Download the full article
The correlation filters have been extensively studied in the field of face recognition. Correlation filters can be used directly on image pixels but also on proper feature spaces. We propose an effective algorithm for feature extraction using a genetic algorithm (GA). The algorithm generates a population of genomes that represents the 2D filter coefficient where new genomes are generated by crossover, mutation operations methods. GA feature correlation filters can achieve better improvements compared with standard filtering techniques.
Index Terms: Face, Recognition, Identification, Genetic, Algorithm, GA, MACE, Filter, Correlation.
Luigi Rosa, “Face Recognition Based on Genetic Algorithms For Feature Correlation”, July 2011.