(46-5) 09 * << * >> * Russian * English * Content * All Issues

High-performance digital image filtering architectures in the residue number system based on the Winograd method
M.V. Valueva 1, P.A. Lyakhov 1, N.N. Nagornov 1, G.V. Valuev 1

FSAEI HE "North-Caucasus Federal University",
355017, Stavropol, Russia, Pushkina 1

 PDF, 866 kB

DOI: 10.18287/2412-6179-CO-933

Pages: 752-762.

Full text of article: Russian language.

Abstract:
Continuous improvement of methods for visual information registration, processing and storage leads to the need of improving technical characteristics of digital image processing systems. The paper proposes new high-performance digital filter architectures for image processing by the Winograd method with calculations performed in a residue number system with special-type moduli. To assess the performance and hardware costs of the proposed architectures, hardware simulation is carried out using a field-programmable gate array in a computer-aided design envi-ronment Xilinx Vivado 2018.3 for the target device Artix-7 xc7a200tffg1156-3. The results of hardware simulation show that the proposed filter architectures have 1.13 – 5.42 times higher performance, but require more hardware costs compared to the known methods. The results of this study can be used in the design of complex systems for image processing and analysis for their performance to be increased.

Keywords:
digital filters, image processing, residue number system, Winograd filtering method, field-programmable gate array.

Citation:
Valueva MV, Lyakhov PA, Nagornov NN, Valuev GV. High-performance digital image filtering architectures in the residue number system based on the Winograd method. Computer Optics 2022; 46(5): 752-762. DOI: 10.18287/2412-6179-CO-933.

Acknowledgements:
The work is supported by the North-Caucasus Center for Mathematical Research under agreement No. 075-02-2021-1749 with the Ministry of Science and Higher Education of the Russian Federation.

References:

