Dissertation > Excellent graduate degree dissertation topics show

Face Recognition System Based on Dual Core Architecture

Author: LiuLi
Tutor: SuJianBo
School: Shanghai Jiaotong University
Course: Control Engineering
Keywords: face detection face recognition ARM+DSP QTEmbedded embedded face recognition system
CLC: TP391.41
Type: Master's thesis
Year: 2012
Downloads: 205
Quote: 2
Read: Download Dissertation

Abstract


With the development of the recognition algorithm, biometric technology has been increasingly used in the field of authentication, such as fingerprint recognition, iris recognition, voice recognition, palm print recognition and face recognition and so on. In all of these, face recognition because of its good user experience, non-contact, not easy to disguise, relatively fixed, has become a research hotspot in recent years and emerges many automatic face recognition system.Current commercial face recognition systems, most are still based on PC platform. So many problems for them such as big power consumption, inconvenient to carry and limited application areas can not avoid. Also there are a small part of the embedded platform products, but they are based on single-core MPU. Limited by the chip computing speed or peripheral devices management capacity constraints, can not get a good performance in automatic face recognition system.For the target of building a practical embedded face recognition system, this thesis proposed to use dual-core architecture embedded platform for the development of system, selected the DM6446 (ARM + DSP) platform, and completed the development of algorithm layer and application layer. The main work of this thesis can be described as follows:Design a two-level software hierarchy based on dual-core architecture hardware which abstracts the whole system into the application layer and the algorithm layer. These two layers are respectively deployed on different hardware platforms, which make full use of every single processor’s advantages: ARM and DSP.In the algorithm layer, complete the face detection, feature location, feature extraction and feature comparison modules’implementation based on the specific platform.Optimize the above algorithm modules in the program-level or strategy-level based on the characteristics of DSP operations. Package the modules in accordance with xDM standard in the form of the codec, so increase the versatility and portability of the algorithm modules.In the application layer, transplant the GUI tools (QTEmbedded) to the embedded platform, and finish the application layer program design in the QTEmbedded environment.Without disrupting the versatility of the codec algorithm, for the integration of the application layer and the algorithm layer, this thesis proposed a method of function package: shell packaging, realizing the call of the codec algorithms in the QTEmbedded frame.

Related Dissertations

  1. Research on Algorithms of 2D Face Template Protection,TP391.41
  2. Research of Video Face Recognition Based on Weighted Voting and Key-Frame Extraction,TP391.41
  3. Face Recognition Method Based on DE,TP391.41
  4. Research on Face Detection Based on Skin Color Segmentation and AdaBoost Algorithm,TP391.41
  5. A Novel Approach for Projection by Optimize Local Area in Face Recognition Applications,TP391.41
  6. Research on Deep Structure Learning Algorithms Based on Dynamic Fuzzy Relation,TP181
  7. 3G network based embedded platform design and implementation of video capture,TP274.2
  8. Face Detection and Implementation on DSP,TP391.41
  9. Design and Realization of Embedded Face Detection and Tracking System,TP274
  10. The Reserch of Rapid Face Detection and Real-time Tracking Algorithms Based on Video Streaming,TP391.41
  11. The Study of Fatigue Detection of Drivers Based on the Infrared Conditions,TP391.41
  12. Research on Face Tracking Technologies Based on Movement Prediction,TP391.41
  13. Research & Implementation of Face Detection Algorithm Based on Adaboost,TP391.41
  14. The Research for Face Recognition Based on Pseudo-Zernike Moment and BP Network,TP391.41
  15. Research on Face Recognition Methods Based on Flexible Neural Tree,TP391.41
  16. Research on Face Recognition Based on AdaBoost Algorithm,TP391.41
  17. The Study of Human Face Detection Method Based on OpenCV,TP391.41
  18. Research on the Vision-Based Driver Fatigue Real-Time Detection,TP391.41
  19. An Illumination Independence Face Recognition Algorithm Based on Gabor and SVM,TP391.41
  20. Research Onamethod for Human Face Recognition Based on MMTD,TP391.41
  21. Research and Implementation on Multi-angle Face Detection Technology Based on Continuous Adaboost Algorithm,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