Dissertation > Excellent graduate degree dissertation topics show

Constraint -based sparse NMF algorithm for face recognition Aging Simulation and its application to face recognition

Author: YeYongQing
Tutor: DuJiXiang
School: Huaqiao University
Course: Applied Computer Technology
Keywords: Aging Simulation Face image Non-negative matrix factorization Sparse constraint Recognition and Retrieval
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 105
Quote: 0
Read: Download Dissertation

Abstract


The aging of the face image based modeling techniques in computer vision and image processing is an important area of ​​research , but also the face recognition is an important field of research and technical difficulties . With sparse constraint NMF algorithm (NMFsc) not only to maintain the original algorithm is non-negative additive , but also through the integration of constraint makes sparse data representation is more local representation. This article from the age change on the impact face of apparent characteristics of the locality , in the sparse constraint NMF algorithm based on the aging of the face image modeling techniques to explore , research, and the technology used has age-related changes in the field of face recognition . Its main achievements are as follows : 1. Sparse constraint is proposed based on non-negative matrix factorization algorithm for face aging simulation face image obtained by the non-negative matrix factorization based matrix or coefficient matrix . Adjustment matrix sparsity , the use of local features of face subspace method to establish a stronger facial feature model and the improved prototype (prototype) based on the human face aging simulation . 2 presents a wavelet transform based on residual images and the combination of facial aging simulation method NMFsc reconstructed image with the original image retained residual image between the high-frequency information of the original image , based on the \Age can synthesize more representative prototype face. Wavelet transform from a given template image can extract the carrier frequency aging skin texture feature subgraph , more conducive to simulate the aging characteristics of the human face images. 3 presents a face recognition with age span and retrieval methods in addition to light , gesture, facial expression , the result of changes due to age face shape and texture changes will greatly affect the face recognition system performance. In this paper, the above proposed face aging simulation method applied to face recognition with age span and retrieval , the simulated virtual sample age-specific rate of increase recognition and retrieval .

Related Dissertations

  1. Research on Co-clustering and Application,TP311.13
  2. Non-negative Local Coordinate Factorization for Image Representation,TP391.41
  3. Non-negative matrix factorization based on sparse image retrieval,TP391.41
  4. Electronic passport quality assessment system,TP391.41
  5. Research on Human Abnormal Behavior Detection and Recognition in Intelligent Video Surveillance,TP391.41
  6. Internet Oriented Sentiment Orientation Analysis of Chinese Public Opinion,TP391.1
  7. Hyperspectral Unmixing Based on Nonnegative Matrix Factorization,TP751.1
  8. 3D Face Reconstruction Based on a Single Frontal Face Image,TP391.41
  9. Research on Hyperspectral Remote Sensing Image Fusion and Quality Evaluation Method,TP751
  10. Research on Mixed-pixel Unmixing of Hyperspectral Imagery,TP751
  11. Spam Filtering System Study Based on Non-negative Matrix Factorization,TP393.098
  12. 2D Facial Transformation Based on Maximum a Posteriori and Subspace Learning,TP391.41
  13. Research of Image Annotation by Sparse Regression Model,TP391.41
  14. Research of Single-document Summarization Based on Semantics,TP391.1
  15. The Research on Image Protection Technology Based on Perceptual Hashing,TP391.41
  16. A Non-negative Matrix Factorization Model with Sparse Constraint and Its Initialization,O151.21
  17. Support vector machine and method for non-negative matrix factorization theory application,TP391.41
  18. The Research of Face Features Extraction Methods Based on Semantic Features,TP391.41
  19. Research on Annotation Technology of Face Images in Network News,TP391.41
  20. Research on Space-Borne Multi-Sensor Image Fusion Based on Non-Negative Matrix Factorization,TP751
  21. Face Recognition Method Research and Implementation,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