Earticle

초록

영어

For solving the picture misappropriation problem in e-commerce, this paper proposes a content-based copyright detection method. In the method, a picture is smoothed by bilateral filter to ensure the integrity of its key points, and the shape feature and texture feature are extracted by Hu moment and Gabor filter respectively. Finally copyright-infringing pictures are detected by calculating the Euclidean distance and we use fuzzy heuristics to measure similarity between the query and the database images. The test dataset is crawled from the largest e-commerce website (Taobao.com). The copyright-infringing pictures can be detected by the method and the average accuracy reaches 91%, achieved the desired effect.

목차

Abstract
 1. Introduction
 2. Problems in Images Protection
 3. Methodology
  3.1. SIFT Feature Extraction Based on Bilateral Filter
  3.2. Extraction of Shape Feature
  3.3. Extraction of Texture Features
  3.4. Similarity Detection
 4. Results
 5. Conclusion
 References

키워드

저자

• Liyi Zhang [ School of information management, Wuhan University ]
• Chang Liu [ School of information management, Wuhan University ] Corresponding author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of u- and e- Service, Science and Technology

• 간기

  격월간

• pISSN

  2005-4246

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605