1 / 7

3D Face Recognition Using Range Images

3D Face Recognition Using Range Images. Final Presentation Joonsoo Lee 5/03/05. Introduction. Face Recognition Develop an automatic system which can recognize the human face as humans do Motivation Growing importance of security systems Advance of image capture technology Objective

adolph
Download Presentation

3D Face Recognition Using Range Images

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. 3D Face Recognition Using Range Images Final Presentation Joonsoo Lee 5/03/05

  2. Introduction • Face Recognition • Develop an automatic system which can recognize the human face as humans do • Motivation • Growing importance of security systems • Advance of image capture technology • Objective • To increase the recognition rate • To keep the computational complexity low

  3. Background • Range Image • Image with depth information • Invariant to the change of illumination & color • Simple representation of 3D information • Previous Approach • Geometrical Approach: Principal Curvature [Gordon (1991)], Spherical Correlation [Tanaka & Ikeda (1998)] • Statistical Approach: Eigenface [Achermann et al. (1997)], Optimal Linear Component [Liu et al. (2004)]

  4. Approach • Pre-processing • Feature Extraction 3D Mesh Image 3D coordinate & texture information Range Image Depth information extracted from 3D mesh Normalized Image Range image normalized by nose position Maximum Curvature Feature 1 PCA Range Image Curvature Analysis Minimum Curvature PCA Feature 2 PCA: Principal Component Analysis

  5. Curvature Analysis • Curvature Calculation • Normal Curvature (max, min) • Estimation of partial derivatives[Besl & Jain, 1986]

  6. Result • Database • Recognition Rate • Frontal & Neutral Expression • Various Expressions : poor performance

  7. Conclusion & Future Work • Conclusion • Curvature information can play an important role in the face recognition problem • It still cannot handle various facial expressions • Future Work • Different kinds of curvature information will be utilized to find the best • Find the elements affected by the change of facial expressions

More Related