Skip to main content

Total-Text: toward orientation robustness in scene text detection

Abstract

At present, text orientation is not diverse enough in the existing scene text datasets. Specifically, curve-orientated text is largely out-numbered by horizontal and multi-oriented text, hence, it has received minimal attention from the community so far. Motivated by this phenomenon, we collected a new scene text dataset, Total-Text, which emphasized on text orientations diversity. It is the first relatively large scale scene text dataset that features three different text orientations: horizontal, multi-oriented, and curve-oriented. In addition, we also study several other important elements such as the practicality and quality of ground truth, evaluation protocol, and the annotation process. We believe that these elements are as important as the images and ground truth to facilitate a new research direction. Secondly, we propose a new scene text detection model as the baseline for Total-Text, namely Polygon-Faster-RCNN, and demonstrated its ability to detect text of all orientations. Images of Total-Text and its annotation are available at https://github.com/cs-chan/Total-Text-Dataset.

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
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21

Notes

  1. 1.

    This is achieved by ‘colorThreshold’ function in MATLAB.

  2. 2.

    https://www.mathworks.com/help/map/ref/polybool.html.

  3. 3.

    http://scikit-image.org/docs/dev/api/skimage.draw.html#skimage.draw.polygon.

  4. 4.

    It is sufficient to cover most of the text regions in Total-Text but not texts with larger curvature. Examples in Fig. 21.

  5. 5.

    Apart from CUTE80 and CTW1500, which we used the model fine-tuned on Total-Text only.

  6. 6.

    The new ground truths will be released in the same GitHub page as well.

  7. 7.

    Credit to Baidu Inc. who helped in re-annotating the ground truth in such format. We (the authors of CTW1500 and us) reached a common ground that Latin scripts should be annotated in word level while Chinese scripts should be annotated in line level due to the nature of both languages.

References

  1. 1.

    Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., i Bigorda, L.G., Mestre, S.R., Mas, J., Mota, D.F., Almazan, J.A., De Las Heras, L.P.: ICDAR 2013 robust reading competition. In: 12th International Conference on Document Analysis and Recognition (ICDAR). 37(7), pp. 1484–1493 (2013)

  2. 2.

    Yao, C., Bai, X., Liu, W., Ma, Y., Tu, Z.: Detecting texts of arbitrary orientations in natural images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1083–1090 (2012)

  3. 3.

    Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 37(7), 1480–1500 (2015)

    Article  Google Scholar 

  4. 4.

    Zhang, Z., Shen, W., Yao, C., Bai, X.: Symmetry-based text line detection in natural scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2558–2567 (2015)

  5. 5.

    Huang, W., Lin, Z., Yang, J., Wang, J.: Text localization in natural images using stroke feature transform and text covariance descriptors. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1241–1248 (2013)

  6. 6.

    Neumann, L., Matas, J.: Scene text localization and recognition with oriented stroke detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 97–104 (2013)

  7. 7.

    Huang, W., Qiao, Y., Tang, X.: Robust scene text detection with convolution neural network induced mser trees. In: European Conference on Computer Vision, pp. 497–511 (2014)

    Chapter  Google Scholar 

  8. 8.

    Pan, Y.-F., Hou, X., Liu, C.-L.: A hybrid approach to detect and localize texts in natural scene images. IEEE Trans. Image Process. 20(3), 800–813 (2011)

    MathSciNet  Article  Google Scholar 

  9. 9.

    Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., Ghosh, S., Bagdanov, A., Iwamura, M., Matas, J., Neumann, L., Chandrasekhar, V.R., Lu, S., Shafait, F. (2015) ICDAR 2015 competition on robust reading. In: 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156–1160

  10. 10.

    Veit, A., Matera, T., Neumann, L., Matas, J., Belongie, S.: Coco-text: dataset and benchmark for text detection and recognition in natural images (2016). arXiv preprint arXiv:1601.07140

  11. 11.

    Gupta, A., Vedaldi, A., Zisserman, A.: Building a perception based model for reading cursive script. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315–2324 (2016)

  12. 12.

    Ch’ng, C.K., Chan, C.S.: Total-Text: a comprehensive dataset for scene text detection and recognition. In: IEEE 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 935–942 (2017)

  13. 13.

