A hybrid method for iris segmentation

Advance development in security technology has caused many major corporations and governments to start employing modern techniques in identifying the identity of the individuals. Among the common biometric identification methods are facial recognition, fingerprint recognition, speaker verification a...

全面介紹

Saved in:
書目詳細資料
主要作者: Mohammed Mukred, Muaadh Shaif
格式: Thesis
語言:English
出版: 2010
主題:
在線閱讀:http://eprints.utm.my/id/eprint/16448/1/MuadhShaifMohammedMFSKSM2010.pdf
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
實物特徵
總結:Advance development in security technology has caused many major corporations and governments to start employing modern techniques in identifying the identity of the individuals. Among the common biometric identification methods are facial recognition, fingerprint recognition, speaker verification and so on, present a new solution for applications that require a high degree of security. Among these biometric methods, iris recognition becomes an important topic in pattern recognition, and it depends on the iris which is located in a place that still stable through human life. Furthermore, the probability to find two identical iris's approaching to zero value is quite easy. The identification system consists of several stages, and segmentation is the most crucial step. The current segmentation methods still have limitation in localizing the iris due to circular shape consideration of the pupil. Therefore, in this research, two segmentation methods of iris are suggested: Daugman method and Gupta method to investigate the feasibility of these segmentations in iris recognition. An enhanced method based on the techniques of the mentioned two methods is proposed, which can guarantee the accuracy of the iris identification system. The proposed method takes into account the elliptical shape of the pupil and iris. Eyelid detection is another step that has been included in this study as a part of segmentation stage. The dataset which is used for the study is CASIA v3 including the three subsets: Interval, Lamp and Twin. The performance measurement of the proposed method is done by determining the number of success images. The results of the study are very promising with an accuracy of 99.9% compared to the related existing methods.