Dissertation > Excellent graduate degree dissertation topics show

Substation Infrared Remote-view Image Recognition

Author: LiRong
Tutor: WuDongMei
School: Xi'an University of Science and Technology
Course: Circuits and Systems
Keywords: Infrared image Image Segmentation Image Recognition Unchanged from the Humanoid recognition
CLC: TP751
Type: Master's thesis
Year: 2010
Downloads: 48
Quote: 0
Read: Download Dissertation

Abstract


With the development of modern mass production and scientific and technological progress , the increasing demand for electricity , higher reliability and economy , as well as the stability of the electric power production equipment . In order to ensure the safety of the power supply system , the infrared technology was applied to the detection of power system . Its image processing technology and pattern recognition technology equipment identification and fault diagnosis . It is the technical issues surrounding the field of substation equipment fault diagnosis , mainly in equipment intelligent recognition method . First , according to the pattern recognition process block diagram of the infrared images obtained pretreatment segmentation method based on morphological edge detection and Ostu of combined watershed segmentation method based on mathematical morphology , experimental results , and on this basis indicate that both methods a good segmentation of the edge image , but a first method is better adaptability . Then, Hu invariant moments to extract image features . Hu invariant moments are calculated for each pixel of the image , the large amount of calculation , in order to solve this problem , this paper introduces the concept of the line moments . Moment of the characteristics of the image using line , although its also have translational and rotational invariance scale before and after the line moments feature but has a very different , but for the same image , up to 12.5934 . According to this problem , in this article from the invariant moments algorithm its analysis and put forward their own improved method . Simulation results improved invariant moments for the same image , the biggest difference between before and after scaling : 0.08622 . This shows that the improved moment invariants good to solve the above problems . Finally, the KNN classifier for classification , identification rate of 100% . In addition, the paper also studied the human form recognition , and humanoid identification method based on neural network , the recognition rate of 92.857% .

Related Dissertations

  1. Research on Image Recognition Algorithm in the Forest Fire Prevention System,TP391.41
  2. Multi-currency Notes Technology Research and Implementation,TP391.41
  3. Application Research of Digital Image Processing on Container Inspection,TP274.4
  4. Study on the Design and Biomechanical Behaviors of Individualized Artificial Knee Joint,R318.1
  5. Based on statistical methods of magnetic resonance imaging of the human brain image segmentation and three-dimensional analysis of the data,R445.2
  6. Road extraction algorithm based on region segmentation of remote sensing image,TP751
  7. Tobacco Diseases Auto-Recognition Research Based on Image Processing Technology,S435.72
  8. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  9. Space Infrared Target Simulation and Application of Target Trace,TP391.41
  10. BF-FCM Clustering Algorithm and Its Application in the Image Segmentation,TP391.41
  11. Study of High Resolution Image Road Extraction Method Based on Morphology Strategy,TP751
  12. Segmentation of cDNA Microarray Image Using Fuzzy C-means Algorithm Optimized by Particle Swarm,TP391.41
  13. Visual-based Localization Algorithm Design on Humanoid Robot Soccer,TP391.41
  14. Extraction Algorithm Research of Phase-change Line from Complex Phase-change Thermography Sequence,TP391.41
  15. Research on Medical Image Segmentation Method Based on Markov Random Field Model,TP391.41
  16. The Research of Key Techniques on Computer-Aided Planning before Liver Transplantation,TP391.41
  17. An Analysis of Image Segmentation Based on Otsu Method and Mathematic Morphology,TP391.41
  18. Research on Segmentation Algorithms of Regions of Interest for Pulmonary Lesions,TP391.41
  19. The Developing of Cotton "Three Wire" Automatic Removing System Based on CCD Detection Technology,TP391.41
  20. Study on Medical Image Segmentation Method Based on Parametric Active Contour Models,TP391.41
  21. The Design of Guide Robot Based on Embedded Technology,TP368.1

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