Deep learning for logo recognition

NEUROCOMPUTING

卷:245

Article

Bianco, Simone¹  Buzzelli, Marco¹  Mazzini, Davide¹  Schettini, Raimondo¹ 

[1] Univ Milano Bicocca, DISCo, I-20126 Milan, Italy

关键词: Logo recognition;    Deep Learning;    Convolutional Neural Network;    Data augmentation;    FlickrLogos-32;   

DOI  :  10.1016/j.neucom.2017.03.051

来源: Elsevier

【 摘 要 】

In this paper we propose a method for logo recognition using deep learning. Our recognition pipeline is composed of a logo region proposal followed by a Convolutional Neural Network (CNN) specifically trained for logo classification, even if they are not precisely localized. Experiments are carried out on the FlickrLogos-32 database, and we evaluate the effect on recognition performance of synthetic versus real data augmentation, and image pre-processing. Moreover, we systematically investigate the benefits of different training choices such as class-balancing, sample-weighting and explicit modeling the background class (i.e. no-logo regions). Experimental results confirm the feasibility of the proposed method, that outperforms the methods in the state of the art. (C) 2017 Elsevier B.V. All rights reserved.

【 授权许可】

Free