Enhanced object recognition in cortex-like machine vision

Aristeidis Tsitiridis; Peter W.T. Yuen; Izzati Ibrahim; Umar Soori; Tong Chen; Kan Hong; Zhengjie Wang; David James; Mark Richardson

doi:10.1007/978-3-642-23960-1_3

Enhanced object recognition in cortex-like machine vision

Aristeidis Tsitiridis^*, Peter W.T. Yuen, Izzati Ibrahim, Umar Soori, Tong Chen, Kan Hong, Zhengjie Wang, David James, Mark Richardson

^*Corresponding author for this work

School of Mechatronical Engineering

Cranfield University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

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.

Original language	English
Title of host publication	Artificial Intelligence Applications and Innovations - 12th INNS EANN-SIG International Conference, EANN 2011 and 7th IFIP WG 12.5 International Conference, AIAI 2011, Proceedings
Publisher	Springer New York LLC
Pages	17-26
Number of pages	10
Edition	PART 2
ISBN (Print)	9783642239595
DOIs	https://doi.org/10.1007/978-3-642-23960-1_3
Publication status	Published - 2011
Event	7th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2011 - Corfu, Greece Duration: 15 Sept 2011 → 18 Sept 2011

Publication series

Name	IFIP Advances in Information and Communication Technology
Number	PART 2
Volume	364 AICT
ISSN (Print)	1868-4238

Conference

Conference	7th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2011
Country/Territory	Greece
City	Corfu
Period	15/09/11 → 18/09/11

Keywords

Biological-like vision algorithms
Computer vision
Generic Object recognition
Human vision models
Machine vision

Access to Document

10.1007/978-3-642-23960-1_3

Cite this

Tsitiridis, A., Yuen, P. W. T., Ibrahim, I., Soori, U., Chen, T., Hong, K., Wang, Z., James, D., & Richardson, M. (2011). Enhanced object recognition in cortex-like machine vision. In Artificial Intelligence Applications and Innovations - 12th INNS EANN-SIG International Conference, EANN 2011 and 7th IFIP WG 12.5 International Conference, AIAI 2011, Proceedings (PART 2 ed., pp. 17-26). (IFIP Advances in Information and Communication Technology; Vol. 364 AICT, No. PART 2). Springer New York LLC. https://doi.org/10.1007/978-3-642-23960-1_3

Tsitiridis, Aristeidis ; Yuen, Peter W.T. ; Ibrahim, Izzati et al. / Enhanced object recognition in cortex-like machine vision. Artificial Intelligence Applications and Innovations - 12th INNS EANN-SIG International Conference, EANN 2011 and 7th IFIP WG 12.5 International Conference, AIAI 2011, Proceedings. PART 2. ed. Springer New York LLC, 2011. pp. 17-26 (IFIP Advances in Information and Communication Technology; PART 2).

@inproceedings{624354619de847b7b9417e8be08ed198,

title = "Enhanced object recognition in cortex-like machine vision",

abstract = "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.",

keywords = "Biological-like vision algorithms, Computer vision, Generic Object recognition, Human vision models, Machine vision",

author = "Aristeidis Tsitiridis and Yuen, {Peter W.T.} and Izzati Ibrahim and Umar Soori and Tong Chen and Kan Hong and Zhengjie Wang and David James and Mark Richardson",

year = "2011",

doi = "10.1007/978-3-642-23960-1_3",

language = "English",

isbn = "9783642239595",

series = "IFIP Advances in Information and Communication Technology",

publisher = "Springer New York LLC",

number = "PART 2",

pages = "17--26",

booktitle = "Artificial Intelligence Applications and Innovations - 12th INNS EANN-SIG International Conference, EANN 2011 and 7th IFIP WG 12.5 International Conference, AIAI 2011, Proceedings",

edition = "PART 2",

note = "7th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2011 ; Conference date: 15-09-2011 Through 18-09-2011",

}

Tsitiridis, A, Yuen, PWT, Ibrahim, I, Soori, U, Chen, T, Hong, K, Wang, Z, James, D & Richardson, M 2011, Enhanced object recognition in cortex-like machine vision. in Artificial Intelligence Applications and Innovations - 12th INNS EANN-SIG International Conference, EANN 2011 and 7th IFIP WG 12.5 International Conference, AIAI 2011, Proceedings. PART 2 edn, IFIP Advances in Information and Communication Technology, no. PART 2, vol. 364 AICT, Springer New York LLC, pp. 17-26, 7th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2011, Corfu, Greece, 15/09/11. https://doi.org/10.1007/978-3-642-23960-1_3

Enhanced object recognition in cortex-like machine vision. / Tsitiridis, Aristeidis; Yuen, Peter W.T.; Ibrahim, Izzati et al.
Artificial Intelligence Applications and Innovations - 12th INNS EANN-SIG International Conference, EANN 2011 and 7th IFIP WG 12.5 International Conference, AIAI 2011, Proceedings. PART 2. ed. Springer New York LLC, 2011. p. 17-26 (IFIP Advances in Information and Communication Technology; Vol. 364 AICT, No. PART 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

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 -

Tsitiridis A, Yuen PWT, Ibrahim I, Soori U, Chen T, Hong K et al. Enhanced object recognition in cortex-like machine vision. In Artificial Intelligence Applications and Innovations - 12th INNS EANN-SIG International Conference, EANN 2011 and 7th IFIP WG 12.5 International Conference, AIAI 2011, Proceedings. PART 2 ed. Springer New York LLC. 2011. p. 17-26. (IFIP Advances in Information and Communication Technology; PART 2). doi: 10.1007/978-3-642-23960-1_3

Enhanced object recognition in cortex-like machine vision

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this