Hand Vein Images Research Articles

Biometric identification using infrared dorsum hand vein images

The evident need for improving access and safety controls has orientated the development of new personal identification systems towards using biometric, physiological and behavioral features guaranteeing increasing greater levels of performance. Motivated by this trend, the development and implementation of a computational tool for recording and validating people’s identity using dorsum hand vein images is presented here. A low-cost hardware module for acquiring infrared images was thus designed; it consisted of a conventional video-camera, optical lenses, controlled infrared illumination sources and a frame grabber. The accompanying software module was concerned with visualizing and capturing images, selecting regions of interest, pattern segmentation in the region and extracting, describing and classifying these features. An artificial neuron network approach was implemented for pattern recognition, resulting in it proving the biometric indicator to be sufficiently discriminating, and a correlation-based approach using a 100 image database for static characterisation, determined the system’s maximum efficiency to be 95.72% at a threshold equal to 65. False acceptance rate (FAR) was 8.57% and false rejection rate (FRR) was 0% at this threshold.

基于多分辨率小波的手背静脉识别算法

A novel hand vein recognition algorithm is developed based on multi-resolution wavelet analysis. The texture feature of hand vein can be extracted by three-level wavelet decomposition. Furthermore, K-nearest neighbor (KNN) with support vector machines (SVM) and minimum distance classifier (MDC) are employed for feature matching. Finally, the experiments are respectively performed in identification and verification modes using Tianjin University (TJU) hand vein image database constructed by our group. The results show the feasibility and effectiveness of the proposed method.