Classification and indexing of gene expression images

Karthik Jayaraman, Sethuraman Panchanathan, Sudhir Kumar

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this paper, we present an approach for classification and indexing of embryonic gene expression pattern images using shape descriptors for retrieval of data in the biological domain. For this purpose, the image is first subjected to a registration process that involves edge fitting and size-standardization. It is followed by segmentation in order to delineate the expression pattern from the cellular background. The moment invariants for the segmented pattern are computed. Image dissimilarity between images is computed based on these moment invariants for each image pair. Area and Centroids of the segmented expression shapes are used to neutralize the invariant behavior of moment invariants during image retrieval. Details of the proposed approach along with analysis of a pilot dataset are presented in this paper.

Original languageEnglish (US)
Pages (from-to)471-481
Number of pages11
JournalUnknown Journal
Volume4472
DOIs
StatePublished - 2001

Fingerprint

gene expression
Information Storage and Retrieval
Image retrieval
Gene expression
Standardization
Gene Expression
moments
retrieval
standardization
centroids
Datasets

Keywords

  • Classification
  • Content-based retrieval
  • Gene expression image database
  • Indexing
  • Pattern recognition
  • Shape features

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Classification and indexing of gene expression images. / Jayaraman, Karthik; Panchanathan, Sethuraman; Kumar, Sudhir.

In: Unknown Journal, Vol. 4472, 2001, p. 471-481.

Research output: Contribution to journalArticle

Jayaraman, Karthik ; Panchanathan, Sethuraman ; Kumar, Sudhir. / Classification and indexing of gene expression images. In: Unknown Journal. 2001 ; Vol. 4472. pp. 471-481.
@article{3017ad398127410d948dd35814567e1c,
title = "Classification and indexing of gene expression images",
abstract = "In this paper, we present an approach for classification and indexing of embryonic gene expression pattern images using shape descriptors for retrieval of data in the biological domain. For this purpose, the image is first subjected to a registration process that involves edge fitting and size-standardization. It is followed by segmentation in order to delineate the expression pattern from the cellular background. The moment invariants for the segmented pattern are computed. Image dissimilarity between images is computed based on these moment invariants for each image pair. Area and Centroids of the segmented expression shapes are used to neutralize the invariant behavior of moment invariants during image retrieval. Details of the proposed approach along with analysis of a pilot dataset are presented in this paper.",
keywords = "Classification, Content-based retrieval, Gene expression image database, Indexing, Pattern recognition, Shape features",
author = "Karthik Jayaraman and Sethuraman Panchanathan and Sudhir Kumar",
year = "2001",
doi = "10.1117/12.449777",
language = "English (US)",
volume = "4472",
pages = "471--481",
journal = "Scanning Electron Microscopy",
issn = "0586-5581",
publisher = "Scanning Microscopy International",

}

TY - JOUR

T1 - Classification and indexing of gene expression images

AU - Jayaraman, Karthik

AU - Panchanathan, Sethuraman

AU - Kumar, Sudhir

PY - 2001

Y1 - 2001

N2 - In this paper, we present an approach for classification and indexing of embryonic gene expression pattern images using shape descriptors for retrieval of data in the biological domain. For this purpose, the image is first subjected to a registration process that involves edge fitting and size-standardization. It is followed by segmentation in order to delineate the expression pattern from the cellular background. The moment invariants for the segmented pattern are computed. Image dissimilarity between images is computed based on these moment invariants for each image pair. Area and Centroids of the segmented expression shapes are used to neutralize the invariant behavior of moment invariants during image retrieval. Details of the proposed approach along with analysis of a pilot dataset are presented in this paper.

AB - In this paper, we present an approach for classification and indexing of embryonic gene expression pattern images using shape descriptors for retrieval of data in the biological domain. For this purpose, the image is first subjected to a registration process that involves edge fitting and size-standardization. It is followed by segmentation in order to delineate the expression pattern from the cellular background. The moment invariants for the segmented pattern are computed. Image dissimilarity between images is computed based on these moment invariants for each image pair. Area and Centroids of the segmented expression shapes are used to neutralize the invariant behavior of moment invariants during image retrieval. Details of the proposed approach along with analysis of a pilot dataset are presented in this paper.

KW - Classification

KW - Content-based retrieval

KW - Gene expression image database

KW - Indexing

KW - Pattern recognition

KW - Shape features

UR - http://www.scopus.com/inward/record.url?scp=0035765568&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035765568&partnerID=8YFLogxK

U2 - 10.1117/12.449777

DO - 10.1117/12.449777

M3 - Article

VL - 4472

SP - 471

EP - 481

JO - Scanning Electron Microscopy

JF - Scanning Electron Microscopy

SN - 0586-5581

ER -