A TensorFlow implementation of Local Binary Patterns Transform
Feature extraction layers like Local Binary Patterns (LBP) transform can be very useful for improving the accuracy of machine learning and deep learning models depending on the problem type. Direct implementations of such layers in Python may result in long running times, and training a computer vis...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Kyrgyz Turkish Manas University
2021-06-01
|
| Series: | MANAS: Journal of Engineering |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/en/download/article-file/1384888 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832542907375026176 |
|---|---|
| author | Devrim Akgün |
| author_facet | Devrim Akgün |
| author_sort | Devrim Akgün |
| collection | DOAJ |
| description | Feature extraction layers like Local Binary Patterns (LBP) transform can be very useful for improving the accuracy of machine learning and deep learning models depending on the problem type. Direct implementations of such layers in Python may result in long running times, and training a computer vision model may be delayed significantly. For this purpose, TensorFlow framework enables developing accelerated custom operations based on the existing operations which already have support for accelerated hardware such as multicore CPU and GPU. In this study, LBP transform which is used for feature extraction in various applications, was implemented based on TensorFlow operations. The evaluations were done using both standard Python operations and TensorFlow library for performance comparisons. The experiments were realized using images in various dimensions and various batch sizes. Numerical results show that algorithm based on TensorFlow operations provides good acceleration rates over Python runs. The implementation of LBP can be used for the accelerated computing for various feature extraction purposes including machine learning as well as in deep learning applications. |
| format | Article |
| id | doaj-art-9e66d7148502464eb8636e51aef7a339 |
| institution | Kabale University |
| issn | 1694-7398 |
| language | English |
| publishDate | 2021-06-01 |
| publisher | Kyrgyz Turkish Manas University |
| record_format | Article |
| series | MANAS: Journal of Engineering |
| spelling | doaj-art-9e66d7148502464eb8636e51aef7a3392025-02-03T12:07:27ZengKyrgyz Turkish Manas UniversityMANAS: Journal of Engineering1694-73982021-06-0191152110.51354/mjen.8226301437A TensorFlow implementation of Local Binary Patterns TransformDevrim Akgün0https://orcid.org/0000-0002-0770-599XSAKARYA ÜNİVERSİTESİFeature extraction layers like Local Binary Patterns (LBP) transform can be very useful for improving the accuracy of machine learning and deep learning models depending on the problem type. Direct implementations of such layers in Python may result in long running times, and training a computer vision model may be delayed significantly. For this purpose, TensorFlow framework enables developing accelerated custom operations based on the existing operations which already have support for accelerated hardware such as multicore CPU and GPU. In this study, LBP transform which is used for feature extraction in various applications, was implemented based on TensorFlow operations. The evaluations were done using both standard Python operations and TensorFlow library for performance comparisons. The experiments were realized using images in various dimensions and various batch sizes. Numerical results show that algorithm based on TensorFlow operations provides good acceleration rates over Python runs. The implementation of LBP can be used for the accelerated computing for various feature extraction purposes including machine learning as well as in deep learning applications.https://dergipark.org.tr/en/download/article-file/1384888tensorflowlocal binary patternsdeep learningfeature extraction |
| spellingShingle | Devrim Akgün A TensorFlow implementation of Local Binary Patterns Transform MANAS: Journal of Engineering tensorflow local binary patterns deep learning feature extraction |
| title | A TensorFlow implementation of Local Binary Patterns Transform |
| title_full | A TensorFlow implementation of Local Binary Patterns Transform |
| title_fullStr | A TensorFlow implementation of Local Binary Patterns Transform |
| title_full_unstemmed | A TensorFlow implementation of Local Binary Patterns Transform |
| title_short | A TensorFlow implementation of Local Binary Patterns Transform |
| title_sort | tensorflow implementation of local binary patterns transform |
| topic | tensorflow local binary patterns deep learning feature extraction |
| url | https://dergipark.org.tr/en/download/article-file/1384888 |
| work_keys_str_mv | AT devrimakgun atensorflowimplementationoflocalbinarypatternstransform AT devrimakgun tensorflowimplementationoflocalbinarypatternstransform |