Dissertation > Excellent graduate degree dissertation topics show

Research on Facial Expression Recognition Using Axial Symmetry Eyes Location and Features Extraction

Author: LiuYang
Tutor: JiGuiShu
School: Central South University
Course: Computer Science and Technology
Keywords: facial expression recognition HMM K-L transform axial symmetry eyes location face detection
CLC: TP391.41
Type: Master's thesis
Year: 2009
Downloads: 199
Quote: 2
Read: Download Dissertation

Abstract


Facial expression is the external exhibition of one’s mood.The current facial expression shows man’s real feeling,so we can know one’s emotion status and recognization status through analyzing one’s facial expression.One American famous psychologist named Albert said: when a man shows his emotions,his words carring 7 percent of emotions, his tune carring 38 percent and his expression earring the rest 55 percent.The purpose of facial expression recognization is to let the computer deduce people’s emotion status,it’s a new hot subject,it is useful in the man-machine interaction, security, robot making, medicine, communication and automobile area.Facial expression recognization contains two main parts: facial expression recognization in video and static picture.This paper does following things in static picture expression recognization:Firstly,this paper researches and implements a face detection method based on template matching, which contains template making, matching method choosing and mosaic testing. To detect face successfully is the first step in an automatic facial expression recognization system.Secondly,this paper researches some pretreatment methods for expression recognization. In different pictures, there are various poses, size, background and light conditions. Histogram equilibria, pictures unification and many other pretreatment steps are used to pretreat the pictures in this paper, which builds a good base for the facial expression recognization.Thirdly,this paper proposes an eye location method based on the axial symmetry. An important step in the facial expression recognization is the eyes and mouth locating.Aming at the shortcomings of generalized centrosymmetric eyes locating method,this method takes advantage of the axisymmetric quality of a half circle about a vertical line which passes the pupil centre,selects the points which have the highest axial symmetry to be intending eyes centre. That method based on that axisymmetric quality proves more accurate and fast.Finally,this paper applys the HMM(Hidden Markov Model) in expression recognition, and makes each model for each expression. Massive data needs to be handle in expression recognition,whose calculation is quite complex, so this paper uses the K-L method to transform the eyes and mouth area, extracts the main features, and then inputs the features to the HMM, trains many times and builds robust models. In the recognization process, it calculates the similarity between given picture and models, and then takes the high similarity model’s expression as the final result. Experimentation shows HMM models are robust, the application of HMM to expression recognition is successful, and the recognition rate is high.

Related Dissertations

  1. Multiple ANN/HMM Hybrid Used in Speech Recognition,TN912.34
  2. Modulation Pattern Recognition and Parameter Estimation for Ground Wave Radiation Sources,TN957.51
  3. Research on Autamatic Music Structrue Analysis,TN912.3
  4. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  5. Research on Recognition of Fabric Weave Pattern Based on Space-Frequency Domain,TS101.923
  6. Research on Identification System of Cashmere and Wool Fiber,TS101.921
  7. Measurement and Reconstruction of Ion Channel Current for Cell Membrane in Rat’s Cerebral Cortex,Q42
  8. Characteristics of sensory stimulation evoked,R318.0
  9. Network transmission ROI image coding algorithm,TN919.81
  10. A Research on Speech Recognition Technology,TN912.34
  11. Based on Contourlet Transform Digital Watermarking Method,TP309.7
  12. Image Fusion Algorithms Based on Multi-scale Analysis,TP391.41
  13. Research on License Plate Location Algorithm of License Plate Recognition System,TP391.41
  14. Feature Extraction Technologies Research and Implementation of 3D Models Based on Wavelet Transform,TP391.41
  15. Research on Face Detection Based on Skin Color Segmentation and AdaBoost Algorithm,TP391.41
  16. Study on Fabric Defect Detection and Sutomati Grad-ing System,TP391.41
  17. An Algorithm on Clustering and Anomaly Detection for Multiple Data Streams,TP311.13
  18. Research on Information Hiding Based on Images,TP309.7
  19. Design and Implication of Image Compression System Based on Wavelet and DM6446,TP391.41
  20. Color Image Compression Based on Quaternion Neural Network,TP391.41
  21. Face Detection and Implementation on DSP,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