Finding a good method for Skin Detection

Detection of skin in image is an important component of systems for detecting, and recognizing faces and hands. Thiswork presents a study of three important methods of the color pixel classification approach to skin segmentation:Support Vector Machines, Multi Layer Perceptrons, and K-nearest neighborhood algorithm. Our analysis of twodifferent types of representative color spaces using these classifiers shows that skin segmentation based on SupportVector Machines and RGB color pixel classification makes a real-time and accurate system

کلیدواژه ها:

Skin Detection ، Neural Networks ، Color space ، Supervised Classification ، Multi layer perceptron ، K nearest neighborhood ، Support Vector Machines ، Correct Detection Rate ، False Acceptance Rate ، False Rejection Rate