LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks

TL;DR

This paper introduces LOGO-Net, a large-scale logo image database, and applies advanced deep region-based convolutional networks to improve logo detection and brand recognition from real-world images.

Contribution

It provides the first large-scale logo dataset and evaluates deep learning methods for logo detection and brand recognition tasks.

Findings

LOGO-Net contains over 130,000 logo objects across 160 classes.

Deep learning techniques significantly improve logo detection accuracy.

The dataset and methods facilitate future research in logo recognition.

Abstract

Logo detection from images has many applications, particularly for brand recognition and intellectual property protection. Most existing studies for logo recognition and detection are based on small-scale datasets which are not comprehensive enough when exploring emerging deep learning techniques. In this paper, we introduce "LOGO-Net", a large-scale logo image database for logo detection and brand recognition from real-world product images. To facilitate research, LOGO-Net has two datasets: (i)"logos-18" consists of 18 logo classes, 10 brands, and 16,043 logo objects, and (ii) "logos-160" consists of 160 logo classes, 100 brands, and 130,608 logo objects. We describe the ideas and challenges for constructing such a large-scale database. Another key contribution of this work is to apply emerging deep learning techniques for logo detection and brand recognition tasks, and conduct extensive experiments by exploring several state-of-the-art deep region-based convolutional networks techniques for object detection tasks. The LOGO-net will be released at http://logo-net.org/