Segmentation of Handwritten Arabic Graphemes Using a Directed Convolutional Neural Network and Mathematical Morphology Operations

作者：

Highlights：

• A directed convolutional neural network model is proposed

• Partial dilation-Global erosion generates resistance against information loss

• Several recent approaches for the segmentation of graphemes/characters are discussed

• The over-traces issue is addressed for the first time in the literature

• MMOs can provide real solutions if a convenient strategy is adopted

摘要

•A directed convolutional neural network model is proposed•Partial dilation-Global erosion generates resistance against information loss•Several recent approaches for the segmentation of graphemes/characters are discussed•The over-traces issue is addressed for the first time in the literature•MMOs can provide real solutions if a convenient strategy is adopted

论文关键词：handwritten Arabic graphemes segmentation,directed convolutional neural network, mathematical morphology,over-traces,partial dilation,global erosion

论文评审过程：Received 14 December 2019, Revised 23 August 2021, Accepted 29 August 2021, Available online 1 September 2021, Version of Record 20 September 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108288