Image classifiers for scene analysis
Le Saux B., Amato G.
Scene analysis Feature selection Image classification Kernel methods
The semantic interpretation of natural scenes, generally so obvious and effortless for humans, still remains a challenge in computer vision. We intend to design classifiers able to annotate images with keywords. Firstly, we propose an image representation appropriate for scene description: images are segmented into regions and indexed according to the presence of given region types. Secondly, we propound a classification scheme de- signed to separate images in the descriptor space. This is achieved by combining feature selection and kernel-method-based classification.
Source: ICCVG 04 - International Conference on Computer Vision and Graphics, Warsaw, Poland, 1-12 September 2004
Back to previous page
@inproceedings{oai:it.cnr:prodotti:388620,
title = {Image classifiers for scene analysis},
author = {Le Saux B. and Amato G.},
booktitle = {ICCVG 04 - International Conference on Computer Vision and Graphics, Warsaw, Poland, 1-12 September 2004},
year = {2004}
}
0000-0003-0171-4315