Dissertation > Excellent graduate degree dissertation topics show

SVM remote sensing image based on thematic information extraction

Author: ZhangYong
Tutor: HongJinYi
School: Central South University
Course: Structural Geology
Keywords: SVM RS mineralizing information extraction algorithm
CLC: TP751
Type: Master's thesis
Year: 2005
Downloads: 339
Quote: 4
Read: Download Dissertation

Abstract


Support Vector Machine (SVM) is a machine learning algorithm based on Statistical Learning Theory.It have a good classification ability for limited training samples,nonlinear separation and high-dimensional pattern recognition.The result of practical application indicates that SVM has good generalization ability.In this paper,we use SVM to extract mineralizing information from RS images and effectually recongnize RS images.The main contents of this paper are as follows.1. This paper elaborates SVM theory,analyzes several popular algorithms and summarizes RS image processing theory.Using many methods,we process RS images.2. This paper researchs how to gather positive samples and negative samples and construct training data set in experiment,and how to learn training data and optimize SVM algorithm.Paper uses k-cross validation to work out penalty parameter C .By experiment, finding out support vectors(SV) and constructing SVM modeling.3. Utilizing SVM modeling to test experimental data of RS images and extract mineralizing information.Paper compares radial basis function(RBF) kernel with polynomial kernel and linear kernel,and analyzes their classification accuracys.4. Experimental result shows that mineralizing information extracted comforms to geological data,and the known mineralizing information is effectually recongnized and extracted.It means that SVM can be used to process RS images and extract mineralizing information of Niu-Shou-Shan area. Experimental result can refer mining companies to register mining rights.

Related Dissertations

  1. Research on Scheduling of Whole-set Orders in JSP Based on Differential Evolution Algorithm,F273
  2. Research on Graph-Based Algorithm for Tagsnps Selection,Q78
  3. Research and Realization on Synchronization Technology of High Sensitivity GNSS Software Receiver,P228.4
  4. Soft Sensor of Naphtha Dry Point on Support Vector Machines Regression,TE622.1
  5. Development of the Platform for Compressor Optimization Design and Aerodynamic Optimization Design in the Transonic Compressor,TH45
  6. Effectiveness Evaluation on the Jointed Combat of the Multiple Missiles and Research on Combinatorial Optimization Algorithm,TJ760.1
  7. The Inductive Load Based Vehicle Body Network Control System,U463.6
  8. The AES Algorithm and Its Implementation in DSP,TN918.1
  9. Optimizing and Realising Research on Vedio Compression in TV Guidance System,TN919.81
  10. Research on Feature Extraction and Classification of Pulse Waveform for Cholecystitis and Nephrotic Syndrome Diagnosis,TP391.41
  11. Research and Implementation on Content-Based Clothing Image Retrieval,TP391.41
  12. Research on Navigation System Related Technology for Moving Objects under Dynamic Environment,TP301.6
  13. Research on Classification Method of Tongue Substance Color and Tongue Coating Color Based on SVM,TP391.41
  14. The Research on Paper Currency Classification Method Based on Harr-Like Feature and Minimal Ball Including Samples,TP391.41
  15. Large the Hongshan iron ore mine personnel tracking positioning system optimization study,TN929.5
  16. Computing Minimum Distance between Curves/Surfaces Based on PSO Algorithm,O182
  17. Study on the Image Registeration Integrated with the LQ Model,R815
  18. Lijiang River,RS and GIS - based Soil Erosion Research,S157
  19. Research on Improved Ant Colony Optimization and Its Application in TSP,TP301.6
  20. Citrus Image Segmentation Based on Genetic Algorithm,TP391.41
  21. Research of Sensitive Information Protection Techniques for Automated Trust Negotiation,TP309

CLC: > Industrial Technology > Automation technology,computer technology > Remote sensing technology > Interpretation, identification and processing of remote sensing images > Image processing methods
© 2012 www.DissertationTopic.Net  Mobile