On accurate orientation extraction and appropriate distance measure for low-resolution palmprint recognition

Orientation feature has been demonstrated to be one of the most effective features for low resolution palmprint recognition. In this paper, using steerable filter, we investigate the accurate orientation extraction and appropriate distance measure problems for effective palmprint recognition. First, we use high order steerable filter to extract accurate continuous orientation, and quantify it into discrete representation. Then, for effective matching of accurate orientations, we propose a generalized orientation distance measure. We further extend the distance measure for matching of discrete orientations, and show that several existing distance measures can be viewed as its special cases. Experimental results on both Hong Kong PolyU and CASIA palmprint databases show that the proposed method can obtain state-of-the-art verification accuracy. With the support of a look up table, the proposed method also enables small template size and satisfactory matching speed for practical applications.     

A survey of palmprint recognition

Palmprint recognition has been investigated over 10 years. During this period, many different problems related to palmprint recognition have been addressed. This paper provides an overview of current palmprint research, describing in particular capture devices, preprocessing, verification algorithms, palmprint-related fusion, algorithms especially designed for real-time palmprint identification in large databases and measures for protecting palmprint systems and users’ privacy. Finally, some suggestion is offered.     

A face and palmprint recognition approach based on discriminant DCT feature extraction

In the field of image processing and recognition, discrete cosine transform (DCT) and linear discrimination are two widely used techniques. Based on them, we present a new face and palmprint recognition approach in this paper. It first uses a two-dimensional separability judgment to select the DCT frequency bands with favorable linear separability. Then from the selected bands, it extracts the linear discriminative features by an improved Fisherface method and performs the classification by the nearest neighbor classifier. We detailedly analyze theoretical advantages of our approach in feature extraction. The experiments on face databases and palmprint database demonstrate that compared to the state-of-the-art linear discrimination methods, our approach obtains better classification performance. It can significantly improve the recognition rates for face and palmprint data and effectively reduce the dimension of feature space.     

Double-cohesion learning based multiview and discriminant palmprint recognition

Palmprint recognition has been widely used in security authentication. However, most of the existing palmprint representation methods are focused on a special application scenario using the hand-crafted features from a single-view. If the features become weak as the application scenario changes, the recognition performance will be degraded. To address this problem, we propose to comprehensively exploit palmprint features from multiple views to improve the recognition performance in generic scenarios. In this paper, a novel double-cohesion learning based multiview and discriminant palmprint recognition (DC_MDPR) method is proposed, which imposes a double-cohesion strategy to reduce the inter-view margins for each subject and the intra-class margins for each view. In this way, for each subject, the features from different views can be closer to each other in the binary-label space. Meanwhile, for each view, the features sharing the same label information can move towards each other by imposing a neighbor graph regularization. The proposed method can be flexibly applied to any type of palmprint feature fusion. Moreover, it presents the multiview features in a low-dimensionality sub-space, effectively reducing the computational complexity. Experimental results on various palmprint databases have shown that the proposed method can always achieve the best recognition performance compared to other state-of-the-art algorithms.     

基于曲面曲率和RLDA的3D掌纹识别方法

提出一种新的3D掌纹识别方法,利用掌纹曲面的3D曲率信息提高当前2D掌纹识别算法的精确度和鲁棒性。首先因曲率是3维物体的重要表征,能够与视点无关地表现曲面的局部形状,不管手掌发生旋转或者平移,曲率信息都是稳定的,因此提取3D掌纹的均值曲面曲率特征来刻画3D掌纹的曲面特征;继而获得3D掌纹映射到2D空间上的灰度图像——均值曲率图像(MCI);然后在获得的MCI上采用正则化的LDA(RLDA)方法来进行二次特征抽取,以消除传统线性判别分析(LDA)应用于识别时存在的小样本问题和优化准则函数并不直接与识别率相关等问题。实验结果表明,所提出的方法相比与传统的LDA、PCA、ICA、LPP等方法有更高的精度和速度。     

A coding-guided holistic-based palmprint recognition approach

In the past few years, the need for accuracy and robustness against luminosity variations has drawn a considerable share of the palmprint research toward coding-based approaches. However, on the downside coding-based approaches require a high computational cost. On the contrary, while holistic-based palmprint recognition methods are easy to implement and have low computational burden, they usually do not result in a highly desirable accuracy. As a result, more recently hybridization of the holistic-based and coding-based methods has gained a boost. These hybridization schemes take advantages of both holistic and coding information to achieve a better performance. However, their computational burden due to incorporating the coding approach is still much heavier than the holistic methods. In this paper, we propose a new hybridization scheme based on Anisotropic Filter (AF) coding and the two-phase test sample representation (TPTSR) for the palmprint identification. In our scheme, the coding-based method is only applied on a super narrowed gallery in order to measure the classification confidence for a given test sample. Then, we apply our Guided Holistic (GH)-based method for classifying the test sample if the holistic-based algorithm is not sufficiently confident. Experimental results demonstrate the efficiency of our method in enhancing both the complexity cost and the accuracy of the results.     

