Dissertation > Excellent graduate degree dissertation topics show

Apple mold heart X-ray image enhancement and de-noising Method

Author: KangLiKui
Tutor: YangFuZeng
School: Northwest University of Science and Technology
Course: Agricultural Electrification and Automation
Keywords: Wavelet Analysis Image Processing Image Enhancement Image noise reduction
CLC: TP391.41
Type: Master's thesis
Year: 2009
Downloads: 97
Quote: 0
Read: Download Dissertation

Abstract


At present, non-destructive testing techniques for the study of fruit mostly reflected in the external quality, the corresponding image processing technology is relatively mature and existing commercial product, but its internal quality nondestructive testing technology research is relatively small. So the fruit internal quality NDT methods a study is a rewarding job. In this thesis, using X-ray technology, the mold heart disease and other causes of internal rot Apple for testing, due to the direct X-ray images obtained are often vague, to solve this problem, the paper in several different wavelet bases are used enhance low frequency, high frequency weakening method of image enhancement processing, and with the conventional histogram equalization image enhancement technology and based on local contrast image enhancement techniques were compared. Compare experimental results show that: histogram equalization method to enhance the processed image information entropy is 7.9698, the peak signal to noise ratio is 64.7107; while the use of local contrast enhancement processed image information entropy is 7.8679, the peak signal to noise ratio is 65.5321; using dmey wavelet enhancement, can get a clearer picture, image information entropy of 7.6335, the maximum peak signal to noise ratio reached 71.7531 (original apple mildew heart image information entropy is 7.9821, the peak signal to noise ratio is 63.9762). Therefore, the use of wavelet enhancement dmey treatment is better than the previous two enhancement methods and the use of several other wavelet enhancement. In addition, from the visual point of view, using the histogram equalization method to enhance the image processed easily lead to loss of edge information; use of local contrast enhancement processing on the image can not be enhanced while enhancing the overall mold heart projecting portion; wavelet selection dmey enhanced processing characteristics of the image information in the most prominent; From the above two aspects to be drawn: selection dmey wavelet bases its enhancement is the best. Images in obtaining or transmitting process will be all kinds of noise due to interference and the fallout of lower quality, the subsequent image processing adversely affected. So it is very necessary for image denoising, as much as possible to retain image detail information to improve image quality. This article is based on non-subsampled Contourlet transform Wiener filter denoising of noisy apple mildew heart image noise reduction processing, and then with the median filter, mean filter, Gaussian filtering, Wiener filtering and other four conventional de-noising method as well as in several different wavelets are used to improve soft threshold denoising method is compared; comparative test results show that: the use of four kinds of conventional de-noising method of the peak signal to noise ratio are 73.8821,75.2116,71.6993 and 74.8975; wavelet Transform improved soft threshold method uses dmey best wavelet denoising, peak signal to noise ratio reached 74.9510; using this method of noisy images are processed apple mildew heart the best effect, the peak signal to noise ratio reached 76.7026 (original image The peak signal to noise ratio is 68.6154), denoising best results.

Related Dissertations

  1. Research on Temperature Measurement Technique Based on CCD Image Sensor,TH811
  2. Research on Testing and Analyzing Technology for Time Parameter of Aerospace Relay,TM58
  3. Research on Basic Algorithms of Digital Image Processing and Implementation with FPGA,TP391.41
  4. Research of Images Enhancing Algorithms on Fog or Backlighting Conditions and Implementation with Hardwares,TP391.41
  5. Research on the Image Real-Time Acquisition, Storage and Image Processing System,TP391.41
  6. The Research of Moving Object Tracking System Based on Embeded Image Process Unit,TP391.41
  7. Research on Visual Servo System of Mechanical ARM,TP242.6
  8. Application Research of Digital Image Processing on Container Inspection,TP274.4
  9. Study of Event Related Potentials Based on Chinese Auditory Cognition,R318.0
  10. Three-Dimensional Numerical Modelling for the Head and the Electric Field Analysis of DBS,R742.5
  11. Application of Semi-Structure in Leisure Dress,TS941.2
  12. Research on Nondestructive Detection Technology for External Qualities of Papayas Based-on Vision,S667.9
  13. Technology of Blood Vessel Diameter Measurement Automatic Based on Digital Image Processing,R310
  14. Research on Detecting Optical Fiber Geometric Parameter Based on Machine Vision,TN253
  15. Research on Identification System of Cashmere and Wool Fiber,TS101.921
  16. Design of Garlic Planting Sorting Machine Based on Image Processing,S223.2
  17. Study on Detection and Grading of ’Jiro’ Persimmon’s External Quality Based on Computer Vision,S665.2
  18. Flow Behavior Description of Two-Phase Flow Based on Image Processing Techniques,TP391.41
  19. Active faults based radar image information extraction method applied research and demonstration,P542.3
  20. Research on License Plate Location Algorithm of License Plate Recognition System,TP391.41
  21. The Designing of HD Vehicle Detection System Based on Fpga,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