Conveyorized implementation of ASWM image filter on PLD
DOI:
https://doi.org/10.15587/2706-5448.2021.225257Keywords:
adaptive filter, nonlinear filter, median filter, impulse noise, Peak Signal-to-Noise Ratio, Structural Similarity Index MeasureAbstract
The object of research is the adaptive switching weighted median image filter (ASWM) algorithm. This algorithm is one of the most effective in the field of impulse noise suppression. The computational complexity and algorithmic features of this adaptive nonlinear filter make it impossible to implement a filter that works in real time on modern PLD microcircuits.
The most problematic areas of the algorithm are the weight coefficient estimation cycle, which has no limit on the number of iterations and contains a large number of division operations. This does not allow implementing the filter on PLDs with a sufficiently effective method.
In the course of the research, the programming model of the filter in Python was used. The performance of the algorithm was assessed using the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) metrics.
Modeling made it possible to find out empirically the number of iterations of the cycle for estimating the weight coefficients at different levels of noise density and to estimate the effect of artificial limitation of the maximum number of iterations on the filter performance. Regardless of the intensity of the noise impact, the algorithm performs less than 40 iterations of the evaluation cycle. Let’s also simulate the operation of the algorithm with different variants of the division module implementation. The paper considers the main of them and offers the most optimal in terms of the ratio of accuracy/hardware costs for implementation. Thus, a modified algorithm was proposed that does not have these disadvantages.
Thanks to modifications of the algorithm, it is possible to implement a pipelined ASWM image filter on modern PLDs. The filter is synthesized for the main families of Intel PLDs. The implementation, which is not inferior in terms of SSIM and PSNR metrics to the original algorithm, requires less than 65,000 FPGA logical cells and allows filtering of monochrome images with FullHD resolution at 48 frames/s at a clock frequency of 100 MHz.
References
- Gonzalez, R C. (2003). Digital Image Processing. Beijing: Publishing Hourse of Electronics Industry, 123–124.
- Brownrigg, D. R. K. (1984). The weighted median filter. Communications of the ACM, 27 (8), 807–818. doi: http://doi.org/10.1145/358198.358222
- Goyal, P., Chaurasia, V. (2017). Application of median filter in removal of random valued impulse noise from natural images. 2017 International Conference of Electronics, Communication and Aerospace Technology (ICECA), 1, 125–128. doi: http://doi.org/10.1109/iceca.2017.8203657
- Konieczka, A., Balcerek, J., Dabrowski, A. (2018). Method of adaptive pixel averaging for impulse noise reduction in digital images. 2018 Baltic URSI Symposium (URSI). Poznan, 221–224. doi: http://doi.org/10.23919/ursi.2018.8406738
- Dawood, H., Dawood, H., Guo, P. (2015). Removal of random-valued impulse noise by Khalimsky grid. 2015 Asia Pacific Conference on Multimedia and Broadcasting. doi: http://doi.org/10.1109/apmediacast.2015.7210268
- Darus, M. S., Sulaiman, S. N., Isa, I. S., Hussain, Z., Tahir, N. M., Isa, N. A. M. (2016). Modified hybrid median filter for removal of low density random-valued impulse noise in images. 2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE). Batu Ferringhi, 528–533. doi: http://doi.org/10.1109/iccsce.2016.7893633
- Zhang, X., Liao, H., Du, X., Xu, B. (2018). A Fast Hybrid Noise Filtering Algorithm Based on Median-Mean. 2018 IEEE International Conference on Mechatronics and Automation (ICMA). Changchun, 2120–2125. doi: http://doi.org/10.1109/icma.2018.8484392
- Hsieh, C., Huang, P., Zhao, Q. (2018). Impulse Noise Replacement With Adaptive Neighborhood Median Filtering. 2018 International Conference on Machine Learning and Cybernetics (ICMLC). Chengdu, 491–496. doi: http://doi.org/10.1109/icmlc.2018.8527058
- Akkoul, S., Ledee, R., Leconge, R., Harba, R. (2010). A New Adaptive Switching Median Filter. IEEE Signal Processing Letters, 17 (6), 587–590. doi: http://doi.org/10.1109/lsp.2010.2048646
- Kang, C.-C., Wang, W.-J. (2009). Modified switching median filter with one more noise detector for impulse noise removal. AEU – International Journal of Electronics and Communications, 63 (11), 998–1004. doi: http://doi.org/10.1016/j.aeue.2008.08.009
- Akkoul, S., Ledee, R., Leconge, R., Harba, R. (2010). A New Adaptive Switching Median Filter. IEEE Signal Processing Letters, 17 (6), 587–590. doi: http://doi.org/10.1109/lsp.2010.2048646
- Wang, Z., Bovik, A. C., Sheikh, H. R., Simoncelli, E. P. (2004). Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing, 13 (4), 600–612. doi: http://doi.org/10.1109/tip.2003.819861
- Intel FPGA Product catalog, Version 20.3. Available at: https://www.intel.com/content/dam/www/programmable/us/en/pdfs/literature/sg/product-catalog.pdf
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2021 Олег Георгиевич Васильченков , Игорь Геннадьевич Либерг , Михаил Александрович Можаев , Дмитрий Валентинович Сальников
This work is licensed under a Creative Commons Attribution 4.0 International License.
The consolidation and conditions for the transfer of copyright (identification of authorship) is carried out in the License Agreement. In particular, the authors reserve the right to the authorship of their manuscript and transfer the first publication of this work to the journal under the terms of the Creative Commons CC BY license. At the same time, they have the right to conclude on their own additional agreements concerning the non-exclusive distribution of the work in the form in which it was published by this journal, but provided that the link to the first publication of the article in this journal is preserved.
