Iris image classification based on texture and Fourier Mellin Transform features

Iris is one of the best biometrics features for human identification and verification. In this paper, an iris image classification framework based on texture and Fourier Mellin Transform (FMT) features is proposed. This framework is consisting of iris image segmentation, normalization, feature extraction and classification. We segmented iris image by using Hough transform. The next stage is image scaling of the iris region so that it has fixed dimensions. The dimensional inconsistencies between eye images are due to the stretching of the iris caused by pupil dilation from varying levels of illumination, varying imaging distance, rotation of the camera, head tilt, and rotation of the eye within the eye socket. We use FMT for making normalized images that are invariant in rotation and translation. Also, by using Gray Level Co-occurrence Matrix (GLCM), statistical features of normalized images are extracted. The results show that a proper algorithm can employed to reduce the dimension of the patterns to have a suitable classification when neural network is used to classify. The proposed way is evaluated on CASIA database standard. Results obtain the better accuracy than other common approach.