Multi-scale Logo detection algorithm based on convolutional neural network

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-...

Full description

Saved in:
Bibliographic Details
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
LanguageEnglish
Published POSTS&TELECOM PRESS Co., LTD 01.04.2020
Subjects
convolutional neural network
feature fusion
logo detection
multi-scale
region proposal network
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2096-109X
DOI:10.11959/j.issn.2096-109x.2020026