Improve the two-phase test samples representation method for palmprint recognition

Palmprint recognition, as a very important personal identification technology, is taking more and more attention. A recently proposed method – two-phase test samples representation method (TPTSR) has attracted much attention and performed very well in biometrics. The TPTSR not only is a competent representation-based classification method, but also is computationally much more efficient than the original sparse representation methods. However, though the TPTSR seems to be suitable for palmprint recognition, it has not been widely tested and it is not known how to properly set the parameter (the number of the nearest neighbors), which is definitely crucial for real-world applications. This paper will analyze the performance of the method in the palmprint identification for the first time and explore the proper value of the parameter of the method. In order to address the above issues, lots of experiments on the palmprint recognition are conducted. This paper also shows experimental comparisons between TPTSR and several other methods. This paper provides significant instructions apply TPTSR to palmprint recognition.     

A palmprint recognition method based on multi-step representation

Sparse representation uses all training samples to represent a test sample only once, which can be regarded as a one step representation. However, in palmprint recognition, the appearances of palms are highly correlated which means the information provided by all the training samples are redundant while using the representation-based methods. Hence, how to obtain suitable samples for representation deserves exploring. In this paper, we devise a multi-step representation manner to extract the most representative samples for representation and recognition. In addition, the proposed sample selection strategy is based on contributions of the classes, not merely the effort of a single sample. Compared with some other appearance-based methods, the proposed method obtained a competitive result on PolyU multispectral palmprint database.     

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.     

Kernel representation-based nearest neighbor classifier

An improvement to the nearest neighbor classifier (INNC) has shown its excellent classification performance on some classification tasks. However, it is not very clearly known why INNC is able to obtain good performance and what the underlying classification mechanism is. Moreover, INNC cannot classify low-dimensional data well and some high-dimensional data in which sample vectors belonging to different class distribution but have the same vector direction. In order to solve these problems, this paper proposes a novel classification method, named kernel representation-based nearest neighbor classifier (KRNNC), which can not only remedy the drawback of INNC on low-dimensional data, but also obtain competitive classification results on high-dimensional data. We reveal the underlying classification mechanism of KRNNC in details, which can also be regarded as a theoretical supplement of INNC. We first implicitly map all samples into a kernel feature space by using a nonlinear mapping associated with a kernel function. Then, we represent a test sample as a linear combination of all training samples and use the representation ability to perform classification. From the way of classifying test samples, KRNNC can be regarded as the nonlinear extension of INNC. Extensive experimental studies on benchmark datasets and face image databases show the effectiveness of KRNNC.     

A novel virtual samples-based sparse representation method for face recognition

A limited training set usually limits the performance of face recognition in practice. Even sparse representation-based methods which outperform in face recognition cannot avoid such situation. In order to effectively improve recognition accuracy of sparse representation-based methods on a limited training set, a novel virtual samples-based sparse representation (VSSR) method for face recognition is proposed in this paper. In the proposed method, virtual training samples are constructed to enrich the size and diversity of a training set and a sparse representation-based method is used to classify test samples. Extensive experiments on different face databases confirm that VSSR is robust to illumination variations and works better than many representative representation-based face recognition methods.     

Sparse representation-based classification algorithm for optical Tibetan character recognition

A sparse representation-based two-phase classification algorithm is proposed for off-line handwritten Tibetan character recognition. The first phase realizes coarse classification with the K-NN classifier by finding the K nearest neighbours of a test sample in the dictionary constructed by K-SVD with samples of all classes, and the classes of these neighbours are regarded as the candidate classes of the test sample. The second phase performs fine classification with the sparse representation classifier by sparsely representing the test sample with all elements of the dictionary constructed by K-SVD with samples of all candidate classes, and the test sample is finally classified into the candidate class with the maximal contribution in sparse representation. Experiments on the Tibetan off-line handwritten character database show that an optimal recognition rate of 97.17% has been reached and it is 2.12% higher than that of K-NN.     

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.     

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。     

Face image recognition via collaborative representation on selected training samples

In this paper, we present a collaborative representation-based classification on selected training samples (CRC_STS) for face image recognition. The CRC_STS uses a two stage scheme: The first stage is to select some most significant training samples from the original training set by using a multiple round of refining process. The second stage is to use collaborative representation classifier to perform classification on the selected training samples. Our method can be regarded as a sparse representation approach but without imposing l₁-norm constraint on representation coefficients. The experimental results on three well known face databases show that our method works very well.     

A novel method for recognizing face with partial occlusion via sparse representation

In this paper, we propose a novel method to recognize the partially occluded face images based on sparse representation. Generally, occlusions, such as glasses and scarf, fall on some random patch of image's pixels of test images, but which is known to be connected. In our method, all images are divided into several blocks and then an indicator based on linear regression technique is presented to determine whether a block is occluded. We utilize those uncontaminated blocks as the new feature of an image. Finally, the sparse representation-based classification (SRC) method serves as the classifier to recognize unknown faces. In the original work of SRC, the extended SRC (eSRC) scheme is presented to deal with occlusions, which has very heavy computational cost. The experimental results show that our method can achieve good recognition accuracy and has much lower computational cost than eSRC.     

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.     

Fingerprint image enhancement using multi-scale DDFB based diffusion filters and modified Hong filters

The main task of a fingerprint image enhancement is to enhance the image in such a way that it not only remove the noise but also enhance the reliable minutiae points. For this purpose, in this paper we propose a multi-scale decimation-free directional filter bank method for reliable orientation estimation. This reliable orientation is used in coherence enhancement diffusion and in Gabor filter based enhancement, which overcomes the drawbacks of these two methods. Experimental results show that the proposed method not only enhances the images but also facilitates the minutiae algorithm, by enhancing the true minutiae points.     

