基于非负矩阵分解和广义判别分析的掌纹识别

非负矩阵分解(NMF)具有非负性和局部性的特点,是一种新型的特征提取方法.由于NMF是非监督学习算法,运用NMF提取掌纹特征时没有考虑训练样本的类别信息,因而分类效果不够理想.为了在提取掌纹特征的同时融人类别信息,提出运用非负矩阵分解和广义判别分析(GDA)相结合的方法进行掌纹识别.为了降低计算的复杂性,在特征提取之前,应用小波变换对掌纹图像进行三级分解,提取低频子图像.在低频子图像上应用NMF+GDA提取掌纹特征,计算特征向量间的余弦距离进行掌纹匹配.运用PolyU掌纹图像库进行测试.结果表明,与主元分析(PCA)、独立元分析(ICA)和NMF相比,算法的等误率(EER)最低为0.16%,特征提取和匹配总时间为0.812 s,满足实时系统的要求.     

融合全局与局部多样性特征的人脸表情识别

通常主成分分析(PCA)只能保持数据的全局结构,邻域保持嵌入(NPE)算法只能保持邻域样本间的相似性,忽略了其差异性。针对上述问题,提出了一种融合全局与局部多样性的特征提取算法,并将其应用于人脸表情识别中。该算法利用PCA算法保持全局结构,并通过流形学习思想定义局部差异离散度和局部相似离散度,结合最大局部散度差准则,有效刻画出局部流形结构的多样性;将全局特征和局部多样性特征相结合,提取出低维流形特征用于表情分类。在JAFFE和Cohn-Kanade人脸表情数据库上的实验表明,该算法与PCA、局部保持投影(LPP)、NPE等算法相比,不仅有效地提高了识别率,而且在取得最高识别率时所需维数最低,证明了此算法在识别效果方面的优越性。     

小波重构与局部DCT的二维主元分析掌纹识别

为了解决掌纹特征提取过程中,手掌的非平面问题导致的伪主线噪音信息并简化运算,对重构的掌纹图像进行了局部离散余弦变换.解决了重构后图像噪音敏感性问题,有效地区分了掌纹主线、掌纹褶纹和乳突纹.由二维主元分析算法获得较稳健的识别特征.通过香港理工大学公布的PolyU掌纹数据库的实验,同二维主元分析算法相比,小波重构与局部离散余弦变换的2DPCA掌纹识别算法正确识别率较高,识别效率较高.     

基于LGSPP-Bayes的故障检测与辨识方法

针对主元分析(Principal component analysis, PCA)和局部保持投影(Locality preserving projections, LPP)方法在降维过程中分别只能保留数据集的整体信息和局部信息,提出一种基于局部整体结构保持投影的贝叶斯故障检测与辨识方法(Local and global structure preserving projections and bayes, LGSPP-Bayes)。首先,将正常工况操作下的原始数据通过局部整体结构保持投影方法投影到低维特征空间,得到高维到低维的数据转换矩阵;然后通过设计贝叶斯分类器来进行故障检测;最后当检测到故障后通过计算贝叶斯分类函数的大小来识别故障种类。将LGSPP-Bayes方法应用于TE过程,仿真结果表明对故障的检测优于其他方法,并且可以很好地将故障种类识别出来。     

核映射和Rank-Order距离的局部保持投影相似性度量方法

针对近红外光谱高维、高冗余、非线性和小样本等特点导致光谱相似性度量时出现的“维度灾难”,提出一种基于核映射和rank-order距离的局部保持投影（KRLPP）算法。首先将光谱数据经过核变换映射到更高维空间,有效保证了流形结构的非线性特征。然后改进局部保持投影(LPP)算法对数据进行降维操作,将rank-order距离替代传统的欧氏距离或测地线距离,通过共享邻近点的信息,得到更加准确的局部邻域关系。最后在低维空间通过距离的计算实现光谱的度量。该方法不仅有效解决了高维空间存在的“距离失效”问题,同时还提高了相似性度量结果的精度。为了验证KRLPP算法的有效性,首先根据降维前后数据集信息残差的变化确定了最佳参数近邻点的个数k和降维后的维数d。其次,从光谱降维投影效果和模型分类效果两个角度与PCA,LPP和INLPP算法进行了对比,结果表明KRLPP算法对于烟叶的部位有较好的区分能力,降维效果以及对于不同部位的正确识别率明显优于PCA,LPP和INLPP。最后,从某品牌卷烟叶组配方中选取了5个代表性烟叶作为目标烟叶,分别采用PCA,LPP和KRLPP方法从300个用于配方维护的烟叶样品中为每个目标烟叶寻找相似烟叶,并从化学成分和感官评价两方面对替换前后的烟叶及叶组配方进行了评价分析。其中LPP和KRLPP用于降维的参数选择保持一致,PCA选择前6个主成分。结果表明,由KRLPP选出的替换烟叶与替换配方在总糖、还原糖、总烟碱、总氮等化学成分以及香气、烟气、口感等感官指标上较PCA、LPP方法差异最小,相似性度量准确度最高。该方法可应用于配方产品替换原料的查找,辅助企业实现产品质量的维护。     

