Recovery of drawing order from multi-stroke English handwritten images based on graph models and ambiguous zone analysis
作者：
Highlights：
• Recovering the drawing orders in static multi-stroke handwritten images.
• Simultaneously separating strokes and finding the smoothest path for each stroke.
• Using graph models with a new cost function.
• Detecting touches and crossings of stroke parts to determine the continuity.
• Using un-smoothness and double-traced segments to break the stroke.
摘要
•Recovering the drawing orders in static multi-stroke handwritten images.•Simultaneously separating strokes and finding the smoothest path for each stroke.•Using graph models with a new cost function.•Detecting touches and crossings of stroke parts to determine the continuity.•Using un-smoothness and double-traced segments to break the stroke.
论文关键词：Multi-stroke handwriting,Static handwritten image,Drawing order,Trajectory recovery,Smoothest path
论文评审过程：Received 21 August 2015, Revised 24 March 2016, Accepted 2 August 2016, Available online 3 August 2016, Version of Record 5 August 2016.
论文官网地址：https://doi.org/10.1016/j.eswa.2016.08.017
