Automatic segmentation of granular objects in images: Combining local density clustering and gradient-barrier watershed
作者：
Highlights：
• Propose a general framework for granular object recognition and segmentation.
• Apply the scheme to a wide variety of applications.
• Propose a modified watershed approach called gradient-barrier watershed.
• Incorporate a clustering step in the marker finding procedure.
• Propose a scheme for edge detection and fore/background separation called intensity moment approach.
摘要
•Propose a general framework for granular object recognition and segmentation.•Apply the scheme to a wide variety of applications.•Propose a modified watershed approach called gradient-barrier watershed.•Incorporate a clustering step in the marker finding procedure.•Propose a scheme for edge detection and fore/background separation called intensity moment approach.
论文关键词：Image segmentation,Granular object recognition,Local density clustering,Gradient-barrier watershed,Intensity moment,Edge detection,Cell/nuclei segmentation,Nanoparticle segmentation
论文评审过程：Received 8 February 2013, Revised 26 September 2013, Accepted 6 November 2013, Available online 20 November 2013.
论文官网地址：https://doi.org/10.1016/j.patcog.2013.11.004
