Abstract
Optical text recognition has seen continual improvement in character accuracy over the past decade. However, as error persists, it is crucial to know when and where a recognition error occurs. Studies have shown that recent development of deep convolutional neural networks tends to increase calibration errors, compared to traditional classifiers such as SVM. Yet, the calibration error in deep neural networks for sequential text recognition has not been studied in the literature.
This paper addresses the probability misalignment problem in unsegmented text recognition models. We analyze the causes of probability misalignment in the popular recurrent text recognition model, the attention encoder-decoder model, and propose a novel probability calibration algorithm for individual character predictions. Experiments show that the proposed methods not only reduce expected calibration error, but also improve the character prediction accuracy. In our experiments, calibration error on authentic industrial datasets improved as much as 68% compared to original text recognizer outputs.
J. Wang—This paper is supported by National Key Research and Development Program of China under grant No. 2018YFB1003500, No. 2018YFB0204400 and No. 2017YFB1401202.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1321–1330. JMLR. org (2017)
Liao, Q., Ding, Y., Jiang, Z.L., Wang, X., Zhang, C., Zhang, Q.: Multi-taskdeep convolutional neural network for cancer diagnosis. Neurocomputing 348, 66–73 (2018)
Platt, J., et al.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Advances in Large Margin Classifiers, vol. 10, no. 3, pp. 61–74 (1999)
Leathart, T., Frank, E., Holmes, G., Pfahringer, B.: Probability calibration trees. In: Asian Conference on Machine Learning, pp. 145–160 (2017)
Pereyra, G., Tucker, G., Chorowski, J., Kaiser, Ł., Hinton, G.: Regularizing neural networks by penalizing confident output distributions. arXiv preprint arXiv:1701.06548 (2017)
Kumar, A., Sarawagi, S., Jain, U.: Trainable calibration measures for neural networks from kernel mean embeddings. In: International Conference on Machine Learning, pp. 2810–2819 (2018)
Graves, A., Fernández, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369–376. ACM (2006)
Hori, T., Watanabe, S., Zhang, Y., Chan, W.: Advances in joint CTC-attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM. arXiv preprint arXiv:1706.02737 (2017)
Kim, S., Hori, T., Watanabe, S.: Joint CTC-attention based end-to-end speech recognition using multi-task learning. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4835–4839. IEEE (2017)
Wojna, Z., et al.: Attention-based extraction of structured information from street view imagery. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 844–850. IEEE (2017)
Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4168–4176 (2016)
Vinyals, O., Kaiser, Ł., Koo, T., Petrov, S., Sutskever, I., Hinton, G.: Grammar as a foreign language. In: Advances in Neural Information Processing Systems, pp. 2773–2781 (2015)
Serfozo, R.: Basics of Applied Stochastic Processes. Springer, Heidelberg (2009)
DeGroot, M.H., Fienberg, S.E.: The comparison and evaluation of forecasters. J. Roy. Stat. Soc.: Ser. D (Stat.) 32(1–2), 12–22 (1983)
Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., Zhou, S.: Focusing attention: towards accurate text recognition in natural images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5076–5084 (2017)
Abadi, M., Agarwal, A., Barham, P., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). Software available from tensorflow.org. http://tensorflow.org/
Zeiler, M.D.: ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Iandola, F., Moskewicz, M., Karayev, S., Girshick, R., Darrell, T., Keutzer, K.: DenseNet: implementing efficient convnet descriptor pyramids. arXiv preprint arXiv:1404.1869 (2014)
Acknowledgement
This paper is supported by National Key Research and Development Program of China under grant No. 2018YFB1003500, No. 2018YFB0204400 and No. 2017YFB1401202.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhu, X., Wang, J., Hong, Z., Guo, J., Xiao, J. (2019). On Probability Calibration of Recurrent Text Recognition Network. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Lecture Notes in Computer Science(), vol 11955. Springer, Cham. https://doi.org/10.1007/978-3-030-36718-3_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-36718-3_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36717-6
Online ISBN: 978-3-030-36718-3
eBook Packages: Computer ScienceComputer Science (R0)