Binarization of degraded document images based on hierarchical deep supervised network
作者：
Highlights：
• We propose a supervised binarization method based on the deep supervised networks.
• The multi-scale deep supervised network for binarization has not been reported yet.
• A hierarchical architecture is designed to distinguish text from background noises.
• Different feature levels are dealt by the multi-scale architecture.
• The performance results are considerably better than state-of-the-art methods.
摘要
•We propose a supervised binarization method based on the deep supervised networks.•The multi-scale deep supervised network for binarization has not been reported yet.•A hierarchical architecture is designed to distinguish text from background noises.•Different feature levels are dealt by the multi-scale architecture.•The performance results are considerably better than state-of-the-art methods.
论文关键词：Document image binarization,Convolutional neural network,Document analysis
论文评审过程：Received 17 April 2017, Revised 17 August 2017, Accepted 23 August 2017, Available online 1 September 2017, Version of Record 28 October 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.08.025
