Robust single-object image segmentation based on salient transition region
作者：
Highlights：
• We propose a robust salient transition region-based image segmentation method.
• It adequately uses transition region for image segmentation from a new viewpoint.
• It alleviates the limitations of transition region-based image thresholding.
• It significantly improves accuracy and robustness of image segmentation.
• It keeps the nature of image thresholding, easy operation and high efficiency.
摘要
•We propose a robust salient transition region-based image segmentation method.•It adequately uses transition region for image segmentation from a new viewpoint.•It alleviates the limitations of transition region-based image thresholding.•It significantly improves accuracy and robustness of image segmentation.•It keeps the nature of image thresholding, easy operation and high efficiency.
论文关键词：Local complexity,Local variance,Salient transition region,Image thresholding,Image segmentation
论文评审过程：Received 27 April 2014, Revised 8 October 2015, Accepted 11 October 2015, Available online 19 October 2015, Version of Record 24 December 2015.
论文官网地址：https://doi.org/10.1016/j.patcog.2015.10.009
