A Component-Labeling Algorithm Using Contour Tracing Technique
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Barcode Readers using the Camera Device in Mobile Phones
CW '04 Proceedings of the 2004 International Conference on Cyberworlds
Automated barcode recognition for smart identification and inspection automation
Expert Systems with Applications: An International Journal
Automatic Recognition of Noisy Code-39 Barcode
ICAT '06 Proceedings of the 16th International Conference on Artificial Reality and Telexistence--Workshops
Simultaneous Real-Time Segmentation of Diversified Barcode Symbols in Complex Background
ICINIS '08 Proceedings of the 2008 First International Conference on Intelligent Networks and Intelligent Systems
A 2D Barcode Extraction Method Based on Texture Direction Analysis
ICIG '09 Proceedings of the 2009 Fifth International Conference on Image and Graphics
Real-time automatic recognition of omnidirectional multiple barcodes and DSP implementation
Machine Vision and Applications
| Hi-index | 0.00 |
Image-based barcode recognition technique is a robust and extendable approach for versatile 1D/2D barcodes reading. Most of methods discussed in literature may either work for single 1D/2D barcode or rely on finding the unique finder pattern. Multi-symbology barcode extraction is a practical issue and yet challenging issue. Extended from our preliminary investigation and for realistic consideration, this work proposes a general segmentation framework to achieve extraction of real barcodes under complex background when multiple types of symbology appear in the same snapshot for 1D barcodes, 2D barcodes, or both co-exist. The proposed algorithm has three main steps: background small clutters elimination, potential barcodes segmentation and barcode verification. The whole algorithm combines several image processing methods, namely, image subtraction, Gaussian smoothing filtering, morphological operation, connected component labeling and iterative thresholding. Experimental results indicate that the proposed approach can segment multiple barcodes from the complex background with acceptable accuracy.