Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Threshold logic based low-level vision sparse object features

Threshold logic based low-level vision sparse object features PurposeThe real-time generation of feature descriptors for object recognition is a challenging problem. In this research, the purpose of this paper is to provide a hardware friendly framework to generate sparse features that can be useful for key feature point selection, feature extraction, and descriptor construction. The inspiration is drawn from feature formation processes of the human brain, taking into account the sparse, modular, and hierarchical processing of visual information.Design/methodology/approachA sparse set of neurons referred as active neurons determines the feature points necessary for high-level vision applications such as object recognition. A psycho-physical mechanism of human low-level vision relates edge detection to noticeable local spatial stimuli, representing this set of active neurons. A cognitive memory cell array-based implementation of low-level vision is proposed. Applications of memory cell in edge detection are used for realizing human vision inspired feature selection and leading to feature vector construction for high-level vision applications.FindingsTrue parallel architecture and faster response of cognitive circuits avoid time costly and redundant feature extraction steps. Validation of proposed feature vector toward high-level computer vision applications is demonstrated using standard object recognition databases. The comparison against existing state-of-the-art object recognition features and methods shows an accuracy of 97, 95, 69 percent for Columbia Object Image Library-100, ALOI, and PASCAL VOC 2007 databases indicating an increase from benchmark methods by 5, 3 and 10 percent, respectively.Originality/valueA hardware friendly low-level sparse edge feature processing system is proposed for recognizing objects. The edge features are developed based on threshold logic of neurons, and the sparse selection of the features applies a modular and hierarchical processing inspired from the human neural system. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Intelligent Computing and Cybernetics Emerald Publishing

Threshold logic based low-level vision sparse object features

Download PDF
11 pages

Loading next page...
 
/lp/emerald-publishing/threshold-logic-based-low-level-vision-sparse-object-features-B1drseZoEF

References (44)

Publisher
Emerald Publishing
Copyright
Copyright © Emerald Group Publishing Limited
ISSN
1756-378X
DOI
10.1108/IJICC-04-2016-0016
Publisher site
See Article on Publisher Site

Abstract

PurposeThe real-time generation of feature descriptors for object recognition is a challenging problem. In this research, the purpose of this paper is to provide a hardware friendly framework to generate sparse features that can be useful for key feature point selection, feature extraction, and descriptor construction. The inspiration is drawn from feature formation processes of the human brain, taking into account the sparse, modular, and hierarchical processing of visual information.Design/methodology/approachA sparse set of neurons referred as active neurons determines the feature points necessary for high-level vision applications such as object recognition. A psycho-physical mechanism of human low-level vision relates edge detection to noticeable local spatial stimuli, representing this set of active neurons. A cognitive memory cell array-based implementation of low-level vision is proposed. Applications of memory cell in edge detection are used for realizing human vision inspired feature selection and leading to feature vector construction for high-level vision applications.FindingsTrue parallel architecture and faster response of cognitive circuits avoid time costly and redundant feature extraction steps. Validation of proposed feature vector toward high-level computer vision applications is demonstrated using standard object recognition databases. The comparison against existing state-of-the-art object recognition features and methods shows an accuracy of 97, 95, 69 percent for Columbia Object Image Library-100, ALOI, and PASCAL VOC 2007 databases indicating an increase from benchmark methods by 5, 3 and 10 percent, respectively.Originality/valueA hardware friendly low-level sparse edge feature processing system is proposed for recognizing objects. The edge features are developed based on threshold logic of neurons, and the sparse selection of the features applies a modular and hierarchical processing inspired from the human neural system.

Journal

International Journal of Intelligent Computing and Cybernetics – Emerald Publishing

Published: Nov 14, 2016

There are no references for this article.