Reducing the run-time complexity in support vector machines
Advances in kernel methods
Detecting Faces in Images: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Detection in Color Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust Real-Time Face Detection
International Journal of Computer Vision
Skin Segmentation Using Color Pixel Classification: Analysis and Comparison
IEEE Transactions on Pattern Analysis and Machine Intelligence
Face segmentation using skin-color map in videophone applications
IEEE Transactions on Circuits and Systems for Video Technology
| Hi-index | 0.00 |
We propose a new face detection model based on the competition between the chrominance and luminance channel decisions. Each of the two detection branches has its own techniques of finding face candidates and the model implies a dual cross-validation of the above channels. One investigates the decision improvement of skin detection over the color channel by applying the conversion from the conventional RGB space into the 3D uncorrelated color space (UCS), using the Karhunen-Loève transform (KLT) in the color space. One evaluates the performances of the proposed model using an UCS by comparison to other two well known color representation (YCbCr) and (HSV). For experimental evaluations, we have chosen 120 images from "Labeled Faces in the Wild" database. The proposed algorithm leads to a correct detection score with about 7% better than the classical Viola-Jones method. The detection rates obtained using UCS representation are better by comparison to YCbCr and HSV color spaces.