Automated categorization of person by gender/ethnicity

As one of the most successful applications of image analysis and understanding, face recognition has recently gained significant attention. Over the last ten years or so, it has become a popular area of research in computer vision and one of the most successful applications of image analysis and understanding. The purpose of this report is to research and understand various facial feature extractors that has been previously been constructed and test the accuracy rates on two such extractors. The focus will be on Gender (Male & Female) and Ethnicity (Chinese, Malay, Indian & Others). Two different feature extractors will be discussed in this report; Gabor wavelet & Gray value. Images are collected to create a database for this project and these images will pre-processed according to project requirements such as gray-scaling, cropping and rotation before extracting the data from them. Once the data are extracted, they are put through a SVM classifier to determine their accuracy. The results from the classifier will then be analyzed and compared to provide a platform on the variation of accuracy due to the different extraction methods, number of images in each set and between Gender & Ethnicity.Bachelor of Engineerin