Dissertation > Excellent graduate degree dissertation topics show

Parallel Image Processing Techniques Using GPU for Surface Defect Inspection

Author: WangChengShun
Tutor: LuRongSheng
School: Hefei University of Technology
Course: Optical Engineering
Keywords: Defect of surface detection Fourier transform Haar wavelettransform CUDA architecture
CLC: TP391.41
Type: Master's thesis
Year: 2012
Downloads: 116
Quote: 0
Read: Download Dissertation

Abstract


In this paper, considered automatic optical methods detect surface defects, taking TFT-LCD panel surface defects as an example. Study the problem of surface defect detection in the condition of the frequency patterned background and low image contrast. At the same time, study the surface defect detection in the condition of non-periodicity background. In order to improve the speed of detection, do parallel optimization of related algorithms on GPU/CUDA.For the LCD panel surface periodic texture background, have some relationship between the distance of adjacent peak value Δx in the spatial domain and Δu in the frequency domain. It eliminates the frequency components that represent the periodic pattern of a TFT-LCD line image in the1-D Fourier spectrum. In order to improve defects contrast, remove high-frequency and reserve the low-frequency which is represent defect, and then reconstruct the1-D Fourier domain image to1-D spatial domain image using the inverse Fourier transform.1-D Haar wavelet transform is applied to remove uneven illumination in the filtered image so that defects can be segmented with simple statistical control limits. Get the Connected Component Labeling (CCL) of each defect and marked them with the Minimum Enclosing Rectangle (MER).In order to improve the speed of the surface defect detection, parallel the image processing based on NVIDIA’s GPU/CUDA. Optimize the algorithm which is time-consuming, such as Fourier transform, wavelet decomposition, connected component labeling, and minimum enclosing rectangle. Apply different optimization strategy to different problem.In the experiment, analyze the coefficient of k which controlled the thresholds and w which decide the range of high-frequency. At the same time, consider the image under different illumination. At last, considered the performance of algorithms run on GPU, According the size of the image, achieved the speedup about20-50times. It has a well reference value on surface defect detection.

Related Dissertations

  1. Analysis of Spread Spectrum Signals Based on FRFT,TN911.6
  2. Research on Improvement of DSSS Receiver Based on Phase Domain,TN914.42
  3. Analysis of Infrared Spectral Features and Identification of Al-responsive Genes in Small Black Soybean with Aluminum Stress,S529
  4. Image Quality Assessment Algorithms in Iris Recognition,TP391.41
  5. The Research on High Frequency UPS Based on Parallel Interleaved Technique,TM464
  6. Single-Channel Color Image Encryption Algorithms with Chaos and Fractional Fourier Transform,TP309.7
  7. Large-capacity digital fingerprint system embedding algorithm,TP309.7
  8. The Break-bar Fault Diagnostics of the Asynchronous Motors Based on Variable Frequency Drives,TM343
  9. Male Silk Properties and Comparative Study of Its Optimal Dyeing Conditions When Dyed with Reactive and Acid Dyes,TS102.33
  10. Research on Robust Digital Audio Watermarking,TP309.7
  11. Research on Point Pattern Matching Algorithm Based on Invariant Sequence,TP391.41
  12. Design and Realization on Harmonic Instrument Equipments Based on DSP,TM935
  13. The Research on the Low Toxic Urea-Formaldehyde Resin Adhesive in Artificial Board,TQ433.431
  14. Studies on Experimental Modeling and Frequency Domain Identification of Nonlinear Systems,O322
  15. The Computation and Research of Optical Diffraction Field,O436.1
  16. Enhance Holographic Reconstructed Image Displayed by DMD,O438.1
  17. Studies on FTIR Features and Physiological Characteristics of Broad Bean under Aluminum,X173
  18. The Application of Rayleigh Wave Investigation in BenXi DongShan’s Mined-out Areas,P631.4
  19. Methods of Compensation for Diffraction Effects in Surface Acoustic Wave Filters,TN713
  20. A Deflection and Vibration Measurement System Based on CCD Imaging Sensor,TN386.5
  21. Study on Key Devices and PAPR Reduction Technologies in All-optical OFDM Systems,TN919.3

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