Dissertation > Excellent graduate degree dissertation topics show

The Algorithm Researching of Iris Recognition Technology

Author: YouHongXia
Tutor: XuWenBo
School: Jiangnan University
Course: Applied Computer Technology
Keywords: Iris Recognition Edge Detection Daubechies-4 wavelet Wavelet Transform Euclidean distance
CLC: TP391.4
Type: Master's thesis
Year: 2006
Downloads: 205
Quote: 3
Read: Download Dissertation

Abstract


With the development of biometric identification technology , iris recognition technology has been widespread concern. Field of iris recognition technology , there are already some of the algorithms are proven to be effective . The entire process of iris recognition roughly divided into the iris localization , feature extraction , feature matching steps . This article discusses a new iris recognition algorithm based on wavelet transform . First , the use of a combination of coarse positioning and fine positioning iris location algorithm . The isolated pupil image binarization method based on the characteristics of the image the eyes , first rough positioning the center and radius of the pupil of the projection method , and then in a small area with the position of the center of the pupil of the precise positioning of the center of gravity method . The priori knowledge interception iris including small image , within a small range after the center position of the pupil is determined using the canny edge edge detection , and then use the method of ranks scan to determine the center position and the radius of the iris . This method is less computation than traditional location algorithm to improve the positioning accuracy premise speed . Secondly, the discussion of a new extraction method based on wavelet transform iris texture features dense texture of the inside of the iris texture distribution sparse outer texture . According to the distribution characteristics of the iris , the iris into the analysis of 10 bands , for each analysis band Daubechies-4 wavelet transform , wavelet transform the mean and standard deviation of the wavelet coefficients of the respective channels as the characteristic value of the iris , and finally get to the iris 112 the bit feature coding, storage capacity is only 1K ~ 2K. Feature matching is used in the weighted Euclidean distance classifier method, the final classification criteria are weighted Euclidean distance between the mean of the vector in the corresponding features of the two iris . The proposed algorithm, the iris image scale , rotation, translation invariance . In order to evaluate the performance of the algorithm , the iris database a large number of experiments , and the experimental results with the existing methods are compared . The experimental results show that the proposed algorithm is effective , and achieved a high recognition rate .

Related Dissertations

  1. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  2. Research on Detecting Optical Fiber Geometric Parameter Based on Machine Vision,TN253
  3. Research on Identification System of Cashmere and Wool Fiber,TS101.921
  4. Research on Abnormal Vehicle Behavior Detection and Application in Traffic Video,TP391.41
  5. Feature Extraction Technologies Research and Implementation of 3D Models Based on Wavelet Transform,TP391.41
  6. An Algorithm on Clustering and Anomaly Detection for Multiple Data Streams,TP311.13
  7. Research on Information Hiding Based on Images,TP309.7
  8. Design and Implication of Image Compression System Based on Wavelet and DM6446,TP391.41
  9. Combined DWT Dynamic Data Reconciliation Research and Application,TP274
  10. Traffic Prediction Model Based on Wavelet and Markov,TP393.06
  11. Research on Location Algorithm of Iris Recognition,TP391.41
  12. The Study of Image Watermark Base on Discrete Wavelet Transformation,TP309.7
  13. Research on Vision Detection Algorithm for Tracing Printing System,TP391.41
  14. The Compression and Application of the Brain CT Image,TP391.41
  15. Research on Image Segmentation Method Based on Measure of Medium Truth Degree,TP391.41
  16. Inspection and Recognition on a Class of Tool Processing Trace,TP391.41
  17. Research on Noise Reducation and Color Interpolation Algorithms Based on Bayer Pattern Images for Digital Camera,TP391.41
  18. Research on Image Super-resolution Reconstruction Based on Non-local Similarity,TP391.41
  19. The Research and Design of a Fire Detection System Based on Combustion Audio Recognition,X924.4
  20. The Realization and Study of a Scalable Data Encoder Based on SPIHT,TN762
  21. Research and Implementation of Dwt-based Video Codec System at Low Bit Rates,TN919.81

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