Iris feature extraction based on gray-scale morphological skeleton

Iris recognition is one of the most reliable biometric technologies. Iris feature extraction is a key issue in iris recognition. This paper proposes a novel method to extract the features of space domain from iris image, which uses gray-scale morphological filtering. It is well known that the skeleton which shows the features of images is extracted from binary images by morphological filtering. The skeleton of gray scale images can be also extracted by gray-scale morphological filtering. In order to extract the features of the iris, we apply the gray-scale morphological filtering to the iris image and obtain its skeleton. The binary skeleton which is regarded as the iris code is obtained by threshold processing. The Hamming distance was employed for classification of iris codes. In the proposed method, the Hamming distance of intro class and inter class are separated completely.