基于学习的高分辨率掌纹细节点质量评价方法

Quality Estimation Algorithm Based on Learning for High-Resolution Palmprint Minutiae

细节点在高分辨率掌纹匹配中扮演了重要角色,然而掌纹图像受到主线、褶皱线等的影响,提取出的细节点质量参差不齐.所以,对细节点进行质量评价并去除伪细节点,成为一个研究课题.提出了一种基于学习的高分辨率掌纹细节点质量评价方法.首先使用了基于图像的Gabor卷积响应和复数滤波响应等的一系列特征,用来对细节点局部进行冗余描述;然后,把每个特征作为弱分类器,用AdaBoost算法进行多层训练,挑选出对真伪细节点判别效果最理想的特征;最后,把弱分类器加权线性组合的响应分数作为细节点质量的得分,筛选出得分在阈值以上的细节点作为真细节点.该方法的实验结果与基于傅里叶变换的方法相比,能够更好地区分真伪细节点,对细节点的质量做出了更好的评价.

While minutiae is important for high-resolution palmprint matching, the quality of minutiae is affected by principal lines, creases and other noises, and therefore it is necessary to estimate the quality of minutiae and to exclude poor minutiae. In this paper, a minutiae quality estimation algorithm based on learning for high-resolution palmprint is proposed. First, a series of features obtained by applying Gabor convolution, complex filtering, etc., are used to describe the local area of minutiae redundancy. Then, with each feature as a weak classifier, AdaBoost algorithm is applied in multi-layered training to identify the best features for discriminating minutiae. Finally, the response of weighted linear combination of weak classifiers is used as minutiae quality score, and minutiae with score above the threshold is selected as true minutiae. Comparing with the method based on Fourier transform response, the presented method is superior at distinguishing true from false minutiae, and provides better evaluation of minutiae quality.