Depth Weighted Modified Hausdorff Distance for Range Face Recognition

Authors:
Affiliations:
Venue:
CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
Year:
2004

Citing 5
Cited 1

Face recognition from range data by structural analysis

Syntactic and structural pattern recognition
Line-Based Face Recognition under Varying Pose

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition: Features Versus Templates

IEEE Transactions on Pattern Analysis and Machine Intelligence
Curvature-Based Face Surface Recognition Using Spherical Correlation - Principal Directions for Curved Object Recognition

FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
3D Human Face Recognition Using Point Signature

FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000

A face and fingerprint identity authentication system based on multi-route detection

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The definition of Hausdorff distance is a measure of thecorrespondence of two point sets. In this paper, wepropose a novel implementation of a person verificationsystem based on depth-weighted Hausdorff distance(DWHD) using the surface curvatures of the human face.This new method incorporates the depth information andcurvatures of local facial features. The weighting functionused in this paper is based on depth values, which havedifferential properties of a face according to the people,so that the distance of this extracted edge maps will beemphasized. Experimental results based on combinationof the maximum, minimum, and Gaussian curvatureaccording to threshold values show that DWHD achievesrecognition rate of 92.8%, 97.6% and 92.8% of the casesfor 5 ranked candidates, respectively, and the proposedmethod of combined recognition rate for each curvatureshows the best.