面向虹膜识别的Gabor特征筛选研究

针对2D-Gabor虹膜特征并不稳定,影响虹膜识别率的问题,提出了一种从多尺度、多方向2D-Gabor小波提取的虹膜特征中,筛选稳定特征应用于虹膜识别的方法。对虹膜图像采用多通道Gabor小波提取虹膜图像特征,然后通过自定义筛选准则从多维特征中筛选出最优特征参数并编码,用Hamming距进行特征匹配识别。基于CASIA虹膜图像库进行实验,结果表明该方法扩大了类内匹配与类间匹配之间的Hamming距,降低了等错率,同时降低了编码的长度,加快了特征匹配速度。     

基于D-LDA与最近特征分类法的眼虹膜识别系统

以3个主要处理阶段来实现一个高识别率的虹膜识别系统。撷取人眼图像进而分离出虹膜图像,再利用图像处理予以改善,使得虹膜图像更适于后续的识别。接着建立虹膜的特征向量,在虹膜图像展开的过程中,解决了虹膜图像旋转不变性的问题,然后利用直接线性判别分析（D-LDA）的方式进行特征抽取,使得所产生出来的特征向量拥有最大类别间距离与最小类别内距离的特性。最后,探讨多种最近特征分类法与其识别效果,并将上述方法设计完成一套眼虹膜识别系统。实验结果显示,在样本特征向量数较少的情况下识别率有96．47％,如果在每个类别中增加样本特征向量的数量,则系统的识别率可以达到98．50％。     

Iris detection using intensity and edge information

In this paper we propose a new algorithm to detect the irises of both eyes from a face image. The algorithm first detects the face region in the image and then extracts intensity valleys from the face region. Next, the algorithm extracts iris candidates from the valleys using the feature template of Lin and Wu (IEEE Trans. Image Process. 8 (6) (1999) 834) and the separability filter of Fukui and Yamaguchi (Trans. IEICE Japan J80-D-II (8) (1997) 2170). Finally, using the costs for pairs of iris candidates proposed in this paper, the algorithm selects a pair of iris candidates corresponding to the irises. The costs are computed by using Hough transform, separability filter and template matching. As the results of the experiments, the iris detection rate of the proposed algorithm was 95.3% for 150 face images of 15 persons without spectacles in the database of University of Bern and 96.8% for 63 images of 21 persons without spectacles in the AR database.     

Reliable detection of eye features and eyes in color facial images using ternary eye-verifier

Eye detection plays an important role in applications related to face recognition. The position of eyes can be used as a reliable reference for other facial feature detection. This paper presents a novel approach for the precise and reliable detection of eyes by introducing a ternary eye-verifier. Initially, the face region is detected by combining color information and the Haar-like feature detector. The face region is then binarized and filtered with circular filters to detect eye candidates at the peaks in the filtered response. Each eye candidate is fed into a ternary eye-verifier that includes a proposed eye feature extractor based on K-means clustering with compensation for variety in iris color. The eye template in the eye-verifier is constructed based on both the knowledge of eye geometry and the detected eye features. The template matching is made by the ternary Hamming distance. Experiments over a collection of FERET face database and house-made face database with different head poses confirm that the proposed method achieves precise and reliable detection of eyes from color facial images with variation in illumination, pose, eye gazing direction, and race.     

基于Log-Gabor滤波的虹膜识别系统

在已有虹膜识别研究成果的基础上,提出基于Log-Gabor滤波的虹膜身份识别图像系统。该系统利用Matlab平台结合一维Log-Gabor滤波器对归一化后的虹膜进行滤波并提取纹理特征,然后对纹理特征进行相位编码,并用汉明距离进行虹膜匹配,匹配时采用干扰掩模屏蔽虹膜预处理过程中的噪音。本文结合CASIA虹膜图像数据库进行实验论证,其结果表明该系统误判率为0.125%,拒判率为0.05%,达到较好的识别效果。     

