Crisp Boundary Detection Using Pointwise Mutual Information^*

Phillip Isola, Daniel Zoran, Dilip Krishnan, and Edward H. Adelson

Abstract. 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.

Keywords: Edge/Contour Detection, Segmentation

Electronic Supplementary Material:

• Electronic Supplementary Material (PDF 4,167 KB)

LNCS 8691, p. 799 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer International Publishing Switzerland 2014