Dissertation > Excellent graduate degree dissertation topics show

Pose Adjustment in Face Recognition Based on Range Image

Author: LiXiaoGuang
Tutor: ZhangXiangDe
School: Northeastern University
Course: Applied Mathematics
Keywords: face recognition range image rigid body transform frame of axes itself SSIM algorithm
CLC: TP391.41
Type: Master's thesis
Year: 2009
Downloads: 10
Quote: 0
Read: Download Dissertation

Abstract


Face recognition is one of the most important tasks at present, and it is also a hotspot both in applied mathematics and information security. But most researches about face recognition are based on the 2D face image. Because of the influences of illumination, pose variation, the improvement of recognition accuracy of 2D face recognition is greatly impeded. Compare to 2D face recognition, the 3D data can more accurately descript face. Therefore,3D recognition has a broad application prospect.In this thesis, we first introduce the background and the main methods of face recognition, and then propose "like rebuilding" algorithm about adjusting pose on the range image. Through this algorithm we transform initial range data to a new frame of axes by the techniques of the simulative KL transform, and then get the precise symmetry plane by the Iterative Closest Point algorithm (ICP). The wavelet transform is used to obtain the stable region which is represented the feature of the face plane; Finally, we can get the frame of axes of itself, and make use of the rigid body transform to achieve the data resample.We assessed the algorithm with SSIM operator, and found the image quality is better than before. We tested the algorithm on the FRGC and BJUT-3D-R1 databases, and achieved 99.5% and 100% satisfying results.

Related Dissertations

  1. Research on Algorithms of 2D Face Template Protection,TP391.41
  2. The Study of 3d Face Recognition System,TP391.41
  3. The Research for Fractal Feature Extraction and Face Recognition Algorithm,TP391.41
  4. Face Recognition Research Based on Manifold Learning,TP391.41
  5. Research on the Key Technique in Face Recognition,TP391.41
  6. An Illumination Independence Face Recognition Algorithm Based on Gabor and SVM,TP391.41
  7. The Research on Neural Network with Quadratic Denominator Cubic Rational Spline Function Weight and Its Application,TP183
  8. Investigation on Characteristics of Staring Lidar System,TN958.98
  9. Study on the High Dynamic Range Image Composition Algorithms Based on Davinci Platform,TP391.41
  10. Stratification and energy optimization based on the brightness of high dynamic range image tone mapping technology research,TP391.41
  11. Based on sparse representation Face Image Recognition Method,TP391.41
  12. Feature Dimensional Reduction for Fast Face Recognition,TP391.41
  13. Based on support vector machines and multi-level B- spline face recognition technology,TP391.41
  14. Study on Illumination Preprocessing Approaches in Face Images,TP391.41
  15. High Dynamic Range Image Generated Based on Multi-Exposure Images,TP391.41
  16. The Design and Implementation of Face Recognition System Based on VC + +,TP391.41
  17. Anti-Photo Spoof Methods in Face Recognition,TP391.41
  18. Based on Sub-pattern Locality Preserving Projection Approaches Research for Race Recognition,TP391.41
  19. Based on the the the flow -shaped learning and the the multi- of the the Zhang the amount of of the pose face recognition research,TP391.41
  20. Three Dimensional Face Recognition for Template Protection Technology,TP391.41
  21. Research of Face Recognition Technology,TP391.41

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net  Mobile