An Image Enhancement Technique for Poor Illumination Face Images

Abstract

Face recognition is used to identify one or more persons from still images or a video image sequence of a scene by comparing input images with faces stored in a database. The face images used for matching the image in the database has to be of good quality with normal lighting condition and contrast. However, face images of poor illumination or low contrast could not be recognized properly. The objective of the work is to enhance the facial features eyes, nose, and mouth for poor contrast facial images for face recognition. The image enhancement is done by first detecting the face part, then applying contrast-limited adaptive histogram equalization technique and thresholding to enhance the facial features. The brightness of the facial features is enhanced by using logarithm transformation. The proposed image enhancement method is implemented on AR database, and the face images appear visually good when compared to original image. The effectiveness of the enhancement method is compared by analyzing the histogram.