Title: An efficient similarity search using a combination between descriptors: a case of study in human face recognition

Authors: Nawfal El Maliki; Hassan Silkan; Mounir El Maghri

Addresses: LAROSERI Laboratory, Computer Science Department, University Chouaib Doukkali, El Jadida, Morocco ' LAROSERI Laboratory, Computer Science Department, University Chouaib Doukkali, El Jadida, Morocco ' Department of Mathematics and Computer Science, Faculty of Sciences Aïn Chock, Hassan II University, Casablanca, Morocco

Abstract: Face recognition is one of the important fields of search in computer vision. Its principle consists to look for images that represent the similar faces to a given face image the image request. This process is done by extracting a set of features of the request image then making comparison between features generated by the request one and the others extracted from whole face image database. Recently, numerous face representation and classification methods have been proposed in the literature. Nevertheless, many issues related to indexing, combination of adequate descriptors and time computing have not yet been solved. In this paper, we deal with problems related to features combination and this, by conceiving a preformat content-based image retrieval that is mainly oriented to handle face authentication challenges. Its convivial interface allows to user the selection of appropriate weighting coefficient values associate to each feature based on human judgment in order to enhance the retrieval performance. We have tested our proposed method on ORL database by using a set of known features. The obtained results show the performance of our proposed method.

Keywords: face recognition; principal component analysis; PCA; local binary patterns; LBP; features; combination; content-based image retrieval; CBIR; histogram of oriented gradients; HOG; Fourier descriptor; distances.

DOI: 10.1504/IJKESDP.2019.103897

International Journal of Knowledge Engineering and Soft Data Paradigms, 2019 Vol.6 No.3/4, pp.170 - 184

Received: 28 Jul 2018
Accepted: 02 Feb 2019
Published online: 02 Dec 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article