Non-Parametric Probabilistic Image Segmentation

Description

We propose a simple probabilistic generative model for image segmentation. Like other probabilistic algorithms (such as EM on a Mixture of Gaussians) the proposed model is principled, provides both hard and probabilistic cluster assignments, as well as the ability to naturally incorporate prior knowledge. While previous probabilistic approaches are restricted to parametric models of clusters (e.g., Gaussians) we eliminate this limitation. The suggested approach does not make heavy assumptions on the shape of the clusters and can thus handle complex structures.
Our experiments show that the suggested approach outperforms previous work on a variety of image segmentation tasks.

Pubblications

M. Andreetto, L. Zelnik-Manor, and P. Perona, "Non-Parametric Probabilistic Image Segmentation", ICCV 2007 (PDF) (Poster)

Software

Supplemental material

• Segmentation of images

• Dataset 1: Internet images (link PDF)

• Dataset 2: egret (link PDF)

• Segmentation of image collections (link PDF)

• Segmentation of video sequences

• Aerobics.avi (link AVI file)

• Ballet.avi (link AVI file)

• Screenshot of the rating application

Last update Nov 21, 2007