Dissertation > Excellent graduate degree dissertation topics show

Research on Face Recognition Based on Binding Feature Extraction and Support Vector Machines

Author: NingZhiGang
Tutor: XieHong
School: Harbin Engineering University
Course: Signal and Information Processing
Keywords: Face Recognition Support Vector Machine Optimal hyperplane Kernel function Dimensional Principal Component Analysis
CLC: TP391.41
Type: Master's thesis
Year: 2009
Downloads: 52
Quote: 0
Read: Download Dissertation

Abstract


The face recognition technology is the use of computer analysis of face images to extract the effective identification information identifying or discriminating a pending state technology . It involves knowledge of pattern recognition , image processing , computer vision , physiology , psychology and many other disciplines , is currently one of the hot spots of pattern recognition and artificial intelligence research , analysis support vector machine method ( SVM ) face recognition application The basic idea of ??the theory of statistical learning theory and support vector machine . Analysis of several classic multi - classification algorithm : one-to-many algorithm , one-on-one algorithm , error correction ended output encoding method and an implicit decomposition strategy algorithm ; analysis of the factors that affect the classification results ; compared several algorithms technical characteristics , select OAO as classification algorithm for face recognition system . Then , the analysis of the two feature extraction algorithms : principal component analysis based on KL transform algorithm (PCA) and two - dimensional principal component analysis algorithm ( 2DPCA ) . PCA feature extraction method is statistically optimal , but the image matrix into higher dimension of the image vector after consuming large amount of computing throughout the feature extraction process . 2DPCA image matrix - based , image feature extraction is simple and intuitive , but in the process of image reconstruction requires more collaborative factors and coefficients . This paper presents an improved feature extraction algorithm that 2DPCA-PCA combined algorithm to further reduce the number of feature dimensions , feature extraction faster , better classification . Finally, the establishment of 2DPCA-PCA - based face recognition and support vector machine simulation system . Simulation based on the ORL and combo face library , compared PCA combined with KNN ( nearest neighbor classifier ) system the the 2DPCA - PCA joint KNN , PCA Joint SVM system , 2DPCA-PCA Joint SVM system . Than KNN classifier , SVM classifier has good generalization , classification accuracy ; of 2DPCA - - PCA the United SVM face recognition system compared to other system recognition speed and recognition rate .

Related Dissertations

  1. Research on Algorithms of 2D Face Template Protection,TP391.41
  2. Fault Diagnosis Method Based on Support Vector Machine,TP18
  3. Research of Fault Diagnosis Method of Analog Circuit Based on Improved Support Vector Machines,TN710
  4. Soft-sensing Technology in the Ethylene Distillation Process Applied Research,TQ221.211
  5. Intelligent Video Surveillance Target Detection Technology,TP391.41
  6. Based on kernel regression and non- local method of image denoising,TP391.41
  7. Face recognition algorithm based on feature fusion research,TP391.41
  8. One kind of empirical data on the workload of a software bug fixes Prediction Model,TP311.53
  9. Computer virus detection method,TP309.5
  10. The image -based face recognition system design and implementation beautification,TP391.41
  11. Distortion effects on image quality evaluation and classification,TP391.41
  12. Capsule endoscopy and endoscopic image portable receiver system bleeding Recognition Algorithm,TP391.41
  13. Based on support vector machine motion prediction image stabilization technology,TP751
  14. P2P traffic identification system design and research,TP393.02
  15. Unbalanced data set classification method and its application in the telecommunications industry,TP311.13
  16. Based on self-learning social relation extraction research,TP391.1
  17. Based on wavelet transform and linear subspace face recognition technology,TP391.41
  18. To guide the Fund to Venture Entrepreneur under investment management team Selection and Evaluation of research,F224
  19. The Design of Identification System for Power Marketing Services,TP391.41
  20. Intelligent Support Vector Machine Approach and Its Application on Melt Index Prediction in Propylene Polymerization,TQ325.14
  21. Fault Diagnosis on Fuel Control System of a Certain Aero-engine,V263.6

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