Open AccessAn Empiric Model of Face Detection based on RGB Skin Tone Color
Author(s) -
. Robin,
Ferawaty,
Jusin,
Hita,
Syanti Irviantina,
Saut Dohot Siregar,
Wenripin Chandra
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1230/1/012014
Subject(s) - artificial intelligence , rgb color model , computer vision , computer science , face detection , face (sociological concept) , object class detection , tone (literature) , segmentation , digital camera , facial recognition system , pattern recognition (psychology) , art , social science , literature , sociology
Modern smartphone has been society’s lifestyle where every smartphone has a high quality digital camera with all the digital image processing feature. One of those features are face detection. Face detection is the most basic process of any face processing operations. Most digital images are stored in the form of RGB (Red, Green, Blue) data. In this research, detection of human face features is done by using different RGB values in digital images. After applying skin tone color segmentation on digital images, detection area will be optimized using human head properties by eliminating non-human face skin tone area. The experiment shows that the detection is mostly accurate for images but there is issue on low light face skin color captured by digital cameras. From the experiment of our model using 10 sample face images, face can be detected on 9 of them, while in 1 image, the face cannot be detected at all because of low light condition.