@inproceedings{scholars3155,
            note = {cited By 2; Conference of 2012 International MultiConference of Engineers and Computer Scientists, IMECS 2012 ; Conference Date: 14 March 2012 Through 16 March 2012; Conference Code:93180},
          volume = {2195},
           title = {Fast Template matching method based on optimized metrics for face localization},
         address = {Kowloon},
            year = {2012},
       publisher = {Newswood Limited},
         journal = {Lecture Notes in Engineering and Computer Science},
           pages = {726--729},
            issn = {20780958},
          author = {Dawoud, N. N. and Samir, B. B. and Janier, J.},
            isbn = {9789881925114},
        keywords = {Computer science; Data processing; Image matching; Optimization; Template matching, Data sets; Face localization; Face position; Fast template matching; Illumination variation; Input image; Localization accuracy; Measurement methods; Normalized cross-correlation; Rectangular block; Similarity measurements; Similarity-matching; Sum of absolute differences; Sum of square differences, Face recognition},
             url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84867471927&partnerID=40&md5=02c053284f4cd3d6d78c25ea177c4047},
        abstract = {Recently, Template matching approach has been widely used for face localization problem. Normalized Cross-correlation (NCC) is a measurement method normally utilized to compute the similarity matching between the templates and the rectangular blocks of the input image to locate the face position. However, the NCC metric is always suffering to locate the face especially in the images with illumination variations. In this paper we proposed a fast template matching technique based on Optimized similarity measurement metrics namely: Sum of Absolute Difference (OSAD) and Sum of Square Difference (SSD) to overcome the drawback of NCC. Our results show the highest performance of OSAD compared with other measurements and the improvement of OSSD comparing with SSD as well. Two sets of faces namely Yale Dataset and MIT-CBCL Dataset were used to evaluate our technique with success localization accuracy up to 100.}
}