Toward Object Recognition with Proto-objects and Proto-scenes

Fabian Nasse, Rene Grzeszick, Gernot A. Fink

2014

Abstract

In this paper a bottom-up approach for detecting and recognizing objects in complex scenes is presented. In contrast to top-down methods, no prior knowledge about the objects is required beforehand. Instead, two different views on the data are computed: First, a GIST descriptor is used for clustering scenes with a similar global appearance which produces a set of Proto-Scenes. Second, a visual attention model that is based on hiearchical multi-scale segmentation and feature integration is proposed. Regions of Interest that are likely to contain an arbitrary object, a Proto-Object, are determined. These Proto-Object regions are then represented by a Bag-of-Features using Spatial Visual Words. The bottom-up approach makes the detection and recognition tasks more challenging but also more efficient and easier to apply to an arbitrary set of objects. This is an important step toward analyzing complex scenes in an unsupervised manner. The bottom-up knowledge is combined with an informed system that associates Proto-Scenes with objects that may occur in them and an object classifier is trained for recognizing the Proto-Objects. In the experiments on the VOC2011 database the proposed multi-scale visual attention model is compared with current state-of-the-art models for Proto-Object detection. Additionally, the the Proto-Objects are classified with respect to the VOC object set.

Paper Citation

in Harvard Style

Nasse F., Grzeszick R. and Fink G. (2014). Toward Object Recognition with Proto-objects and Proto-scenes . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 284-291. DOI: 10.5220/0004657902840291

in Bibtex Style

@conference{visapp14,
author={Fabian Nasse and Rene Grzeszick and Gernot A. Fink},
title={Toward Object Recognition with Proto-objects and Proto-scenes},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={284-291},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004657902840291},
isbn={978-989-758-004-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - Toward Object Recognition with Proto-objects and Proto-scenes
SN - 978-989-758-004-8
AU - Nasse F.
AU - Grzeszick R.
AU - Fink G.
PY - 2014
SP - 284
EP - 291
DO - 10.5220/0004657902840291