DOI QR코드

DOI QR Code

An Efficient Comparing and Updating Method of Rights Management Information for Integrated Public Domain Image Search Engine

  • Kim, Il-Hwan (Dept. of Computer Science and Engineering, Soongsil University) ;
  • Hong, Deok-Gi (Dept. of Computer Science and Engineering, Soongsil University) ;
  • Kim, Jae-Keun (Dept. of Computer Science and Engineering, Soongsil University) ;
  • Kim, Young-Mo (Dept. of Computer Science and Engineering, Soongsil University) ;
  • Kim, Seok-Yoon (Dept. of Computer Science and Engineering, Soongsil University)
  • Received : 2018.12.03
  • Accepted : 2019.01.01
  • Published : 2019.01.31

Abstract

In this paper, we propose a Rights Management Information(RMI) expression systems for individual sites are integrated and the performance evaluation is performed to find out an efficient comparing and updating method of RMI through various image feature point search techniques. In addition, we proposed a weighted scoring model for both public domain sites and posts in order to use the most latest RMI based on reliable data. To solve problem that most public domain sites are exposed to copyright infringement by providing inconsistent RMI(Rights Management Information) expression system and non-up-to-date RMI information. The weighted scoring model proposed in this paper makes it possible to use the latest RMI for duplicated images that have been verified through the performance evaluation experiments of SIFT and CNN techniques and to improve the accuracy when applied to search engines. In addition, there is an advantage in providing users with accurate original public domain images and their RMI from the search engine even when some modified public domain images are searched by users.

Keywords

CPTSCQ_2019_v24n1_57_f0001.png 이미지

Fig. 1. Gaussian Pyramid

CPTSCQ_2019_v24n1_57_f0002.png 이미지

Fig. 2. Orientation Histogram

CPTSCQ_2019_v24n1_57_f0003.png 이미지

Fig. 3. Network with CNN

CPTSCQ_2019_v24n1_57_f0004.png 이미지

Fig. 4. Network Consisting of A complete Connection Layer(Affine layer)

CPTSCQ_2019_v24n1_57_f0005.png 이미지

Fig. 5. Example of Convolution Operation

CPTSCQ_2019_v24n1_57_f0006.png 이미지

Fig. 6. Public Domain Image Search Engine Architecture

CPTSCQ_2019_v24n1_57_f0007.png 이미지

Fig. 7. Average Hash

CPTSCQ_2019_v24n1_57_f0008.png 이미지

Fig. 8. Average Hash Execution Result

CPTSCQ_2019_v24n1_57_f0009.png 이미지

Fig. 9. Similar Image Search Results using Average Hash

CPTSCQ_2019_v24n1_57_f0010.png 이미지

Fig. 10. dHash

CPTSCQ_2019_v24n1_57_f0011.png 이미지

Fig. 11. SIFT Algorithm

CPTSCQ_2019_v24n1_57_f0012.png 이미지

Fig. 12. SIFT Algorithm Result

CPTSCQ_2019_v24n1_57_f0013.png 이미지

Fig. 13. CNN Model Construction

CPTSCQ_2019_v24n1_57_f0014.png 이미지

Fig. 14. CNN Learning

CPTSCQ_2019_v24n1_57_f0016.png 이미지

Fig. 15. Duplicated Images of Sites

CPTSCQ_2019_v24n1_57_f0017.png 이미지

Fig. 16. Weighted Scoring Model-based update results

Table 1. RMI Database Scheme

CPTSCQ_2019_v24n1_57_t0001.png 이미지

Table 2. Integrated RMI Schema of ‘Gong-U Madang’

CPTSCQ_2019_v24n1_57_t0002.png 이미지

Table 3. Integrated RMI Schema of Flikr

CPTSCQ_2019_v24n1_57_t0003.png 이미지

Table 4. Results of Image Feature Point Comparison Search Performance

CPTSCQ_2019_v24n1_57_t0004.png 이미지

Table 5. Evaluation Items of Weighted Scoring Model

CPTSCQ_2019_v24n1_57_t0005.png 이미지

Table 6. Rate this Item by Weight of the Weighted Scoring Model

CPTSCQ_2019_v24n1_57_t0006.png 이미지

Table 7. Results of Evaluation by Public Domain Site

CPTSCQ_2019_v24n1_57_t0007.png 이미지

Table 8. Results of Reliability Calculation by Site

CPTSCQ_2019_v24n1_57_t0008.png 이미지

Table 9. Results of Evaluation by Duplicate Image Article

CPTSCQ_2019_v24n1_57_t0009.png 이미지

Table 10. Results of Duplicate Image Reliability Calculation

CPTSCQ_2019_v24n1_57_t0010.png 이미지

Table 11. Site A, D Reliability Comparison

CPTSCQ_2019_v24n1_57_t0011.png 이미지

References

  1. H. Deok-Gi, K. Il-Hwan, K. Youngmo and K. Seok-Yoon "A Rights Management Information Updating Technique Using Image Feature Points," Proceedings of the Korean Society of Computer Information Conference. Vol. 26, No. 2, pp. 462-464, July 2018.
  2. HackerFactor , http://www.hackerfactor.com/
  3. K. hikodukue, "Python NI YORU SCRAPING & KIKAIGA KUSHU KAIHATSU TECHNIQUE" Japan-Press, pp. 301-320, 2016.
  4. D.G Lowe, "Object recognition from local scale-invariant features,"Proceedings of the Seventh IEEE International Conference on Computer Vision. Vol. 2, p 1150, September 1999.
  5. bskvision, http://http://bskyvision.com/21
  6. A. Krizhevsky, I. Sutskever and G, E, Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," Proceedings of the NIPS'12 Proceedings of the 25th International Conference on Neural Information Processing Systems, Vol 1, pp. 1097-1105, 2010.
  7. S. goki, "Deep Learning from Scratch" Japan-Press, pp.227-235, 2016.
  8. J. SangYup, K. HoYeon and C. Jae-Soo, "Estimation of Non-trained Category in Image Classification Model based on Deep-Learning," Journal of Instritute of Control, Robotics and Systems, Vol. 24, No. 9, pp. 793-801, 2018. https://doi.org/10.5302/J.ICROS.2018.18.0104
  9. K. MyungJoon and P. Byeonghwa, "A Study on Big Data Application using Scoring Model," Jounal of Actuarial Science, Vol. 7, No. 2, pp. 3-22, 2015
  10. S. Ren, K. He, R. Girshick and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29, No. 6, pp. 1137-1149, 2017.
  11. EUN-JI SEO, Il-Hwan Kim, Deok-Gi Hong, Youngmo Kim and Seok-Yoon Kim, "Integrated Multilayer Metadata Based on Intellectual Information Technology for Customization Services of Public Domain Images with Different Usage Permission of License," 28th Journal of Theoretical and Applied Information Technology, Vol. 96, No. 4, pp. 1048-1058, 2018.
  12. N. Hyun Woo, "Research on the Improvement Plan for the Protection and Use Activation of Image Copyright," KOREA SCIENCE & ART FORUM, Vol. 15, pp. 233-246, 2014 https://doi.org/10.17548/ksaf.2014.03.15.233