指纹图像多尺度分类字典稀疏增强  

Fingerprint enhancement using sparse representation by multi-scale classification dictionaries

作　　者：徐德琴[1,2] 卞维新 丁新涛[1,2] 丁玉祥 Xu Deqin;Bian Weixin;Ding Xintao;Ding Yuxiang(School of Mathematics and Computer Science, Anhui Normal University, Wuhu 241002, China;Anhui Provincial Key Laboratory of Network and Information Security, Wuhu 241002, China)

机构地区：[1]安徽师范大学数学计算机科学学院,芜湖241002 [2]网络与信息安全安徽省重点实验室,芜湖241002

出　　处：《中国图象图形学报》2018年第7期1014-1023,共10页Journal of Image and Graphics

基　　金：安徽省自然科学基金项目(1708085MF145)~~

摘　　要：目的自动指纹识别系统大多是基于细节点匹配的,系统性能依赖于输入指纹质量。输入指纹质量差是目前自动指纹识别系统面临的主要问题。为了提高系统性能,实现对低质量指纹的增强,提出了一种基于多尺度分类字典稀疏表示的指纹增强方法。方法首先,构建高质量指纹训练样本集,基于高质量训练样本学习得到多尺度分类字典;其次,使用线性对比度拉伸方法对指纹图像进行预增强,得到预增强指纹;然后,在空域对预增强指纹进行分块,基于块内点方向一致性对块质量进行评价和分级;最后,在频域构建基于分类字典稀疏表示的指纹块频谱增强模型,基于块质量分级机制和复合窗口策略,结合频谱扩散,基于多尺度分类字典对块频谱进行增强。结果在指纹数据库FVC2004上将提出算法与两种传统指纹增强算法进行了对比实验。可视化和量化实验结果均表明,相比于传统指纹增强算法,提出的方法具有更好的鲁棒性,能有效改善低质量输入指纹质量。结论通过将指纹脊线模式先验引入分类字典学习,为拥有不同方向类别的指纹块分别学习一个更为可靠的字典,使得学习到的分类字典拥有更可靠的脊线模式信息。块质量分级机制和复合窗口策略不仅有助于频谱扩散,改善低质量块的频谱质量,而且使得多尺度分类字典能够成功应用,克服了增强准确性和抗噪性之间的矛盾,使得块增强结果更具稳定性和可靠性,显著提升了低质量指纹图像的增强质量。Objective Most automatic fingerprint identification systems （AFISs） are based on minutiae matching. The ac- curacy and reliability of minutiae extraction are largely dependent on the quality of the input fingerprint image. Thus, the performance of these AFISs is largely determined by the quality of input fingerprint images. In practice, the quality of a fin- gerprint image may suffer from various impairments, and the image may appear with ridge adhesions, ridge fractures, or un- even contrast. To improve the performance of AFISs, the quality of fingerprint images must be enhanced. This study propo- ses a novel fingerprint enhancement algorithm that uses sparse representation by muhi-scale classification dictionaries. Method First, we sample high-quality training fingerprints to build the training set for multi-scale classification dictionaries learning, and the multi-scale classification dictionaries are learned from the training set. A crucial issue in enhancing fin-gerprint images is obtaining an effective prior or constraint. Unlike generic images, fingerprint images have a steady and re- liable ridge pattern. To obtain an effective prior or constraint, fingerprint patch orientations are estimated by weighted linear projection analysis （WLPA） on the basis of the vector set of point gradients. We classify training samples with the same size into eight groups according to their ridge orientation pattern. Instead of simply learning a dictionary, we learn a classifi- cation dictionary for each class with the same size. Second, fingerprints are pre-enhanced using the linear contrast stretc- hing method. The sparse grey space in the fingerprint image is used, and the fingerprint image contrast can be stretched to cover the entire greyscale space. Consequently, the gray level information of the input fingerprint can be preserved against loss, and contrast enhancement can be improved. Contrast enhanced fingerprint contributes to the subsequent enhance- ment. Third, a fingerprint has a unique natural pattern, w

关 键 词：指纹 块质量评价 多尺度分类字典 稀疏表示 频谱扩散 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]