Face Recognition Based GLOH Descriptor and Integration of Local Features

In order to reduce the computational complexity of high-dimensional feature descriptor and improve the accuracy of recognition algorithm, the paper proposes a face recognition algorithm based on GLOH descriptor, with scale and geometric invariant. In the paper, face image is divided into four separate sub-regions and clusters the feature points extracted from the every region. In order to describe the feature operator and feature matching more effectively, the different region is to give different weight values according to the distinctiveness. The method of the whole combining with local clustering sub-region is employed for face recognition. The effectiveness of the algorithm is verified by experiments on the ORL face image database, which demonstrates good stability and robustness especially under the conditions of some confounding factors such as different facial expressions, postures and so on.