Shape-Driven Gabor Jets for Face Description and Authentication

• Published in: IEEE transactions on information forensics and security Vol. 2; no. 4; pp. 769 - 780
• Main Authors: Gonzalez-Jimenez, D., Alba-Castro, J.L.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-12-2007; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; AR face database; Authentication; BANCA database; Computer vision; Data mining; Detectors; elastic bunch graph matching (EBGM); face authentication/recognition; Face detection; Face recognition; Feature extraction; Gabor jets; Jets; Lighting; Mathematical analysis; Mouth; Nose; ridges and valleys; shape contexts; Spatial databases; Studies; Valleys; XM2VTS database
• ISSN: 1556-6013; 1556-6021
• DOI: 10.1109/TIFS.2007.910238

This paper proposes, through the combination of concepts and tools from different fields within the computer vision community, an alternative path to the selection of key points in face images. The classical way of attempting to solve the face recognition problem using algorithms which encode local information is to localize a predefined set of points in the image, extract features from the regions surrounding those locations, and choose a measure of similarity (or distance) between correspondent features. Our approach, namely shape-driven Gabor jets, aims at selecting an own set of points and features for a given client. After applying a ridges and valleys detector to a face image, characteristic lines are extracted and a set of points is automatically sampled from these lines where Gabor features (jets) are calculated. So each face is depicted by R 2 points and their respective jets. Once two sets of points from face images have been extracted, a shape-matching algorithm is used to solve the correspondence problem (i.e., map each point from the first image to a point within the second image) so that the system is able to compare shape-matched jets. As a byproduct of the matching process, geometrical measures are computed and compiled into the final dissimilarity function. Experiments on the AR face database confirm good performance of the method against expression and, mainly, lighting changes. Moreover, results on the XM2VTS and BANCA databases show that our algorithm achieves better performance than implementations of the elastic bunch graph matching approach and other related techniques.