CNLS '89 Proceedings of the ninth annual international conference of the Center for Nonlinear Studies on Self-organizing, Collective, and Cooperative Phenomena in Natural and Artificial Computing Networks on Emergent computation
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Learning Object Categories from Google"s Image Search
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Unsupervised Learning of Categories from Sets of Partially Matching Image Features
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Open-ended category learning for language acquisition
Connection Science - Language and Robots
Learning Visual Object Categories with Global Descriptors and Local Features
EPIA '09 Proceedings of the 14th Portuguese Conference on Artificial Intelligence: Progress in Artificial Intelligence
Towards unsupervised discovery of visual categories
DAGM'06 Proceedings of the 28th conference on Pattern Recognition
Learning Visual Object Categories with Global Descriptors and Local Features
EPIA '09 Proceedings of the 14th Portuguese Conference on Artificial Intelligence: Progress in Artificial Intelligence
Hi-index | 0.00 |
Robots need to ground their external vocabulary and internal symbols in observations of the world. In recent works, this problem has been approached through combinations of open-ended category learning and interaction with other agents acting as teachers. In this paper, a complementary path is explored, in which robots also resort to semantic searches in digital collections of text and images, or more generally in the Internet, to ground vocabulary about objects. Drawing on a distinction between broad and narrow (or general and specific) categories, different methods are applied, namely global shape contexts to represent broad categories, and SIFT local features to represent narrow categories. An unsupervised image clustering and ranking method is proposed that, starting from a set of images automatically fetched on the web for a given category name, selects a subset of images suitable for building a model of the category. In the case of broad categories, image segmentation and object extraction enhance the chances of finding suitable training objects. We demonstrate that the proposed approach indeed improves the quality of the training object collections.