Live Detection of Face Using Machine Learning with Multi-feature Method

Facial expression detection (FED) and extraction show the most important role in face recognition. This research proposed a new algorithm for automatic live FED using radial basis function; Haar discrete wavelet transform and Gray-level difference method is used for feature extraction and classification. Detect edges of the facial image by Otsu algorithm. The implementation results worked on Japanese Female Facial Expressions and Cohn–Kanade Extended (CK+) database for facial expression. The other database used for face detection process, namely, CMU, BioID, Long Distance, and FEI. It is usually possible for practical recognition system to record (by a camera or by computer) multiple face images from each subject. Choosing face images with high tone for recognition is a promising strategy for improving the system performance. We propose a learning to rank based (solid basic structure on which bigger things can be built) for evaluating the face image quality. But we improved limitations of this algorithm using contrast enhancement. We solved the problem of long distance and low contrast images. In the initial preprocess stage; perform median filtering for removing noise from an image. This step enhances the feature extraction process. Finding an image from the image components is a typical task in pattern recognition. The detection rate has reached up to 100% for expression recognition. The proposed system estimates the value of precision and recall. This algorithm is compared with the previous algorithm and our proposed proved better than previous algorithms.