Manuscript Number : IJSRSET511813
Facial Marks Soft Biometric for Identification of Identical Twins ,Similar Faces, Sibblings in Face Recognition
Authors(2) :-R. Prema, Dr. PShanmugapriya
We propose to utilize micro features, namely facial marks (e.g., freckles, moles, and scars) to improve face recogni-tion and retrieval performance. This Facial marks are used to differentiate the identical twins and similar face and siblings. Facial marks can be used in three ways: i) to supplement the features in an existing face matcher, ii) to enable fast retrieval from a large database us-ing facial mark based queries, and iii) to enable matching or retrieval from a partial or profile face image with marks. We use Active Appearance Model (AAM) to locate and segment the local or primary facial features (e.g., eyes, nose, and mouth). Then, Laplacian-of-Gaussian (LoG) and morphological operators are used to detect facial marks. Experimental results based on FERET and Mugshot databases show that the use of facial marks improves the identification accuracy of a state-of-the-art face recognition system from 92.96% to 93.90% and from 91.88% to 93.14%, respectively.
R. Prema
Face Recognition System, Facial Marks, Soft Bio-Metrics, Local Features, Active Appearance Model
Publication Details
Published in :
Volume 5 | Issue 1 | March-April 2018 Article Preview
Assistant Professor &Research Scholar Deprtment of CSE, SCSVMV University Kanchipuram,
Tamilnadu, India
Dr. PShanmugapriya
Associate Professor Department of CSE, SCSVMV University Kanchipuram, Tamilnadu, India
Date of Publication :
2018-03-23
License: This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) :
64-69
Manuscript Number :
IJSRSET511813
Publisher : Technoscience Academy
Journal URL :
https://ijsrset.com/IJSRSET511813