Color-based Face Detection using Combination of Modified Local Binary Patterns and embedded Hidden Markov Models

This paper presents an improved face detection method for color images. We propose a boosted skin-color model in RGB space which can reduce more effectively noises forming from similar skin colors. With our solution, we receive more reasonable skin detection for different human races. We modifed local binary pattern (LBP) by adding a set of spatial templates. This LBP considers both principal local shapes and spatial textures of facial components. Human face is represented by LBP histogram. Moreover, the grayscale image of human face is changed to discrete cosine transform (DCT) coefficients used in embedded hidden Markov models (eHMMs). A modified LBP (mLBP) histogram matching and eHMMs are composed to hierarchical classifier to determine whether skin regions are faces or not. The experiments show that our method performs a better capability for face detection in complex environments than using separately eHMMs or LBP histogram. The correct face detection rate of proposed system is over 94% among our test database which consists totally 485 single and multi-face color images of 1429 persons in different lighting conditions, face rotations, occlusions and complex backgrounds from different sources: Caltech face database, Sumgmug image library, family photos, personal digital images and World Wide Web