Title of article :
Automatic Collecting Representative Logo Images from the Internet
Author/Authors :
Liu, Xiaobing Tsinghua University - State Key Laboratory for Intelligent Technology and System, Tsinghua National Laboratory for Information Science and Technology(TNList), Department of Computer Science and Technology, China , Zhang, Bo Tsinghua University - State Key Laboratory for Intelligent Technology and System, Tsinghua National Laboratory for Information Science and Technology(TNList), Department of Computer Science and Technology, China
Abstract :
With the explosive growth of commercial logos, high quality logo images are needed for training logodetection or recognition systems, especially for famous logos 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 logos 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.
Keywords :
logo image , sparse coding , scale invariant , shift invariant , multiple dictionary
Journal title :
Tsinghua Science and Technology
Journal title :
Tsinghua Science and Technology