基于Stein-Weiss函数的彩色掌纹特征识别算法

针对目前掌纹识别算法中对彩色掌纹图像的识别研究不多,提出一种新的基于Stein-Weiss函数解析性质的BP神经网络彩色掌纹图像的识别算法。首先为彩色掌纹图像中的每个像素点构建一个Stein-Weiss函数,再根据Stein-Weiss函数的解析性,计算出相应像素的十六个特征值,将这些特征值输入到BP神经网络的输入层,通过BP神经网络的自学习能力对这些数据进行分类学习;然后通过BP神经网络的泛化能力来获取掌纹边缘线;最后对掌纹边缘线提取成对几何特征建立特征库,通过成对几何直方图相交算法进行掌纹识别。实验结果表明,相对于以往的灰度掌纹图像识别算法,该算法能够更快地提取出更精细的掌纹线,识别率更高,并且对于旋转和噪声的干扰具有较强的鲁棒性。     

基于子空间特征融合的两级掌纹识别算法

针对单一PCA或PCA只能提取掌纹的线性或非线性特征,单一分类器的掌纹识别率低缺陷,提出一种子空间特征融合的两级掌纹识别方法（PCA-KPCA-SVM）。首先采用子空间特征提取方法PCA、KPCA分别提取掌纹图像线性和非线性特征,然后基于融合特征总类间距离最大准则,计算出最佳的融合系数,得到PCA、KPCA的融合掌纹特征,最后将融合特征输入到欧式距离分类器进行掌纹识别,如果拒绝识别,则输入支持向量机进行二次识别。采用Polyu掌纹图像库进行测试实验,结果表明,相对于对比算法,PCA-KPCA-SVM提高了掌纹识别率,有效降低了掌纹的误识率和拒识率。     

A fast and accurate face detector based on neural networks

Detecting faces in images with complex backgrounds is a difficult task. Our approach, which obtains state of the art results, is based on a neural network model: the constrained generative model (CGM). Generative, since the goal of the learning process is to evaluate the probability that the model has generated the input data, and constrained since some counter-examples are used to increase the quality of the estimation performed by the model. To detect side view faces and to decrease the number of false alarms, a conditional mixture of networks is used. To decrease the computational time cost, a fast search algorithm is proposed. The level of performance reached, in terms of detection accuracy and processing time, allows us to apply this detector to a real world application: the indexing of images and videos     

An improved palmprint recognition system using iris features

This paper presents a bimodal biometric recognition system based on the extracted features of the human palmprint and iris using a new graph-based approach termed Fisher locality preserving projections (FLPP). This new technique employs two graphs with the first being used to characterize the within-class compactness and the second dedicated to the augmentation of the between-class separability. By applying the FLPP, only the most discriminant and stable palmprint and iris features are retained. FLPP was implemented on the frequency domain by transforming the extracted region of interest extraction of both biometric modalities using Fourier transform. Subsequently, the palmprint and iris features vectors obtained are matched with their counterpart in the templates databases and the obtained scores are fused to produce a final decision. The proposed combination of palmprint and iris patterns has shown an excellent performance compared to unimodal palmprint biometric recognition. The system was evaluated on a database of 108 subjects and the experimental results show that our system performs very well and achieves a high accuracy expressed by an equal error rate of 0.00%.     

基于顶帽变换的指节纹和掌纹识别改进算法

针对指节纹、掌纹不易提取,且易受光照和手掌颜色不均影响的问题,提出了基于顶帽变换的指节纹、掌纹识别改进算法。顶帽变换能消除光照不均的影响,很好地提取手掌主纹线。对采集的手掌图像进行灰度化和顶帽变换后,进行二值化处理,分离出手掌区域,找到手掌区域所在位置,用Sobel边缘检测器分离出手掌边界,确定指尖指谷坐标,再对手掌区域进行分割,找到指节纹和掌纹大体区域,用互相关法进行掌纹和指节纹匹配。实验结果表明:提出的方法能够消除光照不均和手掌颜色不均的影响,且速度快,抗噪能力强,适合大规模手掌库实现粗筛选。     

基于手形交互与掌纹识别的增强现实应用

针对现有增强现实系统交互方式的不足,提出并实现了一种基于手形交互与掌纹识别的增强现实应用.提出了一种用于快速识别手形轮廓及其运动轮廓的匹配方法.利用一种改进的快速蚁群聚类算法来获取掌形的中心,建立相关的渲染坐标系,从而精确注册虚拟物体.同时,针对个性化应用需求,提出了一种能够在增强现实系统中应用的Harris快速掌纹识别算法.实验表明,识别算法具有较好的跟踪精度和实时性,能够满足增强现实系统的应用要求.     

