شبر سلمان باقر الخفاجي

Face detection plays a main role in many of the application normally faces can be detected by using classifiers and feature extraction but some of the images which has low quality like dark images, dull images, shadow images may cause problems in face detection i.e could not recognized properly to avoid this problem we are going to implement a method that could find the quality of an image and according to that we are going to classify dark, dull, shadow and illuminated images. Based on the quality we are applying techniques like homomorphic, histogram equalization to increase its quality and implementing the face detection technique and recognizing the person properly without any problem .In this after enhancing the quality we are going to extract the LBP features and match with the database using SVM technique and detecting the person. By this we can get mostly 90-95% of accuracy due to enhancing of the quality of image .