Enhanced kinship verification analysis based on color and texture handcrafted techniques

Abstract

Nowadays, kinship verification is considered an attractive research area with a great interest in computer vision. It significantly affects applications in the real world, such as finding missing individuals, forensics, and genealogical research. However, verifying kinship relations between people using facial images is not straightforward. Many limitations affect kinship verification accuracy. Therefore, this paper proposes a new approach for verifying kinship based on facial image analysis. The proposed approach goes into six stages: preprocessing, feature extraction, feature normalization, feature fusion, feature representation, and kinship verification. The preprocessing stage is responsible for converting RGB images into other color models. Different types of handcrafted feature descriptors (i.e., color and texture descriptors) are extracted in the feature extraction stage. The texture features are represented by scale invariant feature transform (SIFT), local binary pattern (LBP), and heterogeneous auto-similarities of characteristics (HASC), whereas the color features are represented by color correlogram (CC) and dense color histogram (DCH). Then, all the features are set to the same range in the feature normalization stage to be suitable for feature fusion. The feature fusion stage takes place where the different types of features are concatenated together. Next, in the feature representation stage, the parent and child features are gathered into one feature vector. Finally, the kinship verification stage produces the final decision of being kin or non-kin using the gentle AdaBoost ensemble classifier. KinFaceW-I and KinFaceW-II datasets were used to evaluate the proposed approach, where the obtained results were 79.54\% and 90.65\%, respectively. It is noteworthy that the proposed approach outperforms many state-of-the-art approaches that verify kinship, including those dependent on metric learning and deep convolutional neural nets (CNNs).