A robust approach for text detection from natural scene images
作者：
Highlights：
• Several open problems in this topic are discussed and we present our solution.
• Color-enhanced CERs are effective to be candidate-text-connected-components.
• Neural networks work very well for the challenging text/non-text classification.
• The “ambiguity-free learning” strategy addresses the ambiguity problem properly.
• The “divide-and-conquer” strategy solves the size normalization problem well.
摘要
•Several open problems in this topic are discussed and we present our solution.•Color-enhanced CERs are effective to be candidate-text-connected-components.•Neural networks work very well for the challenging text/non-text classification.•The “ambiguity-free learning” strategy addresses the ambiguity problem properly.•The “divide-and-conquer” strategy solves the size normalization problem well.
论文关键词：Text detection,Natural scene images,Color-enhanced contrasting extremal region,Neural networks
论文评审过程：Received 19 September 2014, Revised 16 December 2014, Accepted 3 April 2015, Available online 16 April 2015, Version of Record 16 May 2015.
论文官网地址：https://doi.org/10.1016/j.patcog.2015.04.002
