Learning to Read by Spelling: Towards Unsupervised Text Recognition

TL;DR

This paper introduces an unsupervised method for visual text recognition that aligns predicted strings with target corpora, enabling accurate recognition without paired training data.

Contribution

It proposes a novel unsupervised learning approach for text recognition from images using unpaired text samples, eliminating the need for large labeled datasets.

Findings

Achieves high accuracy on synthetic and real printed text images.

Analyzes factors affecting convergence and generalization.

Demonstrates effectiveness without labeled training data.

Abstract

This work presents a method for visual text recognition without using any paired supervisory data. We formulate the text recognition task as one of aligning the conditional distribution of strings predicted from given text images, with lexically valid strings sampled from target corpora. This enables fully automated, and unsupervised learning from just line-level text-images, and unpaired text-string samples, obviating the need for large aligned datasets. We present detailed analysis for various aspects of the proposed method, namely - (1) impact of the length of training sequences on convergence, (2) relation between character frequencies and the order in which they are learnt, (3) generalisation ability of our recognition network to inputs of arbitrary lengths, and (4) impact of varying the text corpus on recognition accuracy. Finally, we demonstrate excellent text recognition accuracy on both synthetically generated text images, and scanned images of real printed books, using no labelled training examples.