DOI QR코드

DOI QR Code

A Study on Rotational Alignment Algorithm for Improving Character Recognition

문자 인식 향상을 위한 회전 정렬 알고리즘에 관한 연구

  • Jin, Go-Whan (Department of IT Convergence, Woosong University)
  • Received : 2019.10.14
  • Accepted : 2019.11.20
  • Published : 2019.11.28

Abstract

Video image based technology is being used in various fields with continuous development. The demand for vision system technology that analyzes and discriminates image objects acquired through cameras is rapidly increasing. Image processing is one of the core technologies of vision systems, and is used for defect inspection in the semiconductor manufacturing field, object recognition inspection such as the number of tire surfaces and symbols. In addition, research into license plate recognition is ongoing, and it is necessary to recognize objects quickly and accurately. In this paper, propose a recognition model through the rotational alignment of objects after checking the angle value of the tilt of the object in the input video image for the recognition of inclined objects such as numbers or symbols marked on the surface. The proposed model can perform object recognition of the rotationally sorted image after extracting the object region and calculating the angle of the object based on the contour algorithm. The proposed model extracts the object region based on the contour algorithm, calculates the angle of the object, and then performs object recognition on the rotationally aligned image. In future research, it is necessary to study template matching through machine learning.

영상을 기반으로 하는 기술들의 지속적인 발전으로 다양한 분야에서 활용되고 있고, 카메라를 통하여 획득한 영상의 객체를 분석하고 판별하는 비전 시스템의 기술 수요가 급속하게 증가하고 있다. 비전 시스템의 핵심 기술인 영상처리는 반도체 생산 분야의 불량 검사, 타이어 표면의 숫자 및 심볼과 같은 객체 인식 검사 등에 사용되고 있고, 자동차 번호판 인식 등의 연구가 계속하여 이루어지고 있는 실정으로, 객체를 신속, 정확하게 인식할 필요가 있다. 본 논문에서는 곡면과 같은 곳에 마킹되어 있는 숫자나 심볼과 같이 기울어진 객체를 인식하기 위하여 입력된 영상 이미지의 객체 기울기에 대한 각도 값을 확인하여 객체의 회전 정렬을 통한 인식 모델을 제안한다. 제안 모델은 컨투어 알고리즘을 기반으로 객체 영역을 추출하고, 객체의 각도를 산출한 후, 회전 정렬된 이미지에 대한 객체 인식을 진행할 수 있는 모델이다. 향후 연구에서는 기계학습을 통한 탬플릿 매칭 연구가 필요하다.

Keywords

References

  1. S. H. Kim. (2016). Realtime 3D Human Full-Body Convergence Motion Capture using a Kinect Sensor. Journal of Digital Convergence, 14(1), 189-194. DOI : 10.14400/JDC.2016.14.1.189
  2. M. Janoczki, A. Becker, L. Jakab, R. Grof & T. Takacs. (2013). Automatic Optical Inspection of Soldering. In aterial Science-Advanced Topics. 387-440. DOI : 10.5772/51699
  3. Y. R. Seo, K. Park, S. K. Kim & S. W. Ra. (2011). Vibration Analysis for a Feeding Unit of Vision Inspection System of Precision Screws. Journal of The Korean Society of Manufacturing Technology Engineers, 20(4), 446-451.
  4. G. S. Kim, Y. H. Park, J. S. Park & J. S. Cho. (2015). Auto parts visual inspection in severe changes in the lighting environment. Journal of Institute of Control, Robotics and Systems, 21(12), 1109-1114. DOI : 10.5302/J.ICROS.2015.15.0134
  5. J. J. Park, G. H. Kim & E. S. Lee. (2014). A study on the elliptical gear inspection system using machine vision. Transactions of the Korean Society of Mechanical Engineers A, 38(1), 59-63. DOI : 10.3795/KSME-A.2014.38.1.059
  6. T. H. Lee, K. R. Park & D. H. Kim. (2017). A Study on Scratch Detection of Semiconductor Package using Mask Image. Journal of the Korea Convergence Society, 8(11), 43-48. DOI : 10.15207/JKCS.2017.8.11.043
  7. G. W. Jin. (2017). A Study on the BGA Package Measurement using Noise Reduction Filters. Journal of the Korea Convergence Society, 8(11), 15-20. DOI : 10.15207/JKCS.2017.8.11.015
  8. J. W. Jang & G. M. Park. (2017). License Plate Recognition System based on Normal CCTV. Journal of The Institute of Electronics and Information Engineers, 54(8), 89-96. DOI : 10.5573/ieie.2017.54.8.89
  9. M. K. Oh & J. C. Park. (2017). Long Distance Vehicle License Plate Region Detection Using Low Resolution Feature of License Plate Region in Road View Images. Journal of Digital Convergence, 15(1), 239-245. DOI : 10.14400/JDC.2017.15.1.239
  10. H. R. Shin, S. H. Lee, J. S. Park & J. K. Song. (2019). Performance Improvement of Optical Character Recognition for Parts Book Using Pre-processing of Modified VGG Model. The Journal of the Korea Institute of Electronic Communication Sciences, 14(2), 433-438. DOI : 10.13067/JKIECS.2019.14.2.433
  11. M. K. Kwon & H. S. Yang. (2017). A scene search method based on principal character identification using convolutional neural network, Journal of Convergence for Information Technology, 7(2), 31-36. DOI : 10.22156/CS4SMB.2017.7.2.031
  12. S. K. Lee, Y. S. Park, G. S. Lee, J. Y. Lee & S. H. Lee. (2013). An Automatic Object Extraction Method Using Color Features of Object and Background in Image. Journal of Digital Convergence, 11(12), 459-465. DOI : 10.14400/JDPM.2013.11.12.459
  13. H. J. Hahm. (2017). A Study of Smart Factory Policy For ICT-Based. Journal of the Global e-Business Association, The e-Business Studies, 18(6), 363-380. DOI : 10.20462/TeBS.2017.12.18.6.363
  14. D. Zhao. (2010). A Study on the Face Expressive Recognition based on the Skin Color and the Face Geometric Characteristics. Master's Thesis. PaiChai University, Daejeon.
  15. J. Y. Song. (2018). A Recognition Algorithm of Handwritten Numerals based on Structure Features. The Journal of The Institute of Internet, Broadcasting and Communication, 18(6), 151-156. DOI : 10.7236/JIIBC.2018.18.6.151
  16. C. H. Woo. (2013). Image Preprocessing in Container Identifier Recognition System Using Multiple Threshold Regions. Journal of Korea Multimedia Society, 16(5), 549-557. DOI : 10.9717/kmms.2013.16.5.549
  17. Y. S. Hwang, H. Y. Yu & J. M. Lee. (2016). Robust Visual Odometry System for Illumination Variations Using Adaptive Thresholding. Journal of Institute of Control, Robotics and Systems, 22(9), 738-744 DOI : 10.5302/J.ICROS.2016.15.0218
  18. S. H. Kwon, H. C. Jeong, S. T. Seo, I. K. Lee & C. S. Son. (2008). Histogram equalization-based thresholding. IEICE TRANSACTIONS on Information and Systems, 91(11), 2751-2753. DOI: 10.1093/ietisy/e91-d.11.2751