Skip to main navigation Skip to search Skip to main content

Barcode detection and decoding method based on deep learning

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

Abstract

Traditional Barcode detection methods are susceptible to environment. It is very difficult to implement bar code detection in complex backgrounds and on-site environments. Barcode detection is mainly divided into two processes of positioning and data decoding. In this paper, a bar code detection method based on deep learning is proposed. The method is based on the single-shot mutibox detector (SSD) method, which can meet the requirements of high speed and high precision. In this paper, the SSD method is used to detect the position of the barcode, and then the image processing method is used to segment the barcode. Then the morphological method and the barcode correction method are used to complete the decoding of the barcode data. The test results on the actual data set show that our method can stably and quickly complete the process of positioning and decoding the barcode.

Original languageEnglish
Title of host publication2019 2nd International Conference on Information Systems and Computer Aided Education, ICISCAE 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages393-396
Number of pages4
ISBN (Electronic)9781728130668
DOIs
StatePublished - Sep 2019
Event2nd IEEE International Conference on Information Systems and Computer Aided Education, ICISCAE 2019 - Dalian, China
Duration: 28 Sep 201930 Sep 2019

Publication series

Name2019 2nd International Conference on Information Systems and Computer Aided Education, ICISCAE 2019

Conference

Conference2nd IEEE International Conference on Information Systems and Computer Aided Education, ICISCAE 2019
Country/TerritoryChina
CityDalian
Period28/09/1930/09/19

Keywords

  • Affine transformation correction
  • Barcode detection
  • Deep learning
  • Morphological method

Fingerprint

Dive into the research topics of 'Barcode detection and decoding method based on deep learning'. Together they form a unique fingerprint.

Cite this