M. Rizon (Malaysia) and T. Kawaguchi (Japan)
Computer vision, face recognition, facedetection, facial features.
In this paper we propose a new algorithm to detect the irises with light reflection from a human face image. Firstly, feature points which are the candidates for the pupil of both eyes are extracted from the face image by using the feature template proposed by Lin and Wu. Next, the proposed algorithm computes a cost for each pair of feature points satisfying a spatial constraint. The cost is computed by searching for a circular region corresponding to the iris around each feature point. Finally, the algorithm determines a pair of feature points with the smallest cost to be the iris of both eyes. As the result of the experiment, we use all persons without spectacles in the first CD-ROM of the AR database [10]. Although face images have the reflected light spots near the center of the irises, the success rate of the proposed algorithm was 96.8[%].
Important Links:
Go Back
