Threshold logic based low-level vision sparse object features

Nitha Thomas, Joshin John Mathew, Alex James

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Purpose: The 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/approach: A 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. Findings: True 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/value: A 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.

Original languageEnglish
Pages (from-to)314-324
Number of pages11
JournalInternational Journal of Intelligent Computing and Cybernetics
Volume9
Issue number4
DOIs
Publication statusPublished - 2016

Fingerprint

Threshold logic
Object recognition
Neurons
Feature extraction
Edge detection
Processing
Hardware
Data storage equipment
Parallel architectures
Volatile organic compounds
Computer vision
Brain
Networks (circuits)

Keywords

  • Active neurons
  • Cognitive memory-cell array
  • Edge detection
  • Feature description
  • Low-level vision
  • Object features
  • Object recognition
  • Sparse features
  • Threshold logic

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Threshold logic based low-level vision sparse object features. / Thomas, Nitha; Mathew, Joshin John; James, Alex.

In: International Journal of Intelligent Computing and Cybernetics, Vol. 9, No. 4, 2016, p. 314-324.

Research output: Contribution to journalArticle

@article{1a65bab6ebb8472cb76c47fd0fb13bab,
title = "Threshold logic based low-level vision sparse object features",
abstract = "Purpose: The 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/approach: A 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. Findings: True 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/value: A 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.",
keywords = "Active neurons, Cognitive memory-cell array, Edge detection, Feature description, Low-level vision, Object features, Object recognition, Sparse features, Threshold logic",
author = "Nitha Thomas and Mathew, {Joshin John} and Alex James",
year = "2016",
doi = "10.1108/IJICC-04-2016-0016",
language = "English",
volume = "9",
pages = "314--324",
journal = "International Journal of Intelligent Computing and Cybernetics",
issn = "1756-378X",
publisher = "Emerald Group Publishing Ltd.",
number = "4",

}

TY - JOUR

T1 - Threshold logic based low-level vision sparse object features

AU - Thomas, Nitha

AU - Mathew, Joshin John

AU - James, Alex

PY - 2016

Y1 - 2016

N2 - Purpose: The 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/approach: A 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. Findings: True 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/value: A 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.

AB - Purpose: The 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/approach: A 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. Findings: True 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/value: A 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.

KW - Active neurons

KW - Cognitive memory-cell array

KW - Edge detection

KW - Feature description

KW - Low-level vision

KW - Object features

KW - Object recognition

KW - Sparse features

KW - Threshold logic

UR - http://www.scopus.com/inward/record.url?scp=84997610856&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84997610856&partnerID=8YFLogxK

U2 - 10.1108/IJICC-04-2016-0016

DO - 10.1108/IJICC-04-2016-0016

M3 - Article

VL - 9

SP - 314

EP - 324

JO - International Journal of Intelligent Computing and Cybernetics

JF - International Journal of Intelligent Computing and Cybernetics

SN - 1756-378X

IS - 4

ER -