An effective and conceptually simple feature representation for off-line text-independent writer identification
作者：
Highlights：
• A novel system for off-line text-independent writer identification is proposed.
• Effective feature extraction and dimensionality reduction methods are proposed.
• Experiments are conducted on four challenging datasets (two English and two Arabic).
• The proposed system provides high identification rates.
• The proposed system demonstrates good performance stability across all the datasets.
摘要
•A novel system for off-line text-independent writer identification is proposed.•Effective feature extraction and dimensionality reduction methods are proposed.•Experiments are conducted on four challenging datasets (two English and two Arabic).•The proposed system provides high identification rates.•The proposed system demonstrates good performance stability across all the datasets.
论文关键词：Text-independent,Off-line writer identification,Handwritten connected components,Texture features,Histogram sequence concatenation,Hamming distance,Dissimilarity measure,Feature histogram descriptors
论文评审过程：Received 12 February 2018, Revised 5 December 2018, Accepted 15 January 2019, Available online 16 January 2019, Version of Record 23 January 2019.
论文官网地址：https://doi.org/10.1016/j.eswa.2019.01.045
