NEW APPROACH FOR 3D OBJECT RECOGNITION USING NON UNIFORM FOURIER AND MOMENTS COEFFICIENTS

NEW APPROACH FOR 3D OBJECT RECOGNITION USING NON UNIFORM FOURIER AND MOMENTS COEFFICIENTS

In this paper, new descriptors have been proposed which are invariant to rotation and affinity transformations (Non Uniform Fourier and moments coefficients). These descriptors are computed using Fourier or moments coefficients obtained from development of object coordinates. These coordinates are p...

Full description

Bibliographic Details
Main Authors: KHALID AZNAG, NOUHOUN KANE, AHMED EL OIRRAK, ESSAID EL BACHARI
Format: Article
Language:English
Published: Taylor's University 2017-05-01
Series:Journal of Engineering Science and Technology
Subjects:
Fourier
Rotation-invariant
3D curve
Online Access:http://jestec.taylors.edu.my/Vol%2012%20issue%205%20May%202017/12_5_16.pdf
id doaj-64425f399a5543aeaad4db664f320fee
record_format Article
spelling doaj-64425f399a5543aeaad4db664f320fee2020-11-25T00:09:39ZengTaylor's UniversityJournal of Engineering Science and Technology1823-46902017-05-0112513541365NEW APPROACH FOR 3D OBJECT RECOGNITION USING NON UNIFORM FOURIER AND MOMENTS COEFFICIENTSKHALID AZNAG0NOUHOUN KANE1AHMED EL OIRRAK2ESSAID EL BACHARI3Faculty of Sciences Semlalia, Cadi Ayyad University, Computer Systems Engineering Laboratory (LISI) Marrakech, MoroccoFaculty of Sciences Semlalia, Cadi Ayyad University, Computer Systems Engineering Laboratory (LISI) Marrakech, MoroccoFaculty of Sciences Semlalia, Cadi Ayyad University, Computer Systems Engineering Laboratory (LISI) Marrakech, MoroccoFaculty of Sciences Semlalia, Cadi Ayyad University, Computer Systems Engineering Laboratory (LISI) Marrakech, MoroccoIn this paper, new descriptors have been proposed which are invariant to rotation and affinity transformations (Non Uniform Fourier and moments coefficients). These descriptors are computed using Fourier or moments coefficients obtained from development of object coordinates. These coordinates are parameterized with a function also invariant to affinity. The normal Fourier transform depends on points index, the Non Uniform transform proposed here depend on a parameter. This parameter depends on shape not on order of points. The proposed descriptors are easy to extract and are extensible to higher dimension. http://jestec.taylors.edu.my/Vol%2012%20issue%205%20May%202017/12_5_16.pdfFourierRotation-invariant3D curve
collection DOAJ
language English
format Article
sources DOAJ
author KHALID AZNAG
NOUHOUN KANE
AHMED EL OIRRAK
ESSAID EL BACHARI
spellingShingle KHALID AZNAG
NOUHOUN KANE
AHMED EL OIRRAK
ESSAID EL BACHARI
NEW APPROACH FOR 3D OBJECT RECOGNITION USING NON UNIFORM FOURIER AND MOMENTS COEFFICIENTS
Journal of Engineering Science and Technology
Fourier
Rotation-invariant
3D curve
author_facet KHALID AZNAG
NOUHOUN KANE
AHMED EL OIRRAK
ESSAID EL BACHARI
author_sort KHALID AZNAG
title NEW APPROACH FOR 3D OBJECT RECOGNITION USING NON UNIFORM FOURIER AND MOMENTS COEFFICIENTS
title_short NEW APPROACH FOR 3D OBJECT RECOGNITION USING NON UNIFORM FOURIER AND MOMENTS COEFFICIENTS
title_full NEW APPROACH FOR 3D OBJECT RECOGNITION USING NON UNIFORM FOURIER AND MOMENTS COEFFICIENTS
title_fullStr NEW APPROACH FOR 3D OBJECT RECOGNITION USING NON UNIFORM FOURIER AND MOMENTS COEFFICIENTS
title_full_unstemmed NEW APPROACH FOR 3D OBJECT RECOGNITION USING NON UNIFORM FOURIER AND MOMENTS COEFFICIENTS
title_sort new approach for 3d object recognition using non uniform fourier and moments coefficients
publisher Taylor's University
series Journal of Engineering Science and Technology
issn 1823-4690
publishDate 2017-05-01
description In this paper, new descriptors have been proposed which are invariant to rotation and affinity transformations (Non Uniform Fourier and moments coefficients). These descriptors are computed using Fourier or moments coefficients obtained from development of object coordinates. These coordinates are parameterized with a function also invariant to affinity. The normal Fourier transform depends on points index, the Non Uniform transform proposed here depend on a parameter. This parameter depends on shape not on order of points. The proposed descriptors are easy to extract and are extensible to higher dimension.
topic Fourier
Rotation-invariant
3D curve
url http://jestec.taylors.edu.my/Vol%2012%20issue%205%20May%202017/12_5_16.pdf
work_keys_str_mv AT khalidaznag newapproachfor3dobjectrecognitionusingnonuniformfourierandmomentscoefficients
AT nouhounkane newapproachfor3dobjectrecognitionusingnonuniformfourierandmomentscoefficients
AT ahmedeloirrak newapproachfor3dobjectrecognitionusingnonuniformfourierandmomentscoefficients
AT essaidelbachari newapproachfor3dobjectrecognitionusingnonuniformfourierandmomentscoefficients
_version_ 1725410630604685312

Similar Items