HUMAN FACE CLASSIFICATTON FOR SECURITY SYSTEM
Toshiki Iso, Yasuhiko Watanabe, Katsunori Shimohara · 1996
We propose a method for classifying faces that uses only simple image processing. The method can rapidly judge whether the person detected by a monitor camera is masked or not. Our algorithm has two stages. The first stage rletects the facial patttirii by template matching wit,li a ncw siinilarity assessnienl. The second stage jiirlges whetlicr the face is masked or not by using optimal features in tile spatial frequency domaiu. Indeed. experiments show th& oui algorithin can form itxi effective security system.