Stochastic circuits for real-time image-processing applications

• Published in: 2013 50th ACM/EDAC/IEEE Design Automation Conference (DAC) pp. 1 - 6
• Main Authors: Alaghi, Armin, Li, Cheng, Hayes, John P.
• Format: Conference Proceeding
• Language: English
• Published: New York, NY, USA ACM 29.05.2013; IEEE
• Series: ACM Conferences
• Subjects: Clocks; Computer systems organization > Embedded and cyber-physical systems; Computer systems organization > Real-time systems; Emerging Technologies; Hardware > Integrated circuits > Logic circuits; Hardware > Integrated circuits > Logic circuits > Arithmetic and datapath circuits; Image edge detection; Image Processing; Noise; Radiation detectors; Real-Time Computing; Real-time systems; Stochastic Computing; Tin; Vision Chips; image processing; emerging technologies; vision chips; stochastic computing; real-time computing
• ISBN: 1450320716; 9781450320719
• ISSN: 0738-100X
• DOI: 10.1145/2463209.2488901

Real-time image-processing applications impose severe design constraints in terms of area and power. Examples of interest include retinal implants for vision restoration and on-the-fly feature extraction. This work addresses the design of image-processing circuits using stochastic computing techniques. We show how stochastic circuits can be integrated at the pixel level with image sensors, thus supporting efficient real-time (pre)processing of images. We present the design of several representative circuits, which demonstrate that stochastic designs can be significantly smaller, faster, more power-efficient, and more noise-tolerant than conventional ones. Furthermore, the stochastic designs naturally produce images with progressive quality improvement.