TY - GEN
T1 - Enhanced object recognition in cortex-like machine vision
AU - Tsitiridis, Aristeidis
AU - Yuen, Peter W.T.
AU - Ibrahim, Izzati
AU - Soori, Umar
AU - Chen, Tong
AU - Hong, Kan
AU - Wang, Zhengjie
AU - James, David
AU - Richardson, Mark
PY - 2011
Y1 - 2011
N2 - This paper reports an extension of the previous MIT and Caltech's cortex-like machine vision models of Graph-Based Visual Saliency (GBVS) and Feature Hierarchy Library (FHLIB), to remedy some of the undesirable drawbacks in these early models which improve object recognition efficiency. Enhancements in three areas, a) extraction of features from the most salient region of interest (ROI) and their rearrangement in a ranked manner, rather than random extraction over the whole image as in the previous models, b) exploitation of larger patches in the C1 and S2 layers to improve spatial resolutions, c) a more versatile template matching mechanism without the need of 'pre-storing' physical locations of features as in previous models, have been the main contributions of the present work. The improved model is validated using 3 different types of datasets which shows an average of ~7% better recognition accuracy over the original FHLIB model.
AB - This paper reports an extension of the previous MIT and Caltech's cortex-like machine vision models of Graph-Based Visual Saliency (GBVS) and Feature Hierarchy Library (FHLIB), to remedy some of the undesirable drawbacks in these early models which improve object recognition efficiency. Enhancements in three areas, a) extraction of features from the most salient region of interest (ROI) and their rearrangement in a ranked manner, rather than random extraction over the whole image as in the previous models, b) exploitation of larger patches in the C1 and S2 layers to improve spatial resolutions, c) a more versatile template matching mechanism without the need of 'pre-storing' physical locations of features as in previous models, have been the main contributions of the present work. The improved model is validated using 3 different types of datasets which shows an average of ~7% better recognition accuracy over the original FHLIB model.
KW - Biological-like vision algorithms
KW - Computer vision
KW - Generic Object recognition
KW - Human vision models
KW - Machine vision
UR - http://www.scopus.com/inward/record.url?scp=80055052410&partnerID=8YFLogxK
U2 - 10.1007/978-3-642-23960-1_3
DO - 10.1007/978-3-642-23960-1_3
M3 - Conference contribution
AN - SCOPUS:80055052410
SN - 9783642239595
T3 - IFIP Advances in Information and Communication Technology
SP - 17
EP - 26
BT - Artificial Intelligence Applications and Innovations - 12th INNS EANN-SIG International Conference, EANN 2011 and 7th IFIP WG 12.5 International Conference, AIAI 2011, Proceedings
PB - Springer New York LLC
T2 - 7th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2011
Y2 - 15 September 2011 through 18 September 2011
ER -