loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Muhammad Ali and Hassan Foroosh

Affiliation: University of Central Florida, United States

Keyword(s): Natural Scene Text Recognition, Tensors, Rank-1 Decomposition, Holistic Character Recognition, Feature Independence.

Abstract: Current methods in scene character recognition heavily rely on discriminative power of local features, such as HoG, SIFT, Shape Contexts (SC), Geometric Blur (GB), etc. One of the problems with this approach is that the local features are rasterized in an ad hoc manner into a single vector perturbing thus spatial correlations that carry crucial information. To eliminate this feature dependency and associated problems, we propose a holistic solution as follows: For each character to be recognized, we stack a set of training images to form a 3-mode tensor. Each training tensor is then decomposed into a linear superposition of ‘k’ rank-1 matrices, whereby the rank-1 matrices form a basis, spanning solution subspace of the character class. For a test image to be classified, we obtain projections onto the pre-computed rank-1 bases of each class, and recognize it as the class for which inner-product of mixing vectors is maximized. We use challenging natural scene character datasets, namely Chars74K, ICDAR2003, and SVT-CHAR. We achieve results better than several baseline methods based on local features (e.g. HoG) and show leave-random-one-out-cross validation yield even better recognition performance, justifying thus our intuition of the importance of feature-independency and preservation of spatial correlations in recognition. (More)

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 18.97.9.170

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:
Ali, M. and Foroosh, H. (2015). Natural Scene Character Recognition Without Dependency on Specific Features. In Proceedings of the 10th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2015) - Volume 3: VISAPP; ISBN 978-989-758-090-1; ISSN 2184-4321, SciTePress, pages 368-376. DOI: 10.5220/0005305603680376

@conference{visapp15,
author={Muhammad Ali and Hassan Foroosh},
title={Natural Scene Character Recognition Without Dependency on Specific Features},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2015) - Volume 3: VISAPP},
year={2015},
pages={368-376},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005305603680376},
isbn={978-989-758-090-1},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2015) - Volume 3: VISAPP
TI - Natural Scene Character Recognition Without Dependency on Specific Features
SN - 978-989-758-090-1
IS - 2184-4321
AU - Ali, M.
AU - Foroosh, H.
PY - 2015
SP - 368
EP - 376
DO - 10.5220/0005305603680376
PB - SciTePress