Dissertation > Excellent graduate degree dissertation topics show

Facial Expression Recognition Based on Independent Component Analysis

Author: DingWeiFu
Tutor: JiangWei
School: Shandong University
Course: Communication and Information System
Keywords: Facial Expression Recognition Feature Extraction Gabor transform Independent Component Analysis
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 74
Quote: 0
Read: Download Dissertation

Abstract


Artificial emotion refers to using artificial methods and techniques to imitate, the extension and expansion of human emotion, the machine has the recognition, understanding and the ability to express emotion. It is a part of the field of artificial intelligence research. With more and more areas of robotics, the robot has artificial emotion becomes very possible and very necessary. Facial expression recognition based on computer vision is an important task in the study of artificial emotion. Facial expression recognition related to image processing, pattern recognition, motion tracking, physiology, psychology and other research areas. It is based on the visual information on the changes in the movement and the facial features of the face of the classification. Facial expression recognition system consists mainly of three parts of the face detection, expression feature extraction and expression classification. Wherein expression feature extraction recognition technology is the key to determine the final identification result. With the deepening of research, there have been a lot of effective expression recognition algorithm, such as the overall identification method, partial identification method and geometric characteristics method. And many face recognition method is also introduced into the expression recognition and higher recognition rate. Including principal component analysis (PCA), independent component analysis method (ICA), Fisher linear discriminant method (FLD), hidden Markov model law. Already adequately studied expression recognition algorithm based on the thesis and strive to find a higher recognition rate and better generalization expression recognition algorithm. This work is as follows: (1) the standard expression database JAFFE effective pretreatment. Screening determines the position of the center of the eye with the manual calibration method, then in accordance with the coordinates of the center of the human eye on the image to be cut, so that after cutting face characteristic portion normalized to the same position. Then histogram equalization, such as centralized approach makes the final image has the same mean and variance. (2) the introduction of independent component analysis algorithm to the field of expression recognition, facial expression recognition algorithm based on ICA. The algorithm takes into account the contribution of higher-order statistical properties of the image on the facial expression recognition, JAFFE expression database in Japan in the experiment to prove the effectiveness of this method. (3) a combination of the Gabor transform and FastICA and K-nearest neighbor classifier expression recognition algorithm. Gabor wavelet has good space-frequency localized and multi-direction selectivity, and therefore more conducive to the extraction of the facial expression details. The FastICA technology able to eliminate the the signal higher order statistical redundancy. First, Gabor transform image after pretreatment, the coefficients obtained are arranged Gabor feature vector, then FastICA Gabor feature vector feature extraction, and finally with the K-nearest neighbor classifier classification. The experiments also determine the scale number and the number of directions of the Gabor transform, and the scale 5, the direction number 4, to obtain the best results. If the number is reduced, affecting the recognition rate; if the number is increased, not only can not improve the recognition rate, but increase the amount of computation. JAFFE expression database related expression recognition and expression has nothing to do with people to identify two sets of experiments. Experimental results show that the algorithm have been greatly improved, the recognition rate and generalization.

Related Dissertations

  1. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  2. ISAR Imaging Simulation of Space Targets and Target Recognition Based on ISAR Images,TN957.52
  3. Research on Feature Extraction and Classification of Pulse Waveform for Cholecystitis and Nephrotic Syndrome Diagnosis,TP391.41
  4. Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
  5. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  6. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  7. Research on Visual Measurement for Spacecraft Rendezvous and Approach,TP391.41
  8. Research on the Image Real-Time Acquisition, Storage and Image Processing System,TP391.41
  9. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  10. Multi-currency Notes Technology Research and Implementation,TP391.41
  11. The Research on Paper Currency Classification Method Based on Harr-Like Feature and Minimal Ball Including Samples,TP391.41
  12. Pavement Distress Recognition Based on Image,TP391.41
  13. Research on Visual Detection and Tracking of Mobile Robots,TP242.62
  14. Research on Fusion Algorithm of Hyper Spectral and High Spatial Resolution Remote Sensing Image,TP751
  15. An Approach for Identifying a Plant Resistance Gene Based on the Random Forest,Q943
  16. Tobacco Diseases Auto-Recognition Research Based on Image Processing Technology,S435.72
  17. Research on Nondestructive Detection Technology for External Qualities of Papayas Based-on Vision,S667.9
  18. Research on Identification System of Cashmere and Wool Fiber,TS101.921
  19. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  20. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  21. Alexithymia individual's facial expression recognition and attentional bias experimental study,B849

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