改进的基于二维主分量分析的掌纹识别

主分量分析(PCA)是一种在众多生物特征识别中获得成功应用的特征提取技术,是一种基于二阶统计的在最小均方误差意义上的最优维数据压缩技术,它所提取的各特征分量之间是互不相关的。传统的PCA变换是对图像向量的分析,但向量维数一般都很高。二维主分量分析方法是最近兴起的针对图像矩阵的主分量分析方法,与一维主分量分析相比能更精确的计算原始数据的协方差矩阵。将其应用于掌纹识别,并在主分量的选取上加以改进,选取了更适合于分类的主分量。实验结果表明,该方法不仅有更高的识别率,而且维数更低。     

主成分分析重建误差掌纹识别方法

主成分分析(PCA)法在掌纹识别方面可以取得较好的效果.但是随着掌纹图像库的扩大,PCA转换矩阵训练时间迅速增长;注册新掌纹时,需要重新训练PCA转换矩阵.添加注册掌纹的代价随着掌纹库的增大迅速增加.如何能够在保持PCA识别效果的情况下提高使用的便捷性成为PCA广泛应用的主要障碍.提出了一种以PCA重建误差为分类依据的PCA重建误差学纹识别方法.该方法与PCA法基于相同的原理,在采用最近邻分类器时可以取得与PCA法相等的性能;同时可以有效减少掌纹图像库的识别时间,可以以极少的代价扩展掌纹库.     

基于多光谱图像融合的掌纹识别方法

生物特征识别在信息安全领域发挥着重要作用,掌纹识别作为一种新型生物特征识别方式,具有低失真、非侵入性和高唯一性等优势。传统掌纹研究大多使用自然光成像系统以灰度格式获取,识别精度很难进一步提升。为了获得更多的身份鉴别信息,提出利用多光谱掌纹图像代替自然光掌纹图像。针对现有掌纹识别算法由于没有考虑到不同光谱的特性而导致纹理细节丢失,识别精准率低的问题,提出了一种基于多光谱图像融合的掌纹识别算法。该方法通过对不同光谱下的掌纹图像进行快速自适应二维经验模式分解（FABEMD）,将多光谱掌纹图像分解成一系列频率由高到低的二维固有模态函数(BIMF)和一个残余分量,残余分量可被视为该光谱图像低频信息的初步估计。图像采集过程中光照条件很难保持稳定,而近红外光谱图像在进行FABEMD分解时对光照变换敏感,容易导致分解后的BIMF背景信息过于冗余;因此对分解后的近红外掌纹图像进行背景重建及特征细化,在对背景冗余信息进行平滑处理的同时可以有效增强高频信息的特征表达。为避免直接融合处理后引发的图像过度曝光问题,提出对近红外特征压缩后再融合。此外,提出了一种结合了注意力机制的改进残差网络（IRCANet）,用于融合后的掌纹图像分类,在网络中引入分阶段残差结构,缓解了网络的退化问题,在学习过程中有效地减少信息丢失,对于融合后的多光谱掌纹图像,分阶段残差结构能够稳定地将图像信息在网络间传输,但对图像中的高低频信息区分效果不够显著,为了使网络关注更多区分性特征,利用特征通道间的相互依赖性,在分阶段残差结构中结合了通道注意力(Channel Attention)机制。最终,在香港理工大学（PolyU）多光谱掌纹数据集上进行的综合实验表明,该方法可以取得良好的效果,算法识别准确率能达到99.67%且具有良好的实时性。     

一种多分辨率高维图像特征匹配算法

通过对图像进行特征提取和变换,图像的相似性匹配可以转换为高维向量空间内的点匹配. 为了解决高维数据的维数灾难问题,提出一种基于多分辨率数据结构的向量近似方法. 从低分辨率开始计算距离下限,如果距离下限大于目前结果集中的最大距离,则不需要在高分辨率上计算其距离而将其排除掉,从而降低了向量近似方法的运算复杂度. 提出应用此方法的近邻搜索算法并运用到图像数据库的特征匹配中,实验证明：新方法搜索效率优于传统的向量近似方法.     

