期刊名称：Oriental Journal of Computer Science and Technology
印刷版ISSN：0974-6471
出版年度：2011
卷号：4
期号：1
页码：01-09
出版社：Oriental Scientific Publishing Company
摘要：Human face detection is one of the vital techniques in computer vision. It plays so importantrole in a wide variety of applications such as surveillance systems, video tracking applications andimage database management. In this paper a new method to detect faces with different pose in colourimages, is proposed. Skin colour, lip position, face shape information and statistical texture propertiesare the key parameters for developing fussy rule based classifiers to extract face candidate from animage. The algorithm consist of two main parts: detecting frontal face system and detecting profile facesystem. In first step, skin regions are identified in HSI colour space, using fuzzy system, applyingdistance of each pixel colour to skin colour cluster as input and producing a skin-likelihood image inoutput. The regions owning the most likelihood of belonging to skin are labelled and enter the frontalface detecting part . To extract frontal face regions ,fuzzy rule based system is used, applying face andlip position, lip area data and face shape. The detected faces are removed and remain areas are testedby the profile face finding algorithm. This algorithm utilizes statistical texture properties of ear to verifyprofile face detection. By this system, 98%, 90% and 83.33% detection rates are achieved, respectivelyfor frontal, near frontal and profile faces
