Automatic signboard detection and semi-automatic ground truth generation

Chen Ya Hong, Chih Yang Lin, Timothy K. Shih

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

1 Scopus citations

Abstract

Data-driven object detection techniques are widely applied to a variety of practical areas (i.e., automatic robots, self-driving vehicles, defect detection, and face detection). Nowadays, many research projects have been proposed to improve the accuracy of computer vision applications. In this paper, we propose an automatic signboard detection method and a semi-automatic ground truth generation method to help visually impaired people walk on streets in Taiwan. We consider that when visually impaired people walk down the street, they may be interested in certain stores. Therefore, we collect images of 12 kinds of the most popular stores in people's daily lives. The collected street images number over 5 million from 6 major cities in Taiwan; however, only about 1% of images contain a signboard. We propose a hierarchical object detection module to pre-label uncertain samples. Based on this module, semi-automatic ground truth generation can be achieved.

Original languageEnglish
Title of host publicationProceedings - 2019 12th International Conference on Ubi-Media Computing, Ubi-Media 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages256-261
Number of pages6
ISBN (Electronic)9781728128207
DOIs
StatePublished - Aug 2019
Event12th International Conference on Ubi-Media Computing, Ubi-Media 2019 - Bali, Indonesia
Duration: 6 Aug 20199 Aug 2019

Publication series

NameProceedings - 2019 12th International Conference on Ubi-Media Computing, Ubi-Media 2019

Conference

Conference12th International Conference on Ubi-Media Computing, Ubi-Media 2019
Country/TerritoryIndonesia
CityBali
Period6/08/199/08/19

Keywords

  • Deep learning
  • Ground truth generation
  • Object detection
  • Signboard detection

Fingerprint

Dive into the research topics of 'Automatic signboard detection and semi-automatic ground truth generation'. Together they form a unique fingerprint.

Cite this