Semi-supervised cluster-and-label with feature based re-clustering to reduce noise in Thai document images
作者:
Highlights:
• We proposed a novel noise reduction method for document images.
• Semi-supervised learning is applied to classify noise from character components.
• The proposed method is suitable for Non-Latin based scripts i.e. Thai document image.
• We proposed an enhance labeling method of semi-supervised cluster-and-label approach.
• The performance of proposed methods are significantly better than comparison methods.
摘要
•We proposed a novel noise reduction method for document images.•Semi-supervised learning is applied to classify noise from character components.•The proposed method is suitable for Non-Latin based scripts i.e. Thai document image.•We proposed an enhance labeling method of semi-supervised cluster-and-label approach.•The performance of proposed methods are significantly better than comparison methods.
论文关键词:Noise reduction,Document enhancement,Semi-supervised classification,Cluster-and-label,Thai document
论文评审过程:Received 6 March 2015, Revised 19 August 2015, Accepted 28 September 2015, Available online 8 October 2015, Version of Record 8 November 2015.
论文官网地址:https://doi.org/10.1016/j.knosys.2015.09.033