Skip to main content

Radical-based extract and recognition networks for Oracle character recognition

A Correction to this article was published on 07 May 2022

This article has been updated


The recognition of Oracle bone inscription (OBI) is one of the most fundamental aspect of OBI study. However, the complex glyph structure and many variants of OBI, which hinder the advancement of automatic recognition research. In order to solve these problems, this paper designs an Oracle radical extract and recognition framework(ORERF) based on deep learning. First, combining the maximally stable extremal regions(MSER) algorithm and self-defined post-processing algorithm to generate Oracle single radical data annotation; then, the generated Oracle radical-level annotation data set is input into the detection network, the detection network integrates multi-scale features, and uses the attention mechanism to implicitly extract Oracle single radical features, and then feeds the feature map to the detection module for radical detection; finally, we put the detected radicals to the auxiliary classifier network for recognition. The method of treating an OBI character as a composition of radicals rather than as a character category is a human-like method that can reduce the size of the vocabulary, ignore redundant information among similar characters. The experimental results are highlighted and compared to demonstrate the efficiency of the method. Furthermore, we also introduce two new datasets containing Oracle radical character dataset(ORCD) and Oracle combined-character dataset(OCCD).

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Change history


  1. Atsushi, S., Toshiya, S.: A survey on the achievements of the Oracle bone digitization projects and prior definitions of the targets. Ipsj Sig Notes. 2013, 1–8 (2013)

    Google Scholar 

  2. Feng, G., Jing, X., Yong-ge, L.: Recognition of fuzzy characters on oracle-bone inscriptions. In: International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing, pp.698-702.IEEE (2015)

  3. Meng, L., Kamitoku, N., Yamazaki, K.: Recognition of oracle bone inscriptions using deep learning based on data augmentation. In: Metrology for Archaeology and Cultural Heritage (MetroArchaeo), 33-38.IEEE (2018)

  4. Dress, A., Grünewald, S., Zeng, Z.B.: A cognitive network for oracle bone characters related to animals. Int. J. Modern Phys. B. 30, 34–45 (2016)

    Article  Google Scholar 

  5. Jin, Y.: The pioneer of oracle-bone inscription studies in North America. J. Sino Western Commun. 6, 190–198 (2014)

    Google Scholar 

  6. Cao, Z., Lu, J., Cui, S., Zhang, C.: Zero-shot handwritten Chinese character recognition with hierarchical decomposition embedding. Pattern Recognit. 2020, 107488 (2020)

    Article  Google Scholar 

  7. Wang, T.Q., Yin, F., Liu, C.L.: Radical-based chinese character recognition via multi-labeled learning of deep residual networks. In: International Conference on Document Analysis and Recognition (ICDAR), 579-584.IEEE (2017)

  8. Zhang, J., Du, J., Dai, L.: Radical analysis network for learning hierarchies of Chinese characters. Pattern Recogni. 103, 107305 (2020)

    Article  Google Scholar 

  9. Meng, L., Lyu, B., Zhang, Z.Y. et al: Oracle bone inscription detector based on SSD. In: International Conference on Image Analysis and Processing(ICIAP), pp.126-136 (2019)

  10. Liu, G.Y., Xing, J.C., Xiong, J.: Spatial pyramid block for oracle bone inscription detection. In Proceedings of the 2020 9th International Conference on Software and Computer Applications(ICSCA), 133-140 (2020)

  11. Lin, T.Y., Dollar, P., Girshick, R.: Feature pyramid networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 45-61 (2017)

  12. Zhou, X.: The graph theory method of oracle automatic recognition. J. Electron. Inf. S1, 41–47 (1996)

    Google Scholar 

  13. Gu, S.T.: Identification of oracle-bone script fonts based on topological registration. Comput. Digital Eng. 44, 2001–2006 (2016)

    Google Scholar 

  14. Guo, J., Wang, C., Roman-Rangel, E., Chao, H., Rui, Y.: Building hierarchical representations for oracle character and sketch recognition. IEEE Trans. Image Process. 25, 104–118 (2016)

    MathSciNet  Article  Google Scholar 

  15. Huang, S., Wang, H., Liu, Y., Shi, X., Jin, L.: OBC306: A large-scale oracle bone character recognition dataset. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), 681-688 (2019)

  16. Li, X., Li, S.: Application of maximum stability extreme value region in dynamic target detection. In: International Conference on Image Vision and Computing (ICIVC), 117-122 (2018)

