A classification-driven partially occluded object segmentation (cpoos) method with application to chromosome analysis

Boaz Lerner; Hugo Guterman; It S.Hak Dinstein

doi:10.1109/78.720391

A classification-driven partially occluded object segmentation (cpoos) method with application to chromosome analysis

Boaz Lerner, Hugo Guterman, It S.Hak Dinstein

Department of Electrical & Computer Engineering

Research output: Contribution to journal › Article › peer-review

43 Scopus citations

Abstract

Classification of segment images created by connecting points of high concavity along curvatures is used to resolve partial occlusion in images. Modeling of shape or curvature is not necessary nor is the traditional excessive use of heuristics. Applied to human cell images, 82.6% of the analyzed clusters of chromosomes are correctly separated, rising to 90.5% following rejection of 8.7% of the images. Index Terms-Chromosome analysis, image classification, image segmentation, neural networks, partial occlusion.

Original language	English
Pages (from-to)	2841-2847
Number of pages	7
Journal	IEEE Transactions on Signal Processing
Volume	46
Issue number	10
DOIs	https://doi.org/10.1109/78.720391
State	Published - 1 Dec 1998

ASJC Scopus subject areas

Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/78.720391

Cite this

@article{251ef490a7ee4da48759a7530a0676eb,

title = "A classification-driven partially occluded object segmentation (cpoos) method with application to chromosome analysis",

abstract = "Classification of segment images created by connecting points of high concavity along curvatures is used to resolve partial occlusion in images. Modeling of shape or curvature is not necessary nor is the traditional excessive use of heuristics. Applied to human cell images, 82.6% of the analyzed clusters of chromosomes are correctly separated, rising to 90.5% following rejection of 8.7% of the images. Index Terms-Chromosome analysis, image classification, image segmentation, neural networks, partial occlusion.",

author = "Boaz Lerner and Hugo Guterman and Dinstein, {It S.Hak}",

year = "1998",

month = dec,

day = "1",

doi = "10.1109/78.720391",

language = "English",

volume = "46",

pages = "2841--2847",

journal = "IEEE Transactions on Signal Processing",

issn = "1053-587X",

publisher = "Institute of Electrical and Electronics Engineers",

number = "10",

}

TY - JOUR

T1 - A classification-driven partially occluded object segmentation (cpoos) method with application to chromosome analysis

AU - Lerner, Boaz

AU - Guterman, Hugo

AU - Dinstein, It S.Hak

PY - 1998/12/1

Y1 - 1998/12/1

N2 - Classification of segment images created by connecting points of high concavity along curvatures is used to resolve partial occlusion in images. Modeling of shape or curvature is not necessary nor is the traditional excessive use of heuristics. Applied to human cell images, 82.6% of the analyzed clusters of chromosomes are correctly separated, rising to 90.5% following rejection of 8.7% of the images. Index Terms-Chromosome analysis, image classification, image segmentation, neural networks, partial occlusion.

AB - Classification of segment images created by connecting points of high concavity along curvatures is used to resolve partial occlusion in images. Modeling of shape or curvature is not necessary nor is the traditional excessive use of heuristics. Applied to human cell images, 82.6% of the analyzed clusters of chromosomes are correctly separated, rising to 90.5% following rejection of 8.7% of the images. Index Terms-Chromosome analysis, image classification, image segmentation, neural networks, partial occlusion.

UR - http://www.scopus.com/inward/record.url?scp=0032186970&partnerID=8YFLogxK

U2 - 10.1109/78.720391

DO - 10.1109/78.720391

M3 - Article

AN - SCOPUS:0032186970

SN - 1053-587X

VL - 46

SP - 2841

EP - 2847

JO - IEEE Transactions on Signal Processing

JF - IEEE Transactions on Signal Processing

IS - 10

ER -

A classification-driven partially occluded object segmentation (cpoos) method with application to chromosome analysis

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this