A Face Recognition Framework for Illumination Compensation Based on Bio-Inspired Algorithms

It is possible to find in the literature a wide range of techniques employed for face recognition. Hence, to select a technique or set of techniques and tune their respective parameters become an optimization task. In this paper, we present a face recognition framework with the aid of bio-inspired optimization algorithms. This approach implements several preprocessing and feature extraction techniques, and the optimization algorithm is responsible for choosing which strategies to use, as well as tunning their parameters. In this work, we analyzed the performance of two optimization algorithms, namely Particle Swarm Optimization (PSO) and Differential Evolution (DE) aiming to address the illumination compensation problem. The well known Yale Extended B database is used in the classification task. The results obtained show that the proposed approach is competitive with literature achieving the average recognition rate of 99.95% with DE.