Contact-Free Palm-Vein Recognition Based on Local Invariant Features

Abstract

Contact-free palm-vein recognition is one of the most challenging and promising areas in hand biometrics. In view of the existing problems in contact-free palm-vein imaging, including projection transformation, uneven illumination and difficulty in extracting exact ROIs, this paper presents a novel recognition approach for contact-free palm-vein recognition that performs feature extraction and matching on all vein textures distributed over the palm surface, including finger veins and palm veins, to minimize the loss of feature information. First, a hierarchical enhancement algorithm, which combines a DOG filter and histogram equalization, is adopted to alleviate uneven illumination and to highlight vein textures. Second, RootSIFT, a more stable local invariant feature extraction method in comparison to SIFT, is adopted to overcome the projection transformation in contact-free mode. Subsequently, a novel hierarchical mismatching removal algorithm based on neighborhood searching and LBP histograms is adopted to improve the accuracy of feature matching. Finally, we rigorously evaluated the proposed approach using two different databases and obtained 0.996% and 3.112% Equal Error Rates (EERs), respectively, which demonstrate the effectiveness of the proposed approach.

Hand-Dorsa Vein Recognition Based on Scale and Contrast Invariant Feature Matching

“…Two kinds of representative hand-crafted feature extraction algorithms are used as reference: The one is the local invariant feature model [4] including SIFT, SURF, ASIFT, Root-SIFT, and it has the advantages of being invariant to rotation, translation, scale uncertainty and even nonuniform illumination, which makes it the best one among all hand-crafted algorithms (Note that all the models adopt DHE for contrast enhancement followed by direct extraction of keypoints and matching without the proposed mismatching removal). The other one is the LBP and its variants including LDP, LTP, and LLBP, and such model is widely applied for vein based identification application for its efficiency, and it also provides competitive recognition results.…”

“…To address this problem, nearly all SIFT/SURF based vein recognition system (as illustrated in Fig. 1 sults reported [4]. However, conclusions in [2], which bring evidence that the number of SIFT keypoints resulted by gradient based detectors increases greatly with CE, while on the other hand the matching result of extracted invariant descriptors is negatively influenced in terms of Precision Recall (PR) and Equal Error Rate (EER), motivate us to rethink and investigate the overall effect of CE on SIFT based vein recognition system, and also design the scale and contrast invariant feature matching (SCIFM) strategy to construct more robust vein recognition system.…”

Feature Extraction of Palm Vein Patterns Based on Two-Dimensional Density Function

“…Its application can be found also in the works by [4,5]. Apart from feature extraction the Gaussian function was applied to improve the image contrast as shown in [6] and [7]. The blood vessel pattern of the hand is extended enough to allow the use of different methods for extracting and coding features.…”

Gender Attribute Mining with Hand-Dorsa Vein Image Based on Unsupervised Sparse Feature Learning

“…Instead, nearly all the related research focuses on vein feature extraction methods design, which serves as the key link for vein recognition task. Among all the reported feature extraction models, we intend to summarize them into four groups [2]: global topological analysis (GTA), global quantification analysis (GQA), local geometric analysis (LGA) and local invariant feature (LIF). Driven by the fact that the subject-specified hand-vein information could be well represented by the four models, is that possible to obtain effective gender-specified representation so that accurate gender classification result would be generated with similar methods?…”