    Liu, Y., Jin, L., Zhang, S., Luo, C., Zhang, S.: Curved scene text detection via transverse and longitudinal sequence connection. In: Pattern Recognition (2019)

    Article  Google Scholar 

  14. 14.

    Risnumawan, A., Shivakumara, P., Chan, C.S., Tan, C.L.: A robust arbitrary text detection system for natural scene images. Expert Syst. Appl. 41(18), 8027–8048 (2014)

    Article  Google Scholar 

  15. 15.

    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)

  16. 16.

    Wolf, C., Jolion, J.M.: Object count/area graphs for the evaluation of object detection and segmentation algorithms. Int. J. Doc. Anal. Recognit. (IJDAR). 8(4), 280–296 (2006)

    Article  Google Scholar 

  17. 17.

    Karatzas, D., Gómez, L., Nicolaou, A., Rusiñol, M.: The robust reading competition annotation and evaluation platform. In: 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 61–66 (2018)

  18. 18.

    Yin, X.C., Pei, W.Y., Zhang, J., Hao, H.W.: Multi-orientation scene text detection with adaptive clustering. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1930–1937 (2015)

    Article  Google Scholar 

  19. 19.

    Nayef, N., Yin, F., Bizid, I., Choi, H., Feng, Y., Karatzas, D., Luo, Z, et al.: ICDAR2017 robust reading challenge on multi-lingual scene text detection and script identification-RRC-MLT. In: IEEE 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1 pp. 1454–1459 (2017)

  20. 20.

    Shi, B., Yao, C., Liao, M., Yang, M., Xu, P., Cui, L., Belongie, S., Lu, S., Bai, X.: ICDAR2017 competition on reading Chinese text in the wild (RCTW-17). In: IEEE 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1 pp. 1429–1434 (2017)

  21. 21.

    He, M., Liu, Y., Yang, Z., Zhang, S., Luo, C., Gao, F., Zheng, Q., Wang, Y., Zhang, X., Jin, L.: ICPR2018 contest on robust reading for multi-type web images. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 7–12 (2018)

  22. 22.

    Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2963–2970 (2010)

  23. 23.

    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide-baseline stereo from maximally stable extremal regions. In: Image and Vision Computing, pp. 761–767 (2004)

    Article  Google Scholar 

  24. 24.

    Wang, T., Wu, D.J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional neural networks. In: International Conference in Pattern Recognition, pp. 3304–3308 (2012)

  25. 25.

    Jaderberg, M., Vedaldi, A., Zisserman, A.: Deep features for text spotting. In: European Conference on Computer Vision, pp. 512–528 (2014)

    Chapter  Google Scholar 

  26. 26.

    He, T., Huang, W., Qiao, Y., Yao, J.: Text-attentional convolutional neural network for scene text detection. IEEE Trans. Image Process. 25(6), 2529–2541 (2016)

    MathSciNet  Article  Google Scholar 

  27. 27.

    Zhang, Z., Zhang, C., Shen, W., Yao, C., Liu, W., Bai, X.: Multi-oriented text detection with fully convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4159–4167 (2016)

  28. 28.

    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431–3440 (2015)

  29. 29.

    He, T., Huang, W., Qiao, Y., Yao, J.: Accurate text localization in natural image with cascaded convolutional text network (2016). arXiv preprint arXiv:1603.09423

  30. 30.

    Tang, Y., Wu, X.: Scene text detection and segmentation based on cascaded convolution neural networks. IEEE Trans. Image Process. 26(3), 1509–1520 (2017)

    Article  Google Scholar 

  31. 31.

    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)

  32. 32.

    Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)

  33. 33.

    Jiang, Y., Zhu, X., Wang, X., Yang, S., Li, W., Wang, H., Fu, P., Luo, Z.: R2CNN: rotational region CNN for orientation robust scene text detection (2017). arXiv preprint arXiv:1706.09579

  34. 34.

    Ma, J., Shao, W., Ye, H., Wang, L., Wang, H., Zheng, Y., Xue, X.: Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans. Multimed. 20, 3111–3122 (2018)

    Article  Google Scholar 

  35. 35.

    Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: SSD: Single shot multibox detector. In: European Conference on Computer Vision, pp. 21–37 (2016)

    Chapter  Google Scholar 

  36. 36.

