Effect of Purposeful Feature Extraction in High-dimensional Kinship Verification Problem

Recently, researchers have shown an increased interest in kinship veri cation via facial images in the eld of computer vision. The matter of fact is that kinship veri cation is done according to similarities of parent and child faces. To this end, we need more local features extraction. All the methods reviewed so far, however, su er the fact that they have divided images into distinct block, to extract more local features. The main problem has two aspects: aimless division and features extraction from unnecessary regions that lead to overlapping, noise and reduction of classi cation rate. In this paper, at rst, the main parts of face such as eyes, nose and mouth are detected along with the whole face image. Then they will be used for feature extraction. In order to reduce feature vectors redundancy, new method of feature selection named as Kinship Feature Selection (KinFS), based on Random Subset Feature Selection (RSFS) algorithm is proposed. This method reduces the redundancy and improves veri cation rate by selecting e ective features. The experiment results show that purposeful feature extraction by proposed KinFS method are ecient in improving kinship veri cation rate.