Dissertation > Excellent graduate degree dissertation topics show

The Research of Medical Images Registration Based on Feature Points and Mutual Information

Author: BaoJunXiao
Tutor: JingJun
School: Yanshan University
Course: Biomedical Engineering
Keywords: Medical Image Registration Image preprocessing harris Mutual Information Powell PSO Registration results assessment
CLC: TP391.41
Type: Master's thesis
Year: 2010
Downloads: 210
Quote: 1
Read: Download Dissertation

Abstract


Medical image registration is one of the hot issues of the field of medical image processing , is the premise and basis of the image information fusion , automatic registration of medical images and theoretical studies on the basis of medical research , clinical diagnosis , treatment , and efficacy evaluation has significance. In this paper, a group of medical image data technology and algorithms for automatic registration key theoretical and experimental research . The main tasks are: for the imaging characteristics of medical images , medical image pre-processing method . Currently popular gray transform , histogram processing , filtering and color enhancement method to summarize and experimental studies , and lay the foundation for the subsequent image registration . Harris feature point - based medical image registration , and focus on the medical image registration based on mutual information . Medical image registration method based on feature points from the feature point extraction operator to start, a comparative study of the accuracy and stability , to improve the algorithm by theoretical and experimental studies . Feature points to match the the neighborhood gray feature points as a similarity measure , search space with affine transform space and Mahalanobis distance affine transformation invariance correct matching feature points , the last parameter optimization . Do not need to do such as feature extraction pretreatment needs of human-computer interaction , and easy to implement automatic registration based on mutual information registration method has advantages . In this paper, based on the research of related concepts and principles , focusing on theoretical and experimental studies of interpolation and optimization methods , including bilinear interpolation and PV (partial volume) interpolation and the Powell optimization algorithm and PSO ( Particle Swarm Optimization ) algorithm theoretical and experimental comparative study . Finally, there is the rating of the registration results . Registration method of the previous two categories in terms of accuracy , rate , noise immunity , etc. on the finishing the basis of the analysis of assessment methods and evaluation , a comparative analysis of performance . The results showed that : paper, two methods have high accuracy , speed , robustness , but the effect of registration application object .

Related Dissertations

  1. Research of Image Mosaic Technology,TP391.41
  2. Word Sense Disambiguation Corpus Automatic Acquisition,TP391.1
  3. Based on particle swarm algorithm for molecular docking,R91
  4. Research on the Improvements and Applications of Particle Swarm Optimization,TP18
  5. Texture Synthesis Algorithm Based on Samples,TP391.41
  6. Research and Implementation of Non-rigid Medical Image Registration Method Based on Improved Optical Flow Model,TP391.41
  7. Research on Route Optimization of Open-pit Mine Road Based on PSO,TP301.6
  8. Based on RFID Prison Intelligent Management System Research and Implementation,TP315
  9. Algorithm and Implementation Based on Non-rigid Medical Image Registration,TP391.41
  10. Research on Supply-production-distribution Planning Model with Variable Cycle for Petro-chemical Products Based on DE-PSO Algorithm,F426.72;F224
  11. Research and Realization of License Plate Character Recognition Algorithm Based on SVM,TP391.41
  12. The Research of QoS Based Routing Algorithm in Wireless Sensor Networks,TP212.9
  13. Research on Multi-time Period Production and Procurement Plan of Supply Chain under Uncertainty,F224
  14. Multi-step-ahead Stock Price Index Forecasting Based on Hybrid Models,F224
  15. Particle Swarm Optimization in Reservoir Flood Dispatching Research,TP301.6
  16. Applied to narrow gap SAW image acquisition and pre-processing System,TG445
  17. Smart Grid battery energy storage value assessment study,TM76
  18. Based on swarm intelligence optimization algorithm for medical image feature,TP391.41
  19. A class of multi-robot systems research task allocation method,TP242
  20. PDE-based image registration and fusion method,TP391.41
  21. Image registration based on the rotation angle calculation methods sand,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