Unsupervised learning of text line segmentation by differentiating coarse patterns

TL;DR

This paper introduces an unsupervised deep learning approach for text line segmentation that embeds document patches into a space reflecting coarse pattern similarities, eliminating manual labeling.

Contribution

The method learns to recognize text line patterns without supervision by embedding patches based on coarse pattern similarity, enabling segmentation with standard techniques.

Findings

Effective on multiple text line segmentation datasets

Achieves comparable results to supervised methods

Requires no manual labeling effort

Abstract

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.