Share Email Print
cover

Proceedings Paper

Image quality assessment for determining efficacy and limitations of Super-Resolution Convolutional Neural Network (SRCNN)
Author(s): Chris M. Ward; Joshua Harguess; Brendan Crabb; Shibin Parameswaran
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Traditional metrics for evaluating the efficacy of image processing techniques do not lend themselves to under- standing the capabilities and limitations of modern image processing methods - particularly those enabled by deep learning. When applying image processing in engineering solutions, a scientist or engineer has a need to justify their design decisions with clear metrics. By applying blind/referenceless image spatial quality (BRISQUE), Structural SIMilarity (SSIM) index scores, and Peak signal-to-noise ratio (PSNR) to images before and after im- age processing, we can quantify quality improvements in a meaningful way and determine the lowest recoverable image quality for a given method.

Paper Details

Date Published: 19 September 2017
PDF: 12 pages
Proc. SPIE 10396, Applications of Digital Image Processing XL, 1039605 (19 September 2017); doi: 10.1117/12.2275157
Show Author Affiliations
Chris M. Ward, Space and Naval Warfare Systems Ctr. Pacific (United States)
Joshua Harguess, Space and Naval Warfare Systems Ctr. Pacific (United States)
Brendan Crabb, Space and Naval Warfare Systems Ctr. Pacific (United States)
Shibin Parameswaran, Space and Naval Warfare Systems Ctr. Pacific (United States)


Published in SPIE Proceedings Vol. 10396:
Applications of Digital Image Processing XL
Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top