Non-negative locality-constrained vocabulary tree for finger vein image retrieval

作     者：Kun SU Gongping YANG Lu YANG Peng SU Yilong YIN 

作者机构：School of Computer Science and Technology Shandong University Jinan 250101 China School of Mechanical Electrical and Information Engineering Shandong University (Weihai)Weihai 264209 China School of Computer Science and Tech no logy Shandong University of Finance and Econo mics Jinan 250014 China School of Mathematics Dali University Dali 671000 China 

出 版 物：《Frontiers of Computer Science》 (中国计算机科学前沿（英文版）)

年 卷 期：2019年第13卷第2期

页      面：318-332页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 

基　　金：the National Natural Science Foundation of China (Grant Nos. 61472226, 61573219 and 61703235) in part by NSFC Joint Fund with Guangdong under Key Project (U1201258) 

主　　题：non-negative locality-constrained vocabulary tree finger vein image retrieval large scale inverted indexing 

摘      要：Finger vein image retrieval is a biometric identification technology that has recently attracted a lot of attention. It has the potential to reduce the search space and has attracted a considerable amount of research effort recently. It is a challenging problem owing to the large number of images in biometric databases and the lack of efficient retrieval schemes. We apply a hierarchical vocabulary tree modelbased image retrieval approach because of its good scalability and high efficiency. However, there is a large accumulative quantization error in the vocabulary tree (VT) model that may degrade the retrieval precision. To solve this problem, we improve the vector quantization coding in the VT model by introducing a non-negative locality-constrained constraint: the non-negative locality-constrained vocabulary tree-based image retrieval model. The proposed method can effectively improve coding performanee and the discriminative power of local features. Extensive experiments on a large fused finger vein database demonstrate the superiority of our encoding method. Experimental results also show that our retrieval strategy achieves better performanee than other state-of-theart methods, while maintaining low time complexity.