Abstract
Aiming at the inefficiency of the manual sorting method used in sorting centers at district and county levels, an algorithm is proposed for the detection and recognition of three-segment waybill codes based on rotating frames and YOLOv5. First of all, the detection of rotation angle is achieved by converting the regression problem into a classification problem through a Circular smooth label to solve the influence of angle periodicity on training. Secondly, the improved algorithm is used to detect the waybill Logo, according to the position relationship between the Logo and the three-segment code, and then combine the Logo position and rotation angle to locate the three-segment code, and use Radon transform to correct the tilt of the three-segment code to improve the three-segment code locating accuracy. Finally, the template matching algorithm is used to identify the three-segment codes. The experimental results show that the proposed algorithm achieves 93.6% detection accuracy of courier Logo and more than 99% positioning accuracy of three-segment code, which can effectively improve courier sorting efficiency.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Jianfeng, Y.: Analysis of logistics express sorting methods in the context of e-commerce. Mod. Trade Ind. 42(23), 25–26 (2021)
Weimin, Z., Gongmu, Z.: Design of dispatch information code based on automatic sorting application. Postal Res. 37(01), 4–8 (2021)
Konovalenko, I., Maruschak, P., Brevus, V.: Steel surface defect detection using an ensemble of deep residual neural networks. J. Comput. Inf. Sci. Eng. 22(1), 1–8 (2021)
Redmon, J., Divvala, S., Girshick, R., et al.: You Only Look Once: Unified, Real-Time Object Detection. IEEE (2016)
Xu, D.-G., Wang, L., Li, F.: A review of research on typical target detection algorithms for deep learning. Comput. Eng. Appl. 57(08), 10–25 (2021)
Jiang, Y., Zhu, X., Wang, X., et al.: R2CNN: rotational region CNN for orientation robust scene text detection (2017)
Ma, J., Shao, W., Ye, H., et al.: Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans. Multimedia PP(99):1–1 (2017)
Zhang, G., Lu, S., Zhang, W.: CAD-Net: a context-aware detection network for objects in remote sensing imagery. IEEE Trans. Geosci. Remote Sens. PP(99):1–10 (2019)
Yang, X., Yang, J., Yan, J., et al.: SCRDet: towards more robust detection for small, cluttered and rotated objects. In: 2019 IEEE/CVF international conference on computer vision (ICCV). IEEE (2019)
Yang, X., Liu, Q., Yan, J., et al.: R3Det: refined single-stage detector with feature refinement for rotating object (2019)
Zhao, L., Wang, X., Zhang, Y., Zhang, M.: Research on vehicle target detection technology based on YOLOv5s fusion SENet. J. Graphology 1–8 (2022)
Yang, X., Yan, J.: on the arbitrary-oriented object detection: classification based approaches revisited. Int. J. Comput. Vision 130(5) (2022)
Lixia, G., Yan**, B.: Application of radon transform in tilted license plate image correction. J. Test. Technol. 23(05), 452–456 (2009)
Zhang, F., Wang, X., Hao, X.: Intelligent vehicle character recognition based on edge features. Autom. Instrum. (06):11–14 (2020)
Ladislav, K., Elena, P.: comparative study of feature extraction and classification methods for recognition of characters taken from vehicle registration plates. Imaging Sci. J. 68(1), 56–68 (2020)
**nSheng, Z., Yu, W.: Industrial character recognition based on improved CRNN in complex environments. Comput Ind 142 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shen, J., Song, W. (2023). Three-Segment Waybill Code Detection and Recognition Algorithm Based on Rotating Frame and YOLOv5. In: **ong, N., Li, M., Li, K., **ao, Z., Liao, L., Wang, L. (eds) Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery. ICNC-FSKD 2022. Lecture Notes on Data Engineering and Communications Technologies, vol 153. Springer, Cham. https://doi.org/10.1007/978-3-031-20738-9_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-20738-9_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20737-2
Online ISBN: 978-3-031-20738-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)