June
2006
Using Multiple Segmentations to Discover Objects and their Extent in Image Collections
Authors:
Abstract:
Given a large dataset of images, we seek to automatically determine the visually similar object and scene classes together with their image segmentation. To achieve this we combine two ideas: (i) that a set of segmented objects can be partitioned into visual object classes using topic discovery models from statistical text analysis; and (ii) that visual object classes can be used to assess the accuracy of a segmentation. To tie these ideas together we compute multiple segmentations of each image and then: (i) learn the object classes; and (ii) choose the correct segmentations. We demonstrate that such an algorithm succeeds in automatically discovering many familiar objects in a variety of image datasets, including those from Caltech, MSRC and LabelMe.
copied = false, 2000);
">
@conference{Russell-2006-9497,
author = {Bryan C. Russell And Alexei A. Efros And Josef Sivic And William T. Freeman And Andrew Zisserman},
title = {Using Multiple Segmentations to Discover Objects and their Extent in Image Collections},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2006},
month = {June},
pages = {1605 - 1614},
}
author = {Bryan C. Russell And Alexei A. Efros And Josef Sivic And William T. Freeman And Andrew Zisserman},
title = {Using Multiple Segmentations to Discover Objects and their Extent in Image Collections},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2006},
month = {June},
pages = {1605 - 1614},
}