Dissertation > Excellent graduate degree dissertation topics show

STUDY OF TARGET RECOGNITION USING JOINT TRANSFORM CORRELATOR

Author: DuanZuoLiang
Tutor: WangShi
School: University of Electronic Science and Technology
Course: Optics
Keywords: all-optical joint transform correlator image segmentation multi-reference images joint power spectra double-JPS interference
CLC: O438
Type: Master's thesis
Year: 2001
Downloads: 306
Quote: 0
Read: Download Dissertation

Abstract


The development of home and abroad and the theory of the joint transform correlator are described briefly in this thesis. The theory, optical implementation and applications of the joint transform correlator have been studied systematically. Some research works have been done to improve the reliability, precision, and parallelism of optical image recognition.The all-optical joint transform correlator are studied, and two methods used to improve its performance are proposed in the image recognition and identification. The one is to segment images which are the identifying image and the reference ones on the input plane, so as to obtain higher and sharper peak of their correlation. The other method is to use multi-reference images, which will produce a standard peak of correlation so as to determine whether the identifying image is correlative with the reference image or not, and make finish the target recognition more concisely.Using the holographic orthogonal grating to produce multi-beam light on the input plane is proposed in order to utilize the coherent light-power of illumination sufficiently. The plane optical wave which is vertical of the input plane are divided multi-beam ones of the several directions which will produce the joint power spectra(JPS) of the identifying image and the reference one respectively. And the joint power spectra lie different places. So they utilize sufficiently the space-bandwidth on the frequency spectrum plane, and try the light power抯 best for obtaining the higher peak of correlation.Finally, the way of the double-JPS interference in order to simplify the architecture and the processing program of joint transform correlator are proposed. Its merit is that needn抰 special optical components, preprocessing the identifying image and the reference one on the input plane, high pass filter in the space domain or frequency domain, and improving the JPS variedly. It can抰 recognize the image of the similar reference one that is its imperfection. The validity and feasibility of these methods are proved though theoretical analysis and experiment.

Related Dissertations

  1. Research on Image Recognition Algorithm in the Forest Fire Prevention System,TP391.41
  2. Application Research of Digital Image Processing on Container Inspection,TP274.4
  3. Study on the Design and Biomechanical Behaviors of Individualized Artificial Knee Joint,R318.1
  4. Based on statistical methods of magnetic resonance imaging of the human brain image segmentation and three-dimensional analysis of the data,R445.2
  5. Road extraction algorithm based on region segmentation of remote sensing image,TP751
  6. Tobacco Diseases Auto-Recognition Research Based on Image Processing Technology,S435.72
  7. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  8. Solder paste printing quality based on image processing techniques to detect,TP391.41
  9. Image Segmentation Based on Multi-Agent,TP391.41
  10. Research on the MRI Brain Image Segmentation Algorithm,TP391.41
  11. Research on Fingerprint Feature Extraction Method Based on Grayscale Image,TP391.41
  12. Markov random field DS evidence theory of the human brain image segmentation,TP391.41
  13. Research on Color Image Segmentation Algorithm,TP391.41
  14. Research of Dual-Mode Recognition Algorithm Based on Fingerprint and Finger Vein,TP391.41
  15. Research on Bayesian Optimization Algorithm and Its Application in Image Segmentation,TP391.41
  16. Segmentation of Image Sequences of Neuron Stem Cells Based on Level-set Algorithm Combined with Local Gray Threshold,TP391.41
  17. Obstacle Detection Method Based on Single Camera,TP242
  18. Research of Infrared Image Segmentation for Power Equipment in Substation,TP391.41
  19. Study on Defect Detection Algorithm of Industrial CT/DR Images Based on Wavelet Transform and C-V Model,TP391.41
  20. Chan-Vese active contour model of,TP391.41
  21. Study on Measurement Algorithm for Surface Area and Lumen Volume of Industrial CT Three-dimensional Images Based on C-V Model,TP391.41

CLC: > Mathematical sciences and chemical > Physics > Optics > Information Optics
© 2012 www.DissertationTopic.Net  Mobile