# Unsupervised learning of text line segmentation by differentiating coarse patterns

arXiv: https://arxiv.org/abs/2105.09405 · HTML: https://mlsanity.com/paper/2105.09405/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 19 May 2021.

## Builds on (most cited first, 7 of 7)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [A Two-Stage Method for Text Line Detection in Historical Documents](https://mlsanity.com/paper/1802.03345/) (2018)
- [Text Line Segmentation for Challenging Handwritten Document Images Using Fully Convolutional Network](https://mlsanity.com/paper/2101.08299/) (2021)
- [Labeling, Cutting, Grouping: an Efficient Text Line Segmentation Method for Medieval Manuscripts](https://mlsanity.com/paper/1906.11894/) (2019)
- [Text line extraction using fully convolutional network and energy minimization](https://mlsanity.com/paper/2101.07370/) (2021)
- [VML-MOC: Segmenting a multiply oriented and curved handwritten text lines dataset](https://mlsanity.com/paper/2101.07542/) (2021)

## Abstract (arXiv)

Despite recent advances in the field of supervised deep learning for text line segmentation, unsupervised deep learning solutions are beginning to gain popularity. In this paper, we present an unsupervised deep learning method that embeds document image patches to a compact Euclidean space where distances correspond to a coarse text line pattern similarity. Once this space has been produced, text line segmentation can be easily implemented using standard techniques with the embedded feature vectors. To train the model, we extract random pairs of document image patches with the assumption that neighbour patches contain a similar coarse trend of text lines, whereas if one of them is rotated, they contain different coarse trends of text lines. Doing well on this task requires the model to learn to recognize the text lines and their salient parts. The benefit of our approach is zero manual labelling effort. We evaluate the method qualitatively and quantitatively on several variants of text line segmentation datasets to demonstrate its effectivity.