.png){kind=icon}
.png){kind=icon}
Return
Learning contextual superpixel similarity for consistent image segmentation
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-019-08391-6.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper addresses the problem of image segmentation by iterative region aggregations starting from an initial superpixel decomposition. Classical approaches for this task compute superpixel similarity using distance measures between superpixel descriptor vectors. This usually poses the well-known problem of the semantic gap and fails to properly aggregate visually non-homogeneous superpixels that belong to the same high-level object. This work proposes to use random forests to learn the merging probability between adjacent superpixels in order to overcome the aforementioned issues. Compared to existing works, this approach learns the fusion rules without explicit similarity measure computation. We also introduce a new superpixel context descriptor to strengthen the learned characteristics towards better similarity prediction. Image segmentation is then achieved by iteratively merging the most similar superpixel pairs selected using a similarity weighting objective function. Experimental results of our approach on four datasets including DAVIS 2017 and ISIC 2018 show its potential compared to state-of-the-art approaches.
Keywords:
Context description
Superpixels similarity
Machine learning
Random forests
Image segmentation
Region-growing
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3
Papers:
1.9W
Citations:
3.2W