Dissertation > Excellent graduate degree dissertation topics show

Integration and multimode biometric - based identification method study

Author: LiuLin
Tutor: GuXiaoFeng
School: University of Electronic Science and Technology
Course: Software Engineering
Keywords: Multi-mode biometrics data fusion face identification fingerprint identification iris identification
CLC: TP391.41
Type: Master's thesis
Year: 2010
Downloads: 77
Quote: 0
Read: Download Dissertation

Abstract


Identification, which is widely used in bank, public security, and judiciary and all other fields, is unavoidable in our daily life. The traditional single-mode identification system has so many limitations (such as: sensitivity to light, etc.) taht result in practical application of this technology in the many difficulties. With the emergence of data fusion technology, the multi-mode biometrics identification can make use of the complementarities information between different biological characteristics, and integration of the key message of various biological characteristics. It can achieve the goal to synthetically determine personal identity. Many scholars firmly believe that the multi-mode biometrics identification is leading in the future direction of biometrics.The multi-mode biological features data fusion methods, the definition, basic principles, hierarchy and structure are introduced on the basis of common biological features. The fusion and identification of multi-mode biometric are focused to study, and the key technologies of face, fingerprint and iris identification technology are involved. The main contributions are as follows:1) Three single-mode authentication technology, based on face, fingerprint and iris identification technology, are studied and improved in this thesis to increase the recognition rate of single-mode authentication issues. However, there always exist the limitations of single-mode biometric, such as face’s sensitivity to light and inaccuracy of iris localization, resulting in low reliability of identification.2) As far as various algorithms of the multi-biometric identification fusion are concerned, the thesis studies fusion algorithm using a Weight-sum in decision-making level. The method overcomes a single biometrics’disadvantages, for example, at collection one of a person’s characteristics makes noise impact of the identification reliability. In the database which we use to make tests, the experiment results of the algorithm show a better advantage.3) A new similarity fusion algorithm, based on similarity coefficient model, is studied in the thesis to solve the integration problems of multi-mode biometric features. In the method, the data were fused in the feature layers after extraction and in the decision-making level after pattern matching. As for the test results in our database, the algorithm’s effectiveness has been well verified.4) Finally, a multi-mode biometric identification system, on the basis of the new algorithm method above, is built in our thesis. The present research provides certain reference value significance not only for single-mode identification but also for design and development of identification system in practical application.

Related Dissertations

  1. The Research of Navigation Multi-Sensor Data Fusion Technology Based on Micro Unmanned Platform,V249.32
  2. Research on Pressure Sensed Fingerprint Identification System and Algorithem,TP391.41
  3. Stage Fault Diagnosis Based on Data Fusion,TP18
  4. The Research on Data Fusion Algorithm and Model for Wireless Sensor Networks,TN929.5
  5. The Study of the Data Fusion Technology in Multi-sensor Network,TN929.5;TP202
  6. Study on Wireless Sensor Networks with Communication Constraints,TN929.5
  7. Research on Multi-modalbiometric Fusion Personalidentification Technology Based on Fingerprint and Name Speech,TP391.41
  8. The Cost and Benefit Analysis of Bank Information Technology Investment,F830.49
  9. Method of Monitoring Vegetation Information on the Mining Based on Multiple Remote Sensing Data,P237
  10. Detection and Research on Pork Freshness Based on RBF Neuronic Network,TP274
  11. Study on Improved Fingerprint Identification Algorithm Based on Delaunay Triangulation,TP391.41
  12. Research on Multi-Sensor Embattling and Continious Tracking Technique Applying for Anti-Stealth and Anti-Interference,TN953
  13. Research of Forecasting the Reliability of Information Sources,TP18
  14. Wireless sensor network routing protocol research and improvement,TP212.9
  15. Design of Automobile Security System Based on Navigation and Positioning,U463.6
  16. Research on Data Acquisition and Data Fusion in Expert System of Vacuum Measurement,TP274.2
  17. Study on Grid Data Fusion of 3DGIS Modeling and FLAC-3D Modeling,TD80
  18. The Study of the Cooperative Spectrum Sensingalgorithm Based on Data Fusion,TN925
  19. Research on Spectrum Sensing in Cognitive Radio Network,TN925
  20. Low quality fingerprint image evaluation and scratch detection and restoration research,TP391.41
  21. Research on the Algorithms of Automatic Fingerprint Identification System,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