Unsupervised document image binarization using a system of nonlinear partial differential equations

作者：

Highlights：

• Unsupervised convergence of PDE based document image binarization.

• Robust to noise and non-uniform illumination.

• Best-in-class performance for images with discontinuous illumination (shadows).

摘要

•Unsupervised convergence of PDE based document image binarization.•Robust to noise and non-uniform illumination.•Best-in-class performance for images with discontinuous illumination (shadows).

论文关键词：Image Processing,Fitzhugh-Nagumo,Finite Difference,Partial Differential Equations

论文评审过程：Received 16 October 2020, Revised 18 October 2021, Accepted 12 November 2021, Available online 27 November 2021, Version of Record 27 November 2021.

论文官网地址：https://doi.org/10.1016/j.amc.2021.126806