Dissertation > Excellent graduate degree dissertation topics show

Research on Face Recognition Baesed on Pincipal Component Analysis

Author: JiaYing
Tutor: DuanYuBo
School: Northeast University of Petroleum
Course: Oil \u0026 Gas Information and Control Engineering
Keywords: Face Recognition Face pretreatment Feature Extraction Principal Component Analysis Dimensional Principal Component Analysis
CLC: TP391.41
Type: Master's thesis
Year: 2010
Downloads: 437
Quote: 0
Read: Download Dissertation

Abstract


Biometric technology is a unique human physiological or behavioral characteristics to personally identifiable, it provides a high reliability, high stability authentication ways. Face detection and recognition is a branch of the biometric most attention, is currently a hot research topic in the field of image processing, pattern recognition and computer vision, criminals search in the public security departments, dynamically monitor the identification of the security sector, banks password system, and many areas have a wide range of research, this paper, a more in-depth research. First describe the face recognition technology research content, method and application prospects of automatic face detection and recognition technology are reviewed. And details of face recognition is a very important step - face pretreatment, face pretreatment methods mentioned in the text are to proceed from the point of view of the image processing, the main purpose is to make the face image standardization and eliminate the influence of light to a certain extent. This article describes several pretreatment methods, such as geometric normalization, gray-scale normalization. Secondly, this paper focuses describes the classic method of face recognition, PCA method. The principal component analysis (Principal Component Analysis, PCA), discrete K-L transform image compression in an optimal orthogonal transformation. To describe it with a low dimensional subspace face image, while at the same time to a certain extent to store the required identification information. Its basic principle is: by high dimensional image space by the K-L transform to obtain a new set of orthogonal base, certain trade-offs of these orthogonal base, wherein part of the generated low-dimensional face space reserved, i.e. face feature subspace, identify the test image projector to this space to obtain a set of projection coefficients by comparison with the face image recognition. This approach makes the minimum mean square error before and after compression, and the transformed low-dimensional space with a good ability to distinguish. However, in such a face recognition technology, a two-dimensional face image matrix must be converted to one-dimensional image vector before PCA analysis, after such conversion, resulting in the number of the dimension of the image vector is generally higher, so that The entire feature extraction process consuming a considerable amount of calculation. In order to overcome the deficiencies of traditional PCA Another face recognition method, 2DPCA methods. And PCA, 2DPCA is based on two-dimensional image matrix, rather than one-dimensional vector, and thus feature extraction image without prior conversion into a vector. Directly using the original image matrix to build the image covariance matrix, its feature vector used for feature extraction. This paper discusses the application of these two methods in the face recognition, and carried out the experiment on the ORL and AR face database, all tests show that the a 2DPCA identification rate is higher than PCA, experimental results also show that 2DPCA feature extraction efficiency is higher in the PCA.

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 Algorithms of 2D Face Template Protection,TP391.41
  4. Research on Feature Extraction and Classification of Pulse Waveform for Cholecystitis and Nephrotic Syndrome Diagnosis,TP391.41
  5. Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
  6. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  7. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  8. Research on Visual Measurement for Spacecraft Rendezvous and Approach,TP391.41
  9. Research on the Image Real-Time Acquisition, Storage and Image Processing System,TP391.41
  10. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  11. Multi-currency Notes Technology Research and Implementation,TP391.41
  12. Pavement Distress Recognition Based on Image,TP391.41
  13. Research on Fusion Algorithm of Hyper Spectral and High Spatial Resolution Remote Sensing Image,TP751
  14. Application of Improved Principal Component Analysis Algorithm in Course Construction,G642.4
  15. Research on Nondestructive Detection Technology for External Qualities of Papayas Based-on Vision,S667.9
  16. Research on Identification System of Cashmere and Wool Fiber,TS101.921
  17. The Impact of Tourism on Typical Vegetation in Luya Mountain Nature Reserve, Shanxi Province,S759.9
  18. A Comparative Study of Sichuan and Shaanxi , Chongqing and Manufacturing Competitiveness,F224
  19. Research of Video Face Recognition Based on Weighted Voting and Key-Frame Extraction,TP391.41
  20. Feature Extraction Technologies Research and Implementation of 3D Models Based on Wavelet Transform,TP391.41
  21. Face Recognition Method Based on DE,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