AN EFFECTIVE DEEP LEARNING MODEL FOR IRIS RECOGNITION PROBLEM

Abstract

Recognition problem on human parts is one of the most important problems in bioinformatics, they have many practical applications especially in the field of security. Biometric characteristics are currently being researched as: Fingerprint, iris, DNA, voice, body,… The iris is one of the best property for recognition. Traditional methods are often based on iris matching to give good results in favorable conditions. However, the precision of the methods decreased significantly in unfavorable conditions. In this paper, we propose a deep learning model based on the artificial neural network to identify and classify objects by iris. The model can produce high accuracy in disadvantaged conditions.