Face Detection using Logit Boost Algorithm with YCbCr Color Space
Deepali G. Ganakwar · International Journal for Research in Applied Science and Engineering Technology · 2020
In this paper, for detecting faces in an image hybrid method is used. It is based on joint haar-like features with LogitBoost algorithm and for skin pixel segmentation YCbCr color space is used. Our method is based on the co-occurrence Haar-like features which can capture the structural characteristic of the face, make it possible to construct a more effective weak classifier. As the Haar-like, the joint Haar-like feature can be calculated very effective and has the robustness to the addition of noise and change in illumination. The face detector is learned by stage wise selection which is different from Viola and JonesDetector is that we use LogitBoost.Our experimental results show that the LogitBoost obtain higher performance than AdaBoost.We have confirmed that our method based on LogitBoost and YCbCr color space yielded higher performance than AdaBoost and YCbCr color space based skin pixel segmentation when acted solely.