Abstract
Two-dimensional convolution plays a fundamental role in different image processing applications. Image convolving with different kernel sizes enriches the overall performance of image processing applications. In this regard, it is necessary to design of reconfigurable convolver with respect to desired kernel sizes list. In this paper, a novel approach is presented for implementation of an area-efficient reconfigurable convolver with appropriate throughput and convolution computational time for an arbitrary kernel size list. This approach is based on the adjustment of logical blocks arrangement in the conventional convolvers. The feasibility and benefits of the proposed approach are demonstrated through a case study of the design implementation on an FPGA platform using the XILINX ISE software. Compared to the well-known reconfigurable convolvers, the proposed design significantly reduces convolution computational time and improves throughput with a reasonable number of hardware resources. For instance, the proposed reconfigurable convolver only requires 0.38 ms to perform a 3 × 3 convolution on a 268 × 460 image with 8-bit pixels and only occupies 455 slices resource of Xilinx Virtex-4 (XC4VLX25) FPGA, in which the throughput of 324 million outputs per second (MOPS) is provided with 81 MHz clock frequency for kernel size of 3 × 3. On average, the MPOS of the proposed approach is approximately improved by 43.13% in relation to the other considered alternatives. Experimental results confirm that the proposed reconfigurable convolver is a very competitive design among the alternative reconfigurable convolvers.
Similar content being viewed by others
References
Lee J, Tang H, Park J (2018) Energy efficient canny edge detector for advanced mobile vision applications. IEEE Trans Circuits Syst Video Technol 28(4):1037–1046. https://doi.org/10.1109/TCSVT.2016.2640038
Sunwoo MH, Oh SK (2004) A multiplierless 2-D convolver chip for real-time image processing. J VLSI Signal Process Syst Signal Image Video Technol 38(1):63–71. https://doi.org/10.1023/B:VLSI.0000028534.35761.a8
Kalbasi M, Nikmehr H (2019) A fine-grained pipelined 2-D convolver for high-performance applications. IEEE Trans Circuits Syst II Express Briefs 66(1):146–150. https://doi.org/10.1109/TCSII.2018.2832064
Özyurt F (2020) Efficient deep feature selection for remote sensing image recognition with fused deep learning architectures. J Supercomput 76(11):8413–8431. https://doi.org/10.1007/s11227-019-03106-y
Lei F, Liu X, Dai Q, Ling BW-K (2020) Shallow convolutional neural network for image classification. SN Appl Sci 2(1):1–8. https://doi.org/10.1007/s42452-019-1903-4
Perri S, Lanuzza M, Corsonello P, Cocorullo G (2005) A high-performance fully reconfigurable FPGA-based 2D convolution processor. Microprocess Microsyst 29(8–9):381–391. https://doi.org/10.1016/j.micpro.2004.10.004
Fons F, Fons M, Cantó E (2011) Run-time self-reconfigurable 2D convolver for adaptive image processing. Microelectronics J 42(1):204–217. https://doi.org/10.1016/j.mejo.2010.08.008
Du L et al (2018) A reconfigurable streaming deep convolutional neural network accelerator for internet of things. IEEE Trans Circuits Syst I Regul Pap 65(1):198–208. https://doi.org/10.1109/TCSI.2017.2735490
Fons F, Fons M, Cantó E, López M (2013) Real-time embedded systems powered by FPGA dynamic partial self-reconfiguration: a case study oriented to biometric recognition applications. J Real-Time Image Process 8(3):229–251. https://doi.org/10.1007/s11554-010-0186-1
Ozturk S, Ozkaya U, Akdemir B, Seyfi L (2018) Convolution kernel size effect on convolutional neural network in histopathological image processing applications. In: 2018 International Symposium on Fundamentals of Electrical Engineering, ISFEE. https://doi.org/10.1109/ISFEE.2018.8742484
