ADAPTIVE INITIAL CONTOUR AND PARTLY-NORMALIZATION ALGORITHM FOR IRIS SEGMENTATION OF BLURRY IRIS IMAGES

Iris segmentation is a process to isolate the accurate iris region from eye image for recognition. on non-ideal and noisy images with active contour. Nevertheless, it currently unclear how contour responds blurry or motion blur, which presents significant obstacle in segmentation. Investigation images, especially initial position, rarely published must be clarified. Moreover, evolution convergence speed remains challenge as segments precise boundary. Therefore, this study carried out experiments achieve an efficient algorithm terms of accuracy fast execution, according aforementioned concerns. In addition, was explored clarify its position. order accomplish these goals, Wiener filter morphological closing were used preprocessing reflection removal. Next, adaptive (AIC), δ, stopping function integrated create Chan-Vese (ACVAC) algorithm. Finally, partly -normalization method normalization feature extraction designed by selecting most prominent features. The findings revealed that outperformed other contour-based approaches computational time accuracy. It proved position could established. This solve inaccurate images.