Optimizing modular image PCA using Genetic algorithm for expression - Invariant face recognition

Abstract

This paper proposes to use Genetic algorithm for optimizing the best Eigen vectors to improve the recognition accuracy of Modular image Principal Component Analysis (MIPCA) for face recognition. Modular Image PCA has been proved to be efficient in extracting features for recognizing face invariant to large expression. It is important to note that all the extracted features are not efficient and required for recognition. Using all the extracted features does not introduce any dimensionality reduction. In General most significant Eigen vectors are used for recognition. This research work concentrates on optimizing the best set features for face recognition using Genetic Algorithm. Results show that the use of Genetic algorithm on the most significant eigen vectors extracted by Modular Image Principal Component Analysis (MIPCA) optimizes the results obtained by Modular Image PCA for expression invariant face recognition.

Comparative Study of Local Binary Pattern Derivatives for Low Size Feature Vector Representation in Face Recognition

“…The Genetic algorithm (GA) is a stochastic algorithm that provides an efficient method of finding the global optimal solution. The GA uses a biological aspect of evolution (evolutionary computing) and is well suited for handling many computational problems [28,29,30,31].…”

“…After the new population is created, the fitness of this population will be evaluated. If the population achieves the desired fitness level or maximal number of generations (g n ), the procedure will be terminated [30].…”