比较

为了实现复杂环境下的人脸特征有效表达,提出一种改进的梯度方向直方图(HOG)人脸识别方法.首先以人脸图像网格作为采样窗口并在其上提取HOG特征;然后将所有网格HOG特征向量进行组合,实现整个人脸特征表达;最后采用最近邻分类器进行识别.另外,比较了该方法与Gabor小波和局部二值模式(LBP)2种著名的人脸局部特征表示方法的优劣.实验结果表明,在调优的HOG参数下,在具有光照和时间环境等复杂变化的FERET人脸库中,较少维数的HOG特征比LBP特征有更好的表现,而且HOG特征提取时间和特征向量维数比Gabor小波方法更具有优势.

基于Gabor滤波器和局部纹理特征提取的SAR目标识别算法

该文提出了一种基于Gabor滤波器和Three-Patch Local Binary Patterns(TPLBP)局部纹理特征提取的合成孔径雷达(Synthetic Aperture Rader,SAR)图像目标识别算法。首先,利用Gabor滤波器对SAR图像在不同方向上进行滤波,增强SAR图像中目标及其阴影的关键特征;然后,利用TPLBP算法对Gabor滤波之后的图像进行局部纹理特征提取,该算法克服了Local Binary Patterns(LBP)算法无法描述大范围领域纹理特征的缺陷,并且保持了LBP旋转不变的特性,减少了SAR图像目标方位变化对识别效果的影响;最后利用极限学习机(Extreme Learning Machine,ELM)分类器实现目标识别。该文通过MSTAR数据库中的3类SAR目标识别实验验证了该算法的有效性。

基于Gabor系数分块统计和自适应特征选择的人脸描述与识别

提出一种新的人脸描述及识别方法,首先对归一化后的人脸图像进行多方向多尺度Gabor变换;然后对人脸区域进行分块,以块为单位统计Gabor系数的均值和方差,求得块特征矢量(block feature vector,BFV),按先行后列的顺序将各块的BFV拼接,构成整幅人脸图像特征矢量(face feature vector,FFV).在分类器设计阶段,引入两两比对和投票机制,用多个两类分类器组合成多类分类器.在训练某个具体的两类分类器时,根据隶属训练样本计算FFV中每项的分辨力,以分辨力大小为依据选出最优特征子集(best subset feature vector,BSFV).基于Yale人脸数据集展开实验,与已发表的算法和结果进行对比,证明了该方法的有效性.

基于Gabor多通道加权优化与稀疏表征的人脸识别方法

稀疏表征理论在模式识别中的应用引起广泛的关注。在用稀疏表征方法研究人脸识别问题中,为了使得表征系数矢量具有更为显著的稀疏性,该文提出一种Gabor稀疏表征分类(Gabor Sparse Representation Classification,GSRC)算法,该算法利用Gabor局部特征构造字典,增强算法对外界环境变化的鲁棒性。GSRC算法对所有的Gabor特征等同对待,通过进一步考虑不同Gabor特征对识别的不同贡献,该文提出了一种加权多通道Gabor稀疏表征分类(WMC-GSRC)算法,该算法通过引入Gabor多通道模型,提取不同通道的Gabor特征分别构造字典和稀疏表征分类器,在决策级执行分类器的加权融合得到识别结果。通过在ORL,AR和FERET人脸库上的实验结果验证了该文算法的有效性。

面向语音情感识别的Gabor分块局部二值模式特征

谱特征在语音情感识别中起到了重要的作用,然而现有的谱特征仍未能充分表达谱图中的语音情感信息。为研究语音情感与谱图之间的联系,提出了一种面向语音情感识别的Gabor分块局部二值模式特征（GBLBP）。首先,获取情感语音的对数能量谱;然后,采用多尺度,多方向的Gabor小波对对数能量谱进行处理,得到Gabor谱图;再次,对每张Gabor谱图进行分块,采用局部二值模式提取每个块的局部能量分布信息;最后,将提取到的所有特征级联,得到GBLBP特征。EMO-DB库及中文语音库上的实验结果表明：GBLBP特征的平均加权召回率比MFCC高了9%~10%,识别性能显著优于众多谱特征,且与现有声学特征有较好的融合性。

基于Gabor特征融合与LBP直方图的人脸表情特征提取方法

针对Gabor特征全局表征能力弱以及特征数据维数存在冗余的问题,提出了一种采用Gabor多方向特征融合与分块直方图相结合的方法以有效提取表情特征.通过对不同表情的重要特征部位进行细化,采用Gabor滤波器有针对性地提取相关区域的多尺度和多方向特征,并对同尺度的特征进行融合,利用各区域内融合特征的直方图分布来表征图像.该方法可以提高特征提取的准确性,有效突出重要特征的辨识作用,大幅度降低特征的维数,在JAFFE表情库可以达到100%的识别率.

