Document image binarization using local features and Gaussian mixture modeling

作者：

Highlights：

• Background removal technique based on adaptive median filtering and thresholding

• A Local Co-occurrence Map with local contrast can distinguish between document text and document stains and background.

• Low complexity approach with fast and accurate binarization results

摘要

•Background removal technique based on adaptive median filtering and thresholding•A Local Co-occurrence Map with local contrast can distinguish between document text and document stains and background.•Low complexity approach with fast and accurate binarization results

论文关键词：Binarization,Handwritten documents,Historic documents,Classification,Background estimation

论文评审过程：Received 26 October 2013, Revised 19 January 2015, Accepted 8 April 2015, Available online 29 April 2015, Version of Record 15 May 2015.

论文官网地址：https://doi.org/10.1016/j.imavis.2015.04.003