Towards Text-Line Segmentation of Historical Documents Using Graph Neural Networks

Kartik Chincholikar, Kaushik Gopalan, Mihir Hasabnis
Proceedings of GRaM: the Second Edition of the Workshop on Geometry-grounded Representation Learning and Generative Modeling, PMLR 326:88-108, 2026.

Abstract

We present an initial investigation into a graph-based problem formulation for performing text-line segmentation of historical documents, by representing characters (or grapheme clusters) as the nodes, and with edges connecting characters to their previous and next characters on the text-line. This converts the image segmentation learning task into a binary edge classification learning task. This also enables training on large-scale synthetic data simulating complex layouts, enabling better robustness to Layout-level distribution shifts observed in historical documents. Furthermore, we introduce a benchmark dataset of 15 Sanskrit manuscripts with diverse layouts. We propose a method based on CRAFT and Graph Neural Networks (GNNs), which uses geometric priors of text-lines to perform competitively with leading approaches in zero-shot and few-shot experimental settings on the Sanskrit dataset introduced and the U-DIADS-TL dataset. The proposed method further demonstrates competitive accuracy and better consistency than leading methods Doc-UFCN and SeamFormer when evaluating robustness to distribution shifts over increasing data sizes (using intra-manuscript and inter-manuscript train-test data splits) on the Sanskrit dataset introduced and the DIVA-HisDB dataset. Finally, we demonstrate that the proposed method achieves strong performance in the downstream, goal-oriented evaluation of text recognized from the segmented text-lines. The dataset, training, and inference code is available at: https://github.com/flame-cai/gnn-synthetic-layout-historical/tree/gram-submission

Cite this Paper

BibTeX
@InProceedings{pmlr-v326-chincholikar26a, title = {{T}owards {T}ext-Line {S}egmentation of {H}istorical {D}ocuments Using {G}raph {N}eural {N}etworks}, author = {Chincholikar, Kartik and Gopalan, Kaushik and Hasabnis, Mihir}, booktitle = {Proceedings of GRaM: the Second Edition of the Workshop on Geometry-grounded Representation Learning and Generative Modeling}, pages = {88--108}, year = {2026}, editor = {Pouplin, Alison and Vadgama, Sharvaree and Bekkers, Erik and Kaba, Sékou-Oumar and Lawrence, Hannah and Lecha, Manuel and Baker, Elizabeth and Suk, Julian and Walters, Robin and Tomczak, Jakub and Jegelka, Stefanie}, volume = {326}, series = {Proceedings of Machine Learning Research}, month = {26 Apr}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v326/main/assets/chincholikar26a/chincholikar26a.pdf}, url = {https://proceedings.mlr.press/v326/chincholikar26a.html}, abstract = {We present an initial investigation into a graph-based problem formulation for performing text-line segmentation of historical documents, by representing characters (or grapheme clusters) as the nodes, and with edges connecting characters to their previous and next characters on the text-line. This converts the image segmentation learning task into a binary edge classification learning task. This also enables training on large-scale synthetic data simulating complex layouts, enabling better robustness to Layout-level distribution shifts observed in historical documents. Furthermore, we introduce a benchmark dataset of 15 Sanskrit manuscripts with diverse layouts. We propose a method based on CRAFT and Graph Neural Networks (GNNs), which uses geometric priors of text-lines to perform competitively with leading approaches in zero-shot and few-shot experimental settings on the Sanskrit dataset introduced and the U-DIADS-TL dataset. The proposed method further demonstrates competitive accuracy and better consistency than leading methods Doc-UFCN and SeamFormer when evaluating robustness to distribution shifts over increasing data sizes (using intra-manuscript and inter-manuscript train-test data splits) on the Sanskrit dataset introduced and the DIVA-HisDB dataset. Finally, we demonstrate that the proposed method achieves strong performance in the downstream, goal-oriented evaluation of text recognized from the segmented text-lines. The dataset, training, and inference code is available at: https://github.com/flame-cai/gnn-synthetic-layout-historical/tree/gram-submission} }
Endnote
%0 Conference Paper %T Towards Text-Line Segmentation of Historical Documents Using Graph Neural Networks %A Kartik Chincholikar %A Kaushik Gopalan %A Mihir Hasabnis %B Proceedings of GRaM: the Second Edition of the Workshop on Geometry-grounded Representation Learning and Generative Modeling %C Proceedings of Machine Learning Research %D 2026 %E Alison Pouplin %E Sharvaree Vadgama %E Erik Bekkers %E Sékou-Oumar Kaba %E Hannah Lawrence %E Manuel Lecha %E Elizabeth Baker %E Julian Suk %E Robin Walters %E Jakub Tomczak %E Stefanie Jegelka %F pmlr-v326-chincholikar26a %I PMLR %P 88--108 %U https://proceedings.mlr.press/v326/chincholikar26a.html %V 326 %X We present an initial investigation into a graph-based problem formulation for performing text-line segmentation of historical documents, by representing characters (or grapheme clusters) as the nodes, and with edges connecting characters to their previous and next characters on the text-line. This converts the image segmentation learning task into a binary edge classification learning task. This also enables training on large-scale synthetic data simulating complex layouts, enabling better robustness to Layout-level distribution shifts observed in historical documents. Furthermore, we introduce a benchmark dataset of 15 Sanskrit manuscripts with diverse layouts. We propose a method based on CRAFT and Graph Neural Networks (GNNs), which uses geometric priors of text-lines to perform competitively with leading approaches in zero-shot and few-shot experimental settings on the Sanskrit dataset introduced and the U-DIADS-TL dataset. The proposed method further demonstrates competitive accuracy and better consistency than leading methods Doc-UFCN and SeamFormer when evaluating robustness to distribution shifts over increasing data sizes (using intra-manuscript and inter-manuscript train-test data splits) on the Sanskrit dataset introduced and the DIVA-HisDB dataset. Finally, we demonstrate that the proposed method achieves strong performance in the downstream, goal-oriented evaluation of text recognized from the segmented text-lines. The dataset, training, and inference code is available at: https://github.com/flame-cai/gnn-synthetic-layout-historical/tree/gram-submission
APA
Chincholikar, K., Gopalan, K. & Hasabnis, M.. (2026). Towards Text-Line Segmentation of Historical Documents Using Graph Neural Networks. Proceedings of GRaM: the Second Edition of the Workshop on Geometry-grounded Representation Learning and Generative Modeling, in Proceedings of Machine Learning Research 326:88-108 Available from https://proceedings.mlr.press/v326/chincholikar26a.html.

Related Material