Iris quality assessment and bi-orthogonal wavelet based encoding for recognition

Iris recognition has been demonstrated to be an efficient technology for personal identification. In this work, methods to perform iris encoding using bi-orthogonal wavelets and directional bi-orthogonal filters are proposed and compared. All the iris images are enhanced using the wavelet domain in-band de-noising method. This method is shown to improve the iris segmentation results. A framework to assess the iris image quality based on occlusion, contrast, focus and angular deformation is introduced and used as part of a novel adaptive matching technique based on the assessed iris image quality. Adaptive matching presents improved performance when compared against the Hamming distance method. Four different databases are used to analyze the system performance. The first two databases include popular CASIA and high resolution University of Bath databases. Results obtained for these databases compare with results from the literature, in terms of speed as well as accuracy. The other two databases have challenging off-angle (WVU database) and uncontrolled (Clarkson database) iris images and are used to assess the limits of system performance. Best results are achieved for directional bi-orthogonal filter based encoding technique combined with the adaptive matching method with EER values of 0.07%, 0.15%, 0.81% and 1.29% for the four databases, which reflect highly competent performance and high correlation with the quality of the iris images.     

一种虹膜图像质量评价的方法

虹膜图像质量是影响虹膜识别系统精度的关键。从序列图像中挑选出符合要求的虹膜图像能有效地降低识别系统的拒识率和误识率。这里按照产生虹膜图像奇异的不同情形：失焦、运动模糊、眼睑遮挡及睫毛遮挡,充分利用虹膜自身的纹理分布特点,在算法中引入了评价区域局部化、小波包分解和能量加权等思想,分别设计相应算法加以评判。实验结果表明该评价方案快速有效,其评价结果和人眼主观评价相吻合。     

基于虹膜纹理深度特征和Fisher向量的人种分类

目的 虹膜是位于人眼表面黑色瞳孔和白色巩膜之间的圆环形区域,有着丰富的纹理信息。虹膜纹理具有高度的区分性和稳定性。人种分类是解决虹膜识别在大规模数据库上应用难题的主要方法之一。现有的虹膜图像人种分类方法主要采用手工设计的特征,而且针对亚洲人和非亚洲人的基本人种分类,无法很好地解决亚种族分类问题。为此提出一种基于虹膜纹理深度特征和Fisher向量的人种分类方法。方法 首先用CNN（convolutional neural network）对归一化后的虹膜纹理图像提取深度特征向量,作为底层特征;然后使用高斯混合模型提取Fisher向量作为最终的虹膜特征表达;最后用支持向量机分类得到最终结果。结果 本文方法在亚洲人和非亚洲人的数据集上采用non-person-disjoint的方式取得99.93%的准确率,采用person-disjoint的方式取得91.94%的准确率;在汉族人和藏族人的数据集上采用non-person-disjoint的方式取得99.69%的准确率,采用person-disjoint的方式取得82.25%的准确率。结论 本文通过数据驱动的方式从训练数据中学习到更适合人种分类的特征,可以很好地实现对基本人种以及亚种族人种的分类,提高了人种分类的精度。同时也首次证明了用虹膜图像进行亚种族分类的可行性,对人种分类理论进行了进一步地丰富和完善。     

Handwritten character classification using nearest neighbor inlarge databases

Shows that systems built on a simple statistical technique and a large training database can be automatically optimized to produce classification accuracies of 99% in the domain of handwritten digits. It is also shown that the performance of these systems scale consistently with the size of the training database, where the error rate is cut by more than half for every tenfold increase in the size of the training set from 10 to 100,000 examples. Three distance metrics for the standard nearest neighbor classification system are investigated: a simple Hamming distance metric, a pixel distance metric, and a metric based on the extraction of penstroke features. Systems employing these metrics were trained and tested on a standard, publicly available, database of nearly 225,000 digits provided by the National Institute of Standards and Technology. Additionally, a confidence metric is both introduced by the authors and also discovered and optimized by the system. The new confidence measure proves to be superior to the commonly used nearest neighbor distance     

