Shape recognition using orientational and morphological scale‐spaces of curvatures
In this study, a scale‐invariant representation for closed planar curves (silhouettes) is proposed. The orientations of all points within the Gaussian scale‐space of the curve are extracted. This orientation scale‐space is used to create the silhouette orientation image in which the positions of eac...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2015-10-01
|
Series: | IET Computer Vision |
Subjects: | |
Online Access: | https://doi.org/10.1049/iet-cvi.2015.0012 |
_version_ | 1797684565607710720 |
---|---|
author | Erdem Akagündüz |
author_facet | Erdem Akagündüz |
author_sort | Erdem Akagündüz |
collection | DOAJ |
description | In this study, a scale‐invariant representation for closed planar curves (silhouettes) is proposed. The orientations of all points within the Gaussian scale‐space of the curve are extracted. This orientation scale‐space is used to create the silhouette orientation image in which the positions of each pixel indicate the curve's pixel positions and scales, whereas the colour represents orientation. The representation is extracted for multiple levels of the morphological scale‐space of the silhouette. The proposed representation is invariant to scale and transformable under planar rotation. Using linear and non‐linear distance learning methods, experiments on the MPEG7, ETH80 and Kimia shape datasets were conducted, with results indicating an advanced recognition capability. |
first_indexed | 2024-03-12T00:31:35Z |
format | Article |
id | doaj.art-c4a4181f8ad8425fbb20809c79002e93 |
institution | Directory Open Access Journal |
issn | 1751-9632 1751-9640 |
language | English |
last_indexed | 2024-03-12T00:31:35Z |
publishDate | 2015-10-01 |
publisher | Wiley |
record_format | Article |
series | IET Computer Vision |
spelling | doaj.art-c4a4181f8ad8425fbb20809c79002e932023-09-15T10:21:07ZengWileyIET Computer Vision1751-96321751-96402015-10-019575075710.1049/iet-cvi.2015.0012Shape recognition using orientational and morphological scale‐spaces of curvaturesErdem Akagündüz0Department of Electro‐Optical Systems Design EngineeringMGEO DivisionASELSAN Inc.AnkaraTurkeyIn this study, a scale‐invariant representation for closed planar curves (silhouettes) is proposed. The orientations of all points within the Gaussian scale‐space of the curve are extracted. This orientation scale‐space is used to create the silhouette orientation image in which the positions of each pixel indicate the curve's pixel positions and scales, whereas the colour represents orientation. The representation is extracted for multiple levels of the morphological scale‐space of the silhouette. The proposed representation is invariant to scale and transformable under planar rotation. Using linear and non‐linear distance learning methods, experiments on the MPEG7, ETH80 and Kimia shape datasets were conducted, with results indicating an advanced recognition capability.https://doi.org/10.1049/iet-cvi.2015.0012shape recognitionclosed planar curvescale-invariant representationGaussian scale-spacemorphological scale-spacesorientation scale-space |
spellingShingle | Erdem Akagündüz Shape recognition using orientational and morphological scale‐spaces of curvatures IET Computer Vision shape recognition closed planar curve scale-invariant representation Gaussian scale-space morphological scale-spaces orientation scale-space |
title | Shape recognition using orientational and morphological scale‐spaces of curvatures |
title_full | Shape recognition using orientational and morphological scale‐spaces of curvatures |
title_fullStr | Shape recognition using orientational and morphological scale‐spaces of curvatures |
title_full_unstemmed | Shape recognition using orientational and morphological scale‐spaces of curvatures |
title_short | Shape recognition using orientational and morphological scale‐spaces of curvatures |
title_sort | shape recognition using orientational and morphological scale spaces of curvatures |
topic | shape recognition closed planar curve scale-invariant representation Gaussian scale-space morphological scale-spaces orientation scale-space |
url | https://doi.org/10.1049/iet-cvi.2015.0012 |
work_keys_str_mv | AT erdemakagunduz shaperecognitionusingorientationalandmorphologicalscalespacesofcurvatures |