Gender Recognition From Face Images Based on Textural Analysis and Machine Learning Approach

The system gender classification from face images based on textural analysis and an artificial neural network. Face granulation process is applied for input faces for slices representation using Difference of gaussian approach. Here Weber’s Local Descriptor is used for gender recognition. Here this local descriptor extends it by introducing local spatial information through divide an image into a number of blocks, calculate WLD descriptor for each block and concatenate them. This spatial WLD descriptor has better discriminatory power and followed by statistical features are evaluated which is useful to distinguish the maximum number of samples accurately and probabilistic neural network with RBF kernel classifier will be used as classifier. The simulated results will be shown that spatial WLD descriptor with used classifier gives much better accuracy with lesser algorithmic complexity than state of the art gender recognition approaches