Dissertation > Excellent graduate degree dissertation topics show

Decision Fusion of Palm and Plam Vein Matching Algorithm Based on Multiple Feature Fusion

Author: ZhangQing
Tutor: SunDongMei
School: Beijing Jiaotong University
Course: Information Security
Keywords: Multi-feature Fusion Contactless Acquisition Equipment DecisionLevel Fusion Palm and Palm Vein Fusion
CLC: TP391.41
Type: Master's thesis
Year: 2012
Downloads: 70
Quote: 0
Read: Download Dissertation

Abstract


For the inherent shortcomings of a single modal biometric system, this paper proposes a new fusion algorithm based on the decision-making level palm palm vein, and use this algorithm to achieve a set of palm palm vein authentication system.This system has the following characteristics:First, design a non-contact palm palm vein harvesting system. Acquisition system is characterized by the following aspects:first, the system uses dual cameras, first camera is used to capture visible light images, palmprint. The second camera is used to capture infrared images of palm vein image. The collector does not require specialized infrared sensor image of the imaging system. With the ordinary camera and filters, so the design is simple and low cost. Second, the acquisition system designed for non-contact. Not only clean and sanitary, humane, and security is also increased, to avoid the palm traces may be used by others.Second, opponents palmprint and palm vein two modes were the primary classifier design, with details of the point matching from the matching between the minimum average distance matching method, matching the results obtained by the three decision-making fusion; and then extracted hand palm and palm vein feature points in series to form a new feature, constitute the two classifiers, and then the same algorithm obtained the results of a match.Finally, the palm, palm vein and palm palm vein fusion, the results of these three identification decision level fusion is to get the final results. Experimental results show that this algorithm can effectively improve the system by reducing the error rate.

Related Dissertations

  1. Research and Design on Image-based Insect Identification,TP391.41
  2. Particle filter based video object tracking method,TP391.41
  3. Based on SVM of microRNA Multi-feature Fusion Model Research,TP391.41
  4. Research on Extraction of Named Entity Translation Equivalents from Comparable Corpus,TP391.2
  5. Virtual community opinion mining model hot topics,TP393.09
  6. Research and Application of Content-Based Image Database Retrieval Technology,TP391.41
  7. Research on 3D Model Retrieval System Based on Multi-feature and Relevance Feedback,TP391.3
  8. Research of Content-based Image Retrieval in Binary Trademark,TP391.41
  9. Study on Multi-target Tracking Method Based on Distributed Co-evolutionary Agents,TP391.41
  10. Design and Implementation of Many Characteristics-Based Image Retrieval System,TP391.41
  11. Tracking moving objects using multi-feature fusion,TP391.41
  12. 3D Face Recognition Using Ifnormation Fusion,TP391.41
  13. The Research for Visual Surveillance System Based on Fusion of Multiple Model Data,TP391.41
  14. Research on Moving Object Detection and Tracking in Complex Condition,TP391.41
  15. Research on Obstacle Detection and Obstacle Avoidance Strategy of Intelligent Vehicle,U495
  16. Skin Color Detection in Static Images,TP391.41
  17. Gait recognition of several key technologies,TP391.41
  18. Research on the Technique of Face Recognition,TP391.41
  19. Research on Methods of Infrared Image Target Detection,TN215
  20. Research and Implementation of Multi-Features Fusion Based Image Retrieval Method,TP391.41
  21. Research on Computer Vision Based Moving Object Tracking,TP391.41

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