Improved Face Detection System

Biometric applications have been using face detection approaches for security purposes such as human–crowd surveillance, many security-related areas, and computer interaction. It is a crucial arena of recent research because there is no fixed system to find the faces in a test image. Face detection is challenging due to varying illumination conditions, pose variations, the complexity of noises, and image backgrounds. In this research, we present a system that can detect and recognize in the face by different pre-processing techniques; Viola-Jones process adds together Haar Cascade, GLCM & Gabor Filter and Support Vector Machine (SVM), is proposed for gaining better accuracy level in the detection of facial portions and recognition of faces. The proposed system has achieved better than other face detection and recognition systems. The experiment has done in a MATLAB environment on different images of the FEI Face, Georgia Tech faces, Faces95, Faces96, and MITCBCL databases. The experimental result achieves detection of faces that represent reasonable accuracy rates of an average of 98.32%.