Dissertation > Excellent graduate degree dissertation topics show

POLSAR Image Classification Using BP Neural Network Based on Quantum Clonal Evolutionary Algorithm

Author: LiHuiJun
Tutor: ZouBin
School: Harbin Institute of Technology
Course: Information and Communication Engineering
Keywords: POLSAR image classification Quantum cloning evolutionary algorithm BP neural network Parallel multi- criteria feature selection algorithm
CLC: TN957.52
Type: Master's thesis
Year: 2010
Downloads: 91
Quote: 0
Read: Download Dissertation

Abstract


The POLSAR image classification is important POLSAR image processing , is also one of the key technologies of image interpretation POLSAR . The classification of POLSAR image is a typical example of the front-end part of a separate POLSAR image interpretation system extracted as a specific application . Fast , accurate POLSAR image classification to achieve a variety of practical applications, such as target detection and identification of the premise . In this paper, a BP neural network classifier evolutionary algorithm based on quantum cloning and the classifier POLSAR image classification . The classifier consists of two steps: the use of quantum cloning evolutionary algorithm to optimize BP neural network 's initial weights and threshold ; using gradient descent method to precisely adjust the weights and threshold . The paper first describes the overview of the development of the background as well as domestic and foreign POLSAR image classification and then describes to clear POLSAR image feature extraction methods , and elaborated how to use parallel multi- criteria based on the chain competitive strategy agent genetic algorithm (LAGA) feature selection algorithm to select the image features extracted POLSAR goes on to describe the quantum cloning the origin of evolutionary algorithms (QCEA) , the basic principles and the algorithm process , and the way to use quantum cloning evolutionary algorithm to optimize BP neural network classifier initial weights and threshold . Finally, the image feature extraction and selection of POLSAR input quantum cloning evolutionary algorithm to optimize the BP neural network classifier to obtain POLSAR image classification results . In summary , this paper mainly to complete two tasks: First, the clonal evolution based on quantum algorithm to optimize the initial weights and threshold of BP neural network method , after optimized BP neural network can converge to the global optimum value , when the BP neural network for classification and function optimization can get more accurate results ; Second, the classifier for POLSAR image classification , the experimental results show that this algorithm is compared with other classic classification algorithms , classification results Figure the better , higher classification accuracy .

Related Dissertations

  1. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  2. Research on Visual Servo System of Mechanical ARM,TP242.6
  3. Municipal tourism land use planning environmental impact assessment,X820.3
  4. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  5. The Research on Evaluation of Living Status Systems of Expressway Relocated People,D523
  6. Mine Risk Information Integration and Intelligent Early Warning,X936
  7. Research of Orange Quality Classification Technology Based on Computer Vision,TP391.41
  8. Optimization Study on Gating System and Molding Process Parameters of Injection Mold Based on Simulation,TQ320.662
  9. Study on Luohe Technical Supervision Bureau of Food Safety Early Warrning System Based on Neural Network,F203
  10. Research of Adaptive Active Noise Control Based on Neural Network,TP183
  11. Research on Automatic Reading System for Digital Meters,TP391.41
  12. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  13. The Research of Evaluation Method in Connect6 Based on BP-TD Learning,TP18
  14. Research on State Diagnosis on Fan Based on Factor Analysis and BP Neural Network,F426.61
  15. The Research and Design of Converter Steelmaking Endpoint Guiding System,TF345
  16. Analysis on Water Ecological Carrying Capacity of Jiangxi Province,TV213.4
  17. Research Offingerprint of Communication Behavior,TP311.13
  18. Research of the Electrode Lifting Hydraulic System of the 60t Electric Arc Furnace,TF748.41
  19. In-furnace Temperature Information Included Combustion Optimization of a Utility Boiler,TK227.1
  20. Research on Daily Load-forecasting for Power Grid Based on ANN,TM715
  21. Study on Safety Comprehensive Assessment of Hydro-Power Construction Sites,TV513

CLC: > Industrial Technology > Radio electronics, telecommunications technology > Radar > Radar equipment,radar > Radar receiving equipment > Data,image processing and admission
© 2012 www.DissertationTopic.Net  Mobile