Barcode detection using local analysis, mathematical morphology, and clustering

Peter Bodnar, L. Nyúl

Research output: Contribution to journalArticle

Abstract

Barcode detection is required in a wide range of real-life applications. Imaging conditions and techniques vary considerably and each application has its own requirements for detection speed and accuracy. In our earlier works we built barcode detectors using morphological operations and uni-form partitioning with several approaches and showed their behaviour on a set of test images. In this work, those ideas have been extended with clus-tering, contrast measuring, distance transformation and probabilistic Hough transformation. Using more than one feature for localization leads to better accuracy, which makes detectors based on simple features, a competitive solution for commercial softwares and helps to fulll the requirements of industrial applications even more.

Original languageEnglish
Pages (from-to)21-35
Number of pages15
JournalActa Cybernetica
Volume21
Issue number1
Publication statusPublished - 2013

Fingerprint

Mathematical morphology
Mathematical Morphology
Detector
Clustering
Detectors
Morphological Operations
Requirements
Industrial Application
Industrial applications
Partitioning
Imaging
Vary
Imaging techniques
Software
Range of data
Mathematical analysis
Barcode
Form
Life

Keywords

  • Barcode detection
  • Clustering
  • Computer vision
  • Distance transformation
  • Feature extraction
  • Hough transformation
  • Morphological lters

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Barcode detection using local analysis, mathematical morphology, and clustering. / Bodnar, Peter; Nyúl, L.

In: Acta Cybernetica, Vol. 21, No. 1, 2013, p. 21-35.

Research output: Contribution to journalArticle

@article{26180d2fab3e4a18b1d1186bb95d48ac,
title = "Barcode detection using local analysis, mathematical morphology, and clustering",
abstract = "Barcode detection is required in a wide range of real-life applications. Imaging conditions and techniques vary considerably and each application has its own requirements for detection speed and accuracy. In our earlier works we built barcode detectors using morphological operations and uni-form partitioning with several approaches and showed their behaviour on a set of test images. In this work, those ideas have been extended with clus-tering, contrast measuring, distance transformation and probabilistic Hough transformation. Using more than one feature for localization leads to better accuracy, which makes detectors based on simple features, a competitive solution for commercial softwares and helps to fulll the requirements of industrial applications even more.",
keywords = "Barcode detection, Clustering, Computer vision, Distance transformation, Feature extraction, Hough transformation, Morphological lters",
author = "Peter Bodnar and L. Ny{\'u}l",
year = "2013",
language = "English",
volume = "21",
pages = "21--35",
journal = "Acta Cybernetica",
issn = "0324-721X",
publisher = "University of Szeged",
number = "1",

}

TY - JOUR

T1 - Barcode detection using local analysis, mathematical morphology, and clustering

AU - Bodnar, Peter

AU - Nyúl, L.

PY - 2013

Y1 - 2013

N2 - Barcode detection is required in a wide range of real-life applications. Imaging conditions and techniques vary considerably and each application has its own requirements for detection speed and accuracy. In our earlier works we built barcode detectors using morphological operations and uni-form partitioning with several approaches and showed their behaviour on a set of test images. In this work, those ideas have been extended with clus-tering, contrast measuring, distance transformation and probabilistic Hough transformation. Using more than one feature for localization leads to better accuracy, which makes detectors based on simple features, a competitive solution for commercial softwares and helps to fulll the requirements of industrial applications even more.

AB - Barcode detection is required in a wide range of real-life applications. Imaging conditions and techniques vary considerably and each application has its own requirements for detection speed and accuracy. In our earlier works we built barcode detectors using morphological operations and uni-form partitioning with several approaches and showed their behaviour on a set of test images. In this work, those ideas have been extended with clus-tering, contrast measuring, distance transformation and probabilistic Hough transformation. Using more than one feature for localization leads to better accuracy, which makes detectors based on simple features, a competitive solution for commercial softwares and helps to fulll the requirements of industrial applications even more.

KW - Barcode detection

KW - Clustering

KW - Computer vision

KW - Distance transformation

KW - Feature extraction

KW - Hough transformation

KW - Morphological lters

UR - http://www.scopus.com/inward/record.url?scp=84885219273&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885219273&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84885219273

VL - 21

SP - 21

EP - 35

JO - Acta Cybernetica

JF - Acta Cybernetica

SN - 0324-721X

IS - 1

ER -