Gender Classification of Consumer Face Images using Gabor Filters

Gender classification of consumer face images has been investigated using Gabor Filter method. Consumer images when taken into analysis such kind of classification make the task difficult for their diversity in appearance, pose, gesture and illumination conditions. The first step of this study is normalization of input image and next steps are extracting feature vector using Gabor filter which is further used as input for support vector machine SVM. SVM has proved to be finest supervised learning methodology for gender classification under applied experimental setup. Three face image databases [MUCT, AR and IMM] were utilized for training and testing. These databases were found precisely close to consumer face images for their variety of image acquisition procedure like use of different camera distance, subject pose, background and illumination.