  1. Li H, Fan J, Yu K, Qi X, Wen Z, Hua Q, Zhang M, Zheng Q. Medical image coloring based on gabor filtering for internet of medical things. IEEE Access 2020; 8: 104016-104025. DOI: 10.1109/ACCESS.2020.2999454.
  2. Kamirul K, Hasbi W, Hakim PR, Syafrudin AH. Automatic ship recognition chain on satellite multispectral imagery. IEEE Access 2020; 8: 221918-221931. DOI: 10.1109/ACCESS.2020.3042702.
  3. Wang G, Li B, Zhang Y, Yang J. Background modeling and referencing for moving cameras-captured surveillance video coding in HEVC. IEEE Trans Multimedia 2018; 20(11): 2921-2934. DOI: 10.1109/TMM.2018.2829163.
  4. Alonzo LMB, Chioson FB, Co HS, Bugtai NT, Baldovino RG. A machine learning approach for coconut sugar quality assessment and prediction. 2018 IEEE 10th Int Conf on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM) 2018; 1-4. DOI: 10.1109/HNICEM.2018.8666315.
  5. Thanh DNH, Hien NN, Kalavathi P, Surya Prasath VB. Adaptive switching weight mean filter for salt and pepper image denoising. Procedia Computer Science 2020; 171: 292-301. DOI: 10.1016/j.procs.2020.04.031.
  6. Minnema J, Wolff J, Koivisto J, Lucka F, Batenburg KJ, Forouzanfar T, Eijnatten M. Comparison of convolutional neural network training strategies for conebeam CT image segmentation. Comput Methods Programs Biomed 2021; 207: 106192. DOI: 10.1016/j.cmpb.2021.106192.
  7. Hespeler SC, Hespeler SC, Nemati H, Dehghan-Niri E. Non-destructive thermal imaging for object detection via advanced deep learning for robotic inspection and harvesting of chili peppers. Artificial Intelligence in Agriculture 2021; 5: 102-117. DOI: 10.1016/j.aiia.2021.05.003.
  8. Chervyakov NI, Lyakhov PA, Nagornov NN, Valueva MV, Valuev GV. Hardware implementation of a convolutional neural network using calculations in the residue number system. Computer Optics 2019; 43(5): 857-868. DOI: 10.18287/2412-6179-2019-43-5-857-868.
  9. Chriskos P, Frantzidis CA, Gkivogkli PT, Bamidis PD, Kourtidou-Papadeli C. Automatic sleep staging employing convolutional neural networks and cortical connectivity images. IEEE Trans Neural Netw Learn Syst 2020; 31(1): 113-123. DOI: 10.1109/TNNLS.2019.2899781.
  10. Tian Y. Artificial intelligence image recognition method based on convolutional neural network algorithm. IEEE Access 2020; 8: 125731-125744. DOI: 10.1109/ACCESS.2020.3006097.
  11. Gonzalez RC, Woods RE. Digital image processing. 3rd ed. Prentice Hall; 2008.
  12. Bovik AC. Handbook of image and video processing, 2nd ed. San Diego: Elsevier Academic Press; 2005.
  13. Nakasone S, Öfverstedt L, Wilken G, Skoglund U. An OpenCL implementation of an image filter on FPGA. 2019 IEEE 5th Int Conf on Computer and Communications (ICCC) 2019; 272-276. DOI: 10.1109/ICCC47050.2019.9064160.
  14. Tung CA, Huang S. High-performance multiply-accumulate unit by integrating additions and accumulations into partial product reduction process. IEEE Access 2020; 8: 87367-87377. DOI: 10.1109/ACCESS.2020.2992286.
  15. Lyakhov P, Valueva M, Valuev G, Nagornov N. A method of increasing digital filter performance based on truncated multiply-accumulate units. Appl Sci 2020; 10: 9052. DOI: 10.3390/app10249052.
  16. Winograd S. Arithmetic complexity of computations. Siam; 1980: 33. DOI: 10.1137/1.9781611970364.
  17. Lavin A, Gray S. Fast algorithms for convolutional neural networks. 2016 IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2016: 4013-4021. DOI: 10.1109/CVPR.2016.435.
  18. Yepez J, Ko S. Stride 2 1-D, 2-D, and 3-D Winograd for convolutional neural networks. IEEE Trans Very Large Scale Integr VLSI Syst 2020; 28(4): 853-863. DOI: 10.1109/TVLSI.2019.2961602.
  19. Molahosseini AS, De Sousa LS, Chang CH, eds. Embedded systems design with special arithmetic and number systems. Springer International Publishing; 2017.
  20. Lyakhov P, Valueva M, Valuev G, Nagornov N. High-performance digital filtering on truncated multiply-accumulate units in the residue number system. IEEE Access 2020; 8: 209181-209190. DOI: 10.1109/ACCESS.2020.3038496.
  21. Chervyakov NI, Lyakhov PA, Nagornov NN, Kaplun DI, Voznesenskiy AS, Bogayevskiy DV. Implementation of smoothing image filtering in the residue number system. 2019 8th Mediterranean Conference on Embedded Computing (MECO) 2019: 1-4. DOI: 10.1109/MECO.2019.8760190.
  22. Vassalos E, Bakalis D, Vergos HT. RNS assisted image filtering and edge detection. 2013 18th Int Conf on Digital Signal Processing (DSP) 2013: 1-6. DOI: 10.1109/ICDSP.2013.6622821.
  23. Cardarilli GC, Di Nunzio L, Fazzolari R, Nannarelli A, Petricca M, Re M. Design space exploration based methodology for residue number system digital filters implementation. IEEE Trans Emerg Topics Comput 2020; 10(1): 186-198. DOI: 10.1109/TETC.2020.2997067.
  24. Belghadr A, Jaberipur G. FIR filter realization via deferred end-around carry modular addition. IEEE Trans Circuits Syst I Regul Pap 2018; 65(9): 2878-2888. DOI: 10.1109/TCSI.2018.2798595.
  25. Omondi A, Premkumar B. Residue number systems: Theory and implementation. London: Imperial College Press; 2007.
  26. Vergos HT, Dimitrakopoulos G. On Modulo 2n+1 adder design. IEEE Trans Comput 2012; 61(2): 173-186. DOI: 10.1109/TC.2010.261.
  27. Mohan PVA, Premkumar AB. RNS-to-Binary Converters for Two Four-Moduli Sets {2n−1, 2n, 2n+1, 2n+1−1} and {2n−1, 2n, 2n+1, 2n+1+1}. IEEE Trans Circuits Syst I Regul Pap 2007; 54(6): 1245-1254. DOI: 10.1109/TCSI.2007.895515.
  28. Živaljević D, Stamenković N, Stojanović V. Digital filter implementation based on the RNS with diminished-1 encoded channel. 2012 35th Int Conf on Telecommunications and Signal Processing (TSP) 2012: 662-666. DOI: 10.1109/TSP.2012.6256380.
  29. Chervyakov NI, Lyakhov PA, Kalita DI, Shulzhenko KS. Effect of RNS dynamic range on grayscale images filtering. 2016 XV Int Symp Problems of Redundancy in Information and Control Systems (REDUNDANCY) 2016: 33-37. DOI: 10.1109/RED.2016.7779323.
  30. Parhami B. Computer arithmetic: algorithms and hard-ware designs. Oxford University Press; 2010.
  31. Kogge PM, Stone HS. A parallel algorithm for the efficient solution of a general class of recurrence equations. IEEE Trans Comput 1973; C-22(8): 786-793. DOI: 10.1109/TC.1973.5009159.
  32. Zimmermann R. Binary adder architectures for cell-based VLSI and their synthesis. Hartung-Gorre; 1998.
  33. Valueva MV, Nagornov NN, Lyakhov PA, Valuev GV, Chervyakov NI. Application of the residue number system to reduce hardware costs of the convolutional neural network implementation. Math Comput Simul 2020; 177: 232-243. DOI: 10.1016/j.matcom.2020.04.031.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20