Dissertation > Excellent graduate degree dissertation topics show

Research and Implementation of Face Recognition Technology Based on Embedded Hidden Markov Model

Author: DaiFen
Tutor: ZhaoLong
School: National University of Defense Science and Technology
Course: Computer Science and Technology
Keywords: Face Recognition Eigenvectors Feature Fusion Embedded hidden Markov model
CLC: TP391.41
Type: Master's thesis
Year: 2007
Downloads: 112
Quote: 3
Read: Download Dissertation


The face is the most common mode of human vision , therefore , face recognition has become one of the most easily acceptable identification method . In recent years , face recognition technology, more and more attention and has become one of the most successful technology applications in computer vision, image analysis and understanding . This study and analysis of the face recognition technology at home and abroad in recent years progress , a systematic study of the composition of the face recognition system based on embedded hidden Markov model (EHMM) Principles and Implementation . The completion of the main work are the following: First, the analysis of the advantages and disadvantages to the pixel values ??of the image of the human face and the feature vectors extracted based on facial image as an observation vector . Focuses on the two-dimensional discrete cosine transform (DCT) and two-dimensional discrete wavelet transform (DWT) principle and its advantages and disadvantages of these two feature extraction methods , and by experimental analysis and comparison . The experiments show that the low frequency coefficients obtained with the two - dimensional discrete cosine transform as a feature vector , generally, from the recognition rate is obtained than only the discrete wavelet transform , the low - frequency sub-band as the effect of the feature vector . For the complex structure of embedded hidden Markov model (EHMM) , the training needs of more than one sample , and long time - consuming problem , the model training method based on the fusion of multiple features . The method first extracts the feature vectors of the respective sample images of the same object , and a plurality of feature vector integration as a single feature vector ( can take the average , weighted average) can also be based on the amount of information of the image taken , and then based on the fusion of the feature vector training. Experiments show that the method is feasible and can effectively reduce the sample training time . Third, based on embedded hidden Markov model recognition system image feature vector extraction , model training and identify three functional modules , respectively, for research and analysis on the basis of the software architecture of the system design and a face recognition system, the system has a clear function of each part , independent, and a low degree of coupling .

Related Dissertations

  1. Research on Algorithms of 2D Face Template Protection,TP391.41
  2. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  3. The Compression and Fusion Technique Research of Underwater Target Feature,TN911.7
  4. Research of Video Face Recognition Based on Weighted Voting and Key-Frame Extraction,TP391.41
  5. Face Recognition Method Based on DE,TP391.41
  6. Research on Face Recognition Methods Based on Flexible Neural Tree,TP391.41
  7. Research on Methods of Fingerprint Image Segmentation,TP391.41
  8. Research on Face Recognition Based on AdaBoost Algorithm,TP391.41
  9. Research Onamethod for Human Face Recognition Based on MMTD,TP391.41
  10. The Research on Neural Network with Quadratic Denominator Cubic Rational Spline Function Weight and Its Application,TP183
  11. The Design of Identification System for Power Marketing Services,TP391.41
  12. Based on wavelet transform and linear subspace face recognition technology,TP391.41
  13. \,R338
  14. Based on local binary pattern and Weber local descriptor Face Recognition,TP391.41
  15. Expression of face recognition algorithm based on sparse research,TP391.41
  16. Color Face Detection and Recognition,TP391.41
  17. Under the conditions of variable lighting and occlusion of face recognition technology and its application,TP391.41
  18. Based on sparse representation Face Image Recognition Method,TP391.41
  19. Based on Information Fusion Fault Diagnosis of Analog Circuits,TN710
  20. Based on the feature fusion membrane protein transmembrane helix prediction,Q51
  21. Research on Methods for Pedestrian Association Across Non-overlapping Camera Views,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