Identifying Surgical Images Using Local Facial Features

Face identification is one of the most interesting and important research fields. The reasons come from the need of automatic face identifications and surveillance systems, the interest in human visual system on face identification, and the design of computer interface, etc. The facial appearance using surgical procedures is big a challenge for face recognition algorithms. These procedures shows the facial features and skin texture thereby providing a change in the appearance of face widespread acceptability and use of biometrics for person authentication has instigated several techniques for identification. Such technique is checking facial appearance using surgical measures that has raised a challenge for face recognition algorithms. There is rise popularity of plastic surgery and its effect on automatic face identification has attracted attention from the research group. However, the plastic surgery introduced nonlinear variations which remain difficult to be modeled by existing face identification systems. In this research, a multi objective evolutionary granular algorithm matching the facial images before and after plastic surgery. The algorithm first gives non-disjoint face granules at many levels of granularity. The granular information is assimilated using a multi objective genetic approach that at a time optimizes the selection of feature extractor for each face granule along with the weights of individual granules.