Detection of facial parts in kinship verification based on edge information

Kinship verification using facial images is gaining substantial attention by different researchers in the field of computer vision, pattern recognition and image processing. Kinship verification via facial images is motivated by the findings that individuals with some genetic relations have certain similarities in their facial appearance. These similarities in facial appearance is a result of inherited facial features from one generation to next generation. Most of the papers based on kinship verification focus on complete facial appearance of kinship image pairs for finding kinship relations. Rather, researchers should focus on salient facial parts of kinship image pairs. In this paper, we present a relevant and effective method to detect and extract different facial parts in kinship image pairs. A detailed output is shown for father-son image pair and performance accuracy is evaluated for different kinship datasets for robustness of the proposed work. The experimental results show that proposed method effectively detect and extract different facial parts in kinship image pairs and would work as a novel algorithm for kinship verification.