Crisp Boundary Detection Using Pointwise Mutual Information


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.

DOI: 10.1007/978-3-319-10578-9_52

Extracted Key Phrases

10 Figures and Tables

Citations per Year

93 Citations

Semantic Scholar estimates that this publication has 93 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Isola2014CrispBD, title={Crisp Boundary Detection Using Pointwise Mutual Information}, author={Phillip Isola and Daniel Zoran and Dilip Krishnan and Edward H. Adelson}, booktitle={ECCV}, year={2014} }