Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313293824> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4313293824 abstract "Abstract Convolution widely has been used as the main part of the improvement in digital image processing applications. In convolutional computations, a large number of memory accesses and a huge amount of computations challenge its performance. Many of the related proposed convolvers are based on exact computations. Although exact convolvers keep the accuracy of the convolution operation at the top level, sometimes by missing a negligible amount of accuracy, the performance can be improved. Approximate computing is a new technique for solving computation overhead problems. In this paper, approximate 2D convolvers are presented which minimize the memory access rate and computations by a special factor of Multiply-and-Accumulate (MAC) terms. On the other hand, to preserve the flexibility for supporting different required accuracy, the proposed approximate convolvers are combined with the exact designs with real-time pre-processing stages by exploiting innovative methods which manage the hardware overhead. In comparison to conventional convolvers, the proposed designs improve the number of active resources which causes a significant reduction in power consumption. For 3 × 3 kernel size, the evaluation results on the Xilinx Virtex-7 (XC7V2000t) FPGA device show 34% and 20% power optimization of the proposed approximate and combined convolvers respectively, in comparison to Exact Convolver (EC). Also, this improvement grows by increasing the kernel size. Finally, a comparison based on RMSE and PSNR for different sample images and filters reveals that the error rate and image quality reduction are acceptable for many real-time image processing applications." @default.
- W4313293824 created "2023-01-06" @default.
- W4313293824 creator A5003762154 @default.
- W4313293824 creator A5037464058 @default.
- W4313293824 creator A5040770919 @default.
- W4313293824 creator A5087690244 @default.
- W4313293824 date "2022-12-29" @default.
- W4313293824 modified "2023-09-23" @default.
- W4313293824 title "Real-Time Approximate and Combined 2D Convolvers for FPGA-based Image Processing" @default.
- W4313293824 cites W2097470759 @default.
- W4313293824 cites W2142796063 @default.
- W4313293824 cites W2317956196 @default.
- W4313293824 cites W2772395823 @default.
- W4313293824 cites W2903732333 @default.
- W4313293824 cites W3036312397 @default.
- W4313293824 cites W3184420298 @default.
- W4313293824 cites W4301248396 @default.
- W4313293824 doi "https://doi.org/10.21203/rs.3.rs-2396811/v1" @default.
- W4313293824 hasPublicationYear "2022" @default.
- W4313293824 type Work @default.
- W4313293824 citedByCount "0" @default.
- W4313293824 crossrefType "posted-content" @default.
- W4313293824 hasAuthorship W4313293824A5003762154 @default.
- W4313293824 hasAuthorship W4313293824A5037464058 @default.
- W4313293824 hasAuthorship W4313293824A5040770919 @default.
- W4313293824 hasAuthorship W4313293824A5087690244 @default.
- W4313293824 hasBestOaLocation W43132938241 @default.
- W4313293824 hasConcept C111335779 @default.
- W4313293824 hasConcept C111919701 @default.
- W4313293824 hasConcept C113775141 @default.
- W4313293824 hasConcept C11413529 @default.
- W4313293824 hasConcept C114614502 @default.
- W4313293824 hasConcept C154945302 @default.
- W4313293824 hasConcept C173608175 @default.
- W4313293824 hasConcept C2524010 @default.
- W4313293824 hasConcept C2779960059 @default.
- W4313293824 hasConcept C33923547 @default.
- W4313293824 hasConcept C41008148 @default.
- W4313293824 hasConcept C42935608 @default.
- W4313293824 hasConcept C45347329 @default.
- W4313293824 hasConcept C45374587 @default.
- W4313293824 hasConcept C50644808 @default.
- W4313293824 hasConcept C74193536 @default.
- W4313293824 hasConcept C9390403 @default.
- W4313293824 hasConceptScore W4313293824C111335779 @default.
- W4313293824 hasConceptScore W4313293824C111919701 @default.
- W4313293824 hasConceptScore W4313293824C113775141 @default.
- W4313293824 hasConceptScore W4313293824C11413529 @default.
- W4313293824 hasConceptScore W4313293824C114614502 @default.
- W4313293824 hasConceptScore W4313293824C154945302 @default.
- W4313293824 hasConceptScore W4313293824C173608175 @default.
- W4313293824 hasConceptScore W4313293824C2524010 @default.
- W4313293824 hasConceptScore W4313293824C2779960059 @default.
- W4313293824 hasConceptScore W4313293824C33923547 @default.
- W4313293824 hasConceptScore W4313293824C41008148 @default.
- W4313293824 hasConceptScore W4313293824C42935608 @default.
- W4313293824 hasConceptScore W4313293824C45347329 @default.
- W4313293824 hasConceptScore W4313293824C45374587 @default.
- W4313293824 hasConceptScore W4313293824C50644808 @default.
- W4313293824 hasConceptScore W4313293824C74193536 @default.
- W4313293824 hasConceptScore W4313293824C9390403 @default.
- W4313293824 hasLocation W43132938241 @default.
- W4313293824 hasOpenAccess W4313293824 @default.
- W4313293824 hasPrimaryLocation W43132938241 @default.
- W4313293824 hasRelatedWork W2023487731 @default.
- W4313293824 hasRelatedWork W2070391474 @default.
- W4313293824 hasRelatedWork W2135192563 @default.
- W4313293824 hasRelatedWork W2791204867 @default.
- W4313293824 hasRelatedWork W2963993660 @default.
- W4313293824 hasRelatedWork W3022446491 @default.
- W4313293824 hasRelatedWork W4210398058 @default.
- W4313293824 hasRelatedWork W4295127407 @default.
- W4313293824 hasRelatedWork W4316829953 @default.
- W4313293824 hasRelatedWork W4382322717 @default.
- W4313293824 isParatext "false" @default.
- W4313293824 isRetracted "false" @default.
- W4313293824 workType "article" @default.