Dissertation > Excellent graduate degree dissertation topics show

Supervised Learning Based Image Local Interest Points Detector

Author: LiBing
Tutor: LvBaoLiang
School: Shanghai Jiaotong University
Course: Computer Software and Theory
Keywords: KImageLocalInterestPointsDetector ScaleInvariantFeature Transform (SIFT) Learning to Rank Image Retrieval Cate-gory Classi?cation Rank Scale Invariant Feature Transform (Rank-SIFT) Repeatability Score Matching Score Sparse Coding RankSupport Vector Machine
CLC: TP391.41
Type: Master's thesis
Year: 2012
Downloads: 88
Quote: 0
Read: Download Dissertation

Abstract


In recent years, the research of most image local interest points methods focus ondesigning and learning an e?ective local interest point descriptor algorithm to charac-terize a local interest point, and few research focuses on the algorithm of local inter-est point detector. However, how to identify stable local interest points is still a verychallenging problem. Traditional local interest point detector algorithm is based onhand-craft strategies to select stable local interest point, in which it is hard to choosea common strategy for all the images. In this master thesis, we adopt a supervisedlearning based data-driven approach to improve the algorithm of selecting stable localinterest points. We mainly focus on the algorithm of Scale Invariant Feature Transfor-m (SIFT). We propose a new algorithm which is called Rank-SIFT. In this algorithm,we adopt learning to rank framework, design a set of di?erential, grads and edge re-sponse features from each point, and de?ne the stability score of a point across imagescontaining the same visual objects. We train Rank-SVM model on extracted trainingdata based on the proposed features and stability score. This model is used to predic-t the stability of each point, which is helpful to select stable interest points. At thesame time, we construct images database for evaluation, and de?ne the standards ofRepeatability and Matching score measures. And also, we carry on image retrievaland category classi?cation experiments on the Oxford and PASCAL database, respec-tively. The experimental results show that compared with traditional SIFT method,Rank-SIFT can substantially improve the stability of detected local interest points. Wealso analyze the importance of each designed feature in the stability score predictionusing sparse coding algorithm in the experiments. Finally, an online web image localinterest point detection system is implemented, and also a open source software for Rank-SIFT algorithm is released.

Related Dissertations

  1. Research on Facial Feature Extraction and Matching Algorithms for Image Retrieval,TP391.41
  2. The Research and Implemention of Image Retrieval Based on User Interested Feature,TP391.41
  3. Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
  4. Research and Implementation on Content-Based Clothing Image Retrieval,TP391.41
  5. The Discovery of User Concept Region Based on Multiple Instance Learning,TP391.41
  6. Research on Sparse Image Representation and Coding Model,TP391.41
  7. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  8. Research and Application of Diverse Density Learning Algorithm,TP181
  9. Research of Shape Based Image Retrieval in Han Dynasty Stone,TP391.41
  10. The Research on Content-based Medical Image Retrieval Algorithm,TP391.41
  11. Research on Content-based Trademark Image Retrieval Technology,TP391.3
  12. Research on Relevance Feedback Techniques Based on Long-term Log Learning and RW-Soft SVM in CBIR,TP391.3
  13. Research on Locally Features Aggregating and Indexing Algorithm in Large-scale Image Retrieval,TP391.3
  14. Face Image Retrieval and Recognition Based on Data Dimension Reduction,TP391.41
  15. Research and Application of Illuminant Invariant Features in Image Retrieval and Recognition,TP391.41
  16. Jade Multi-Agent Based Image Retrieval System,TP391.3
  17. Based on sparse representation of high spatial resolution remote sensing image texture description Method,TP751
  18. Non-negative Local Coordinate Factorization for Image Representation,TP391.41
  19. Non-negative matrix factorization based on sparse image retrieval,TP391.41
  20. Content-based image retrieval technology research large-scale digital,TP391.41
  21. Image retrieval method and system for parallel computing,TP391.3

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