Facial image detection with multiple filters and neural network for classification
G. Hemalatha, C. P. Sumathi · 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI) · 2017
Face detection is still a challenging factor in biometric research. Face detection technologies has wide range of applications. Many advanced techniques have been introduced for detection of human face but the efficiency differs based on the techniques. The detection becomes complicated due to various external factors like lightening, variation in the pose, expression etc. In order to minimize the disturbing factors and to improve the quality of image, preprocessing of image becomes essential and it should be an efficient technique. The process involved in this work is preprocessing with multiple filters that is the median and gabor filter for detecting the face in a image. The median filter is used to remove the noise in the image and 2D gabor filter for extracting the features from the image, based on the extracted features, the image is classified as face or non-face using a supervised classification technique with Feed Forward neural network. Face database used for training the network is Yale face database.