Face recognition by using fractal encoding and backpropagation neural network

Presents a frontal view face recognition method by using fractal codes which are determined by a fractal encoding method from the edge pattern of the face region which covers eyebrows, eyes and a nose. In recognition process, these fractal codes are fed as inputs to a backpropagation neural network for learning and identifying a person. The experiments were performed with one in-room (ten distinct subjects) and one public database (the ORL face database which has twenty distinct subjects). The recognition rate is 90% for the in-room database and 85% for the ORL face database.