A locally adaptive, diffusion based text binarization technique

作者：

Highlights：

• Novel adaptive binarization technique based on linear diffusion with a nonlinear source term.

• Extremely low sensitivity to noise.

• Excellent results and stability compared to existing techniques.

• Results have been compared with the state-of-the-art techniques presented in DIBCO.

摘要

•Novel adaptive binarization technique based on linear diffusion with a nonlinear source term.•Extremely low sensitivity to noise.•Excellent results and stability compared to existing techniques.•Results have been compared with the state-of-the-art techniques presented in DIBCO.

论文关键词：Binarization,Image denoising,Diffusion,Fitzhugh–Nagumo,Document image,GPGPU

论文评审过程：Received 16 December 2014, Revised 17 July 2015, Accepted 23 July 2015, Available online 2 September 2015, Version of Record 2 September 2015.

论文官网地址：https://doi.org/10.1016/j.amc.2015.07.091