Multi-scale Logo detection algorithm based on convolutional neural network

• Published in: 网络与信息安全学报 Vol. 6; no. 2; pp. 116 - 124
• Main Author: JIANG Yuchao, JI Lixin, GAO Chao, LI Shaomei
• Format: Journal Article
• Language: English
• Published: POSTS&TELECOM PRESS Co., LTD 01.04.2020
• Subjects: convolutional neural network; feature fusion; logo detection; multi-scale; region proposal network
• DOI: 10.11959/j.issn.2096-109x.2020026
• ISSN: 2096-109X

Aiming at the requirements for multi-scale Logo detection in natural scene images, a multi-scale Logo detection algorithm based on convolutional neural network was proposed. The algorithm was based on the realization of two-stage object detection. By constructing feature pyramids and adopting layer-by-layer prediction, multi-scale region proposals were generated. The multi-layer feature maps in convolutional neural networks were fused to enhance the feature representation. The experimental results on the FlickrLogos-32 dataset show that compared with the baseline, the proposed algorithm can improve the recall rate of region proposals, and can improve the performance of small Logo detection while ensuring the accuracy of large and middle Logo, proving the superiority of the proposed algorithm.