Dissertation > Excellent graduate degree dissertation topics show

Expression Recognition Based on Improved ODP and Gabor Wavelets

Author: ZhangXiaoCui
Tutor: ZhangJianMing
School: Jiangsu University
Course: Applied Computer Technology
Keywords: expression recognition partially occluded improved Optimal Discriminant Plane Gabor wavelet transformation symmetry transformation Embedded Hidden Markov Model
CLC: TP391.41
Type: Master's thesis
Year: 2009
Downloads: 83
Quote: 0
Read: Download Dissertation

Abstract


Facial expression recognition is to analyze and detect the special expression state from given expression images or video frames and then to ascertain the subject’s specific inborn emotion, achieving smarter and more natural interaction between human beings and computers. The study of facial expression recognition has found its values in economy and society.In this thesis, after analyzing the expression recognition methods currently used by others, we present the expression recognition method based on improved ODP and Gabor wavelets of optimal frequences under partial occlusion. The main work is described as bellows:(1)According to the characteristics of different expressions and the knowledge of psychology and biology, a elementary classification of expression based on improved Optimal Discriminant Plane is proposed. This method is intended to improve inter-class divergence matrix to solve the problem of rank constraint in original ODP; get the orthogonal vector of eigenvector and then they are constituted the Optimal Discriminant Plane, 2 Classification are extended to Multi-classification problem at the same time; We choose the ODP as projection space, so the six basic expressions are divided into four classes: happy, surprise, fear, and confused expressions (disgust, anger, sad).(2)After delving into the relationships between Gabor wavelet scales, facial feature regions (mainly the eye area and mouth area), and confused expressions, a efficient facial expression extraction method based on optimal Gabor wavelets is presented to distinguish the confused expressions (disgust, anger, sad).First, locate human face feature areas of the eye and mouth using the integral projection method. Second, features for the eye area and mouth area are extracted by using optimal Gabor wavelet transformation, then the features are weighted to form the basic emotional expression features. This method can effectively extract the details of expression features, And can mitigate the problem of too high-dimension cased by conventional Gabor wavelet transform.(3)In order to solve the problem that facial expressions are difficult to recognized when the human eyes are partially occluded due to the fringe of hair or hats, a new method based on symmetry transformation is presented. To begin with, referring to the facial geometrical properties, a vertical integral projection arithmetic is dopted on normalization image. Through the midline detection algorithm which is used to judge how much the eyes are occluded, the midline of the face can be got. When the occlusion is intolerant, the image has to be renovated by symmetry transformation. Experiment results indicate that better recognition effect can be got by this method. What’s more, it can tolerate the head’s deflection within a certain range.(4)A prototype system of facial expression recognition is designed and implemented by object oriented technology. This system consist three modules that is expression image preprocessing, facial expression feature extraction, expression classification. It proved the validity of our method.

Related Dissertations

  1. Research on Temporal Information Recognition and Normalization,TP391.1
  2. Alexithymia individual's facial expression recognition and attentional bias experimental study,B849
  3. Primary emotions and emotional expression recognition characteristics and relationship between the amount of words to master,B844.2
  4. Facial expression recognition based on sparse representation residuals fusion,TP391.41
  5. Research on Mechanism and Control System of Robot Head,TP242.6
  6. Face annotation and expression analysis method,TP391.41
  7. Facial expression recognition research based on manifold learning,TP391.41
  8. Facial Expression Recognition Based on Geometrical Characteristics and Subspace Learning,TP391.41
  9. Facial Expression Recognition Based on Gabor and Neural Network,TP391.41
  10. Research on Post-processing Techniques of Mathematical Formula Structural Analysis,TP391.4
  11. The Study on the Relation between Facial Expression Recognition and Emotional Intelligence,TP391.41
  12. Research of Expression Recognition Based on EHMM,TP391.41
  13. Human Emotion Recognition Using Fused 2D-Fractional Fourier Transform Features Based on CCA,TP391.41
  14. The Research on Facial Expression Recognition Method,TP391.41
  15. Manifold Learning Algorithm for Facial Expression Recognition of Pain in Neonates,TP391.41
  16. Infant Pain Facial ExpressioN Recogintion Based on Compressive Sensing,TP391.41
  17. Facial Expression Recognition Based on Independent Component Analysis,TP391.41
  18. Research on Vision-Based Emotion Cognition of Home Service Robot,TP242
  19. Facial Expression Recognition and Its Application in Video Classification and Recommendation,TP391.41
  20. Bionic features based facial expression recognition,TP391.4
  21. Analysis and Research on Algorithm of Facial Expression Recognition Based on Wavelet Transform,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