基于图像特征提取的脱机手写数字识别方法

脱机手写数字识别其本质是数字的图像特征匹配问题,所以需要进行手写数字的特征提取,为了准确识别,往往使用较高的特征维数,这就导致识别效率较低。为了提高识别效率,同时为了保持较高的识别率,提出了一种基于图像特征提取的脱机手写数字识别方法。首先利用主分量分析法抽取数字字符图像的统计特征,来降低数字的特征维数,通过对主分量重建模型的误差分析进行数字识别;然后,结合手写数字的笔画结构不稳定的特点,设计并提取数字的宽高比结构特征,进一步比对识别;最后,利用自制训练样本及测试样本库进行仿真实验,数字识别率为96%,识别准确率较高。     

Quaternion-based improved LPP method for color face recognition

In recent years, pattern recognition and computer vision have increasingly become the focus of research. Locality preserving projection (LPP) is a very important learning method in these two fields and has been widely used. Using LPP to perform face recognition, we usually can get a high accuracy. However, the face recognition application of LPP suffers from a number of problems and the small sample size is the most famous one. Moreover, though the face image is usually a color image, LPP cannot sufficiently exploit the color and we should first convert the color image into the gray image and then apply LPP to it. Transforming the color image into the gray image will cause a serious loss of image information. In this paper, we first use the quaternion to represent the color pixel. As a result, an original training or test sample can be denoted as a quaternion vector. Then we apply LPP to the quaternion vectors to perform feature extraction for the original training and test samples. The devised quaternion-based improved LPP method is presented in detail. Experimental results show that our method can get a higher classification accuracy than other methods.     

Palmprint recognition based on the representation in the feature space

In this paper, we propose a palmprint recognition method based on the representation in the feature space. The proposed method seeks to represent the test sample as a linear combination of all the training samples in the feature space and then exploits the obtained linear combination to perform palmprint recognition. We can implement the mapping from the original space to the feature space by using the kernel functions such as radial basis function (RBF). In this method, the selection of the parameter of the kernel function is important. We propose an automatic algorithm for selecting the parameter. The basic idea of the algorithm is to optimize the feature space such that the samples from the same class are well clustered while the samples from different classes are pushed far away. The proposed criterion measures the goodness of a feature space, and the optimal kernel parameter is obtained by minimizing this criterion. Experimental results on multispectral palmprint database show that the proposed method is more effective than 2DPCA, 2DLDA, AANNC, CRC_RLS, nearest neighbor method (NN) and competitive coding method in terms of the correct recognition rate.     

Palmprint recognition method based on score level fusion

Different palmprint recognition methods have different advantages. The texture- and feature-based palmprint recognition methods can well exploit the minutiae of the palmprint but are not very robust to the possible variation such as the rotation and shift of the palm. The representation-based palmprint recognition method can well take advantage of the holistic information but seems not to be able to fully exploit the minutiae of the palmprint. In this paper, we propose to fuse the competitive coding method and two-phase test sample sparse representation (TPTSR) method for palmprint recognition. As one of representation-based methods, TPTSR method takes the whole palmprint image as the input and determines the contribution of the training samples of each class in representing the test sample. TPTSR also uses the contribution to calculate the similarities between the test sample and every class. The competitive coding method is a feature-based method and is highly complementary with TPTSR. We use a weighted fusion scheme to combine the matching scores generated from TPTSR and the competitive coding method. The experimental results show that the proposed method can obtain a very high classification accuracy and outperforms both TPTSR and the competitive coding method.     

Multi-radius centralized binary pattern histogram projection for face recognition

The existing local binary pattern (LBP) operators have several disadvantages such as rather long histograms,lower discrimination,and sensitivity to noise.Aiming at these problems,we propose the centralized binary pattern (CBP) operator.CBP operator can significantly rcduce the histograms' dimensionality,offer stronger discrimination,and decrease the white noise's influence on face images.Moreover,for increasing the recognition accuracy and speed,we use multi-radius CBP histogram as face representation and project it onto locality preserving projection (LPP) space to obtain lower dimensional features.Experiments on FERET and CAS-PEAL databases demonstrate that the proposed method is superior to other modern approaches not only in recognition accuracy but also in recognition speed.     

Feature fusion of palmprint and face via tensor analysis and curvelet transform

In order to improve the recognition accuracy of the unimodal biometric system and to address the problem of the small samples recognition, a multimodal biometric recognition approach based on feature fusion level and curve tensor is proposed in this paper. The curve tensor approach is an extension of the tensor analysis method based on curvelet coefficients space. We use two kinds of biometrics: palmprint recognition and face recognition. All image features are extracted by using the curve tensor algorithm and then the normalized features are combined at the feature fusion level by using several fusion strategies. The k-nearest neighbour (KNN) classifier is used to determine the final biometric classification. The experimental results demonstrate that the proposed approach outperforms the unimodal solution and the proposed nearly Gaussian fusion (NGF) strategy has a better performance than other fusion rules.