Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo Classification.

Abstract

Logo classification has gained increasing attention for its various applications, such as copyright infringement detection, product recommendation and contextual advertising. Unfortunately, some datasets do not include a wide range of logo images and are lack of diversity and coverage in logo categories, they are not sufficient to support complex statistical models. Therefore, this article proposes a dataset, Logo- 2K+, a new large-scale publicly available real-world logo dataset with 2,341 categories and 167,140 images. Moreover, the article proposes a unified framework for logo classification, which is capable of discovering more informative logo regions and augmenting these image regions. We identifie main issues affecting logo classification including the real-world logo images have larger variety in logo appearance and more complexity in their background, analyzing unique logo characteristics. We then review existing solutions for these issues, and finally elaborate research challenges and future directions in this field. To our knowledge, this is the largest logo dataset and is expected to further the development of scalable logo image recognition to benefit researchers in this field.

• Jing Wang, Weiqing Min, Sujuan Hou, Shengnan Ma, Yuanjie Zheng, Haishuai Wang, Shuqiang Jiang. Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo Classification. Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI2020), February 7-12, 2020, New York, USA