Efficient Bag of Scenes Analysis for Image Categorization

Sébastien Paris, Xanadu Halkias, Hervé Glotin

2013

Abstract

In this paper, we address the general problem of image/object categorization with a novel approach referred to as Bag-of-Scenes (BoS).Our approach is efficient for low semantic applications such as texture classification as well as for higher semantic tasks such as natural scenes recognition or fine-grained visual categorization (FGVC). It is based on the widely used combination of i) Sparse coding (Sc), ii) Max-pooling and iii) Spatial Pyramid Matching (SPM) techniques applied to histograms of multi-scale Local Binary/Ternary Patterns (LBP/LTP) and its improved variants. This approach can be considered as a two-layer hierarchical architecture: the first layer encodes the local spatial patch structure via histograms of LBP/LTP while the second encodes the relationships between pre-analyzed LBP/LTP-scenes/objects. Our method outperforms SIFT-based approaches using Sc techniques and can be trained efficiently with a simple linear SVM.

Paper Citation

in Harvard Style

Paris S., Halkias X. and Glotin H. (2013). Efficient Bag of Scenes Analysis for Image Categorization . In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8565-41-9, pages 335-344. DOI: 10.5220/0004198303350344

in Bibtex Style

@conference{icpram13,
author={Sébastien Paris and Xanadu Halkias and Hervé Glotin},
title={Efficient Bag of Scenes Analysis for Image Categorization},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2013},
pages={335-344},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004198303350344},
isbn={978-989-8565-41-9},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Efficient Bag of Scenes Analysis for Image Categorization
SN - 978-989-8565-41-9
AU - Paris S.
AU - Halkias X.
AU - Glotin H.
PY - 2013
SP - 335
EP - 344
DO - 10.5220/0004198303350344