A new model for face detection in cluttered backgrounds using saliency map and C2 texture features. Issue 4 (2nd October 2018)

• Record Type: Journal Article
• Authors: Saraf Esmaili, Somayeh; Maghooli, Keivan; Nasrabadi, Ali Motie
• Is Part Of: International journal of computers and applications. Volume 40:Issue 4(2018)
• Page Start: 214
• Page End: 222
• Publication Date: 2018-10-02
• Subjects: Face detection -- face candidate regions -- saliency map -- C2 texture features -- visual attention model; Computers -- Periodicals; Computer software -- Periodicals; Computer networks -- Periodicals; Multimedia systems -- Periodicals; Internet -- Periodicals; World Wide Web -- Periodicals; Minicomputers -- Periodicals; Microcomputers -- Periodicals; 004.05
• DOI: 10.1080/1206212X.2017.1399721
• Languages: English
• ISSNs: 1206-212X

Abstract

Abstract: This paper introduces a new model for face detection, which is based on the saliency map of a visual attention model and C2 features of the visual cortex HMAX model. The visual attention model is tuned by top-down skin color features for finding saliency maps of face candidate regions, and the top-down C2 texture features of the visual cortex HMAX model are used for face detection task. After the candidate regions of faces are found, the C2 texture features from them are extracted to categorize face or non-face regions using support vector machine classifier. A Caltech face database with background is utilized for testing the proposed model. Experimental results demonstrate that the proposed model provides plausible performance and it is reliable against variations in face illuminations, expressions and cluttered backgrounds.