Discovery of topical object in image collections
Huaping Liu, Yunhui Liu, Liming Huang, Fuchun Sun, Di Guo
Abstract
Automatic discovery of topical objects from a set of image collections provides more strong cognitive capability of robot to understand the unstructured environment. In this paper, we propose a novel framework based on dictionary learning for such a task. Different from existing work which utilizes multiple segmentations to coarsely obtain the object regions, we adopt the most recently developed objectness operator to extract candidate objects. Such a method admits a great advantage that the interested objects can be more reliably segmented. A dictionary learning method is proposed to discover the topical objects. Such an optimization model exploits the observation that any image only includes a few topical objects and therefore sparsity is encouraged. Further, a globally convergent algorithm is developed to solve the dictionary learning problem and extensive experiments show that the proposed method outperforms the state-of-the-arts.
BibTeX
@inproceedings{icra2015_discoveryoftopic,
title = {Discovery of topical object in image collections},
author = {Huaping Liu and Yunhui Liu and Liming Huang and Fuchun Sun and Di Guo},
booktitle = {ICRA 2015},
year = {2015}
}