Feature based face recognition using slopes
No Thumbnail Available
Date
2016
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
UMT.Lahore
Abstract
Face recognition from image is a popular problem in biometrics research. In the last decade, a lot of research has been done in this area. The actual advantages of face based identification over other biometrics are uniqueness and acceptance. Face recognition is one of the most relevant applications of image analysis. It’s a true challenge to build an automated system which equals human ability to recognize faces. The advantage of face based identification over other biometrics is its wide acceptability because it does not require any keys, tokens, smart cards, PINs, plastic cards, passwords etc., In this research work, face recognition has been done using various feature based approaches. In this research, new approaches for feature based face recognition are presented. In these approaches, new features are proposed and evaluated. The main contribution of this paper is usage of a slope table along with other features for face recognition. That are the Random Projection, Regional Properties and Safety Driving Features. The slopes of different fiducial points of facial components (left eye, right eye, nose and lips) are computed to fill the slope table. These features are merged with the features extracted by the above mentioned approaches.. These approaches are compared on the UMT Face data set, on the metrics of accuracy and time efficiency. The results show that the combination of all the extracted features approach outperform the other computed approaches.