MataDoc: Margin and Text Aware Document Dewarping for Arbitrary Boundary

TL;DR

MataDoc is a novel document dewarping method that effectively handles arbitrary boundaries by leveraging margin and text-aware regularizations, improving OCR accuracy and document understanding.

Contribution

This paper introduces MataDoc, the first approach specifically designed for arbitrary boundary document dewarping using margin and text-aware regularizations.

Findings

Outperforms existing methods on ArbDoc benchmark with arbitrary boundaries.

Effectively preserves text line straightness in rectified images.

Demonstrates superior performance on multiple datasets like DocUNet, DIR300, and WarpDoc.

Abstract

Document dewarping from a distorted camera-captured image is of great value for OCR and document understanding. The document boundary plays an important role which is more evident than the inner region in document dewarping. Current learning-based methods mainly focus on complete boundary cases, leading to poor document correction performance of documents with incomplete boundaries. In contrast to these methods, this paper proposes MataDoc, the first method focusing on arbitrary boundary document dewarping with margin and text aware regularizations. Specifically, we design the margin regularization by explicitly considering background consistency to enhance boundary perception. Moreover, we introduce word position consistency to keep text lines straight in rectified document images. To produce a comprehensive evaluation of MataDoc, we propose a novel benchmark ArbDoc, mainly consisting of document images with arbitrary boundaries in four typical scenarios. Extensive experiments confirm the superiority of MataDoc with consideration for the incomplete boundary on ArbDoc and also demonstrate the effectiveness of the proposed method on DocUNet, DIR300, and WarpDoc datasets.