Software Investigate

3D Face Recognition Using 2DPCA

Download now Free registration required

Executive Summary

Robustness of face recognition systems are measured by its ability to overcome the problem of changing in facial expression and rotation of individuals' face images. This paper represents a face recognition system that overcomes the problem of changes in facial expressions in Three-Dimensional (3D) range images. A local variation detection and restoration method based on the Two-Dimensional (2D) Principal Component Analysis (PCA) is proposed. The depth map of 3D facial image is first thresholded to discard the back ground information. Then, the detected face shape is normalized to standard size 100x100 pixels and nose point is selected to be the image center.

  • Format: PDF
  • Size: 334.8 KB