基于Gabor滤波器和聚类的图像配准算法

提出一种基于多尺度、多方向Gabor滤波器提取图像局部不变特征并用AP聚类进行约束的配准算法。该方法首先利用Gabor尺度空间核函数对图像进行尺度空间分解,在每一层尺度图像的不同方向上提取Harris角点,在以Harris角点为中心的固定大小的搜索窗内搜索三维尺度空间的极值点作为局部特征点的位置和特征尺度;在特征子区域内用梯度描述特征点;将得到的两幅图像的特征点AP聚类分析,实现m:n的粗匹配,最终通过各类之间的欧式距离实现对应点的匹配,通过AP聚类可有效排除多相似内容的图像之间的误匹配。实验结果表明,该算法能够提取稳健的精确特征点,并且可以有效去除多相似内容图像带来的匹配误差,实现图像的配准。     

黎曼流形上的保局投影在图像集匹配中的应用

目的提出了黎曼流形上局部结构特征保持的图像集匹配方法。方法该方法使用协方差矩阵建模图像集合,利用对称正定的非奇异协方差矩阵构成黎曼流形上的子空间,将图像集的匹配转化为流形上的点的匹配问题。通过基于协方差矩阵度量学习的核函数将黎曼流形上的协方差矩阵映射到欧几里德空间。不同于其他方法黎曼流形上的鉴别分析方法,考虑到样本分布的局部几何结构,引入了黎曼流形上局部保持的图像集鉴别分析方法,保持样本分布的局部邻域结构的同时提升样本的可分性。结果在基于图像集合的对象识别任务上测试了本文算法,在ETH80和YouTube Celebrities数据库分别进行了对象识别和人脸识别实验,分别达到91.5%和65.31%的识别率。结论实验结果表明,该方法取得了优于其他图像集匹配算法的效果。     

An effective approach for iris recognition using phase-based image matching

This paper presents an efficient algorithm for iris recognition using phase-based image matching --- an image matching technique using phase components in 2D Discrete Fourier Transforms (DFTs) of given images. Experimental evaluation using CASIA iris image databases (ver. 1.0 and ver. 2.0) and Iris Challenge Evaluation (ICE) 2005 database clearly demonstrates that the use of phase components of iris images makes possible to achieve highly accurate iris recognition with a simple matching algorithm. This paper also discusses major implementation issues of our algorithm. In order to reduce the size of iris data and to prevent the visibility of iris images, we introduce the idea of 2D Fourier Phase Code (FPC) for representing iris information. 2D FPC is particularly useful for implementing compact iris recognition devices using state-of-the-art DSP (Digital Signal Processing) technology.     

基于局部纹理分析的虹膜识别算法

提出了一种新的基于局部纹理分析的虹膜识别算法。基于多通道Gabor滤波器，滤波图像的系数定量地描述了虹膜纹理局部子块和给定滤波器之间的相似度，系数越大，说明该子块在空间形态上和滤波器越相似。采用局部滤波图像系数的加权平均作为特征编码，那些具有较大系数的点，即和滤波器最相似的点对特征点的位置贡献较大，更能真实的反应虹膜纹理结构。基于欧氏距离的特征匹配试验表明了该方法的有效性。     

Effect of Severe Image Compression on Iris Recognition Performance

We investigate three schemes for severe compression of iris images in order to assess what their impact would be on recognition performance of the algorithms deployed today for identifying people by this biometric feature. Currently, standard iris images are 600 times larger than the IrisCode templates computed from them for database storage and search; but it is administratively desired that iris data should be stored, transmitted, and embedded in media in the form of images rather than as templates computed with proprietary algorithms. To reconcile that goal with its implications for bandwidth and storage, we present schemes that combine region-of-interest isolation with JPEG and JPEG2000 compression at severe levels, and we test them using a publicly available database of iris images. We show that it is possible to compress iris images to as little as 2000 bytes with minimal impact on recognition performance. Only some 2% to 3% of the bits in the IrisCode templates are changed by such severe image compression, and we calculate the entropy per code bit introduced by each compression scheme. Error tradeoff curve metrics document very good recognition performance despite this reduction in data size by a net factor of 150, approaching a convergence of image data size and template size.     

