Document - Image recognition for digital libraries

2004

Conference article Restricted

Image recognition for digital libraries

Le Saux B., Amato G.

Image segmentation Feature selection Scene analysis Image Segmentation Clustering Kernel-method Image classification

The interpretation of natural scenes, generally so obvious and effortless for humans, still remains a challenge in computer vision. To allow the search of image-based documents in digital libraries, we propose to design classifiers able to annotate images with keywords. First, we propose an image representation appropriate for scene description. Images are segmented into regions, and then indexed according to the presence of given region types. Second, we propound a classification scheme designed to separate images in the descriptor space. This is achieved by combining feature selection and kernel-method-based classification.

Source: MIR '04 Proceedings of the 6th ACM SIGMM international workshop on Multimedia information retrieval, pp. 91–98, New York, USA, 10-16 October 2004

Publisher: ACM Press, New York, USA

Metrics

Back to previous page

Cite as

BibTeX entry

@inproceedings{oai:it.cnr:prodotti:91077,
	title = {Image recognition for digital libraries},
	author = {Le Saux B. and Amato G.},
	publisher = {ACM Press, New York, USA},
	doi = {10.1145/1026711.1026727},
	booktitle = {MIR '04 Proceedings of the 6th ACM SIGMM international workshop on Multimedia information retrieval, pp. 91–98, New York, USA, 10-16 October 2004},
	year = {2004}
}