Crisp Boundary Detection Using Pointwise Mutual Information
Author(s)
Isola, Phillip; Zoran, Daniel; Krishnan, Dilip; Adelson, Edward H.
DownloadAdelson_Crisp boundary.pdf (5.195Mb)
OPEN_ACCESS_POLICY
Open Access Policy
Creative Commons Attribution-Noncommercial-Share Alike
Terms of use
Metadata
Show full item recordAbstract
Detecting boundaries between semantically meaningful objects in visual scenes is an important component of many vision algorithms. In this paper, we propose a novel method for detecting such boundaries based on a simple underlying principle: pixels belonging to the same object exhibit higher statistical dependencies than pixels belonging to different objects. We show how to derive an affinity measure based on this principle using pointwise mutual information, and we show that this measure is indeed a good predictor of whether or not two pixels reside on the same object. Using this affinity with spectral clustering, we can find object boundaries in the image – achieving state-of-the-art results on the BSDS500 dataset. Our method produces pixel-level accurate boundaries while requiring minimal feature engineering.
Date issued
2014Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Brain and Cognitive SciencesJournal
Computer Vision – ECCV 2014
Publisher
Springer-Verlag
Citation
Isola, Phillip, Daniel Zoran, Dilip Krishnan, and Edward H. Adelson. “Crisp Boundary Detection Using Pointwise Mutual Information.” Lecture Notes in Computer Science (2014): 799–814.
Version: Author's final manuscript
ISBN
978-3-319-10577-2
978-3-319-10578-9
ISSN
0302-9743
1611-3349