Kinship Measurement on Face Images by Structured Similarity Fusion

Kinship Measurement on Face Images by Structured Similarity Fusion

Publication Date : 2023-08-05
Author(s) :

Akash R, Sukanya S. T
Conference Name :

International Conference on scientific innovations in Science, Technology, and Management (NGCESl-2023)
Abstract :

Kinship verification, which is a challenging problem in computer vision and pattern discovery. It has several applications, such as organizing photo albums, recognizing resemblances among humans, and finding missing children. A system for facial kinship verification based on several kinds of texture descriptors (local binary patterns, local ternary patterns, local directional patterns, local phase quantization, and binarized statistical image features) with pyramid multilevel (PML) face representation for feature extraction along with our proposed paired feature representation and our proposed robust feature selection to reduce the number of features. The proposed approach consists of the following three main stages: (1) face pre-processing, (2) feature extraction and selection, and (3) kinship verification. Extensive experiments are conducted on five publicly available databases (Cornell, UB KinFace, Family 101, KinFace W-I, and KinFace W-II). Additionally, a wide experiment for each stage to find the best and most suitable settings. Many comparisons with state-of-the-art methods and through these comparisons, it appears that our experiments show stable and good results.

No. of Downloads :

2