ROI Segmentation for Feature Extraction from Human Facial Images
This addresses feature extraction for human-computer interaction, but appears incremental as it combines existing methods without clear novelty.
The paper tackles feature extraction from facial images by using skin color segmentation, thresholding, and knowledge-based techniques for face recognition, but does not report specific results or numbers.
Human Computer Interaction (HCI) is the biggest goal of computer vision researchers. Features form the different facial images are able to provide a very deep knowledge about the activities performed by the different facial movements. In this paper we presented a technique for feature extraction from various regions of interest with the help of Skin color segmentation technique, Thresholding, knowledge based technique for face recognition.