Iris Feature Extraction and Recognition using Unbalanced Haar Wavelets & Modified Multi Texton Histogram

Colored disk in the eye, the iris, attracted biometric Technologies to create potential and robust identification and verification systems designed for human identification in a no. of applications. Many techniques have been developed for iris recognition so far. Here, a new iris recognition system utilizing unbalanced wavelet coefficients and modified multi texton histogram feature coefficients is proposed. In our proposed system, iris part is localized from the eye images obtained from the iris database using active contour model with PMS. Then unbalanced wavelet packets coefficients and Modified Multi Texton Histogram (MMTH) features are extracted from the localized iris image. Then MMTH features extracted are clustered by using the MFCM technique. After clustering, the dimensionality of the features is reduced by using PCA. FFBNN_ABC algorithm is used in recognition process. The performance of our proposed iris recognition system is validated by using CASIA database and compared with other wavelets. Our proposed iris recognition system is implemented in the working platform of MATLAB.