A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Expert Systems with Applications: An International Journal
International Journal of Human-Computer Studies
Hi-index | 0.00 |
This study proposes techniques for detecting unintentional protruding objects from a subject's head in environmental portraits. The protruding objects are determined based on the color and edge information of the background regions adjacent to the head regions in an image sequence. The proposed algorithm consists of watershed segmentation and KLT feature tracking model for extracting foreground regions, a ROI (Region of Interest) extracting model based on face detection results, and a protruding object detection model based on the color clusters and edges of the background regions inside the ROI. Experimental evaluations using four test videos with different backgrounds, lighting conditions, and head ornaments show that the average detection rate and false detection rate of the proposed algorithm are 87.40% and 12.11% respectively.