Phu HV, Minh Tan T, Van Men P, Van Hieu N, Van Cuong T (2019) Design and implementation of configurable convolutional neural network on FPGA. In: Proceedings—2019 6th NAFOSTED Conference on Information and Computer Science, NICS 2019, pp 298–302. https://doi.org/10.1109/NICS48868.2019.9023810
Di Carlo S, Gambardella G, Marco M, Rolfo D, Tiotto G, Prinetto P (2011) An area-efficient 2-D convolution implementation on FPGA for space applications. In: International Design and Test Workshop, pp 88–92. https://doi.org/10.1109/IDT.2011.6123108
Licciardo GD, Cappetta C, Di Benedetto L (2017) FPGA optimization of convolution-based 2D filtering processor for image processing. In: 2016 8th Computer Science and Electronic Engineering Conference, CEEC 2016—Conference Proceedings, pp 180–185. https://doi.org/10.1109/CEEC.2016.7835910
Zhang H, Xia M, Hu G (2007) A multiwindow partial buffering scheme for FPGA-based 2-D convolvers. IEEE Trans Circuits Syst II Express Briefs 54(2):200–204. https://doi.org/10.1109/TCSII.2006.886898
Salvador R, Otero A, Mora J, De La Torre E, Riesgo T, Sekanina L (2013) Self-reconfigurable evolvable hardware system for adaptive image processing. IEEE Trans Comput 62(8):1481–1493. https://doi.org/10.1109/TC.2013.78
Sreenivasulu M, Meenpal T (2019) Efficient hardware implementation of 2D convolution on FPGA for image processing application. In: 2019 IEEE International Conference on Electrical, Computer and Communication Technologies (ICECCT), pp 1–5. https://doi.org/10.1109/ICECCT.2019.8869347
BinMa Z, Yang Y, Liu YX, Bharath AA (2016) Recurrently decomposable 2-D convolvers for FPGA-based digital image processing. IEEE Trans Circuits Syst II Express Briefs 63(10):979–983. https://doi.org/10.1109/TCSII.2016.2536202
Strollo AGM, Napoli E, De Caro D, Saggese GP (2001) A reconfigurable 2D convolver for real-time SAR imaging. Proc IEEE Int Conf Electron Circuits Syst 2:741–744. https://doi.org/10.1109/ICECS.2001.957581
Perri S, Corsonello P (2007) VLSI implementations of efficient isotropic flexible 2D convolvers. IET Circuits Devices Syst 1(4):263–269. https://doi.org/10.1049/iet-cds:20070056
Bosi B, Bois G, Savaria Y (1999) Reconfigurable pipelined 2-D convolvers for fast digital signal processing. IEEE Trans Very Large Scale Integr Syst 7(3):299–308. https://doi.org/10.1109/92.784091
Sriram V, Kearney D (2007) A FPGA implementation of variable kernel convolution. In: Eighth International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT 2007), pp 105–110. https://doi.org/10.1109/PDCAT.2007.45
Wang W, Sun G (2019) A DSP48-based reconfigurable 2-D convolver on FPGA. In: Proceedings—2019 International Conference on Virtual Reality and Intelligent Systems, ICVRIS 2019, pp 342–345. https://doi.org/10.1109/ICVRIS.2019.00089
Cabello F, León J, Iano Y, Arthur R (2015) Implementation of a fixed-point 2D Gaussian filter for image processing based on FPGA. In: 2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), Poznan, pp 28–33. https://doi.org/10.1109/SPA.2015.7365108
Kalbasi M, Nikmehr H (2020) Noise-robust, reconfigurable canny edge detection and its hardware realization. IEEE Access 8:39934–39945. https://doi.org/10.1109/ACCESS.2020.2976860
Zou G, Fu G, Gao M, Shen J, Yin L, Ben X (2019) A novel construction method of convolutional neural network model based on data-driven. Multimed Tools Appl 78(6):6969–6987. https://doi.org/10.1007/s11042-018-6449-8
Liu B, Yao K, Huang M, Zhang J, Li Y, Li R (2018) Gastric pathology image recognition based on deep residual networks. Proc Int Comput Softw Appl Conf 2:408–412. https://doi.org/10.1109/COMPSAC.2018.10267
Virtex-4 FPGAs Data Sheet (2010) Xilinx, Inc. https://www.xilinx.com/support/documentation/data_sheets/ds112.pdf
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Dehghani, A., Kavari, A., Kalbasi, M. et al. A new approach for design of an efficient FPGA-based reconfigurable convolver for image processing. J Supercomput 78, 2597–2615 (2022). https://doi.org/10.1007/s11227-021-03963-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-021-03963-6