Skip to Main Content
Iris biometric systems identify individuals by comparing the characteristics of the iris acquired by the acquisition sensors. When reflections are present in the iris image, the portion of the image covered by reflections must be discarded from any further comparison since it can produce false matches. The paper presents a methodology for reflections identification in iris biometric images based on neural networks. In particular, this paper proposes a set of features which can be extracted from the iris image and that can be effectively used to achieve an accurate identification of the reflection position using a neural network Moreover, the paper presents how the radial symmetry operator can be used as a proper feature to identify the reflections in iris images. The method is general and can be used in any biometric system based on iris images.