33969

3D Object Categorization Using Spin-Images with MPI Parallel Implementation

Article

Last updated: 04 Jan 2025

Subjects

-

Tags

-

Abstract

Object recognition and categorization are two important key features of computer vision. Accuracy aspects
representresearchchallengeforbothobjectrecognitionandcategorization techniques. High performance computing
(HPC) technologies usually manage the increasing time and complexity of computations. In this paper, an approach
utilizing3Dspin-imagesfor3Dobjectcategorizationisproposed.Themaincontributionofthisapproach is that item ploys the MPI
techniques in a unique way to extract spin-images. The technique proposed utilizes the independence between spin-images generated a teach point. Time estimation of this technique has shown dramatic decrease of the categorization time proportion alto number of workers used.

DOI

10.21608/ijci.2014.33969

Keywords

Object categorization, spin-image, support vectormachine, MPI

Authors

First Name

D.

Last Name

Hegazy

MiddleName

-

Affiliation

Computer Systems Department, Ain Shams University

Email

-

City

-

Orcid

-

First Name

A.

Last Name

Hamdy

MiddleName

-

Affiliation

Computer Systems Department, Ain Shams University

Email

-

City

-

Orcid

-

First Name

W.

Last Name

Elkilany

MiddleName

-

Affiliation

Computer Systems Department, Ain Shams University

Email

wail.elkilani@cis.asu.edu.eg

City

-

Orcid

-

Volume

3

Article Issue

1

Related Issue

5677

Issue Date

2014-06-01

Receive Date

2014-01-06

Publish Date

2014-06-01

Page Start

75

Page End

87

Print ISSN

1687-7853

Online ISSN

2735-3257

Link

https://ijci.journals.ekb.eg/article_33969.html

Detail API

https://ijci.journals.ekb.eg/service?article_code=33969

Order

6

Type

Original Article

Type Code

877

Publication Type

Journal

Publication Title

IJCI. International Journal of Computers and Information

Publication Link

https://ijci.journals.ekb.eg/

MainTitle

3D Object Categorization Using Spin-Images with MPI Parallel Implementation

Details

Type

Article

Created At

22 Jan 2023