A face recognition algorithm based on collaborative representation

In this paper, we propose a face recognition algorithm by incorporating a neighbor matrix into the objective function of sparse coding. We first calculate the neighbor matrix between the test sample and each training sample by using the revised reconstruction error of each class. Specifically, the revised reconstruction error (RRE) of each class is the division of the l₂-norm of reconstruction error to the l₂-norm of reconstruction coefficients, which can be used to increase the discrimination information for classification. Then we use the neighbor matrix and all the training samples to linearly represent the test sample. Thus, our algorithm can preserve locality and similarity information of sparse coding. The experimental results show that our algorithm achieves better performance than four previous algorithms on three face databases.     

A novel chaotic stream cipher and its application to palmprint template protection

Based on a coupled nonlinear dynamic filter (NDF), a novel chaotic stream cipher is presented in this paper and employed to protect palmprint templates. The chaotic pseudorandom bit generator (PRBG) based on a coupled NDF, which is constructed in an inverse flow, can generate multiple bits at one iteration and satisfy the security requirement of cipher design. Then, the stream cipher is employed to generate cancelable competitive code palmprint biometrics for template protection. The proposed cancelable palmprint authentication system depends on two factors: the palmprint biometric and the password/token. Therefore, the system provides high-confidence and also protects the user's privacy. The experimental results of verification on the Hong Kong PolyU Palmprint Database show that the proposed approach has a large template re-issuance ability and the equal error rate can achieve 0.02%. The performance of the palmprint template protection scheme proves the good practicability and security of the proposed stream cipher.     

基于可见-近红外光谱与稀疏表示的注水肉识别

为了能快速准确的识别原料肉与注水肉,提出了一种基于可见-近红外光谱和稀疏表示的无损的识别方法。通过向猪肉样本(包括猪皮、脂肪层和肌肉层)注水的方法建立注水肉模型,采集未注水的原料肉和6类不同注水量的注水肉的可见和近红外漫反射光谱数据。为了消除光谱数据中的冗余信息并提高分类效果,对光谱数据进行光调制和归一化等预处理并截取有效波段,根据是否注水以及注水量的多少对样本进行分类。用所有训练样本构成原子库(字典),通过ｌ1最小化将测试样本表示为这些原子的最稀疏的线性组合。计算测试样本与各类的投影误差,将最小投影误差对应的类作为测试样本的所属类别,并应用留一法进行交叉检验,比较了稀疏表示法与支持向量机的识别结果。实验结果表明,利用稀疏表示法对于原料肉与注水肉的识别准确率可达到90%以上,获得了较好的分类效果,优于支持向量机的识别结果。而对于不同注水量的注水肉识别准确率与注水量之差正相关。稀疏方法不需要进行传统模式识别模型的前期学习与特征提取,适用于高维、小样本量数据的处理,计算成本低,将其用于注水肉的光谱数据识别具有一定的创新性,并取得了较满意的结果,为原料肉和注水肉的无损识别提供了一种有效方法。     

Complexity reduced coding of binary pattern units in image classification

The ability to simulate and control complex physical situations in real time is an important element of many engineering and robotics applications, including pattern recognition and image classification. One of the ways to meet specific requirements of a process is a reduction of computational complexity of algorithms. In this work we propose a new coding of binary pattern units (BPU) that reduces the time and spatial complexity of algorithms of image classification significantly. We apply this coding to a particular but important case of the coordinated clusters representation (CCR) of images. This algorithm reduces the dimension of the CCR feature space and, as a consequence, the time and space complexity of the CCR based methods of image classification, exponentially. In addition, the new coding preserves all the fundamental properties of the CCR that are successfully used in the recognition, classification and segmentation of texture images. The same approach to the coding of BPUs can be used in the Local Binary Pattern (LBP) method. In order to evaluate the reduction of time and space complexity, we did an experiment on multiclass classification of images using the “traditional” and the new coding of the CCR. This test showed very effective reduction of the computing time and required computer memory with the use of the new coding of BPUs of the CCR, retaining 100% or a little less efficiency of classification at the time.     

Modular Fisher Discriminant Sparse Representation for robust face recognition

This paper proposes a novel framework for robust face recognition based on sparse representation and discrimination ranking. This method consists of three stages. The first stage partitions each training sample into some overlapped modules and then computes each module's Fisher ratio, respectively. The second stage selects modules which have higher Fisher ratios to comprise a template to filter training and test images. The dictionary is constructed by the filtered training images. The third stage computes the sparse representation of filtered test sample on the dictionary to perform identification. The advantages of the proposed method are listed as follows: the first stage can preserve the local structure. The second stage removes the modules that have little contribution for classification. Then the method uses the retaining modules to classify the test sample by SRC which makes the method robust. Compared with the related methods, experimental results on benchmark face databases verify the advancement of the proposed method. The proposed method not only has a high accuracy but also can be clearly interpreted.     

Ising Model for Interpolation of Spatial Data on Regular Grids

We apply the Ising model with nearest-neighbor correlations (INNC) in the problem of interpolation of spatially correlated data on regular grids. The correlations are captured by short-range interactions between “Ising spins”. The INNC algorithm can be used with label data (classification) as well as discrete and continuous real-valued data (regression). In the regression problem, INNC approximates continuous variables by means of a user-specified number of classes. INNC predicts the class identity at unmeasured points by using the Monte Carlo simulation conditioned on the observed data (partial sample). The algorithm locally respects the sample values and globally aims to minimize the deviation between an energy measure of the partial sample and that of the entire grid. INNC is non-parametric and, thus, is suitable for non-Gaussian data. The method is found to be very competitive with respect to interpolation accuracy and computational efficiency compared to some standard methods. Thus, this method provides a useful tool for filling gaps in gridded data such as satellite images.