Efficient Face Extraction Using Skin-Color Model and a Neural Network

Authors:
Jong Bae Kim;Chae-Hyun Moon;Hang Joon Kim
Affiliations:
-;-;-
Venue:
IDEAL '02 Proceedings of the Third International Conference on Intelligent Data Engineering and Automated Learning
Year:
2002

Citing 3
Cited 0

Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations

IEEE Transactions on Pattern Analysis and Machine Intelligence
Mixture model for face-color modeling and segmentation

Pattern Recognition Letters
A highly efficient system for automatic face region detection in MPEG video

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, we present a method to efficiently extract a human's face from a given image sequence. The method consists of two steps: image segmentation and facial region extraction. In the image segmentation, the input frames are segmented using watershed algorithms segmenting the frame into an appropriate set of arbitrary regions. In the facial region extraction, the facial regions are extracted by integrating the results of facial region detection using a skin-color model and the results of facial region identification using a Neural Network (NN). The results of the image segmentation and facial region extraction are integrated to provide facial regions with accurate and closed boundaries. In our experiments, the presented method detected 92.2% of the faces and the average run time ranged from 0.31 to 0.48 sec per frame.