[Comp-neuro] Large real-world color object dataset available

Alexander Gepperth alexander.gepperth at honda-ri.de
Mon Oct 15 16:08:06 CEST 2007


A large dataset of real-world color objects is now available. It
consists of the object classes "car" (~1800 examples), "signal
board"(~1000 examples)
and "clutter"(~3500 examples). The objects were taken from the
segmentation results of a vision system operating within a moving car
and are thus
biased as well as imperfectly segmented, posing challenges to object
recognition. The data is partitioned into 4 classes of (heuristically
determined)
increasing complexity and difficulty.
The dataset consists of images in the standard PPM format and can be
obtained from

http://www.gepperth.eu/alexander/carDatasetsICANN.html

The paper in which this dataset is described and used is
A. Gepperth, B. Mersch, J. Fritsch, C. Goerick. Color object recognition
in real-world scenes.
In J.M. de Sa, editor, ICANN 2007, part II, Lecture notes in Computer
Science, number 4469.
Springer Verlag Berlin, Heidelberg, New York, 2007.

available from the same site:
http://www.gepperth.eu/alexander/papers/gepperthEtAl2007.ps





More information about the Comp-neuro mailing list