An Adaptive Central Force Optimization (ACFO) and Feed Forward Back Propagation Neural Network (FFBNN) based iris recognition system

Article type: Research Article

Authors: Shaikh, Nuzhat F.^{a; *} | Doye, Dharmpal D.^b

Affiliations: [a] Department of Computer Engineering, Modern Education Society’s College of Engineering, Pune | [b] Department of Electronics and Telecommunication, SGGSIET, Nanded

Correspondence: [*] Corresponding author. Nuzhat F. Shaikh, Department of Computer Engineering, Modern Education Society’s College of Engineering, Pune. Tel./Fax: +91 9822336455; E-mail: nfshaikh76@gmail.com.

Abstract: Iris Recognition that emerged two decades back has a number of algorithms developed and vast amount of work has been carried out since its inception. Iris recognition uses pattern-recognition techniques based on high-resolution images of the person. This paper proposes a novel iris recognition system using FFBNN-ACFO. Initially the given input images are preprocessed using adaptive median filter to remove noise. Then the features which are extracted from the preprocessed image are used to train the FFBNN. During training, FFBNN parameters are optimized by ACFO to get high recognition accuracy. In the testing phase sufficient number of iris images, are utilized to analyze the performance of the proposed iris recognition system. The results of the proposed method are compared with FFBNN-AAPSO, FFBNN-PSO, and FFBNN techniques. The comparison result shows that the proposed iris recognition system based on FFBNN-ACFO, gives higher recognition accuracy than the existing iris recognition systems.

Keywords: Feed forward back propagation neural network (FFBNN), adaptive median filter, feature extraction, iris recognition, central force optimization (CFO)

DOI: 10.3233/IFS-151921

Journal: Journal of Intelligent & Fuzzy Systems, vol. 30, no. 4, pp. 2083-2094, 2016