Dissertation > Excellent graduate degree dissertation topics show

Facial Expression and Gender Recognition Based on Static Facial Image

Author: LiuHua
Tutor: LiJinPing
School: Jinan University
Course: Computer Software and Theory
Keywords: Gender recognition Expression Recognition Principal component analysis (PCA) Linear discriminant analysis (LDA)
CLC: TP391.41
Type: Master's thesis
Year: 2010
Downloads: 133
Quote: 0
Read: Download Dissertation

Abstract


The human face is one of the most important human biometric reflect many important biological information, such as identity, expression, gender, race, age, and so on. With the rapid development of computer technology, computer vision and pattern recognition problems face image has also become a hot research topic in recent years. As an important part of the face recognition technology, face expression, gender recognition technology has also been widespread concern that the technology can further improve the recognition rate of the face recognition, face recognition provides a meaningful supplement to people face identify a fuller richer, more broad application prospects. Therefore, to study the expression, gender recognition is important. Face expression, gender recognition system is divided into three parts: image preprocessing face, facial feature extraction and classification recognizes three parts. This article is from the three main aspects of study. Face image preprocessing directly affect the recognition rate of facial expression, gender. The image preprocessing including face detection, scale normalized grayscale normalized. Important theory in the face detection problem, this paper uses hierarchical face detection based on AdaBoost algorithm strategy. The reason for using this method is that: the detection method detection speed, high detection accuracy. Then, the human face detected by the scale normalized and gradation normalization processing. Face gender identification, this section includes facial feature extraction and classification, feature extraction is more important, the ability to be interested in the facial feature extracted from the face of the high-dimensional image, is to identify the key. This paper first introduces the classic strategy based on principal component analysis (PCA) feature extraction, and then describes with particular emphasis on class and inter-class information feature extraction strategies based on the linear discriminant analysis (LDA), LDA algorithm can not be applied to small sample defects combining the PCA and LDA algorithm, overcoming the defects of the LDA algorithm, and finally using the Euclidean distance as the measure of similarity between the pattern features, based on the distance function classifier. Experiment mean face generalization of the algorithm is not high, and the future need to be further improved. Facial expression recognition experiments using facial expression feature extraction method based on Gabor wavelet and flexible template matching, the first image pixel by pixel Gabor wavelet transform, and then extract the local critical areas of wavelet coefficients using Euclidean distance The formula to calculate similarity matching to identify elastic template matching method, the last seven basic expressions of human face recognition using K-nearest neighbor classifier achieved a good result. Experimental process used K-nearest neighbor classifier complexity, further improvements in the future.

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. Industrial Cluster Circum-Bohai Sea Port Logistics Layout Optimization Research,F259.2
  6. Study of NMR-spectroscopy-based Liver Metabonomics of Hyperhomocysteinemia of Rat Following Restraint Stress,R363
  7. Research on Mechanism and Control System of Robot Head,TP242.6
  8. Face annotation and expression analysis method,TP391.41
  9. Facial expression recognition research based on manifold learning,TP391.41
  10. Facial Expression Recognition Based on Geometrical Characteristics and Subspace Learning,TP391.41
  11. Facial Expression Recognition Based on Gabor and Neural Network,TP391.41
  12. Research on Post-processing Techniques of Mathematical Formula Structural Analysis,TP391.4
  13. The Research and Implementation of Detecting System in Concrete Beam of Bridges,TP274
  14. The Study on the Relation between Facial Expression Recognition and Emotional Intelligence,TP391.41
  15. Research and Implementation in Face Recognition Based on Multiple Classifiers,TP391.41
  16. Research of Expression Recognition Based on EHMM,TP391.41
  17. Study on Emotional Event-related Potential by EEG Data,TN911.6
  18. Human Emotion Recognition Using Fused 2D-Fractional Fourier Transform Features Based on CCA,TP391.41
  19. The Research on Facial Expression Recognition Method,TP391.41
  20. Manifold Learning Algorithm for Facial Expression Recognition of Pain in Neonates,TP391.41
  21. Infant Pain Facial ExpressioN Recogintion Based on Compressive Sensing,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