Welcome to the InfoSci Platform
Histogram of Oriented Directional Features for Robust Face Recognition

Histogram of Oriented Directional Features for Robust Face Recognition

Almabrok Essa, Vijayan K. Asari
Copyright: © 2016 |Volume: 4 |Issue: 3 |Pages: 17
ISSN: 2166-7241|EISSN: 2166-725X|EISBN13: 9781466693807|DOI: 10.4018/IJMSTR.2016070103
Cite Article Cite Article

MLA

Essa, Almabrok, and Vijayan K. Asari. "Histogram of Oriented Directional Features for Robust Face Recognition." IJMSTR vol.4, no.3 2016: pp.35-51. http://doi.org/10.4018/IJMSTR.2016070103

APA

Essa, A. & Asari, V. K. (2016). Histogram of Oriented Directional Features for Robust Face Recognition. International Journal of Monitoring and Surveillance Technologies Research (IJMSTR), 4(3), 35-51. http://doi.org/10.4018/IJMSTR.2016070103

Chicago

Essa, Almabrok, and Vijayan K. Asari. "Histogram of Oriented Directional Features for Robust Face Recognition," International Journal of Monitoring and Surveillance Technologies Research (IJMSTR) 4, no.3: 35-51. http://doi.org/10.4018/IJMSTR.2016070103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

This paper presents an illumination invariant face recognition system that uses directional features and modular histogram. The proposed Histogram of Oriented Directional Features (HODF) produces multi-region histograms for each face image, then concatenates these histograms to form the final feature vector. This feature vector is used to recognize the face image by the help of k nearest neighbors classifier (KNN). The edge responses and the relationship among pixels are very important and play the main role for improving the face recognition accuracy. Therefore, this work presents the effectiveness of using different directional masks for detecting the edge responses on face recognition accuracy, such as Prewitt kernels, Kirsch masks, Sobel kernels, and Gaussian derivative masks. The performance evaluation of the proposed HODF algorithm is conducted on several publicly available databases and observed promising recognition rates.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.