Face Detection Using Colour and Haar Features for Indoor Surveillance
Sharmeena Naido, Rosalyn R. Porle · 2020
For the past few decades, the evolution of human-computer interaction has significantly impacted face detection methods. In this paper, an experiment was conducted to detect frontal and side-view faces from indoor surveillance videos. The proposed method comprises skin colour segmentation, Haar feature extraction and classification. Skin colour segmentation involves the conversion of RGB images to the YCbCr colour space. Then, histogram analysis is performed to extract skin pixels in images. Afterward, Haar features are used. Finally, the cascaded AdaBoost classifier is used to classify faces into frontal and sideview faces while removing non-face regions. The proposed method successfully detected an average of 70.96% of frontal faces. The detection for side-view faces, however, have low performance, with average of 32.67%.