# Convolutional Neural Networks for Font Classification

arXiv: https://arxiv.org/abs/1708.03669 · HTML: https://mlsanity.com/paper/1708.03669/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2017.

## Built on by (most cited first, 6 of 6)

- [Importance of Textlines in Historical Document Classification](https://mlsanity.com/paper/2201.09575/) (2022)
- [CONSENT: Context Sensitive Transformer for Bold Words Classification](https://mlsanity.com/paper/2205.07683/) (2022)
- [Exploring Multi-Tasking Learning in Document Attribute Classification](https://mlsanity.com/paper/2108.13382/) (2021)
- [Reimagining Application User Interface (UI) Design using Deep Learning Methods: Challenges and Opportunities](https://mlsanity.com/paper/2303.13055/) (2023)
- [Combining OCR Models for Reading Early Modern Printed Books](https://mlsanity.com/paper/2305.07131/) (2023)
- [Font Representation Learning via Paired-glyph Matching](https://mlsanity.com/paper/2211.10967/) (2022)

## Abstract (arXiv)

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.