Abstract
Robust facial feature extraction is an effective and important process for face recognition and identification system. The facial features should be invariant to scaling, translation, illumination and rotation, several feature extraction techniques may be used to increase the recognition accuracy. This paper inspects three-moment invariants techniques and then determines how is influenced by the variation which may happen to the various shapes of the face (globally and locally) Globally means the whole face shapes and locally means face part's shape (right eye, left eye, mouth, and nose). The proposed technique is tested using CARL database images. The proposal method of the new method that collects the robust features of each method is trained by a feed-forward neural network. The result has been improved and achieved an accuracy of 99.29%.
Highlights
Face recognition techniques are very important, especially in security systems
This work proposes a technique to recognize faces using moment shape descriptors applied on the global whole face and different face parts (Right eye, left eye, mouth, and nose), a feature selection process based on Sequential Forward Feature Selection (SFFS) and Feed Forward Neural Network to test this technique on face images of CARL database
RELATED WORK: Extensive studies have been proposed for face recognition in [11], [12], some of these studies used the moment invariant techniques as a robust statistical shape descriptor [7], [13]
Summary
Face recognition techniques are very important, especially in security systems. To identify a face shape, the face should be represented with specific features [1]. The most utilized descriptors are the moment invariants which go about as "The first choice descriptors" [3] which is a standout amongst the critical strategies for making an estimate of the implementation about different descriptor types. Regardless of those distributed studies, a considerable measure of issues even must be solved [3]-[6]. This work proposes a technique to recognize faces using moment shape descriptors applied on the global whole face and different face parts (Right eye, left eye, mouth, and nose), a feature selection process based on SFFS and Feed Forward Neural Network to test this technique on face images of CARL database
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have