Dissertation > Excellent graduate degree dissertation topics show

Research and Implementation of hand vein recognition system in the military

Author: WangZuo
Tutor: HeXingGao；AnNa
School: University of Electronic Science and Technology
Course: Software Engineering
Keywords: Palm-dorsal vein Biometric identification Feature matching
CLC: TP391.41
Type: Master's thesis
Year: 2012
Downloads: 59
Quote: 0
Read: Download Dissertation

Abstract

The arrival of the information times has brought about tremendous changes to military, it is particularly important to military information security, human Authentication also gained a new connotation in the information times. Biometrics makes use of the inherent physiological or behavioral characteristics of human beings to identify individuals. Due to the unique, stable and live physiological properties, palm-dorsa vein patterns is receiving extensive attention and becoming an active topic in military biometrics.This paper systematically studies the theory and technology of image processing under military background, and put forward a complete set of palm-dorsal vein image processing algorithm, the specific researches are as follows:First, this paper analyses the research background the significance of palm-dorsal vein recognition, and introduces the national and overseas research status quo, by explaining many advantages of vein recognition, such as in vivid identification, internal features, non-contact model, it points out that this study is significant and feasible. Meanwhile the paper accounts for the research results and content arrangement.Second, the paper put forwards the use of self-adaptive algorithm of palm-dorsal vein image, according to the features of palm-dorsal vein image’s effective regional location. The algorithms take full advantage of the palm’s lateral boundary contour‘s linear characteristics to process effective regional location. Experiments show that this algorithm suffers little outside interference and self-adaptive, it can segment the palm’s effective regional rapidly and accurately.Then, the paper researches the vein image enhancement methods and segmentation processing, proposes a self-adaptive histogram equalization method based on local gray amendments to enhance the palm-dorsal vein images. Contrast with the overall and local histogram equalization, experiments show that this algorithm not only enhances the overall contrast, but also give prominence to some of the details, it’s more effective when processing the hand vein image. The paper points out that the traditional several multi-threshold segmentations usually can’t retain enough information of the vein image and have lots of noise, aimed at these shortcomings the paper put forward the use of threshold image method to carry out palm-dorsal vein image’s segmentation, this algorithm uses a threshold image and the original image to process a point -by-point discrimination, accordingly to actualize binarization. After comparing experiments of the above algorithm, it was found that the threshold image method can guarantee not to loss the effective information of hand vein, and work better to wipe off noises.After that, the paper discussed the thinning algorithm of palm-dorsal vein image. Applied to the improved mathematical morphology thinning algorithm, the experimental results show that this algorithm can not only accurately approximate the mid-axes of two value vein image, but also optimizes the calculation method and vastly improved the operational speed, it’s efficient and effective.Finally, the paper researched the geometry and structure feature extraction and image matching based on the feature extracted.

Related Dissertations

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net Mobile