Convolutional Neural Networks for Font Classification
This work addresses font classification to enhance OCR performance, particularly for historical documents, but is incremental as it applies existing CNN techniques to new domains.
The paper tackles font classification for improved OCR accuracy by using a CNN-based method that classifies small text patches and averages predictions for page or line images, achieving 98.8% line-level accuracy on Arabic fonts and 86.6% page-level accuracy on medieval Latin manuscripts.
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.