DOI QR코드

DOI QR Code

기계 학습을 활용한 이미지 결함 검출 모델 개발

Development of Image Defect Detection Model Using Machine Learning

  • 이남영 (전남대학교 멀티미디어전공) ;
  • 조혁현 (전남대학교 멀티미디어전공) ;
  • 정희택 (전남대학교 멀티미디어전공)
  • 투고 : 2020.04.02
  • 심사 : 2020.06.15
  • 발행 : 2020.06.30

초록

최근 기계 학습을 활용한 비전 검사 시스템의 개발이 활발해지고 있다. 본 연구는 기계 학습을 활용한 결함 검사 모델을 개발하고자 한다. 이미지에 대한 결함 검출 문제는 기계 학습에 있어 지도 학습 방법인 분류 문제에 해당한다. 본 연구에서는 특징을 자동 추출하는 알고리즘과 특징을 추출하지 않는 알고리즘을 기반으로 결함 검출 모델을 개발한다. 특징을 자동 추출하는 알고리즘으로 1차원 합성곱 신경망과 2차원 합성곱 신경망을 활용하였으며, 특징을 추출하지 않는 알고리즘으로 다중 퍼셉트론, 서포트 벡터 머신을 활용하였다. 4가지 모델을 기반으로 결함 검출 모델을 개발하였고 이들의 정확도와 AUC를 기반으로 성능 비교하였다. 이미지 분류는 합성곱 신경망을 활용한 모델 개발이 일반적임에도, 본 연구에서 이미지의 화소를 RGB 값으로 변환하여 서포트 벡터 머신 모델을 개발할 때 높은 정확도와 AUC를 얻을 수 있었다.

Recently, the development of a vision inspection system using machine learning has become more active. This study seeks to develop a defect inspection model using machine learning. Defect detection problems for images correspond to classification problems, which are the method of supervised learning in machine learning. In this study, defect detection models are developed based on algorithms that automatically extract features and algorithms that do not extract features. One-dimensional CNN and two-dimensional CNN are used as algorithms for automatic extraction of features, and MLP and SVM are used as algorithms for non-extracting features. A defect detection model is developed based on four models and their accuracy and AUC compare based on AUC. Although image classification is common in the development of models using CNN, high accuracy and AUC is achieved when developing SVM models by converting pixels from images into RGB values in this study.

키워드

참고문헌

  1. H. Kang, J. Lee, S. Choi, H. Kim, J. Park, J. Son, B. Kim, and S. noh, "Smart Manufacturing: Past Research, Present Findings, and Future Directions," J. of Precision Engineering and Manufacturing-Green Technology, vol. 3, no. 1, 2016, pp. 111-128. https://doi.org/10.1007/s40684-016-0015-5
  2. J. Ha and T, Song, "Automatic detection of surface area for the inspection of color fastener," J. of the Korea Institute of Electronic Communication Science, vol. 11, no. 1, 2016, pp. 107-112. https://doi.org/10.13067/JKIECS.2016.11.1.107
  3. C. Moon, "Implementation of an FPGA-based Frame Grabber System for PCB Pattern Detection," J. of the Korea Institute of Electronic Communication Science, vol. 13, no. 2, 2018, pp. 435-442. https://doi.org/10.13067/JKIECS.2018.13.2.435
  4. Envision, "Understanding Line Scan Camera Applications," Technical report, July 2014.
  5. Y. Cha and W. Choi, "Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks," Computer-Aided Civil and Infrastructure Engineering, vol. 32, 2017, pp. 361-378. https://doi.org/10.1111/mice.12263
  6. J. Park, B. Kwon, J. Park, and D. Kang, "Machine Learning-Based Imaging System for Surface Defect Inspection," J. of Precision Engineering and Manufacturing-Green Technology, vol. 3, no. 3, 2016, pp. 303-310. https://doi.org/10.1007/s40684-016-0039-x
  7. C. C. Aggarwal, Neural Networks and Deep Learning. A Textbook. Basel: Springer, 2018.
  8. X. Zhang, J. Zou, K. He, and J. Sun, "Accelerating very deep convolutional networks for classification and detection," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 38, 2015, pp. 1943-1955. https://doi.org/10.1109/TPAMI.2015.2502579
  9. S. Bak, M. Jeong, D. Hwang, U. Enkhjargal, and H. Yoon, "Study on Cochlodinium polykrikoides Red tide Prediction using Deep Neural Network," J. of the Korea Institute of Electronic Communication Science, vol. 14, no. 6, 2019, pp. 1161-1170. https://doi.org/10.13067/JKIECS.2019.14.6.1161
  10. S. Bang, "Implementation of Image based Fire Detection System Using Convolution Neural Network," J. of the Korea Institute of Electronic Communication Science, vol. 12, no. 2, 2017, pp. 331-336. https://doi.org/10.13067/JKIECS.2017.12.2.331
  11. J. Jo, "Effectiveness of normalization Pre-Processing of Big Data to the Machine Learning Performance," J. of the Korea Institute of Electronic Communication Science, vol. 14, no. 3, 2019, pp. 547-552. https://doi.org/10.13067/JKIECS.2019.14.3.547