Improving classification of neural networks by reducing lens aperture

Inna Stainvas; Zeev Zalevsky; David Mendlovic; Nathan Intrator

doi:10.1117/12.453545

Improving classification of neural networks by reducing lens aperture

Inna Stainvas^*, Zeev Zalevsky, David Mendlovic, Nathan Intrator

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

Abstract

Image blur strongly degrades object recognition. We propose a mechanism to reduce defocus blur by reducing the aperture of the camera lens, and show that it leads to a far more robust recognition. The recognition is demonstrated via a Neural Network architecture that we have previously proposed for blurred face recognition.

Original language	English
Pages (from-to)	267-276
Number of pages	10
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	4787
DOIs	https://doi.org/10.1117/12.453545
State	Published - 2002
Event	Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation V - Seattle, WA, United States Duration: 9 Jul 2002 → 10 Jul 2002

Keywords

Artificial neural networks
Classification network
Face recognition
Hybrid architecture
Image blur
Lens aperture
Network ensembles

Access to Document

10.1117/12.453545

Cite this

@article{d445778c609e4f18992514c73de883e2,

title = "Improving classification of neural networks by reducing lens aperture",

abstract = "Image blur strongly degrades object recognition. We propose a mechanism to reduce defocus blur by reducing the aperture of the camera lens, and show that it leads to a far more robust recognition. The recognition is demonstrated via a Neural Network architecture that we have previously proposed for blurred face recognition.",

keywords = "Artificial neural networks, Classification network, Face recognition, Hybrid architecture, Image blur, Lens aperture, Network ensembles",

author = "Inna Stainvas and Zeev Zalevsky and David Mendlovic and Nathan Intrator",

year = "2002",

doi = "10.1117/12.453545",

language = "אנגלית",

volume = "4787",

pages = "267--276",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "null ; Conference date: 09-07-2002 Through 10-07-2002",

}

TY - JOUR

T1 - Improving classification of neural networks by reducing lens aperture

AU - Stainvas, Inna

AU - Zalevsky, Zeev

AU - Mendlovic, David

AU - Intrator, Nathan

PY - 2002

Y1 - 2002

N2 - Image blur strongly degrades object recognition. We propose a mechanism to reduce defocus blur by reducing the aperture of the camera lens, and show that it leads to a far more robust recognition. The recognition is demonstrated via a Neural Network architecture that we have previously proposed for blurred face recognition.

AB - Image blur strongly degrades object recognition. We propose a mechanism to reduce defocus blur by reducing the aperture of the camera lens, and show that it leads to a far more robust recognition. The recognition is demonstrated via a Neural Network architecture that we have previously proposed for blurred face recognition.

KW - Artificial neural networks

KW - Classification network

KW - Face recognition

KW - Hybrid architecture

KW - Image blur

KW - Lens aperture

KW - Network ensembles

UR - http://www.scopus.com/inward/record.url?scp=0036995855&partnerID=8YFLogxK

U2 - 10.1117/12.453545

DO - 10.1117/12.453545

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.conferencearticle???

AN - SCOPUS:0036995855

SN - 0277-786X

VL - 4787

SP - 267

EP - 276

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

Y2 - 9 July 2002 through 10 July 2002

ER -

Improving classification of neural networks by reducing lens aperture

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this