Image segmentation through gabor-based neural networks

J. Mario Aguilar; José L. Contreras-Vidal

doi:10.1117/12.140037

Image segmentation through gabor-based neural networks

J. Mario Aguilar, José L. Contreras-Vidal

Houston Methodist

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

1 Scopus citations

Abstract

An image segmentation system based on known cortical interactions and topography is presented. First, a space variant retinal-like representation of the image is obtained not only to provide with spatial focusing but also to reduce the computational load. Next, a layer of receptive fields for feature extraction was evolved from a set of Gabor functions with multiple orientational characteristics. Shunting competitive interactions among different features eliminate local ambiguities. Long-range interactions among "winning" cells, sharing similar orientation preferences, but with possible different spatial scales, are used to form a congruent description of the visual scene taking into account spatial context. The output of this layer js used to partition the image into emergent segments. Encouraging results of MRI images processing are presented.

Original language	English (US)
Pages (from-to)	44-51
Number of pages	8
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	1709
DOIs	https://doi.org/10.1117/12.140037
State	Published - Sep 16 1992
Event	Applications of Artificial Neural Networks III 1992 - Orlando, United States Duration: Apr 20 1992 → …

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.140037

Cite this

@article{89e2f64f81a841e48faa755f6b38ad62,

title = "Image segmentation through gabor-based neural networks",

abstract = "An image segmentation system based on known cortical interactions and topography is presented. First, a space variant retinal-like representation of the image is obtained not only to provide with spatial focusing but also to reduce the computational load. Next, a layer of receptive fields for feature extraction was evolved from a set of Gabor functions with multiple orientational characteristics. Shunting competitive interactions among different features eliminate local ambiguities. Long-range interactions among {"}winning{"} cells, sharing similar orientation preferences, but with possible different spatial scales, are used to form a congruent description of the visual scene taking into account spatial context. The output of this layer js used to partition the image into emergent segments. Encouraging results of MRI images processing are presented.",

author = "Aguilar, {J. Mario} and Contreras-Vidal, {Jos{\'e} L.}",

year = "1992",

month = sep,

day = "16",

doi = "10.1117/12.140037",

language = "English (US)",

volume = "1709",

pages = "44--51",

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

issn = "0277-786X",

publisher = "SPIE",

note = "Applications of Artificial Neural Networks III 1992 ; Conference date: 20-04-1992",

}

TY - JOUR

T1 - Image segmentation through gabor-based neural networks

AU - Aguilar, J. Mario

AU - Contreras-Vidal, José L.

PY - 1992/9/16

Y1 - 1992/9/16

N2 - An image segmentation system based on known cortical interactions and topography is presented. First, a space variant retinal-like representation of the image is obtained not only to provide with spatial focusing but also to reduce the computational load. Next, a layer of receptive fields for feature extraction was evolved from a set of Gabor functions with multiple orientational characteristics. Shunting competitive interactions among different features eliminate local ambiguities. Long-range interactions among "winning" cells, sharing similar orientation preferences, but with possible different spatial scales, are used to form a congruent description of the visual scene taking into account spatial context. The output of this layer js used to partition the image into emergent segments. Encouraging results of MRI images processing are presented.

AB - An image segmentation system based on known cortical interactions and topography is presented. First, a space variant retinal-like representation of the image is obtained not only to provide with spatial focusing but also to reduce the computational load. Next, a layer of receptive fields for feature extraction was evolved from a set of Gabor functions with multiple orientational characteristics. Shunting competitive interactions among different features eliminate local ambiguities. Long-range interactions among "winning" cells, sharing similar orientation preferences, but with possible different spatial scales, are used to form a congruent description of the visual scene taking into account spatial context. The output of this layer js used to partition the image into emergent segments. Encouraging results of MRI images processing are presented.

UR - http://www.scopus.com/inward/record.url?scp=85075551441&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075551441&partnerID=8YFLogxK

U2 - 10.1117/12.140037

DO - 10.1117/12.140037

M3 - Conference article

AN - SCOPUS:85075551441

SN - 0277-786X

VL - 1709

SP - 44

EP - 51

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

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

T2 - Applications of Artificial Neural Networks III 1992

Y2 - 20 April 1992

ER -

Image segmentation through gabor-based neural networks

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this