Segmentation of neuronal nuclei based on clump splitting and a two-step binarization of images
作者：
Highlights：
• We propose a automatic segmentation algorithm for confocal microscope images.
• Algorithm based on two-steps binarization and extended clump splitting algorithm.
• Compared with state-of-the-art algorithms (Watershed, Level Set Methods).
• Validation on a set of representative images coming from the rat neocortex.
• Accurate segmentations (91–98% of properly identified cells’ nuclei).
摘要
•We propose a automatic segmentation algorithm for confocal microscope images.•Algorithm based on two-steps binarization and extended clump splitting algorithm.•Compared with state-of-the-art algorithms (Watershed, Level Set Methods).•Validation on a set of representative images coming from the rat neocortex.•Accurate segmentations (91–98% of properly identified cells’ nuclei).
论文关键词：Segmentation,Clump splitting,Concavity analysis,Overlapping objects,Binarization
论文评审过程：Available online 18 June 2013.
论文官网地址：https://doi.org/10.1016/j.eswa.2013.06.010
