arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1701.02620cs.CV
收藏

用于标识识别的深度学习

Deep Learning for Logo Recognition

Università degli Studi di Milano-Bicocca(米兰比可卡大学)

Simone Bianco, Marco Buzzelli, Davide Mazzini, Raimondo Schettini

摘要:

在本文中,我们提出了一种使用深度学习的徽标识别方法。我们的识别管道由一个标志区域提案和一个专门为标志分类训练的卷积神经网络(CNN)组成,即使它们没有精确定位。在FlickrLogos-32数据库上进行了实验,并评估了合成与真实数据增强和图像预处理对识别性能的影响。此外,我们系统地研究了不同训练选择的好处,例如类平衡,样本加权和显式建模背景类(即无标志区域)。实验结果证实了该方法的可行性,优于现有的方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