DOI QR코드

DOI QR Code

Design and Implementation of Luo-kuan Recognition Application

낙관 인식을 위한 애플리케이션의 설계 및 구현

  • Kim, Han-Syel (Department of Computer Software Engineering, Soonchunhyang University) ;
  • Seo, Kwi-Bin (Department of Computer Science, Soonchunhyang University) ;
  • Kang, Mingoo (Department of IT Contents, Hanshin University) ;
  • Ryu, Gee Soo (Department of Chinese Culture & Art Studies, Hanshin University) ;
  • Hong, Min (Department of Computer Software Engineering, Soonchunhyang University)
  • Received : 2017.11.14
  • Accepted : 2017.12.12
  • Published : 2018.02.28

Abstract

In oriental paintings, there is Luo-kuan that expressed in a single picture by compressing the artist's information. Such Luo-kuan includes various information such as the title of the work or the name of the artist. Therefore, information about Luo-kuan is considered important to those who collect or enjoy oriental paintings. However, most of the letters in the Luo-kuan are difficult kanji, kanzai, or various shapes, so it is difficult for the ordinary people to interpret. In this paper, we developed an Luo-kuan search application to easily check the information of the Luo-kuan. The application uses a search algorithm that analyzes the captured Luo-kuan image and sends it to the server to output information about the Luo-kuan candidates that are most similar to the Luo-kuan images taken from the database in the server. We also compared and analyzed the accuracy of the algorithm based on 170 Luo-kuan data in order to find out the ranking of the Luo-kuan that matched the Luo-kuan among the candidates. Accuracy Analysis Experimental Results The accuracy of the search algorithm of this application is confirmed to be about 90%, and it is anticipated that it will be possible to develop a platform to automatically analyze and search images in a big data environment by supplementing the optimizing algorithm and multi-threading algorithm.

대부분의 동양화 작품에는 작가의 정보를 압축시켜 하나의 그림으로 표현한 낙관이 존재하고 이러한 낙관은 작품의 제목이나 작가의 이름 등 다양한 정보를 포함하고 있다. 따라서 동양화를 수집하거나 즐기는 사람들에게 낙관은 동양화에 대한 중요한 정보를 제공하는 단서 역할을 한다. 하지만 낙관에 있는 글자들은 대부분 어려운 한자나 간자 혹은 다양한 모양으로 변형되어 있어 일반인들이 쉽게 해석하기 어려운 문제점이 있다. 본 논문에서는 낙관의 정보를 손쉽게 확인할 수 있도록 안드로이드 기반의 낙관 검색 애플리케이션을 개발하였다. 해당 애플리케이션은 촬영한 낙관 이미지를 분석하여 서버에 전송해 서버 내의 데이터베이스에서 촬영한 낙관 사진과 가장 유사한 낙관 후보에 대한 정보를 검색하는 알고리즘을 적용하였다. 또한 제안하는 알고리즘의 성능 분석을 위해서 촬영된 낙관 사진과 170개의 낙관 데이터 후보 중에서 정확하게 낙관을 찾아내는지에 대한 여부와 제공되는 낙관의 순위를 바탕으로 알고리즘의 정확도를 비교 및 분석하였다. 정확도 분석 실험 결과 본 애플리케이션의 검색 알고리즘의 정확도는 약 90%로 확인되었으며 추후 알고리즘의 최적화와 멀티쓰레딩 알고리즘의 보완을 통해 빅 데이터 환경에서 자동으로 이미지를 분석 및 검색하는 플랫폼으로의 발전이 가능할 것으로 기대한다.

Keywords

References

  1. Sanya Patel, Aliya Sayyed, P.P Bastawade, "Smart Attendance Application Using Android and PHP", International Journal of Advanced Research in Computer and Communication Engineering, Vol. 6, Issue 3, 2017 https://doi.org/10.17148/ijarcce.2017.6351
  2. Shoki Fukuda, Shun Kurihara, Shintaro Hamanaka, Masato Oguchi, Saneyasu Yamaguchi, "Accelerated test for applications with client application and server software", IMCOM '17 Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, No.100, 2017 http://dx.doi.org/10.1145/3022227.3022326
  3. HAN Lu, LI Zu-shu, CHEN Dong-yi, "Object detection module based on implementation of Java and OpenCV", Journal of Computer Applications, pp. 733-775, 2008 https://doi.org/10.3724/sp.j.1087.2008.00773
  4. Pavel JETENSKY, "Using Open Source OpenCV Library for practical coureses of Computer Vision", Journal of Technology and Information Education, Vol. 5, Issue 1, 2013 https://doi.org/10.5507/jtie.2013.017
  5. R. Manoharan, S. Chandrakala, "Android OpenCV based effective driver fatigue and distraction monitoring system", Computing and Communications Technologies (ICCCT), 2015 International Conference on, 2015 https://doi.org/10.1109/iccct2.2015.7292757
  6. OpenCV, "Feature Matching", http://docs.opencv.org/trunk/dc/dc3/tutorial_py_matcher.html
  7. Wikipedia, "Feature detection(computer vision)", https://en.wikipedia.org/wiki/Feature_detection_(computer_vision)
  8. Wikipedia, "Speeded up robust features(SURF)", https://en.wikipedia.org/wiki/Speeded_up_robust_features
  9. S. Li "The Application of Face Recognition Based on OpenCV", Advanced Materials Research, Vols. 403-408, pp. 2350-2353, 2012 https://doi.org/10.4028/www.scientific.net/amr.403-408.2350
  10. Guobo Xie, Wen Lu, "Image Edge Detection Based On Opencv", International Journal of Electronics and Electrical Engineering, Vol.1, No.2, 2013 https://doi.org/10.12720/ijeee.1.2.104-106
  11. Kim, Gihong, Chong, Kyusoo, Youn, Junhee, "Automatic Recognition of Direction Information in Road Sign Image Using OpenCV", Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Volume 31, Issue 4, pp. 293-300, 2013. http://dx.doi.org/10.7848/ksgpc.2013.31.4.293
  12. Ye Zhao, Richang Hong, Jianguo Jiang, Jing Wen, Hengheng Zhang, "Image matching by fast random sample consensus", ICIMCS '13 Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service, pp.159-162, 2013. http://dx.doi.org/10.1145/2499788.2499852
  13. Raj Kumar Gupta, Alex Yong-Sang Chia, Deepu Rajan, Ee Sin Ng, Huang Zhiyoung, "Image colorization using similar images", MM '12 Proceedings of the 20th ACM international conference on Multimedia, pp. 369-378, 2012. http://dx.doi.org/10.1145/2393347.2393402
  14. Yaron Lipman, Stav Yagev, Roi Poranne, David W. Jacobs, Ronen Basri, "Feature Matching with Bounded Distortion", ACM Transactions on Graphics (TOG), Volume 33, Issue 3, 2014. http://dx.doi.org/10.1145/2602142