Shape Recognition Based on Projected Edges and Global Statistical Features

Shape Recognition Based on Projected Edges and Global Statistical Features

A combined shape descriptor for object recognition is presented, along with an offline and online learning method. The descriptor is composed of a local edge-based part and global statistical features. We also propose a two-level, nearest neighborhood type multiclass classification method, in which...

Full description

Bibliographic Details
Main Authors: Attila Stubendek, Kristóf Karacs
Format: Article
Language:English
Published: Hindawi Limited 2018-01-01
Series:Mathematical Problems in Engineering
Online Access:http://dx.doi.org/10.1155/2018/4763050
id doaj-dd6d4d9092ce4f62b41dc10b49c98944
record_format Article
spelling doaj-dd6d4d9092ce4f62b41dc10b49c989442020-11-24T23:57:06ZengHindawi LimitedMathematical Problems in Engineering1024-123X1563-51472018-01-01201810.1155/2018/47630504763050Shape Recognition Based on Projected Edges and Global Statistical FeaturesAttila Stubendek0Kristóf Karacs1Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Prater 50/A, Budapest 1083, HungaryFaculty of Information Technology and Bionics, Pázmány Péter Catholic University, Prater 50/A, Budapest 1083, HungaryA combined shape descriptor for object recognition is presented, along with an offline and online learning method. The descriptor is composed of a local edge-based part and global statistical features. We also propose a two-level, nearest neighborhood type multiclass classification method, in which classes are bounded, defining an inherent rejection region. In the first stage, global features are used to filter model instances, in contrast to the second stage, in which the projected edge-based features are compared. Our experimental results show that the combination of independent features leads to increased recognition robustness and speed. The core algorithms map easily to cellular architectures or dedicated VLSI hardware.http://dx.doi.org/10.1155/2018/4763050
collection DOAJ
language English
format Article
sources DOAJ
author Attila Stubendek
Kristóf Karacs
spellingShingle Attila Stubendek
Kristóf Karacs
Shape Recognition Based on Projected Edges and Global Statistical Features
Mathematical Problems in Engineering
author_facet Attila Stubendek
Kristóf Karacs
author_sort Attila Stubendek
title Shape Recognition Based on Projected Edges and Global Statistical Features
title_short Shape Recognition Based on Projected Edges and Global Statistical Features
title_full Shape Recognition Based on Projected Edges and Global Statistical Features
title_fullStr Shape Recognition Based on Projected Edges and Global Statistical Features
title_full_unstemmed Shape Recognition Based on Projected Edges and Global Statistical Features
title_sort shape recognition based on projected edges and global statistical features
publisher Hindawi Limited
series Mathematical Problems in Engineering
issn 1024-123X
1563-5147
publishDate 2018-01-01
description A combined shape descriptor for object recognition is presented, along with an offline and online learning method. The descriptor is composed of a local edge-based part and global statistical features. We also propose a two-level, nearest neighborhood type multiclass classification method, in which classes are bounded, defining an inherent rejection region. In the first stage, global features are used to filter model instances, in contrast to the second stage, in which the projected edge-based features are compared. Our experimental results show that the combination of independent features leads to increased recognition robustness and speed. The core algorithms map easily to cellular architectures or dedicated VLSI hardware.
url http://dx.doi.org/10.1155/2018/4763050
work_keys_str_mv AT attilastubendek shaperecognitionbasedonprojectededgesandglobalstatisticalfeatures
AT kristofkaracs shaperecognitionbasedonprojectededgesandglobalstatisticalfeatures
_version_ 1725455625794617344

Similar Items