Improved Fuzzy and Artificial Neural Networks based Skin Detection System for Effective Face Detection

摘要

Skin detection is one of the biometric methods that is used to identify any given face image using the main features of this face. In this research, skin detection for face recognition system is proposed based on Artificial Neural Network (ANN) method called as the Feed Forward Back Propagation Neural Network (FFBPNN). The ANN model is constructed with 7 layers input layer, 5 hidden layers each with 15 hidden units and an output layer. The Proposed System has three steps. Initially, the pixels of the different types of facial grey scale images are computed. Secondly, the computed pixels are compared with the original grey scale image based on the fuzzy rules. This process is done for the first pixel to the last pixel so that all the pixels which are present in the entire image can be included in the overall process. Finally, the FFBPNN is trained and tested for its accuracy of the face detection. The proposed system is tested with different facial images. The results of the proposed method were compared according with different existing methods to find the accuracy. Experimental results reveal that an average of 94.06% in accuracy is obtained for the proposed methodology.