Barcode Recognition Using Principal Component Analysis and Support Vector Machine

DOI

10.2991/miseic-18.2018.26How to use a DOI?

Keywords

Barcode, Principal Componenet Analysis (PCA), Support Vector Machine (SVM)

Abstract

Barcode is visual code to identify the symbols of the data in the form of one or two-dimension image contains lines and spaces based on detecting the edges. The use of barcode has significantly contributed for warehouses and retail product. Nowadays, the research about barcode is still an interesting topic especially from blurry, low contrast, low resolution, rotated barcode and fixed-focuse lenses. Datasets of barcode are taken from WWU Muenster Barcode Database University of Muenster Germany as many as 142 images consisting 13 types of barcode EAN-13. This research aims to investigate the possibilities of one-dimensional barcode recognition in image region using Support Vector Machine (SVM) multiclass one-against-all with feature extraction using Principal Component Analysis (PCA) variation of principal component are 8, 12, 17, 25, 38, and 70 features. Dataset were randomly separated into data train and data test using cross validation repeated five times with ratio 2:1 of 95 images data train and 47 images data test. Based on the best performance result, SVM was capable for classifying barcode accurately with accuracy 0.92 ± 0.02. Based on computation time, the average of training time is about 3.21 seconds and testing time is about 0.66 seconds.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Clarin Mulyaningtyas
AU  - Elly Matul Imah
PY  - 2018/07
DA  - 2018/07
TI  - Barcode Recognition Using Principal Component Analysis and Support Vector Machine
BT  - Proceedings of the Mathematics, Informatics, Science, and Education International Conference (MISEIC 2018)
PB  - Atlantis Press
SP  - 106
EP  - 110
SN  - 1951-6851
UR  - https://doi.org/10.2991/miseic-18.2018.26
DO  - 10.2991/miseic-18.2018.26
ID  - Mulyaningtyas2018/07
ER  -