  17. Qu, Z., Mei, J., Liu, L., Zhou, D.: Crack detection of concrete pavement with cross-entropy loss function and improved vgg16 network model. IEEE Access. 8, 54564–54573 (2020)

    Article  Google Scholar 

  18. Rangarajan, A.K., Purushothaman, R.: Disease classification in eggplant using pre-trained vgg16 and msvm. Sci. Rep. 10, 2322 (2020)

    Article  Google Scholar 

  19. Brua, R.B., Culp, J.M., Benoy, G.A.: Comparison of benthic macroinvertebrate communities by two methods: Kick- and U-net sampling. Hydrobiologia. 658, 293–302 (2011)

    Article  Google Scholar 

  20. Li, B., Dai, Q., et al.: HWOBC-A handwriting oracle bone character recognition database. J. Phys.: Conf. Series. 1651, 012050 (2020)

    Google Scholar 

  21. Shahab, A., Shafait , F., Dengel, A.: ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images. In: International Conference on Document Analysis and Recognition (ICDAR), 1491-1496 (2011)

  22. Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform(SWT). In: IEEE computer society conference on computer vision and pattern recognition, 2963-2970 (2010)

  23. Xiao, X., Yang, C., Yang, X.: Adaptive learning-based projection method for smoke simulation: Adaptive projection method based on machine learning. Comput. Anim. Virt. Worlds. 29(3–4), e1837 (2018)

    Google Scholar 

  24. Sun, C., Vallotton, P.: Fast linear feature detection using multiple directional non-maximum suppression. In: International Conference on Pattern Recognition (ICPR), 288-291 (2006)

  25. Bodla, N., Singh, B., Chellappa, R. et al: Soft-NMS - Improving Object Detection with One Line of Code. In: International Conference on Computer Vision (ICCV), 5562-5570 (2017)

  26. Zhou, X., Yao, C. et al: East: An efficient and accurate scene text detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 263-271 (2017)

  27. Baek, Y., Lee, B. et al: Character region awareness for text detection. In: International Conference on Computer Vision and Pattern Recognition (CVPR), 353-364 (2019)

  28. Zhai, W., Chu, X.: Research on aoctpn-based modeling and simulation technology of semiconductor fabrication line. Inter. J. Adv. Manuf. Technol. 28, 814–821 (2006)

    Article  Google Scholar 

  29. Gao, W., Zhao, Y., Smidts, C.: Component detection in piping and instrumentation diagrams of nuclear power plants based on neural networks. Prog. Nucl. Energy. 128, 103491 (2020)

    Article  Google Scholar 

  30. Liao, M., Shi, B.F., Bai, X.: Textboxes++: A single-shot oriented scene text detector. IEEE Trans. Image Process. 27, 3676–3690 (2018)

    MathSciNet  Article  Google Scholar 

  31. Dan, D.: PixelLink: Detecting Scene Text via Instance Segmentation. Dissertation, University of Zhejiang (2018)

  32. Yuan, Z.W., Zhang, J.: Feature extraction and image retrieval based on alexnet. In: International Conference on Digital Image Processing (ICDIP), 100330E (2016)

  33. Raja, J., Shanmugam, P., Pitchai, R.: An automated early detection of glaucoma using support vector machine based visual geometry group 19 (vgg-19) convolutional neural network. Wirel. Pers. Commun. 118, 523–534 (2021)

    Article  Google Scholar 

  34. Ramkumar, M.O., Catharin, S.S., Ramachandran, V., Sakthikumar, A.: Cercospora identification in spinach leaves through resnet-50 based image processing. J. Phys.: Conf. Series. 1717, 012046 (2021)

    Google Scholar 

  35. Zhang, Z.H., Yang, Z., Sun, Y. et al: Lenet-5 convolution neural network with mish activation function and fixed memory step gradient descent method. In: International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), 196-199 (2019)

Download references


This work was supported by the National Social Science Foundation (19BYY171) and the Key Laboratory of Oracle Information Processing of the Ministry of Education (OIP2019E009). At the same time, Thanks to Professor Liu Chenglin from the Institute of Automation of the Chinese Academy of Sciences for his guidance on this work.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Xiaoyu Lin.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Lin, X., Chen, S., Zhao, F. et al. Radical-based extract and recognition networks for Oracle character recognition. IJDAR 25, 219–235 (2022).

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:


  • Oracle radical
  • MSER
  • Attention mechanism
  • Text detection and recognition