Geometric shaped facial feature extraction for face recognition

Facial feature extraction is the process of extracting face component features like eyes, nose, mouth, etc from human face image. Facial feature extraction is very much important for the initialization of processing techniques like face tracking, facial expression recognition or face recognition. Among all facial features, eye localization and detection is essential, from which locations of all other facial features are identified. However, the existing face recognition techniques failed to identify the exact person. In order to overcome this issue, Geometric Shaped Facial Feature Extraction for Face Recognition (GSF²EFR) is designed for identifying the exact person by finding the center and corners of the eye using eye detection and eye localization modules. An input facial image is given where the face map gets initialized and processed in the form of coarse-to-fine manner with two modules. In the first module, eye detector is used to detect the eye pattern using Gabor filter. In the second module, the location of eye center is found using SVM classifier to reduce the eye localization time. Finally, after locating the center and corners of eye fiducial points are found from which the face of an individual gets recognized. The better performance of proposed GSF²EFR system is measured in terms of eye detection accuracy, eye localization time and true positive rate.

I. Introduction

Face recognition is a challenging area in computer vision and pattern recognition because of its varied facial expressions, poses and illumination. Face recognition and facial expression recognition is very essential in areas like access management, human-computer communication, production control, e-learning, fatigue driving recognition and emotional robot. Facial expression method is categorized depending on the input data to sequence video or static image.