Dissertation > Excellent graduate degree dissertation topics show

Image Fusion New Algorithm Based on the Combination of NSCT and Region Segmentation

Author: MiaoFengMei
Tutor: WuYan
School: Xi'an University of Electronic Science and Technology
Course: Circuits and Systems
Keywords: NSCT Region segmentation Image Fusion Graph Theory Edge Detection
CLC: TP391.41
Type: Master's thesis
Year: 2009
Downloads: 388
Quote: 5
Read: Download Dissertation

Abstract


In recent years , image fusion has become an important technology in the field of image understanding and computer vision . Image fusion can produce more accurate than a single source of information , more complete , more reliable judgment . The characteristics of the infrared image and visible image , this paper studies a new algorithm based on edge detection and region segmentation , image fusion . The main work is as follows : In this paper, on the basis of the basic theory of the introductory image fusion of traditional image fusion method . The Nonsubsampled Contourlet Transform (NonSubsampled Contourlet Transfrom, NSCT) theory , and further NSCT and edge detection based image fusion algorithm . Firstly, the image NSCT; Secondly, the low frequency approximation component images using region - based information fusion rules for high-frequency detail image edge feature information and normalized correlation moment combined fusion rules ; Finally , non- downsampling Contourlet inverse transform fusion image is obtained . This paper also proposed a new algorithm based on NSCT and regional segmentation of image fusion . The algorithm based on graph theory and FCM ( Fuzzy C -Means Clustering FCM) method of infrared image and visible image region segmentation by region merging heterogeneous image area associated segmentation map . NSCT, then the image fusion component images the use of regional energy ratio and regional sharpness than the characteristics of the two regions metric operator for the low-frequency approximation measure for high-frequency detail image use the regional characteristics of the area boundary definition operator fusion . Through the simulation of multiple infrared and visible light images , and compared with a local window energy - based wavelet transform and NSCT fusion algorithm , the simulation results show that : In this paper, two new algorithms get rich fusion of images in visible light images reserved background information , are inherited infrared image of the target information .

Related Dissertations

  1. Research on Joint Target Detection for Dual-Sensor Image and System Implementation,TP391.41
  2. Research on Detecting Optical Fiber Geometric Parameter Based on Machine Vision,TN253
  3. Research on Contourlet Transform and Its Application on Image Processing,TP391.41
  4. The Research of Application of Ridgelet Transform in the Fusion of Multispectral and Panchromatic Images,TP391.41
  5. Multi-source image fusion technology research,TP391.41
  6. Research of Image Segmentation in Web Image Search Based on GPUs,TP391.41
  7. Visual underwater target detection and recognition,TP391.41
  8. Image intensifier and a screen resolution of defect detection technology,TN144
  9. Color medical image segmentation technology research,TP391.41
  10. Based on structural similarity with the MTF image quality evaluation method,TP391.41
  11. Research on Fundus Image Fusion and System Implementation,TP391.41
  12. Multi-source Remote Sensing Image Fusion and Its Application Research,TP751
  13. The Image Fusion Technology Based on Multiscale Geometric Analysis,TP391.41
  14. Researches on Image Segmentation Approaches,TP391.41
  15. SAR image denoising and fusion based on multiscale geometric analysis,TN957.52
  16. Research on Technology of Medical Images Fusion,TP391.41
  17. Research of Image Mosaic Technology,TP391.41
  18. Research and Implementation of Reconfigurable Computing System for Image Edge Detection,TP391.41
  19. Edge Detection of Leukemia Cell Image Based on Spiking Neural Network,TP391.41
  20. Research on Pixel-level Pretreatment of Remote Sensing Image and Fusion,TP751
  21. Remote sensing image fusion technology based quality improvement and repair,TP751

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