Convolutional Neural Networks for Font Classification

Preprint English OPEN
Tensmeyer, Chris ; Saunders, Daniel ; Martinez, Tony (2017)
  • Subject: Computer Science - Computer Vision and Pattern Recognition

Classifying pages or text lines into font categories aids transcription because single font Optical Character Recognition (OCR) is generally more accurate than omni-font OCR. We present a simple framework based on Convolutional Neural Networks (CNNs), where a CNN is trained to classify small patches of text into predefined font classes. To classify page or line images, we average the CNN predictions over densely extracted patches. We show that this method achieves state-of-the-art performance on a challenging dataset of 40 Arabic computer fonts with 98.8\% line level accuracy. This same method also achieves the highest reported accuracy of 86.6% in predicting paleographic scribal script classes at the page level on medieval Latin manuscripts. Finally, we analyze what features are learned by the CNN on Latin manuscripts and find evidence that the CNN is learning both the defining morphological differences between scribal script classes as well as overfitting to class-correlated nuisance factors. We propose a novel form of data augmentation that improves robustness to text darkness, further increasing classification performance.
  • References (20)
    20 references, page 1 of 2

    [1] A. W. Harley, A. Ufkes, and K. G. Derpanis, “Evaluation of deep convolutional nets for document image classification and retrieval,” in Proc. ICDAR 2015. IEEE, 2015, pp. 991-995.

    [2] M. Z. Afzal, S. Capobianco, M. I. Malik, S. Marinai, T. M. Breuel, A. Dengel, and M. Liwicki, “Deepdocclassifier: Document classification with deep convolutional neural network,” in Proc. ICDAR 2015. IEEE, 2015, pp. 1111-1115.

    [3] L. Kang, J. Kumar, P. Ye, Y. Li, and D. Doermann, “Convolutional neural networks for document image classification,” in Proc. ICPR 2014. IEEE, 2014, pp. 3168- 3172.

    [4] J. Pastor-Pellicer, S. Espan˜a-Boquera, F. Zamora-Mart´ınez, M. Z. Afzal, and M. J. Castro-Bleda, “Insights on the use of convolutional neural networks for document image binarization,” in International Work-Conference on Artificial Neural Networks. Springer, 2015, pp. 115-126.

    [5] B. Shi, X. Bai, and C. Yao, “Script identification in the wild via discriminative convolutional neural network,” Pattern Recognition, vol. 52, pp. 448-458, 2016.

    [6] P. Y. Simard, D. Steinkraus, and J. C. Platt, “Best practices for convolutional neural networks applied to visual document analysis.” in Proc. ICDAR 2003, vol. 3, 2003, pp. 958-962.

    [7] H. Shi and T. Pavlidis, “Font recognition and contextual processing for more accurate text recognition,” in Proc. ICDAR 1997, vol. 1. IEEE, 1997, pp. 39-44.

    [8] H. S. Baird and G. Nagy, “Self-correcting 100-font classifier,” in IS&T/SPIE 1994 International Symposium on Electronic Imaging: Science and Technology. International Society for Optics and Photonics, 1994, pp. 106-115.

    [9] H. Luqman, S. A. Mahmoud, and S. Awaida, “Kafd arabic font database,” Pattern Recognition, vol. 47, no. 6, pp. 2231-2240, 2014.

    [10] F. Cloppet, V. Eglin, V. Kieu, D. Stutzmann, and N. Vincent, “Icfhr2016 competition on the classification of medieval handwritings in latin script,” in Proc. ICFHR 2016, 2016.

  • Metrics
    No metrics available
Share - Bookmark