双重注意力机制下的跨光谱虹膜识别优化算法

跨光谱虹膜识别任务,通常是指匹配不同光谱下采集的虹膜图像,针对光谱域变化对虹膜识别率影响的问题,提出一种基于双重注意力机制下的跨光谱虹膜识别优化算法。该算法首先通过浅层网络的特征提取,将可见光与近红外光谱域中的浅层特征送入各自的专有外部注意力模块进行优化,以分别存储各自光谱域中虹膜样本数据集的特有信息,随后将优化后的浅层特征送入共享的深度特征提取网络,再将深度特征先后送入改进的空间注意力模块和外部注意力模块,强化虹膜关键特征信息的表达,同时以改进的加性角间距损失函数ArcFace Loss(additive angular margin loss)动态调整对于困难样本的优化力度。该算法在PolyU数据集上进行了实验验证,等错误率EER(equal error rate)达到了0.23%,分离度达到了8.56,该实验结果与跨光谱虹膜识别SOTA(state-of-the-art)算法进行了比较,远高于其他主流算法。     

Performance analysis of iris-based identification system at the matching score level

Practical iris-based identification systems are easily accessible for data collection at the matching score level. In a typical setting, a video camera is used to collect a single frontal view image of good quality. The image is then preprocessed, encoded, and compared with all entries in the biometric database resulting in a single highest matching score. In this paper, we assume that multiple scans from the same iris are available and design the decision rules based on this assumption. We consider the cases where vectors of matching scores may be described by a Gaussian model with dependent components under both genuine and imposter hypotheses. Two test statistics: the plug-in loglikelihood ratio and the average Hamming distance are designed. We further analyze the performance of filter-based iris recognition systems. The model fit is verified using the Shapiro-Wilk test for normality. We show that the loglikelihood ratio with well-estimated maximum-likelihood parameters in it often outperforms the average Hamming distance statistic. The problem of identification with M iris classes is further stated as an (M+1)ary hypothesis testing problem. We use empirical approach, Chernoff bound, and Large Deviations approach to predict the performance of the iris-based identification system. The bound on the probability of error is evaluated as a function of the number of classes and the number of iris scans per class.     

基于改进的等距离映射算法的人脸识别

针对等距离映射(Isomap)算法在处理扰动图像时拓扑结构不稳定的缺点,提出了一种改进算法。改进算法将图像欧氏距离(IMED)嵌入到等距离映射算法之中。首先引入坐标度量系数计算图像的坐标度量矩阵,通过线性变换将原始图像从欧氏距离(ED)空间转换到图像欧氏距离空间;然后计算变换空间中样本的欧氏距离矩阵,并在此基础上构建样本邻域图,得到近似测地距离矩阵;最后采用多维标度(MDS)分析算法构造样本的低维表示。对ORL和Yale人脸数据库降维并结合最近邻分类器进行实验,基于改进算法的识别率平均分别提高了5.57%和3.95%,表明与原算法相比,改进算法在人脸识别中对图像扰动具有较好的鲁棒性。     

基于多维匹配距离融合的指节纹识别

指节纹识别(FKP)作为一种新型的生物特征识别方式,以其安全性和稳定性而备受关注.基于编码的方法被认为是该领域最有成效法之一,在模板匹配阶段通常根据所提取的特征信息计算出2张图片之间的匹配距离来判断样本.然而,一些模糊样本无法通过单一的匹配距离进行有效区分,从而导致较高的错误接受率和错误拒绝率.针对这一问题,提出了一种...