Back to Search
Start Over
Error-tolerant label prior for interactive image segmentation
- Source :
- Information Sciences. 538:384-395
- Publication Year :
- 2020
- Publisher :
- Elsevier BV, 2020.
-
Abstract
- User interactions are generally utilized to impose the hard constraint and estimate the label prior probability in the interactive image segmentation methods. The conventional interactive approaches cannot work well when the user inputs contain incorrect marks. The existing error tolerance methods mainly focus on the interaction itself and try to eliminate the influence of incorrect hard constraint, which however ignore the label prior estimation. This paper mainly focuses on solving the label prior estimation problem when error marks appear. The prior probability is generally defined as the matching degree between pixels and the cluster centers of marked pixels. Incorrect interaction leads to the formation of incorrect clusters. Therefore, a reliability learning model is constructed in this paper by 1) assigning smaller weighting factors to incorrect clusters, 2) assigning larger weighting factors to correct clusters with higher matching degree. Accurate label prior probability can be obtained by the weighted averaging. Then referring to the existing methods, an error-tolerant segmentation model is designed as a ratio energy function, which can both overcome the hard constraint and the label prior limitation with error marks. Experiments on the challenging Berkeley segmentation data set and Microsoft GrabCut database demonstrate the effectiveness of the proposed method.
- Subjects :
- Matching (statistics)
Information Systems and Management
Pixel
Computer science
business.industry
05 social sciences
050301 education
Pattern recognition
02 engineering and technology
Image segmentation
Computer Science Applications
Theoretical Computer Science
Weighting
Constraint (information theory)
GrabCut
Artificial Intelligence
Control and Systems Engineering
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Segmentation
Artificial intelligence
business
0503 education
Software
Subjects
Details
- ISSN :
- 00200255
- Volume :
- 538
- Database :
- OpenAIRE
- Journal :
- Information Sciences
- Accession number :
- edsair.doi...........e9d65595f4f48fcbe63552d768e97be9