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。

采用聚合Gabor核和局部二元模式的烟雾识别方法

针对图像烟雾识别存在高误报率和高错误率的问题,提出一种新的结合聚合Gabor核和局部二值模式(LBP)的烟雾识别方法.首先使用加权平均法生成聚合Gabor核,以减少Gabor核的数目,并将聚合Gabor核和原图像进行卷积,生成聚合Gabor特征图.为了增强分类性能,本文提出了一个自定义比较函数,用于原图像和Gabor特征图的局部二值编码.然后生成3种LBP映射模式的特征,并串联这3种特征得到LBP串联模式特征.最后串联所有的LBP串联模式特征作为原图像的局部聚合Gabor二值模式(LAGBP)特征.与传统方法的比较实验显示,在3个测试集上,本文方法都分别要优于传统方法,且具有最低的错误率;与深度学习方法的比较实验中,本文方法也有很好的表现.实验表明LAGBP方法具有很好的烟雾特征表达能力,非常适用于烟雾识别.

基于多通道Gabor滤波与CS-LBP的人脸识别方法

近来,局部二值模式(Local Binary Pattern,LBP)在人脸识别中取得了成功应用。然而,LBP提取的特征维数通常很高。而中心对称局部二值模式(Center-Symmetric Local Binary Pattern,CS-LBP)采用中心对称思想对图像进行编码,能够显著降低提取的特征的维数。为此,将CS-LBP应用于人脸图像特征提取,并结合多通道Gabor滤波,提出了基于多通道Gabor滤波与CS-LBP的人脸识别算法。在Yale,ORL,FETER标准人脸库上的实验结果表明,相比局部二值模式,CS-LBP以提取更少的特征维数取得了相当的识别率,并且,基于多通道Gabor滤波的CS-LBP能显著提高识别精度。

基于能量的自适应局部Gabor特征提取的人脸识别

为了解决传统Gabor滤波器组在人脸识别过程中特征提取时间长、计算量大的问题,从不同方向、不同尺度以及全局角度按照能量大小构建了3种不同的局部Gabor滤波器组用来提取人脸特征。首先,分析数据库中部分图像Gabor变换后的图像能量,从不同角度选出能量较大的图像构建对应的局部Gabor滤波器组;其次,根据所选滤波器组提取局部Gabor特征;然后,采用线性判别分析(LDA)法进一步提取Fisher特征;最后,利用最近邻法识别人脸图像。基于ORL人脸库和YALE人脸库的实验结果表明提出的人脸识别方法降低了人脸图像的特征维数,缩短了特征提取的时间,有效地提高了人脸识别率。

基于Gabor小波和局部二值模式的步态识别

利用步态对个人身份进行识别已经受到越来越多生物识别技术研究者的重视。步态能量图(GEI-Gait Energy Image)是一种有效的步态表征方法,Gabor小波能提取不同方向、不同尺度空间频率特征,因此,首先利用Gabor小波提取步态能量图不同方向、不同尺度的信息,得到其幅值谱图,再利用LBP来提取Gabor幅值谱图的局部信息,相对于LBP直接作用于步态能量图,能提取步态能量图更多方向、更多尺度的局部特征。最后,利用具有良好降维和辨识能力的辨识共同向量(DCV-Discriminant Common Vector)对提取的LBP特征进行维数约减和特征选择,只需利用简单的最近邻分类器就能取得较好的识别效果。该算法在中科院自动化所的CASIA数据库上面进行试验取得了较高的正确识别率。还针对步态识别中的小样本问题提出了一种样本扩充方法,解决了步态识别中的小样本问题,并提高了算法的识别率。

基于二维多尺度局部Gabor二进制模式特征的表情识别

为了在独立于个体身份的面部表情识别中取得更加理想的效果,提出了一种基于二维多尺度局部Gabor二进制模式(MB-LGBP)特征的识别方法。对于表情识别而言,MB-LGBP已被证明了是一种局部和整体上都具有很强表征能力的描绘子。将MB-LGBP与灰度共现矩阵(GLCM)结合起来得到了可以更好地描述局部纹理空间结构特性的二维MB-LGBP特征。在识别中,分别选择了支持向量机(SVM)和基于卡方距离的K-最近邻(KNN)分类器,并对结果进行了比较。实验结果证明了二维MB-LGBP特征相比于MB-LGBP以及其他一些主要的表情识别特征的优越性。

基于局部二元模式Gabor小波变换的人脸识别

将局部二元模式(LBP)与Gabor小波变换相结合,用LBP算子对Gabor特征幅值的邻域变化进行编码,并用直方图分析LBP编码后的局部变化属性,这样避免了因下采样造成的信息损失,同时又通过直方图统计达到了降维的目的。实验结果表明,该方法结合了LBP与Gabor变换的优点,增强了直方图的鉴别能力,又能有效降低维数,取得了较理想的识别效果。