Approximate Stochastic Computing (ASC) for Image Processing Applications
SC (stochastic computation) has been found to be very advantageous in image processing applications because of its lower area consumption and low-power operation. However, one of the major issues with the SC is its long run-Time requirement for accurate results. In this paper, a new technique called the approximate stochastic computing (ASC) approach called the approximate stochastic computing (ASC) focusing on image processing applications is proposed to reduce the computation time of a SC by a factor of 16 at a trade-off of an error percentage of 3.13% in the absolute stochastic value ([0, 1)) computed. The proposed technique considers only the first four MSBs of the image pixel value for SC, which introduce a maximum error of 6.25% in the stochastic output. Attempts have been made to reduce this error to 3.13% by linearly increasing the clock cycles from 16 to 17 rather than exponentially (ex: 32, 64, 128,256...). Experimental results from SC edge detection circuit indicate that this technique is a promising approach for efficient approximate image processing.
R. Seva et al., "Approximate Stochastic Computing (ASC) for Image Processing Applications," Proceedings of the International SoC Design Conference (2016, Jeju, South Korea), pp. 31-32, Institute of Electrical and Electronics Engineers (IEEE), Oct 2016.
The definitive version is available at https://doi.org/10.1109/ISOCC.2016.7799758
International SoC Design Conference: ISOCC (2016: Oct. 23-26, Jeju, South Korea)
Electrical and Computer Engineering
Keywords and Phrases
Economic and Social Effects; Edge Detection; Errors; Stochastic Systems; Computation Time; Detection Circuits; Image Pixel Value; Image Processing Applications; Low-Power Operation; Stochastic Computations; Stochastic Computing; Stochastic Values; Image Processing
International Standard Book Number (ISBN)
Article - Conference proceedings
© 2016 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
01 Oct 2016