A Human Identification System based on Retinal Image Processing Using Partitioned Fourier Spectrum
Retinal image is one of the robust and accurate biometrics. A new biometric identification system base on Fourier transform and that special partitioning presented in this article. In this method, at first, optical disc is localized using template matching technique and use it for rotate the retinal image to reference position. Fourier transform coefficient and angular partitioning of these coefficients is used for feature definition. Finally we employ Manhattan distance for feature matching. The proposed method applied on a database consist 200 retinal images from 40 persons. In this article noisy and rotate retinal image are used in identification process. ％98 identification rate can achieve in this proposed method.
A.Zahedi H.Sadjedi
Department of engineering, Shahed University, Tehran, Iran
国际会议
上海
英文
435-438
2010-10-20（万方平台首次上网日期，不代表论文的发表时间）