Dissertation > Excellent graduate degree dissertation topics show

A Texture Analysis and Neural Network Method for the Classification of SAR Images with Spilled Oil

Author: ZhuLiSong
Tutor: AnJuBai
School: Dalian Maritime University
Course: Applied Computer Technology
Keywords: Synthetic Aperture Radar (SAR) Texture analysis BP neural network RBF neural network Probabilistic neural network
CLC: TN957.51
Type: Master's thesis
Year: 2005
Downloads: 323
Quote: 7
Read: Download Dissertation

Abstract


Synthetic Aperture Radar (Synthetic Aperture Radar, SAR) images have been widely used in marine oil spill monitoring , since the oil spill from the smoothing effect weakening effect on radar reflectivity , so the radar image will be displayed on the dark shaded area , while the surrounding waters , but because the role of surface roughness and display brighter . Using this principle , SAR can be used to observe sea oil spill occurred . In order to accurately spill SAR image classification , this paper proposes a texture analysis method combined with neural network to classify oil spill images. This article uses texture analysis phase GLCM method to calculate the oil spill in SAR images of the most sensitive four texture feature values ??, combined with the composition of the gray value pixel classification feature vector images . Taking into account the neural network with self- organizing, self -learning, adaptive and associative ability , through repeated training sample , sample characteristics can distinguish various types of this advantage . Typical paper selected image area , the extracted feature vector is input to the neural network for training. Commonly used neural network model BP neural network, RBF neural network (RBF) and probabilistic neural network image and sea oil spill and other substances for training. Network convergence, the use of an image to be recognized classification test results. By comparing three network models of SAR image recognition spill effects and classification accuracy , three network models are able to achieve more satisfactory results. And probabilistic neural network classification model , not only in classification accuracy and computation time are better than in the other two models .

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. Information Extraction of Marine Oil Spill with Collaborative Images of ASAR and MODIS,X87
  7. Mine Risk Information Integration and Intelligent Early Warning,X936
  8. Research of Orange Quality Classification Technology Based on Computer Vision,TP391.41
  9. Study on Risk Identification and Evaluation of Manufacturing Green Products R & D,F205;F224
  10. Optimization Study on Gating System and Molding Process Parameters of Injection Mold Based on Simulation,TQ320.662
  11. Study on Luohe Technical Supervision Bureau of Food Safety Early Warrning System Based on Neural Network,F203
  12. Research of Adaptive Active Noise Control Based on Neural Network,TP183
  13. Research on Automatic Reading System for Digital Meters,TP391.41
  14. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  15. The Research of Evaluation Method in Connect6 Based on BP-TD Learning,TP18
  16. Research on State Diagnosis on Fan Based on Factor Analysis and BP Neural Network,F426.61
  17. The Research and Design of Converter Steelmaking Endpoint Guiding System,TF345
  18. Analysis on Water Ecological Carrying Capacity of Jiangxi Province,TV213.4
  19. Research Offingerprint of Communication Behavior,TP311.13
  20. Inspection and Recognition on a Class of Tool Processing Trace,TP391.41
  21. Research of the Electrode Lifting Hydraulic System of the 60t Electric Arc Furnace,TF748.41

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