An effective pose invariant face recognition system with the aid of ABC optimized ANFIS

Abstract

Utilizing a stocked up database of faces, Face recognition recognizes or verifies one or else more individuals in the specified still or else video images of a scene. This is owing to its abundant vital applications in security, human–computer interactions, authentication, and surveillance. A method intended for efficacy face recognition system on the video sequence is splashed by this paper. Deducting its intricacies is the salient cause of this paper. In the proposed posture invariant face recognition technique, first database video clip is separated into variant frames. Preprocessing is executed for every frame for removing the noise utilizing Gaussian filtering. The Face is identified from the preprocessed image by utilizing Viola–Jones algorithm. Then effective features are excerpted from detected face. Next, the excerpted feature value will present as input to train for adaptive neuro-fuzzy inference system (ANFIS) classifier. ANFIS parameters are optimized through artificial bee colony ABC algorithm to derive prompt high acknowledgment throughout the training. Likely the query image’s features are employed for verifying the suggested recognition system performance. The technique will be achieved on the working platform in MATLAB in addition the outcome will be examined and matched with the prevailing techniques for elucidating the suggested video face recognition method’s performance.