VOLTAGE: A Versatile Contrastive Learning based OCR Methodology for ultra low-resource scripts through Auto Glyph Feature Extraction

2025-10-12

AI Summary

To address the lack of unsupervised OCR methods for low-resource endangered languages—hindering their digital preservation—this paper proposes VOLTAGE, the first end-to-end unsupervised OCR framework integrating contrastive learning with automatic glyph clustering. Without requiring any human annotation, VOLTAGE employs contrastive learning to extract discriminative glyph representations, leverages adaptive clustering to generate high-quality pseudo-labels, and incorporates image augmentation and GAN-based synthesis to enhance diversity among scarce character samples. Evaluated across multiple Indian scripts, VOLTAGE demonstrates cross-script generalizability; on the critically endangered Takri script, it achieves 95% accuracy on printed text and 87% on handwritten text. This work significantly advances automated recognition of low-resource scripts and supports scalable digital archiving of endangered languages.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Learning & Optimization for CV
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

UNESCO has classified 2500 out of 7000 languages spoken worldwide as endangered. Attrition of a language leads to loss of traditional wisdom, folk literature, and the essence of the community that uses it. It is therefore imperative to bring digital inclusion to these languages and avoid its extinction. Low resource languages are at a greater risk of extinction. Lack of unsupervised Optical Character Recognition(OCR) methodologies for low resource languages is one of the reasons impeding their digital inclusion. We propose VOLTAGE - a contrastive learning based OCR methodology, leveraging auto-glyph feature recommendation for cluster-based labelling. We augment the labelled data for diversity and volume using image transformations and Generative Adversarial Networks. Voltage has been designed using Takri - a family of scripts used in 16th to 20th century in the Himalayan regions of India. We present results for Takri along with other Indic scripts (both low and high resource) to substantiate the universal behavior of the methodology. An accuracy of 95% for machine printed and 87% for handwritten samples on Takri script has been achieved. We conduct baseline and ablation studies along with building downstream use cases for Takri, demonstrating the usefulness of our work.

Problem

• Developing OCR for endangered low-resource scripts lacking digital preservation
• Creating unsupervised methodology using contrastive learning and glyph features
• Addressing handwritten and printed text recognition for Himalayan scripts

Innovation

• Contrastive learning OCR for low-resource scripts
• Auto-glyph feature extraction for cluster-based labeling
• Data augmentation with GANs and image transformations