A TensorFlow implementation of Local Binary Patterns Transform
Abstract
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.
Keywords
tensorflow, local binary patterns, deep learning, feature extraction
References
- M. Abadi et al., “TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems,” arXiv Prepr. arXiv1603.04467, 2016.
- M. Abadi et al., “TensorFlow: A system for large-scale machine learning,” in Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016, 2016, pp. 265–283
- S. W. D. Chien, S. Markidis, V. Olshevsky, Y. Bulatov, E. Laure, and J. Vetter, “TensorFlow Doing HPC,” in 2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2019, pp. 509–518.
- A. Agrawal et al., “TensorFlow Eager: A Multi-Stage, Python-Embedded DSL for Machine Learning,” arXiv Prepr. arXiv1903.01855, 2019.
- L. Parisi, D. Neagu, R. Ma, and F. Campean, “QReLU and m-QReLU: Two novel quantum activation functions to aid medical diagnostics,” arXiv Prepr. arXiv2010.08031, 2020.
- T. Williams and R. Li, “Wavelet pooling for convolutional neural networks,” in 6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings, 2018.
- S. Pakravan, P. A. Mistani, M. A. Aragon-Calvo, and F. Gibou, “Solving inverse-PDE problems with physics-aware neural networks,” arXiv Prepr. arXiv2001.03608, 2020.
- D. Perepelkin and M. Ivanchikova, “Research of Neural Network Architectures for Solving Adaptive Routing Problems in Multiprovider Networks of Distributed Data Centers,” in 2020 9th Mediterranean Conference on Embedded Computing, MECO 2020, 2020, pp. 1–5.
- M. Pietikäinen, A. Hadid, G. Zhao, and T. Ahonen, Computer Vision Using Local Binary Patterns, vol. 40. Springer Science & Business Media, 2011.
- M. Pietikäinen, “Local Binary Patterns,” Scholarpedia, vol. 5, no. 3, p. 9775, 2010.