Abstract
This paper proposes the use of strings as a new local descriptor for face recognition. The face image is first divided into nonoverlapping subregions from which the strings (words) are extracted using the principle of chain code algorithm and assigned into the nearest words in a dictionary of visual words (DoVW) with the Levenshtein distance (LD) by applying the bag of visual words (BoVW) paradigm. As a result, each region is represented by a histogram of dictionary words. The histograms are then assembled as a face descriptor. Our methodology depends on the path pursued from a starting pixel and do not require a model as the other approaches from the literature. Therefore, the information of the local and global properties of an object is obtained. The recognition is performed by using the nearest neighbor classifier with the Hellinger distance (HD) as a comparison between feature vectors. The experimental results on the ORL and Yale databases demonstrate the efficiency of the proposed approach in terms of preserving information and recognition rate compared to the existing face recognition methods.
Highlights
A New Local Descriptor Based on Strings for Face RecognitionHicham Zaaraoui ,1 Abderrahim Saaidi, Rachid El Alami ,3 and Mustapha Abarkan. Received 11 April 2019; Revised 1 September 2019; Accepted 20 January 2020; Published 18 February 2020
Face recognition is a biometric technology to identify an individual from a picture of his face, which is a passive and nonintrusive system to verify the identity of a person, and this field has progressed significantly in recent years due to its many applications primarily in forensic sciences, driver’s licenses and passport verification, missing identification, surveillance systems, social networks, access control, and location of missing persons [1, 2]
Our study focuses on the variation of the number of blocks in an image, the number of visual words in a dictionary, and the dictionary words extracted from the face images to improve the face recognition rate. e proposed algorithm is evaluated on the ORL (Olivetti Research Laboratory, Cambridge) [9] and Yale [10] databases. e results obtained are very satisfactory in terms of recognition rate and efficiency
Summary
Hicham Zaaraoui ,1 Abderrahim Saaidi, Rachid El Alami ,3 and Mustapha Abarkan. Received 11 April 2019; Revised 1 September 2019; Accepted 20 January 2020; Published 18 February 2020. Is paper proposes the use of strings as a new local descriptor for face recognition. E face image is first divided into nonoverlapping subregions from which the strings (words) are extracted using the principle of chain code algorithm and assigned into the nearest words in a dictionary of visual words (DoVW) with the Levenshtein distance (LD) by applying the bag of visual words (BoVW) paradigm. Each region is represented by a histogram of dictionary words. E histograms are assembled as a face descriptor. E recognition is performed by using the nearest neighbor classifier with the Hellinger distance (HD) as a comparison between feature vectors. E experimental results on the ORL and Yale databases demonstrate the efficiency of the proposed approach in terms of preserving information and recognition rate compared to the existing face recognition methods Our methodology depends on the path pursued from a starting pixel and do not require a model as the other approaches from the literature. erefore, the information of the local and global properties of an object is obtained. e recognition is performed by using the nearest neighbor classifier with the Hellinger distance (HD) as a comparison between feature vectors. e experimental results on the ORL and Yale databases demonstrate the efficiency of the proposed approach in terms of preserving information and recognition rate compared to the existing face recognition methods
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
