Automatic Collecting Representative Logo Images from the Internet 被引量：2

Automatic Collecting Representative Logo Images from the Internet

导出

摘要 With the explosive growth of commercial Iogos, high quality logo images are needed for training logo detection or recognition systems, especially for famous Iogos or new commercial brands. This paper focuses on automatic collecting representative logo images from the internet without any human labeling or seed images. We propose multiple dictionary invariant sparse coding to solve this problem. This work can automatically provide prototypes, representative images, or weak labeled training images for logo detection, logo recognition, trademark infringement detection, brand protection, and ad-targeting. The experiment results show that our method increases the mean average precision for 25 types of Iogos to 80.07% whereas the original search engine results only have 32% representative logo images. The top images collected by our method are accurate and reliable enough for practical applications in the future. With the explosive growth of commercial Iogos, high quality logo images are needed for training logo detection or recognition systems, especially for famous Iogos or new commercial brands. This paper focuses on automatic collecting representative logo images from the internet without any human labeling or seed images. We propose multiple dictionary invariant sparse coding to solve this problem. This work can automatically provide prototypes, representative images, or weak labeled training images for logo detection, logo recognition, trademark infringement detection, brand protection, and ad-targeting. The experiment results show that our method increases the mean average precision for 25 types of Iogos to 80.07% whereas the original search engine results only have 32% representative logo images. The top images collected by our method are accurate and reliable enough for practical applications in the future.

作者 Xiaobing Liu Bo Zhang

机构地区 State Key Laboratory for Intelligent Technology and System

出处《Tsinghua Science and Technology》 SCIE EI CAS 2013年第6期606-617,共12页 清华大学学报（自然科学版（英文版）

基金 National Key Basic Research and Development(973)Program of China(Nos.2012CB316301 and 2013CB329403) National Natural Science Foundation of China(No.91120011) Tsinghua University Initiative Scientific Research Program(No.20121088071) Basic Research Foundation of Tsinghua National Laboratory for Information Science and Technology(TNList)

关键词 logo image sparse coding scale invariant shift invariant multiple dictionary logo image sparse coding scale invariant shift invariant multiple dictionary

分类号 TP393.0 [自动化与计算机技术—计算机应用技术] TP391.41 [自动化与计算机技术—计算机应用技术]

引文网络
相关文献

参考文献37

1J. Kleban, X. Xie, and W. Ma, Spalial pyramid mining fl/r logo detection in natural scenes, ill Proc. ~/" International Conference on Multimedia and E.vpo (ICME), Hannovei, Germany, 2008, pp. 1077-1080.
2G. Zhu and D. Doermann, Automatic document logo detection, in Ptwc. of 9th hlternatitmal Cot![~'rence on Document Analysis and Recognitioll (ICDAR), Curitiba, Brazil, 2007, pp. 864-868.
3J. Chen, M. Leung, and Y. Gao, Noisy logo recognition using line segment Hausdorff distance, Pattertt Recognition, vol. 36, no. 4, pp. 943-955, April 2003.
4H. Sulehria and Y. Zhang, Vehicle logo recognition using mathematical Morphology, in Proc. ~['htte171ational Cot~ference on Telecomnmnications and h!forntatics, Xi'an, Shaanxi, China, 2007, pp. 95-98.
5D. Doermann, E. Rivlin, and I. Weiss, Logo recognition using geometric inwlriants, in Proc. ~?/ the 2nd International Cot!/'erence on Document Analysis and Recognition (ICDAR), Tsukuba, Japan, 1993, pp. 894-897.
6W. Yah, J. Wang, and M. Kankanhalli. Automatic video logo detection and removal, Mtdtimedia Systenl, vol. 10, no. 5, pp. 379-391. August 2005.
7K. Meisinger, T. Troeger, M. Zeller, and A. Kaup, Atltomatic TV logo removal using statistical based logo detection and frequency selective inpaiming, in EltropeanSignal Processing Col!ference, Antalya, Turkey, 2005, pp. 147-150.
8X. Liu and B. Zhang, Learning complex ilnage paltcrnswith scale and shift invariant sparse coding, in Proc. of 18th International Conference on Image Processing (ICIP), Brussels, Belgium, 2011, pp. 1225-1228.
9T. Berg and D. Forsyth, Animals on the web, in Proc. of Computer Vision and Pattern Recognition (CVPR), New York, NY, USA, 2006, pp. 1463-1470.
10J. Besemer, A. Lomsadze, and M. Borodovsky, GeneMarkS: A self-training method for prediction of gene starts in microbial genomes--Implications for finding sequence motifs in regulatory regions, Nucleic Acids Research, vol. 29, no. 12, pp. 2607-2618, 200l.