Dissertation > Excellent graduate degree dissertation topics show

Research on Image Edge Detection Base on Rough Sets and Mathematical Morphology

Author: LiuWenJie
Tutor: DengTingQuan
School: Harbin Engineering University
Course: System theory
Keywords: Fuzzy logic (I,T)- fuzzy rough sets edge detection path-based morphology edge thinning
CLC: TP391.41
Type: Master's thesis
Year: 2009
Downloads: 67
Quote: 2
Read: Download Dissertation

Abstract


Edge is one of the most fundamental and significant features of an image. Edge detection is the most fundamental issue in the area of image processing, image analysis and computer vision, and is a basic method for pattern recognition and image information extraction. There has been various algorithms proposed for it, but each of the algorithms has its drawbacks. So, current research mainly focuses on the work to find new methods for edge detection with specific application requirements or to make improvements on existing methods.Rough set is a theoretical method that deals with knowledge with uncompleteness and uncertainty, expresses, learns and deduces knowledge. In classic rough sets theory, the boundary of knowledge is defined according to upper approximation and lower approximation operator. In this dissertation we regard an image as a knowledge base, the boundary of knowledge as the edge of the image, and propose a method of edge detection using ((?),T)-fuzzy rough set when the relationship between ((?),T)-fuzzy rough approximation operators and classic rough approximation operators is investigated and discussed deeply. Experimental results demonstrate that the proposed edge detection algorithm has a better performance of smoothening edges, clarifying characteristic and enriching information of edges than traditional edge detectors.Mathematical morphology is a new discipline based on strict mathematical theory. Path-based morphology, a specification of mathematical morphology, is mainly used for the analysis of linear structures in images. The ((?),T)-fuzzy rough set can detect lots of information of images, but usually makes edges wide. We consider edges of images as linear structures to express image characteristic and propose an edge thinning method based on path-based morphology, and achieve desired purpose.

Related Dissertations

  1. Research on Detecting Optical Fiber Geometric Parameter Based on Machine Vision,TN253
  2. VSCF doubly-fed wind turbine maximum power point tracking control,TM614
  3. Image intensifier and a screen resolution of defect detection technology,TN144
  4. Based on structural similarity with the MTF image quality evaluation method,TP391.41
  5. Study on Intelligent Control System of Power Assembly for Hybrid Electric Vehicle,U469.72
  6. Research on Algorithm of Image Edge Detection Based on Wavelet Transformation,TP391.41
  7. The Research and Application of Image Recognition in Laser Welding Locating System,TP391.41
  8. Research on the Algorithm of Human Motion Detection in Interactive Projection System,TP391.41
  9. The Design and Implementation of the Finger Vein Recognition Prototype System,TP391.41
  10. The Research of FSVM and Its Application in Image Edge Detection,TP391.41
  11. Studies on Compression and Edge Detection of Medical Image,TP391.41
  12. Medical Image Registration Based on Mutual Information and Wavelet Transformation,TP391.41
  13. Researching of Self-Adaptable Wavelet Transform Arithmetic in the Image Edge Detection,TP391.41
  14. The Study of Support Vector Machine for Color Image Segmentation,TP391.41
  15. The Research and Improvement of Two Image Segmentation Methods Based on CT Images,TP391.41
  16. The Research of Unfertilized Eggs Automatic Verification System Based on the ARM Embedded Platform,TP391.41
  17. Edge Detection with Diffusion Filter,TP391.41
  18. Research and Implementation of Image Edge Detection Based on Regional Features,TP391.41
  19. Research of the Edge Detection Technology in Wireless Sensor Networks,TN929.5
  20. Research on Edge Detection and Segmentation Methods of Cardiac Magnetic Resonance Images,TP391.41
  21. Research on Vehicle-logo Location Technology,TP391.41

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