A Neuro-Cognitive Approach for Iris Recognition Using Back Propagation

Abstract

Abstract: This article presents a biometric technique for identification of a person using the iris image. The iris is first segmented from the acquired image using an edge detection algorithm. The disk shaped area of iris is transformed into rectangular form. Since the image is in high resolution it will require a soaring number of neurons in the input layer, if the image data is directly clamped to the neural network, making the problem irrepressible. Resolution to this problem is sought through compression of data using a bottleneck network. The recognition neural network is trained using the compressed data using back propagation. The overall accuracy of system is 95.2 percent after reasonable training. Key words: Iris Neural networks Compression Back propagation Biometrics Image processing