3D object recognition with a linear time‐varying system of overlay layers
Abstract Object recognition is a challenging task in computer vision with numerous applications. The challenge is in selecting appropriate robust features with tolerable computing costs. Feature learning attempts to solve the feature extraction problem through a learning process using various sample...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-08-01
|
Series: | IET Computer Vision |
Subjects: | |
Online Access: | https://doi.org/10.1049/cvi2.12029 |
_version_ | 1798037199821733888 |
---|---|
author | Mohammad Sohrabi Nasrabadi Reza Safabakhsh |
author_facet | Mohammad Sohrabi Nasrabadi Reza Safabakhsh |
author_sort | Mohammad Sohrabi Nasrabadi |
collection | DOAJ |
description | Abstract Object recognition is a challenging task in computer vision with numerous applications. The challenge is in selecting appropriate robust features with tolerable computing costs. Feature learning attempts to solve the feature extraction problem through a learning process using various samples of the objects. This research proposes a two‐stage optimization framework to identify the structure of a first‐order linear non‐homogeneous difference equation which is a linear time‐varying system of overlay layers (LtvoL) that construct an image. The first stage consists of the determination of a finite set of impulses, called overlay layers, by the application of a genetic algorithm. The second stage defines the coefficients of the corresponding difference equation derived from L2 regularization. Classification of the test images is possible by a novel process exclusively designed for this model. Experiments on the Washington RGB‐D dataset and ETH‐80 show promising results which are comparable to those of state‐of‐the‐art methods for RGB‐D‐based object recognition. |
first_indexed | 2024-04-11T21:23:21Z |
format | Article |
id | doaj.art-c0e031af2177440a92d90e062fa14ba4 |
institution | Directory Open Access Journal |
issn | 1751-9632 1751-9640 |
language | English |
last_indexed | 2024-04-11T21:23:21Z |
publishDate | 2021-08-01 |
publisher | Wiley |
record_format | Article |
series | IET Computer Vision |
spelling | doaj.art-c0e031af2177440a92d90e062fa14ba42022-12-22T04:02:32ZengWileyIET Computer Vision1751-96321751-96402021-08-0115538039110.1049/cvi2.120293D object recognition with a linear time‐varying system of overlay layersMohammad Sohrabi Nasrabadi0Reza Safabakhsh1Department of Computer Engineering Amirkabir University of Technology Tehran IranDepartment of Computer Engineering Amirkabir University of Technology Tehran IranAbstract Object recognition is a challenging task in computer vision with numerous applications. The challenge is in selecting appropriate robust features with tolerable computing costs. Feature learning attempts to solve the feature extraction problem through a learning process using various samples of the objects. This research proposes a two‐stage optimization framework to identify the structure of a first‐order linear non‐homogeneous difference equation which is a linear time‐varying system of overlay layers (LtvoL) that construct an image. The first stage consists of the determination of a finite set of impulses, called overlay layers, by the application of a genetic algorithm. The second stage defines the coefficients of the corresponding difference equation derived from L2 regularization. Classification of the test images is possible by a novel process exclusively designed for this model. Experiments on the Washington RGB‐D dataset and ETH‐80 show promising results which are comparable to those of state‐of‐the‐art methods for RGB‐D‐based object recognition.https://doi.org/10.1049/cvi2.12029computer visiondifference equationsfeature extractiongenetic algorithmsimage colour analysislearning (artificial intelligence) |
spellingShingle | Mohammad Sohrabi Nasrabadi Reza Safabakhsh 3D object recognition with a linear time‐varying system of overlay layers IET Computer Vision computer vision difference equations feature extraction genetic algorithms image colour analysis learning (artificial intelligence) |
title | 3D object recognition with a linear time‐varying system of overlay layers |
title_full | 3D object recognition with a linear time‐varying system of overlay layers |
title_fullStr | 3D object recognition with a linear time‐varying system of overlay layers |
title_full_unstemmed | 3D object recognition with a linear time‐varying system of overlay layers |
title_short | 3D object recognition with a linear time‐varying system of overlay layers |
title_sort | 3d object recognition with a linear time varying system of overlay layers |
topic | computer vision difference equations feature extraction genetic algorithms image colour analysis learning (artificial intelligence) |
url | https://doi.org/10.1049/cvi2.12029 |
work_keys_str_mv | AT mohammadsohrabinasrabadi 3dobjectrecognitionwithalineartimevaryingsystemofoverlaylayers AT rezasafabakhsh 3dobjectrecognitionwithalineartimevaryingsystemofoverlaylayers |