LOCAL BLUR ASSESSMENT IN NATURAL IMAGES

Loreta Adriana Suta, Mihaela Scuturici, Serge Miguet, Laure Tougne, Mircea-Florin Vaida

2012

Abstract

This paper presents a local no-reference blur assessment method in natural macro-like images. The purpose is to decide the blurriness of the object of interest. In our case, it represents the first step for a plant recognition system. Blur detection works on small non-overlapping blocks using wavelet decomposition and edge classification. At the block level the number of edges is less than on global images. A new set of rules is obtained by a supervised decision tree algorithm trained on a manually labelled base of 1500 blurred/un-blurred images. Our purpose is to achieve a qualitative decision of the blurriness/sharpness of the object of interest making it the first step towards a segmentation process. Experimental results show this method outperforms two other methods found in literature, even if applied on a block basis. Together with a pre-segmentation step, the method allows to decide if the object of interest (leaf, flower) is sharp in order to extract precise botanical key identification features (e. g. leaf border).

Paper Citation

in Harvard Style

Suta L., Scuturici M., Miguet S., Tougne L. and Vaida M. (2012). LOCAL BLUR ASSESSMENT IN NATURAL IMAGES . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 123-128. DOI: 10.5220/0003854001230128

in Bibtex Style

@conference{visapp12,
author={Loreta Adriana Suta and Mihaela Scuturici and Serge Miguet and Laure Tougne and Mircea-Florin Vaida},
title={LOCAL BLUR ASSESSMENT IN NATURAL IMAGES},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={123-128},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003854001230128},
isbn={978-989-8565-03-7},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - LOCAL BLUR ASSESSMENT IN NATURAL IMAGES
SN - 978-989-8565-03-7
AU - Suta L.
AU - Scuturici M.
AU - Miguet S.
AU - Tougne L.
AU - Vaida M.
PY - 2012
SP - 123
EP - 128
DO - 10.5220/0003854001230128