A novel classification method for palmprint recognition based on reconstruction error and normalized distance

In this paper, we propose a fusion classification method based on reconstruction error and normalized distance for palmprint recognition. This method first obtains an approximate representation of the test sample by solving a linear system in which the test sample is assumed to be a linear combination of all the original training samples. Then it replaces the test sample by its approximate representation and decomposes the approximate representation as a weighted sum of all the training samples. The proposed method calculates the reconstruction error of the approximate representation from the weighted sum of the training samples from each class. The method also computes the normalized distance between the test sample and each class. Finally, the method integrates the reconstruction error and normalized distance between the test sample and a class to form the matching score and assigns the test sample into the class that has the smallest matching score. Experimental results on the palmprint databases demonstrate the effectiveness of our method.     

一种基于对数极坐标变换的快速目标识别算法

在目标识别的过程中,观察目标图像相对于基准目标图像会存在尺度、方向和位置的变化,使得识别速度和准确率降低. 针对这一问题,提出了一种快速对数极坐标变换算法,加快了从笛卡儿坐标转换到对数极坐标的过程. 通过采用双轴投影相似度分析算法对目标图像进行匹配,进一步加快了识别速度,同时保证了匹配的可靠性. 理论分析和试验结果表明,该算法在计算效率和目标识别正确率方面具有较好的性能.     

基于近邻三值模式和协作表示的三维掌纹识别

针对二维掌纹图像存在易伪造、抗噪能力差的问题，提出一种基于近邻三值模式（NTP）和协作表示的三维掌纹识别方法。首先，利用形状指数把三维掌纹的表面几何信息映射成二维数据，以弥补常用均值或高斯曲率映射无法精确描述三维掌纹特征的缺陷；其次，对形状指数图作分块处理，利用近邻三值模式提取分块形状指数图的纹理特征；最后，利用协作表示的方法进行特征分类。在三维掌纹库上和经典算法进行的对比实验中，该方法的识别率为99.52%，识别时长为0.6738 s，优于其他算法；在识别率方面，与经典的局部二值模式（LBP）、局部三值模式（LLTP）、CompCode、均值曲率图（MCI）法相比分别提高了7.77%、6.02%、5.12%和3.97%；在识别时间方面，与Homotopy、对偶增广拉格朗日法（DALM）、SpaRSA方法相比分别降低了6.7 s、15.9 s和61 s。实验结果表明，所提算法具有良好的特征提取和分类能力，能够有效地提高识别精度并减少识别时间。     

基于小波分解和高低帽变换的在线掌纹识别*

用于身份鉴别的掌纹识别为信息安全提供一种新的方案。为减少对图像采集的限制,本文提出在小波变换的基础上,利用高低帽变换寻找低频子图像中的灰度槽,获取对比度增强的图像。把此子图像所有的变换值组合起来作为图像的特征向量以用于识别。运用UST掌纹图像库,对本文算法进行了测试。从实验的结果看,此方法解决了在线掌纹图像低对比度问题,图像识别率得以提高。证明此方法能够满足对采集图像无过多要求的认证系统的使用。     

A key binding system based on n-nearest minutiae structure of fingerprint

Biometric cryptosystem has gained increasing attention in recent years. One of the difficulties in this field is how to perform biometric matching under template protection. In this paper, we propose a key binding system based on n-nearest minutiae structures of fingerprint. Unlike the traditional fingerprint recognition method, the matching of nearest structures are totally performed in the encrypted domain, where the template minutiae are protected. Three levels of secure sketch are applied to deal with error correction and key binding: (1) The wrap-around construction is used to tolerate random errors that happens on paired minutiae; (2) the PinSketch construction is used to recover nearest structures which are disturbed by burst errors; and (3) Shamir’s secret sharing scheme is used to bind and recover a key based on template minutia structures. The experimental results on FVC2002 DB1 and DB2 and security analysis show that our system is efficient and secure.     

b-COELM: A fast,lightweight and accurate activity recognition model for mini-wearable devices

Various mini-wearable devices have emerged in the past few years to recognize activities of daily living for users. Wearable devices are normally designed to be miniature and portable. Models running on the devices inevitably face following challenges: low-computational-complexity, lightweight and high-accuracy. In order to meet these requirements, a novel powerful activity recognition model named b-COELM is proposed in this paper. b-COELM retains the superiorities (low-computational-complexity, lightweight) of Proximal Support Vector Machine, and extends the powerful generalization ability of Extreme Learning Machine in multi-class classification problems. Experimental results show the efficiency and effectiveness of b-COELM for recognizing activities of daily living.