loading
Documents

Research.Publish.Connect.

Paper

Paper Unlock

Author: Jean Martinet

Affiliation: Université Lille 1, France

ISBN: 978-989-758-004-8

ISSN: 2184-4321

Keyword(s): Bag-of-Features, Quantization, Vocabulary, Zipf’s Law, Evaluation.

Abstract: The popular "bag-of-visual-words" approach for representing and searching visual documents consists in describing images (or video keyframes) using a set of descriptors, that correspond to quantized low-level features. Most of existing approaches for visual words are inspired from works in text indexing, based on the implicit assumption that visual words can be handled the same way as text words. More specifically, these techniques implicitly rely on the same postulate as in text information retrieval, stating that the words distribution for a natural language globally follows Zipf's law -- that is to say, words from a natural language appear in a corpus with a frequency inversely proportional to their rank. However, our study shows that the visual words distribution depends on the choice of low-level features, and also especially on the choice of the clustering method. We also show that when the visual words distribution is close to this of text words, the results of an image retriev al system are increased. To the best of our knowledge, no prior study has yet been carried out to compare the distributions of text words and visual words, with the objective of establishing the theoretical foundations of visual vocabularies. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 34.204.176.125

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Martinet, J. (2014). From Text Vocabularies to Visual Vocabularies - What Basis?.In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, ISSN 2184-4321, pages 668-675. DOI: 10.5220/0004749606680675

@conference{visapp14,
author={Jean Martinet.},
title={From Text Vocabularies to Visual Vocabularies - What Basis?},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={668-675},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004749606680675},
isbn={978-989-758-004-8},
}

TY - CONF

JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014)
TI - From Text Vocabularies to Visual Vocabularies - What Basis?
SN - 978-989-758-004-8
AU - Martinet, J.
PY - 2014
SP - 668
EP - 675
DO - 10.5220/0004749606680675

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.