A novel parallel texture feature extraction method using log-gabor filter and singular value decomposition (SVD)
This conference paper was published in the ACM International Conference Proceeding Series [© 2017 ACM] and the definite version is available at : http://doi.org/10.1145/3036331.3036352 The Journal's website is at: https://dl.acm.org/citation.cfm?doid=3036331.3036352
| Huvudupphovsmän: | , , |
|---|---|
| Övriga upphovsmän: | |
| Materialtyp: | Conference paper |
| Språk: | English |
| Publicerad: |
© 2017 ACM
2018
|
| Ämnen: | |
| Länkar: | http://hdl.handle.net/10361/9519 http://doi.org/10.1145/3036331.3036352 |
| id |
10361-9519 |
|---|---|
| record_format |
dspace |
| spelling |
10361-95192018-07-25T10:31:46Z A novel parallel texture feature extraction method using log-gabor filter and singular value decomposition (SVD) Ratul, Md Aminur Rab Raja, Sharif Ahmmad Uddin, Jia Department of Computer Science and Engineering, BRAC University Feature extraction Gabor filter Log-gabor filter Parallel processing This conference paper was published in the ACM International Conference Proceeding Series [© 2017 ACM] and the definite version is available at : http://doi.org/10.1145/3036331.3036352 The Journal's website is at: https://dl.acm.org/citation.cfm?doid=3036331.3036352 Texture feature extraction consolidated with texture feature detection and feature matching solves many typical problems of image processing and computer vision; such as, texture classification, pattern recognition, object detection, and image segmentation. Through this paper, a new method for texture feature extraction is presented which uses Log-Gabor Filter and Singular Value Decomposition (SVD) algorithm. In the proposed model, sample images are converted to gray level images. And then, to elicit suitable distinctive texture orientation, a 2D Log- Gabor filter with various frequencies and different edges disintegrated with the SVD employ on each converted gray level images. Finally, singular values of SVD used as feature vector for this texture feature extraction model. For training and testing of experimental datasets, Naive Bayes classifier has been used. The Log-Gabor and SVD based feature extraction shows improved performance by exhibiting higher classification accuracy for our tested dataset compare to conventional Gabor and SVD feature extraction method. Furthermore, in order to decrease the computational and time complexity, an NVIDIA GeForce GTX780 GPU is used to implement our proposed model in parallel. The GPU implementation of proposed model showed average 3X speedup for per image than conventional CPU implementation. Published 2018-02-20T05:49:36Z 2018-02-20T05:49:36Z 2017-01 Conference paper Ratul, M. A. R., Raja, S. A., & Uddin, J. (2017). A novel parallel texture feature extraction method using log-gabor filter and singular value decomposition (SVD). Paper presented at the ACM International Conference Proceeding Series, , Part F128047 187-191. 10.1145/3036331.3036352 978-145034816-4 http://hdl.handle.net/10361/9519 http://doi.org/10.1145/3036331.3036352 en https://dl.acm.org/citation.cfm?doid=3036331.3036352 © 2017 ACM |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
Feature extraction Gabor filter Log-gabor filter Parallel processing |
| spellingShingle |
Feature extraction Gabor filter Log-gabor filter Parallel processing Ratul, Md Aminur Rab Raja, Sharif Ahmmad Uddin, Jia A novel parallel texture feature extraction method using log-gabor filter and singular value decomposition (SVD) |
| description |
This conference paper was published in the ACM International Conference Proceeding Series [© 2017 ACM] and the definite version is available at : http://doi.org/10.1145/3036331.3036352 The Journal's website is at: https://dl.acm.org/citation.cfm?doid=3036331.3036352 |
| author2 |
Department of Computer Science and Engineering, BRAC University |
| author_facet |
Department of Computer Science and Engineering, BRAC University Ratul, Md Aminur Rab Raja, Sharif Ahmmad Uddin, Jia |
| format |
Conference paper |
| author |
Ratul, Md Aminur Rab Raja, Sharif Ahmmad Uddin, Jia |
| author_sort |
Ratul, Md Aminur Rab |
| title |
A novel parallel texture feature extraction method using log-gabor filter and singular value decomposition (SVD) |
| title_short |
A novel parallel texture feature extraction method using log-gabor filter and singular value decomposition (SVD) |
| title_full |
A novel parallel texture feature extraction method using log-gabor filter and singular value decomposition (SVD) |
| title_fullStr |
A novel parallel texture feature extraction method using log-gabor filter and singular value decomposition (SVD) |
| title_full_unstemmed |
A novel parallel texture feature extraction method using log-gabor filter and singular value decomposition (SVD) |
| title_sort |
novel parallel texture feature extraction method using log-gabor filter and singular value decomposition (svd) |
| publisher |
© 2017 ACM |
| publishDate |
2018 |
| url |
http://hdl.handle.net/10361/9519 http://doi.org/10.1145/3036331.3036352 |
| work_keys_str_mv |
AT ratulmdaminurrab anovelparalleltexturefeatureextractionmethodusingloggaborfilterandsingularvaluedecompositionsvd AT rajasharifahmmad anovelparalleltexturefeatureextractionmethodusingloggaborfilterandsingularvaluedecompositionsvd AT uddinjia anovelparalleltexturefeatureextractionmethodusingloggaborfilterandsingularvaluedecompositionsvd AT ratulmdaminurrab novelparalleltexturefeatureextractionmethodusingloggaborfilterandsingularvaluedecompositionsvd AT rajasharifahmmad novelparalleltexturefeatureextractionmethodusingloggaborfilterandsingularvaluedecompositionsvd AT uddinjia novelparalleltexturefeatureextractionmethodusingloggaborfilterandsingularvaluedecompositionsvd |
| _version_ |
1814308206375075840 |