Efficient Implementation of a Recognition System using the Cortex Ventral Stream Model

Ahmad Bitar, Mohammad M. Mansour, Ali Chehab

2015

Abstract

In this paper, an efficient implementation for a recognition system based on the original HMAX model of the visual cortex is proposed. Various optimizations targeted to increase accuracy at the so-called layers S1, C1, and S2 of the HMAX model are proposed. At layer S1, all unimportant information such as illumination and expression variations are eliminated from the images. Each image is then convolved with 64 separable Gabor filters in the spatial domain. At layer C1, the minimum scales values are exploited to be embedded into the maximum ones using the additive embedding space. At layer S2, the prototypes are generated in a more efficient way using Partitioning Around Medoid (PAM) clustering algorithm. The impact of these optimizations in terms of accuracy and computational complexity was evaluated on the Caltech101 database, and compared with the baseline performance using support vector machine (SVM) and nearest neighbor (NN) classifiers. The results show that our model provides significant improvement in accuracy at the S1 layer by more than 10% where the computational complexity is also reduced. The accuracy is slightly increased for both approximations at the C1 and S2 layers.

Paper Citation

in Harvard Style

Bitar A., Mansour M. and Chehab A. (2015). Efficient Implementation of a Recognition System using the Cortex Ventral Stream Model . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-090-1, pages 138-147. DOI: 10.5220/0005308901380147

in Bibtex Style

@conference{visapp15,
author={Ahmad Bitar and Mohammad M. Mansour and Ali Chehab},
title={Efficient Implementation of a Recognition System using the Cortex Ventral Stream Model},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={138-147},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005308901380147},
isbn={978-989-758-090-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)
TI - Efficient Implementation of a Recognition System using the Cortex Ventral Stream Model
SN - 978-989-758-090-1
AU - Bitar A.
AU - Mansour M.
AU - Chehab A.
PY - 2015
SP - 138
EP - 147
DO - 10.5220/0005308901380147