한국산업정보학회논문지 (Journal of Korea Society of Industrial Information Systems)

한국산업정보학회 (Korea Society of Industrial Information Systems)
권호 표지
DOI QR코드

DOI QR Code

HOG와 인공신경망을 이용한 자동차 모델 인식 시스템 성능 분석

Performance Evaluation of Car Model Recognition System Using HOG and Artificial Neural Network

  • 박기완 (금오공과대학교 컴퓨터소프트웨어공학과) ;
  • 방지성 (금오공과대학교 컴퓨터소프트웨어공학과) ;
  • 김병만 (금오공과대학교 컴퓨터소프트웨어공학과)
  • 투고 : 2016.09.09
  • 심사 : 2016.10.27
  • 발행 : 2016.10.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 영상처리와 기계학습을 이용하여 자동차를 판별하는 시스템을 제안하고 그 성능을 확인한다. 차량의 앞면을 인식 하도록 하였으며 앞면을 선택한 이유는 제조사, 모델별로 앞면이 다르고 개조가 힘들기 때문이다. 제안하는 방법은 먼저 학습 데이터로부터 HOG특징을 추출하고, 이 특징 데이터에 대해 인공신경망 학습기법을 적용하여 판별 모델을 구축한다. 그리고 사용자가 자동차의 앞면을 찍으면 그 사진에서 특징점을 추출하고 특징점을 학습된 판별 모델을 거쳐 차량의 정보를 표시한다. 실험 결과, 98%의 높은 평균 인식률을 보였다.

In this paper, a car model recognition system using image processing and machine learning is proposed and it's performance is also evaluated. The system recognizes the front of car because the front of car is different for every car model and manufacturer, and difficult to remodel. The proposed method extracts HOG features from training data set, then builds classification model by the HOG features. If user takes photo of the front of car, then HOG features are extracted from the photo image and are used to determine the model of car based on the trained classification model. Experimental results show a high average recognition rate of 98%.

키워드

참고문헌

  1. Woo-Tae Kim, Kil-Taek Lim, "Extraction of Car License Plate Region Using Histogram Features of Edge Direction", Journal of the Korea Industrial Information Systems Research, Vol. 14, No. 3, pp. 1-14, 2009.
  2. Chang-Seok Park, Byeong Man Kim, Byung-Hoon Seo, Jun-Woo Kim, Kwang-Ho Lee, "Real-time Recognition of Car Licence Plate on a Moving Car", Journal of the Korea Industrial Information Systems Research, Vol. 9, No. 2, pp. 32-43, 2004.
  3. Byung-Hoon Seo, Byeong Man Kim, Chang-Bae Moon, Yoon-Sik Shin, "Binarization of Number Plate Image with a Shadow", Journal of the Korea Industrial Information Systems Research, Vol. 13, No. 4, pp. 1-13, 2008.
  4. Pyeng-Won Lee, "Development of an Image Processing Algorithm for the Recognition of Car Types and Number Plate", Department of Control and Measurement Engineering, The University of Seoul Graduate School, 2000.
  5. Tae-Joon Ha, "A Recognition System for Car Images Based on the HTM Network", Department of Computer and Information Science, Graduate School of Industry Gyeongsang National University, 2010.
  6. Hyo-Jong Lee, "A Study on the Model Recognition of Moving Vehicles Using a Neural Network", Journal of the Institute of Electronics Engineers of Korea SP, Vol. 42, No. 4, pp. 69-78, 2005.
  7. Min-Ho Kim and Doo-Hyun Choi, "Model Recognition of Moving Vehicles Based on Features of Car Head Lights", Proceedings of Information and Control Symposium, pp. 211-212, 2011.
  8. Woo-Young Kang, Tae-Gyun Lee, Min-Ho Kwak, Hyo-Jong Lee, "Development of Model Recognition Algorithm for Moving Vehicles", Proceedings of Korean Institute of Information Scientists and Engineers, Vol. 39, No. 2, pp. 214-216, 2012.
  9. Yeunghak Lee, Jooyoung Ko, Jung-Hee Suk, Tae Moon Roh, Jaechang Shim, "Pedestrian Recognition using Adaboost Algorithm Based on Cascade Method by Curvature and HOG", Journal of KIISE : Computing Practices and Letters Vol. 16, No. 6, pp. 654-662, 2010.
  10. Won Taek Woo, "A Design And Implementation Of Simple Neural Networks System In Turbo Pascal", The Journal of Information Systems, Vol. 2000, No. 6, pp. 33-88, 2000.
  11. Altman, N. S., "An introduction to Kernel and Nearest-Neighbor Nonparametric Regression", The American Statistician, Vol. 46, No. 3, pp. 175-185, 1992.