Bottom-up unsupervised image segmentation using FC-Dense u-net based deep representation clustering and multidimensional feature fusion based region merging
作者：
Highlights：
• Unsupervised image segmentation employing deep learning approaches is a recent advancement.
• FC dense u-net deep network is employed to generate a high-quality clustering-based over-segmented image.
• Feature fusion based high-dimensional feature vector is employed to effectively merge similar regions.
• High-dimensional feature vector based region merging performs far better as compared to simple feature region merging.
摘要
•Unsupervised image segmentation employing deep learning approaches is a recent advancement.•FC dense u-net deep network is employed to generate a high-quality clustering-based over-segmented image.•Feature fusion based high-dimensional feature vector is employed to effectively merge similar regions.•High-dimensional feature vector based region merging performs far better as compared to simple feature region merging.
论文关键词：Unsupervised image segmentation,Deep learning,Feature fusion,Region merging,Image processing
论文评审过程：Received 16 July 2019, Revised 3 September 2019, Accepted 29 December 2019, Available online 8 January 2020, Version of Record 16 January 2020.
论文官网地址：https://doi.org/10.1016/j.imavis.2020.103871
