Journal of the Institute of Convergence Signal Processing (융합신호처리학회논문지)

The Korea Institute of Convergence Signal Processing (한국융합신호처리학회)
권호 표지
DOI QR코드

DOI QR Code

3D Film Image Inspection Based on the Width of Optimized Height of Histogram

히스토그램의 최적 높이의 폭에 기반한 3차원 필름 영상 검사

  • Jae-Eun Lee (Div. of Computer Engineering, Pukyong National University) ;
  • Jong-Nam Kim (Div. of Computer Engineering, Pukyong National University)
  • 이재은 (부경대학교 컴퓨터공학부) ;
  • 김종남 (부경대학교 컴퓨터공학부)
  • Received : 2022.06.19
  • Accepted : 2022.06.30
  • Published : 2022.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

In order to classify 3D film images as right or wrong, it is necessary to detect the pattern in a 3D film image. However, if the contrast of the pixels in the 3D film image is low, it is not easy to classify as the right and wrong 3D film images because the pattern in the image might not be clear. In this paper, we propose a method of classifying 3D film images as right or wrong by comparing the width at a specific frequency of each histogram after obtaining the histogram. Since, it is classified using the width of the histogram, the analysis process is not complicated. From the experiment, the histograms of right and wrong 3D film images were distinctly different, and the proposed algorithm reflects these features, and showed that all 3D film images were accurately classified at a specific frequency of the histogram. The performance of the proposed algorithm was verified to be the best through the comparison test with the other methods such as image subtraction, otsu thresholding, canny edge detection, morphological geodesic active contour, and support vector machines, and it was shown that excellent classification accuracy could be obtained without detecting the patterns in 3D film images.

3차원 필름 영상을 양품 또는 불량품으로 분류하기 위해서는 필름의 영상 내 무늬를 검출해야 한다. 하지만 만약 필름 내 화소의 명암이 낮다면 영상 내 무늬가 선명하지 않아서 분류하기가 쉽지 않다. 본 논문에서는 3D 필름 영상들의 히스토그램을 구한 후, 각 히스토그램의 특정 빈도에서의 폭을 비교하여 정품과 불량품으로 분류하는 방법을 제안한다. 실험을 통하여 정품과 불량품의 히스토그램이 뚜렷하게 다르다는 것을 보였으며, 이러한 특징을 반영한 제안 알고리즘을 이용하여 히스토그램의 특정 빈도에서 모든 3D 필름 영상들이 정확하게 분류되는 것을 보였다. 기존에 연구된 방법들인 차영상, 오츠의 이진화 알고리즘, 캐니 엣지, 모폴로지 지오데식 엑티브 컨투어, 그리고 서포트 벡터 머신과의 성능 비교를 통하여 제안한 알고리즘의 성능이 가장 우수함을 검증하였으며, 영상 내 무늬를 검출할 필요 없이도 우수한 분류 정확도를 얻을 수 있다는 것을 보였다.

Keywords

Acknowledgement

본 논문은 부경대학교 자율창의연구사업의 지원으로 수행되었습니다.

References

  1. W. A. Mustafa, and M. A. Kader, "Binarization of document images: A comprehensive review," In Journal of Physics: Conference Series, IOP Publishing, Vol.1019, No.1, pp.012023, 2018.
  2. Y. S. Owotogbe, T. S. Ibiyemi, and B. A. Adu, "Edge Detection Techniques on Digital Images-A Review," Int J Innov Sci Res Technol, Vol.4, pp.329-332,
  3. L. Alvarez, L. Baumela, P. M. Neila, and P. Henriquez, "A Real Time Morphological Snakes Algorithm," Image Processing on Line, Vol. 2, pp.1-7, 2014.
  4. J. Ma, D. Wang, X. P. Wang, and X. Yang, "A Fast Algorithm for Geodesic Active Contours with Applications to Medical Image Segmentation," Computer Vision and Pattern Recognition pp.1-10, 2020.
  5. J. N. Mlyahilu, J. N. Mlyahilu, J. E. Lee, Y. B. Kim, and J.N. Kim, "Morphological geodesic active contour algorithm for the segmentation of the histogram- equalized welding bead image edges," IET Image Processing, 2022.
  6. R. Wang, W. Li, R. Li, and L. Zhang, "Automatic blur type classification via ensemble SVM," Signal processing: image communication, Vol.71, pp.24-35, 2019 https://doi.org/10.1016/j.image.2018.08.003
  7. P. Hsu, and B. Y. Chen. "Blurred image detection and classification,"International Conference on Multimedia Modeling, Berlin, Heidelberg,pp.277-286, Springer 2008.
  8. A. Salman, A. Semwal, U. Bhatt, and V. M. Thakkar, "Leaf classification and identification using Canny Edge Detector and SVM classifier," 2017 International Conference on Inventive Systems and Control (ICISC). IEEE, 2017.
  9. M. V. Thomas, C. Kanagasabapthi, and S. S. Yellampalli, "VHDL implementation of pattern based template matching in satellite images," 2017 International Conference on Smart Technologies for Smart Nation (SmartTechCon) , IEEE, Bangalore, India, pp.820-824, August 2017.
  10. B. Satish, P. Jayakrishnan, "Hardware implementation of template matching algorithm and its performance evaluation," International Conference on Microelectronics Devices, Circuits and Systems (ICMDCS), IEEE, Vellore, India, pp.1-7, August 2017.
  11. R. Wang, W. Li, R. Qin, and J. Wu, "Blur image classification based on deep learning," In 2017 IEEE International Conference on Imaging Systems and Techniques (IST), pp.1-6, 2017.
  12. Y. Li, X. Ye, and Y. Li, "Image quality assessment using deep convolutional networks," AIP Advances, Vol.7, No.12, pp.125324, 2017.
  13. U. Sara, A. Morium, and M. S. Uddin, "Image quality assessment through FSIM, SSIM, MSE and PSNR-a comparative study," Journal of Computer and Communications, Vol. 7, No3, pp.8-18, 2019.