A Modified Approach for Face Recognition using PSO and ABC Optimization

Face Recognition (FR) has established noteworthy attention in the recent years due to its wide applications in various fields. FR technology uses image processing algorithms for comparing and verifying the human faces. This paper proposes a FR system which employs a novel mixture of Fast Fourier Transform (FFT), Discrete Cosine Transform (DCT) and Swarm Intelligence (SI). FFT and DCT help in extracting the features efficiently. PSO and ABC are used for feature selection that finds the best solution for a given problem. Many hybrid approaches are used to overcome its weakness and more over fit for various applications. The usage of transformation techniques helps in reducing image information redundancy. Experimental results show that there is a notable reduction in the number of features and a considerable increase in the recognition rate