paper-with-me

홈 › Papers

Document Rectification and Illumination Correction using a Patch-based CNN

2019-09-20 · Xiaoyu Li, Bo Zhang, Jing Liao, Pedro V. Sander

We propose a novel learning method to rectify document images with various distortion types from a single input image. As opposed to previous learning-based methods, our approach seeks to first learn the distortion flow on input image patches rather than the entire image. We then present a robust technique to stitch the patch results into the rectified document by processing in the gradient domain. Furthermore, we propose a second network to correct the uneven illumination, further improving the readability and OCR accuracy. Due to the less complex distortion present on the smaller image patches, our patch-based approach followed by stitching and illumination correction can significantly improve the overall accuracy in both the synthetic and real datasets.

📄 PDF Abstract BibTeX arXiv:1909.09470

Code (1)

xiaoyu258/DocProj pytorch

Tasks

Optical Character Recognition (OCR)

Similar Papers 제목 키워드 기반

DocMAE: Document Image Rectification via Self-supervised Representation Learning

2023-04-20 · Shaokai Liu, Hao Feng, Wengang Zhou, Houqiang Li 외

Tremendous efforts have been made on document image rectification, but how to learn effective representation of such distorted images is still under-explored. In this paper, we present DocMAE, a novel self-supervised fra…

Representation LearningSelf-Supervised Learning

DocScanner: Robust Document Image Rectification with Progressive Learning

2021-10-28 · Hao Feng, Wengang Zhou, Jiajun Deng, Qi Tian 외

Compared with flatbed scanners, portable smartphones provide more convenience for physical document digitization. However, such digitized documents are often distorted due to uncontrolled physical deformations, camera po…

Optical Character Recognition (OCR)

DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction

2021-10-25 · Hao Feng, Yuechen Wang, Wengang Zhou, Jiajun Deng 외

In this work, we propose a new framework, called Document Image Transformer (DocTr), to address the issue of geometry and illumination distortion of the document images. Specifically, DocTr consists of a geometric unwarp…

Optical Character Recognition (OCR)

UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior

2022-10-15 · Yonghui Wang, Wengang Zhou, Zhenbo Lu, Houqiang Li

Document images captured by mobile devices are usually degraded by uncontrollable illumination, which hampers the clarity of document content. Recently, a series of research efforts have been devoted to correcting the un…

PhaSR: Generalized Image Shadow Removal with Physically Aligned Priors

2026-01-24 · Chia-Ming Lee, Yu-Fan Lin, Yu-Jou Hsiao, Jin-Hui Jiang 외 arxiv

Shadow removal under diverse lighting conditions requires disentangling illumination from intrinsic reflectance, a challenge compounded when physical priors are not properly aligned. We propose PhaSR (Physically Aligned …

Image Shadow Removal