Feature Selection using Particle Swarm Optimization for Thermal Face Recognition

This paper presents an algorithm for feature selection based on particle swarm optimization (PSO) for thermal face recognition. The total algorithm goes through many steps. In the very first step, thermal human face image is preprocessed and cropping of the facial region from the entire image is done. In the next step, scale invariant feature transform (SIFT) is used to extract the features from the cropped face region. The features obtained by SIFT are invariant to object rotation and scale. But some irrelevant and noisy features could be produced with the actual features. Unwanted features have to be removed. In other words, optimum features have to be selected for better recognition accuracy. Since PSO is an optimization method, which works with the principle of local as well as global searches for finding optimum set of features. Here, this process has been implemented to select a subset of features that effectively represents original feature extracted for better classification convergence. Finally, minimum distance classifier is used to find the class label of each testing images. Minimum distance classifier acts as an objective function for PSO. In this work, all the experiments A. Seal (&) S. Ganguly D. Bhattacharjee M. Nasipuri Department of Computer Science and Engineering, Jadavpur University, Kolkata, India e-mail: [email protected] S. Ganguly e-mail: [email protected] D. Bhattacharjee e-mail: [email protected] M. Nasipuri e-mail: [email protected] A. Seal C. Gonzalo-Martin Center for Biomedical Technology, Universidad Politecnica de Madrid, Madrid, Spain e-mail: [email protected] Springer India 2015 R. Chaki et al. (eds.), Applied Computation and Security Systems, Advances in Intelligent Systems and Computing 304, DOI 10.1007/978-81-322-1985-9_2 25 have been performed on UGC-JU thermal face database. The maximum success rate of 98.61 % recognition has been achieved using SIFT and PSO for frontal face images and 90.28 % for all images.