Multiple face contour detection using adaptive flows

Authors:
Fuzhen Huang;Jianbo Su
Affiliations:
Institute of Automation & Research Center of Intelligent Robotics, Shanghai Jiaotong University, Shanghai, China;Institute of Automation & Research Center of Intelligent Robotics, Shanghai Jiaotong University, Shanghai, China
Venue:
SINOBIOMETRICS'04 Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication
Year:
2004

Citing 6
Cited 0

Active shape models—their training and application

Computer Vision and Image Understanding
A variational level set approach to multiphase motion

Journal of Computational Physics
A Multiphase Level Set Framework for Image Segmentation Using the Mumford and Shah Model

International Journal of Computer Vision
Extending the Feature Vector for Automatic Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Segmentation and Tracking of Faces in Color Images

FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
Active contours without edges

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel method based on a curve evolution approach using adaptive flows is presented for multiple face contour detection in grayscale images Assuming that the image consists of an arbitrary unknown number of separated faces and a uniform background region, the proposed method adaptively estimates mean intensities for each separated region and use a single curve to capture multiple regions with different intensities The adaptive flow developed in this paper is easily formulated and solved using level set method Experiments are performed on a large test set and show the efficiency of our method.