Abstract
Two-dimensional (2D) codes are subject to distortion when printed on non-rigid materials, such as papers and clothes. Although general 2D code decoders correct uniform distortion such as perspective distortion, it is difficult to correct non-uniform and irregular distortion of the 2D code itself. To overcome this problem, an agent-based approach is presented here to reconstruct the 2D code. In this approach, auxiliary lines are placed on a 2D code and used to recognize distortion. First, 2D code area is identified through feature patterns composed by the auxiliary lines, and Convolutional Neural Network (CNN) is used to discriminate the patterns. Then, many agents simultaneously trace the lines referring to the various image features and the neighborhood agents. The feature weights are optimized by Genetic Algorithm. The experimental results indicate that agents successfully tracked auxiliary lines right up to occluded area, and the proposed method could decode distorted 2D codes. The performance of the proposed method against distortion level and occlusion amount was also clarified.
| Original language | English |
|---|---|
| Pages (from-to) | 60-70 |
| Number of pages | 11 |
| Journal | International Journal of Computer Information Systems and Industrial Management Applications |
| Volume | 9 |
| Issue number | 2017 |
| Publication status | Published - Jan 1 2017 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Management Information Systems
- Signal Processing
- Information Systems
- Computer Vision and Pattern Recognition
- Strategy and Management
- Artificial Intelligence
Cite this
Multi-agent-based two-dimensional barcode decoding robust against non-uniform geometric distortion. / Nakamura, Kazuya; Kamizuru, Kohei; Kawasaki, Hiroshi; Ono, Satoshi.
In: International Journal of Computer Information Systems and Industrial Management Applications, Vol. 9, No. 2017, 01.01.2017, p. 60-70.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Multi-agent-based two-dimensional barcode decoding robust against non-uniform geometric distortion
AU - Nakamura, Kazuya
AU - Kamizuru, Kohei
AU - Kawasaki, Hiroshi
AU - Ono, Satoshi
PY - 2017/1/1
Y1 - 2017/1/1
N2 - Two-dimensional (2D) codes are subject to distortion when printed on non-rigid materials, such as papers and clothes. Although general 2D code decoders correct uniform distortion such as perspective distortion, it is difficult to correct non-uniform and irregular distortion of the 2D code itself. To overcome this problem, an agent-based approach is presented here to reconstruct the 2D code. In this approach, auxiliary lines are placed on a 2D code and used to recognize distortion. First, 2D code area is identified through feature patterns composed by the auxiliary lines, and Convolutional Neural Network (CNN) is used to discriminate the patterns. Then, many agents simultaneously trace the lines referring to the various image features and the neighborhood agents. The feature weights are optimized by Genetic Algorithm. The experimental results indicate that agents successfully tracked auxiliary lines right up to occluded area, and the proposed method could decode distorted 2D codes. The performance of the proposed method against distortion level and occlusion amount was also clarified.
AB - Two-dimensional (2D) codes are subject to distortion when printed on non-rigid materials, such as papers and clothes. Although general 2D code decoders correct uniform distortion such as perspective distortion, it is difficult to correct non-uniform and irregular distortion of the 2D code itself. To overcome this problem, an agent-based approach is presented here to reconstruct the 2D code. In this approach, auxiliary lines are placed on a 2D code and used to recognize distortion. First, 2D code area is identified through feature patterns composed by the auxiliary lines, and Convolutional Neural Network (CNN) is used to discriminate the patterns. Then, many agents simultaneously trace the lines referring to the various image features and the neighborhood agents. The feature weights are optimized by Genetic Algorithm. The experimental results indicate that agents successfully tracked auxiliary lines right up to occluded area, and the proposed method could decode distorted 2D codes. The performance of the proposed method against distortion level and occlusion amount was also clarified.
UR - http://www.scopus.com/inward/record.url?scp=85009804086&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85009804086&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:85009804086
VL - 9
SP - 60
EP - 70
JO - International Journal of Computer Information Systems and Industrial Management Applications
JF - International Journal of Computer Information Systems and Industrial Management Applications
SN - 2150-7988
IS - 2017
ER -