Home // VISUAL 2016, The First International Conference on Applications and Systems of Visual Paradigms // View article

Local Edge/Corner Feature Integration for Illumination Invariant Face Recognition

Authors:
Almabrok Essa
Vijayan Asari

Keywords: Face recognition, Frei-Chen edge detector, modular histogram, chi-square similarity measure, libsvm classifier, local edge/corner feature integration (LFI).

Abstract:
In this paper, we present a new appearance based feature descriptor, named Local edge/corner Feature Integration (LFI), which efficiently summarizes the local structure of face images. LFI is a non-parametric descriptor that utilizes a combined edge/corner detection strategy. The proposed method uses the approach suggested by Frei and Chen for corner and edge detection with nine different masks. After we obtain the information about corners and edges of the image, for each pixel position, we describe the relationship of pixels to their local neighborhood from the local edge/corner features using the edges and corners information separately. Then, we concatenate these patterns together to form the final LFI feature vector. The performance evaluation of the proposed LFI algorithm is conducted on several publicly available databases and observed promising recognition rates.

Pages: 13 to 18

Copyright: Copyright (c) IARIA, 2016

Publication date: November 13, 2016

Published in: conference

ISSN: 2519-8645

ISBN: 978-1-61208-520-3

Location: Barcelona, Spain

Dates: from November 13, 2016 to November 17, 2016