    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)

  37. 37.

    Liu, Y., Jin, L.: Deep matching prior network: toward tighter multi-oriented text detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3454–3461 (2017)

  38. 38.

    Shi, B., Bai, X., Belongie, S.: Detecting oriented text in natural images by linking segments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)

  39. 39.

    Liao, M., Shi, B., Bai, X., Wang, X., Liu, W.: TextBoxes: a fast text detector with a single deep neural network. In: AAAI, pp. 4161–4167 (2017)

  40. 40.

    Liao, Minghui, Shi, Baoguang, Bai, Xiang, and and: TextBoxes++: A Single-Shot Oriented Scene Text Detector. IEEE Transactions on Image Processing 27(8), 3676–3690 (2018)

    MathSciNet  Article  Google Scholar 

  41. 41.

    He, W., Zhang, X.Y., Yin, F., Liu, C.L.: Deep direct regression for multi-oriented scene text detection. In: Proceedings of the IEEE International Conference on Computer Vision (2017)

  42. 42.

    Adams Jr., R.B., Adams, R.B., Ambady, N., Shimojo, S., Nakayama, K. (eds.): The Science of Social Vision: The Science of Social Vision, vol. 7. Oxford University Press, Oxford (2011)

    Google Scholar 

  43. 43.

    Yao, C., Bai, X., Sang, N., Zhou, X., Zhou, S., Cao, Z.: Scene text detection via holistic, multi-channel prediction (2016). arXiv preprint arXiv:1606.09002

  44. 44.

    Xu, Y., Wang, Y., Zhou, W., Wang, Y., Yang, Z., Bai, X.: TextField: learning a deep direction field for irregular scene text detection. Trans. Image Process. (2019)

  45. 45.

    Lyu, P., Liao, M., Yao, C., Wu, W., Bai, X.: Mask textspotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 67–83 (2018)

    Chapter  Google Scholar 

  46. 46.

    Xue, C., Lu, S., Zhang, W.: MSR: multi-scale shape regression for scene text detection (2019). arXiv preprint arXiv:1901.02596

  47. 47.

    Castrejón, L., Kundu, K., Urtasun, R., Fidler, S.: Annotating object instances with a polygon-RNN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, p. 2 (2017)

  48. 48.

    Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., Fischer, I., Wojna, Z., Song, Y., Guadarrama, S., Murphy, K.: Speed/accuracy trade-offs for modern convolutional object detectors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 4 (2017)

  49. 49.

    Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. AAAI 4, 12 (2017)

    Google Scholar 

  50. 50.

    Liu, X., Liang, D., Yan, S., Chen, D., Qiao, Y., Yan, J.: Fots: fast oriented text spotting with a unified network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5676–5685 (2018)

  51. 51.

    Sun, Y., Zhang, C., Huang, Z., Liu, J., Han, J., Ding, E.: TextNet: irregular text reading from images with an end-to-end trainable network. In: Asian Conference on Computer Vision (2018)

  52. 52.

    Long, S., Ruan, J., Zhang, W., He, X., Wu, W., Yao, C.: Textsnake: a flexible representation for detecting text of arbitrary shapes In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 20–36 (2018)

    Chapter  Google Scholar 

  53. 53.

    Dai, Y., Huang, Z., Gao, Y., Xu, Y., Chen, K., Guo, J., Qiu, W.: Fused text segmentation networks for multi-oriented scene text detection. In: Proceedings of the IEEE International Conference on Pattern Recognition (ICPR), pp. 3604–3609 (2018)

  54. 54.

    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2961–2969 (2018)

Download references

Acknowledgements

Funding was provided by Fundamental Research Grant Scheme (FRGS) MoHE (Grant No. FP004-2016) and Postgraduate Research Grant (PPP) (Grant No. PG350-2016A). The authors acknowledge all the authors who provided their results for our experiments. Also, we would like to thank Chun Chet Ng for his contribution in aiding the annotation process of Total-Text.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Chee Seng Chan.

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

Ch’ng, CK., Chan, C.S. & Liu, CL. Total-Text: toward orientation robustness in scene text detection. IJDAR 23, 31–52 (2020). https://doi.org/10.1007/s10032-019-00334-z

Download citation

Keywords

  • Curved text
  • Scene text detection