Browse State-of-the-Art › Document Shadow Removal

Document Shadow Removal

15 papers with code · 0 benchmarks · 3 datasets archive 2025-07-28

Computer Vision

Document shadow removal refers to the process of eliminating or reducing the appearance of shadows in scanned or photographed documents. Shadows can occur due to various factors, such as uneven lighting, folds in the paper, or the presence of objects casting shadows during the scanning or capturing process.

Removing shadows from documents is important because they can degrade the readability and quality of the content. Shadows can obscure text or graphics, making it difficult to extract accurate information from the document. By eliminating shadows, the document becomes more legible and suitable for various purposes, including optical character recognition (OCR), document analysis, and archival purposes.

Document shadow removal techniques typically involve image processing and enhancement algorithms. These algorithms analyze the image and identify regions that contain shadows. They then adjust the brightness, contrast, and other image properties in the shadowed areas to minimize or eliminate the shadow effect. This process often requires advanced image analysis and manipulation techniques, such as histogram equalization, adaptive filtering, and image segmentation.

In recent years, machine learning and deep learning approaches have also been applied to document shadow removal. These methods utilize large datasets of shadowed and non-shadowed documents to train models that can automatically detect and remove shadows from new images. The models learn to recognize the characteristics of shadows and generate shadow-free versions of the documents.

Overall, document shadow removal plays a crucial role in improving the quality and legibility of scanned or photographed documents, making them more suitable for various applications in areas such as digital archiving, document analysis, and information extraction.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

3 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 17 · with a code link: 15 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran: none of the 17 tagged papers has a Syntology run on record

Page 1 of 1: papers 1 to 17 of 17, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections