PyTorch Operations Based Approach for Computing Local Binary Patterns

Advances in machine learning frameworks like PyTorch provides users with various machine learning algorithms together with general purpose operations. PyTorch framework provides Numpy like functions and makes it practical to use computational resources for accelerating computations. Also users may d...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Devrim Akgun
Formato: article
Lenguaje:EN
Publicado: Universidade do Porto 2021
Materias:
Acceso en línea:https://doaj.org/article/ab3a7b869ce449639237f5c7f471a3bc
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:ab3a7b869ce449639237f5c7f471a3bc
record_format dspace
spelling oai:doaj.org-article:ab3a7b869ce449639237f5c7f471a3bc2021-11-26T12:34:57ZPyTorch Operations Based Approach for Computing Local Binary Patterns2183-649310.24840/2183-6493_007.004_0005https://doaj.org/article/ab3a7b869ce449639237f5c7f471a3bc2021-11-01T00:00:00Zhttps://journalengineering.fe.up.pt/index.php/upjeng/article/view/829https://doaj.org/toc/2183-6493Advances in machine learning frameworks like PyTorch provides users with various machine learning algorithms together with general purpose operations. PyTorch framework provides Numpy like functions and makes it practical to use computational resources for accelerating computations. Also users may define their custom layers or operations for feature extraction algorithms based on the tensor operations. In this paper, Local Binary Patterns (LBP) which is one of the important feature extraction approaches in computer vision were realized using tensor operations of PyTorch framework. The algorithm was written both using Python code with standard libraries and tensor operations of PyTorch in Python. According to experimental measurements which were realized for various batches of images, the algorithm based on tensor operations considerably reduced the computation time and provides significant accelerations over Python implementation with standard libraries.Devrim AkgunUniversidade do Portoarticlepytorchlocal binary patternsfeature extractionmachine learningEngineering (General). Civil engineering (General)TA1-2040Technology (General)T1-995ENU.Porto Journal of Engineering, Vol 7, Iss 4, Pp 61-69 (2021)
institution DOAJ
collection DOAJ
language EN
topic pytorch
local binary patterns
feature extraction
machine learning
Engineering (General). Civil engineering (General)
TA1-2040
Technology (General)
T1-995
spellingShingle pytorch
local binary patterns
feature extraction
machine learning
Engineering (General). Civil engineering (General)
TA1-2040
Technology (General)
T1-995
Devrim Akgun
PyTorch Operations Based Approach for Computing Local Binary Patterns
description Advances in machine learning frameworks like PyTorch provides users with various machine learning algorithms together with general purpose operations. PyTorch framework provides Numpy like functions and makes it practical to use computational resources for accelerating computations. Also users may define their custom layers or operations for feature extraction algorithms based on the tensor operations. In this paper, Local Binary Patterns (LBP) which is one of the important feature extraction approaches in computer vision were realized using tensor operations of PyTorch framework. The algorithm was written both using Python code with standard libraries and tensor operations of PyTorch in Python. According to experimental measurements which were realized for various batches of images, the algorithm based on tensor operations considerably reduced the computation time and provides significant accelerations over Python implementation with standard libraries.
format article
author Devrim Akgun
author_facet Devrim Akgun
author_sort Devrim Akgun
title PyTorch Operations Based Approach for Computing Local Binary Patterns
title_short PyTorch Operations Based Approach for Computing Local Binary Patterns
title_full PyTorch Operations Based Approach for Computing Local Binary Patterns
title_fullStr PyTorch Operations Based Approach for Computing Local Binary Patterns
title_full_unstemmed PyTorch Operations Based Approach for Computing Local Binary Patterns
title_sort pytorch operations based approach for computing local binary patterns
publisher Universidade do Porto
publishDate 2021
url https://doaj.org/article/ab3a7b869ce449639237f5c7f471a3bc
work_keys_str_mv AT devrimakgun pytorchoperationsbasedapproachforcomputinglocalbinarypatterns
_version_ 1718409370599948288