Multiscale Edge Detection Using Wavelet Maxima for Iris Localization

Automated personal identification based on biometrics has been receiving extensive attention over the past decade. Iris recognition, as an emerging biometric recognition approach, is becoming a very active topic in both research and practical applications and is regarded as the most reliable and accurate biometric identification system available. Common problems include variations in lighting, poor image quality, noise and interference caused by eyelashes while feature extraction and classification steps rely heavily on the rich textural details of the iris to provide a unique digital signature for an individual. As a result, the stability and integrity of a system depends on effective localization of the iris to generate the iris-code. A new localization method is presented in this paper to undertake these problems. Multiscale edge detection using wavelet maxima is discussed as a preprocessing technique that detects a precise and effective edge for localization and which greatly reduces the search space for the Hough transform, thus improving the overall performance. Linear Hough transform has been used for eyelids isolating, and an adaptive thresholding has been used for eyelashes isolating. A large number of experiments on the CASIA iris database demonstrate the validity and the effectiveness of the proposed approach.