DeepText: Detecting text from the wild with multi-ASPP-assembled deeplab

Qingqing Wang, Wenjing Jia, Xiangjian He, Yue Lu, Michael Blumenstein, Ye Huang, Shujing Lyu

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

In this paper, we address the issue of scene text detection in the way of direct regression and successfully adapt an effective semantic segmentation model, DeepLab v3+ [1], for this application. In order to handle texts with arbitrary orientations and sizes and improve the recall of small texts, we propose to extract features of multiple scales by inserting multiple Atrous Spatial Pyramid Pooling (ASPP) layers to the DeepLab after the feature maps with different resolutions. Then, we set multiple auxiliary IoU losses at the decoding stage and make auxiliary connections from the intermediate encoding layers to the decoder to assist network training and enhance the discrimination ability of lower encoding layers. Experiments conducted on the benchmark scene text dataset ICDAR2015 demonstrate the superior performance of our proposed network, named as DeepText, over the state-of-the-art approaches.

Original languageEnglish
Title of host publicationProceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019
PublisherIEEE Computer Society
Pages208-213
Number of pages6
ISBN (Electronic)9781728128610
DOIs
Publication statusPublished - Sept 2019
Externally publishedYes
Event15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019 - Sydney, Australia
Duration: 20 Sept 201925 Sept 2019

Publication series

NameProceedings of the International Conference on Document Analysis and Recognition, ICDAR
ISSN (Print)1520-5363

Conference

Conference15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019
Country/TerritoryAustralia
CitySydney
Period20/09/1925/09/19

Keywords

  • Auxiliary IoU losses
  • Auxiliary connections
  • DeepLab
  • Multiple ASPP
  • Scene text detection

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'DeepText: Detecting text from the wild with multi-ASPP-assembled deeplab'. Together they form a unique fingerprint.

Cite this