Authors:
Séverine Cloix
1
;
Thierry Pun
2
and
David Hasler
3
Affiliations:
1
CSEM SA and University of Geneva, Switzerland
;
2
University of Geneva, Switzerland
;
3
CSEM SA, Switzerland
Keyword(s):
Object Recognition, Object Classification, Light Field, Plenoptic Function, Scale Invariance, Real-time, Dataset.
Related
Ontology
Subjects/Areas/Topics:
Computer Vision, Visualization and Computer Graphics
;
Features Extraction
;
Image and Video Analysis
Abstract:
We present a novel light field dataset along with a real-time and scale-invariant object recognition system. Our
method is based on bag-of-visual-words and codebook approaches. Its evaluation was carried out on a subset
of our dataset of unconventional images. We show that the low variance in scale inferred from the specificities
of a plenoptic camera allows high recognition performance. With one training image per object to recognise,
recognition rates greater than 90 % are demonstrated despite a scale variation of up to 178 %. Our versatile
light-field image dataset, CSEM-25, is composed of five classes of five instances captured with the recent
industrial Raytrix R5 camera at different distances with several poses and backgrounds. We make it available
for research purposes.