High-performance digital image filtering architectures in the residue number system based on the Winograd method

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 environment 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.