.png){kind=icon}
.png){kind=icon}
Return
Superpixels With Content-Adaptive Criteria
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2021.3108403.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Superpixels are widely used in computer vision applications. Most of the existing superpixel methods use established criteria to indiscriminately process all pixels, resulting in superpixel boundary adherence and regularity being unnecessarily inter-inhibitive. This study builds upon a previous work by proposing a new segmentation strategy that classifies image content into meaningful areas containing object boundaries and meaningless parts that include color-homogeneous and texture-rich regions. Based on this classification, we design two distinct criteria to process the pixels in different environments to achieve highly accurate superpixels in content-meaningful areas and keep the regularity of the superpixels in content-meaningless regions. Additionally, we add a group of weights when adopting the color feature, successfully reducing the undersegmentation error. The superior accuracy and the moderate compactness achieved by the proposed method in comparative experiments with several state-of-the-art methods indicate that the content-adaptive criteria efficiently reduce the compromise between boundary adherence and compactness.
Keywords:
Image color analysis
Shape
Image segmentation
Clustering algorithms
Visualization
Topology
Shape measurement
Superpixel
image segmentation
content-adaptive criteria
real-time
boundary refinement
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W