.png){kind=icon}
.png){kind=icon}
Return
Explored Normalized Cut With Random Walk Refining Term for Image Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2022.3162475.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The Normalized Cut (NCut) model is a popular graph-based model for image segmentation. But it suffers from the excessive normalization problem and weakens the small object and twig segmentation. In this paper, we propose an Explored Normalized Cut (ENCut) model that establishes a balance graph model by adopting a meaningful-loop and a k-step random walk, which reduces the energy of small salient region, so as to enhance the small object segmentation. To improve the twig segmentation, our ENCut model is further enhanced by a new Random Walk Refining Term (RWRT) that adds local attention to our model with the help of an un-supervising random walk. Finally, a move-making based strategy is developed to efficiently solve the ENCut model with RWRT. Experiments on three standard datasets indicate that our model can achieve state-of-the-art results among the NCut-based segmentation models.
Keywords:
Image segmentation
Image edge detection
Task analysis
Computational modeling
Analytical models
Partitioning algorithms
Object segmentation
Normalized Cut (NCut)
image segmentation
unsupervised learning
graph signal processing
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W