Dissertation > Excellent graduate degree dissertation topics show

Research on Morphological Associative Memories Based on Dynamic Kernel and Its Application

Author: HuangShaoFang
Tutor: WuXiSheng
School: Jiangnan University
Course: Applied Computer Technology
Keywords: Associative Memory Morphology Neural Network Pattern Recognition Image processing Dynamic nuclear
CLC: TP18
Type: Master's thesis
Year: 2006
Downloads: 68
Quote: 0
Read: Download Dissertation

Abstract


Associative memory is one of the important functions of the human brain cells . In recent years , the form of proposed by GXRitter et al bidirectional associative memory network ( MBAM ) [ 1,2 ] is a more effective method of associative memory , to overcome the limited sample storage capacity of traditional associative memory network , associative memory requires multiple iterations , etc. defects , a better solution to the binary image associative memory problems . Binary image with a single noise , has been more successful applications , but was powerless to do anything MBAM binary image containing random noise . At the same time can be used for gray-scale image associative memory network is also unusual , and can handle grayscale images containing random noise is even more rare . This article is in MBAM based on , put forward a dynamic nuclear morphological associative memory network , which aims to address the problem of containing any random noise image associative memory . This method was added to the idea of a dynamic core , able to get the right associative memory results in a binary image containing random noise associative memory . Also utilized in the binary image pattern recognition . As an original nuclear is not the only selected according to the desired identity contain noise image , different contain noise image , nuclear , so called dynamic nuclear . The experiment proved its recognition accuracy is superior to classical associative memory method and MBAM , especially when the noise is more and more complex, the image data is relatively large , this advantage will be more obvious. In this paper, the dynamic kernel method based on improvements and modifications , and then he promote the use of grayscale image associative memory and recognition , and to obtain the desired results . It can not only better treatment containing noise gradation image associative memory problems, but can also be used to identify whether or not an image containing noise gray-scale image and stored in the database matching , so as to solve the identification problem , our experiment also verified that conclusions.

Related Dissertations

  1. Development of the Platform for Compressor Optimization Design and Aerodynamic Optimization Design in the Transonic Compressor,TH45
  2. Research on Temperature Measurement Technique Based on CCD Image Sensor,TH811
  3. The Classification of High Dimsnsion Flew Field Based on Manifold Learning,V231.3
  4. Research on Basic Algorithms of Digital Image Processing and Implementation with FPGA,TP391.41
  5. Tongue Feature Extraction and Research of Fusion Classification,TP391.41
  6. Research of Images Enhancing Algorithms on Fog or Backlighting Conditions and Implementation with Hardwares,TP391.41
  7. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  8. Study on Virtual Detector of Infrared Hyper-Spectral Image,TP391.41
  9. Research on Text Classification Based on Biomimetic Pattern Recongnition,TP391.1
  10. Research on the Image Real-Time Acquisition, Storage and Image Processing System,TP391.41
  11. The Research of Moving Object Tracking System Based on Embeded Image Process Unit,TP391.41
  12. The Application of Fuzzy Control and Neural Network in Planar Double Inverted Pendulum,TP273.4
  13. Research of Visual Servoing in 4-DOF Robotic Manipulator,TP242.6
  14. Research on Visual Servo System of Mechanical ARM,TP242.6
  15. Application Research of Digital Image Processing on Container Inspection,TP274.4
  16. Design of Weapon Detection Device Control System,TP183
  17. The Properties of Laser Speckle Based on the Mathematical Morphology,O29
  18. Municipal tourism land use planning environmental impact assessment,X820.3
  19. Three-Dimensional Numerical Modelling for the Head and the Electric Field Analysis of DBS,R742.5
  20. Research on the Inteligent System of High Performance Concrete Mix Design in Zhujiang Triangle Area,TU528
  21. Application of Semi-Structure in Leisure Dress,TS941.2

CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory
© 2012 www.DissertationTopic.Net  Mobile