Search space partitioning using convex hull and concavity features for fast medical image retrieval

Nikolay M. Sirakov, Phillip A Mlsna

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

A new approach is presented for partitioning an image database by classifying and indexing the convex hull shapes and the concavity features of regions. The result is a significant increase in image search and retrieval speed. The convex hull is first determined using a novel and efficient approach based on the geometrical heat differential equation. Next, the convex hull is represented by a triad of boundary shapes and other parameters as viewed from three viewpoints. This information enables the regions in the image database to be divided into 344 convex hull classes. Concavity information, obtained using a boundary support parameterization, further partitions the database. Since a given query must now be compared only to shapes of the same class, searching is much faster. Both theoretical background and practical results are discussed.

Original languageEnglish (US)
Title of host publication2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano
Pages796-799
Number of pages4
Volume1
StatePublished - 2004
Event2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano - Arlington, VA, United States
Duration: Apr 15 2004Apr 18 2004

Other

Other2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano
CountryUnited States
CityArlington, VA
Period4/15/044/18/04

Fingerprint

Image retrieval
Parameterization
Differential equations

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Sirakov, N. M., & Mlsna, P. A. (2004). Search space partitioning using convex hull and concavity features for fast medical image retrieval. In 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano (Vol. 1, pp. 796-799)

Search space partitioning using convex hull and concavity features for fast medical image retrieval. / Sirakov, Nikolay M.; Mlsna, Phillip A.

2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano. Vol. 1 2004. p. 796-799.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sirakov, NM & Mlsna, PA 2004, Search space partitioning using convex hull and concavity features for fast medical image retrieval. in 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano. vol. 1, pp. 796-799, 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano, Arlington, VA, United States, 4/15/04.
Sirakov NM, Mlsna PA. Search space partitioning using convex hull and concavity features for fast medical image retrieval. In 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano. Vol. 1. 2004. p. 796-799
Sirakov, Nikolay M. ; Mlsna, Phillip A. / Search space partitioning using convex hull and concavity features for fast medical image retrieval. 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano. Vol. 1 2004. pp. 796-799
@inproceedings{8c556e923653496dac466a8959e4e53e,
title = "Search space partitioning using convex hull and concavity features for fast medical image retrieval",
abstract = "A new approach is presented for partitioning an image database by classifying and indexing the convex hull shapes and the concavity features of regions. The result is a significant increase in image search and retrieval speed. The convex hull is first determined using a novel and efficient approach based on the geometrical heat differential equation. Next, the convex hull is represented by a triad of boundary shapes and other parameters as viewed from three viewpoints. This information enables the regions in the image database to be divided into 344 convex hull classes. Concavity information, obtained using a boundary support parameterization, further partitions the database. Since a given query must now be compared only to shapes of the same class, searching is much faster. Both theoretical background and practical results are discussed.",
author = "Sirakov, {Nikolay M.} and Mlsna, {Phillip A}",
year = "2004",
language = "English (US)",
isbn = "0780383885",
volume = "1",
pages = "796--799",
booktitle = "2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano",

}

TY - GEN

T1 - Search space partitioning using convex hull and concavity features for fast medical image retrieval

AU - Sirakov, Nikolay M.

AU - Mlsna, Phillip A

PY - 2004

Y1 - 2004

N2 - A new approach is presented for partitioning an image database by classifying and indexing the convex hull shapes and the concavity features of regions. The result is a significant increase in image search and retrieval speed. The convex hull is first determined using a novel and efficient approach based on the geometrical heat differential equation. Next, the convex hull is represented by a triad of boundary shapes and other parameters as viewed from three viewpoints. This information enables the regions in the image database to be divided into 344 convex hull classes. Concavity information, obtained using a boundary support parameterization, further partitions the database. Since a given query must now be compared only to shapes of the same class, searching is much faster. Both theoretical background and practical results are discussed.

AB - A new approach is presented for partitioning an image database by classifying and indexing the convex hull shapes and the concavity features of regions. The result is a significant increase in image search and retrieval speed. The convex hull is first determined using a novel and efficient approach based on the geometrical heat differential equation. Next, the convex hull is represented by a triad of boundary shapes and other parameters as viewed from three viewpoints. This information enables the regions in the image database to be divided into 344 convex hull classes. Concavity information, obtained using a boundary support parameterization, further partitions the database. Since a given query must now be compared only to shapes of the same class, searching is much faster. Both theoretical background and practical results are discussed.

UR - http://www.scopus.com/inward/record.url?scp=17144398907&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17144398907&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:17144398907

SN - 0780383885

SN - 9780780383883

VL - 1

SP - 796

EP - 799

BT - 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano

ER -