Share Email Print

Proceedings Paper

Evaluation of image deblurring methods via a classification metric
Author(s): Daniele Perrone; David Humphreys; Robert A. Lamb; Paolo Favaro
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

The performance of single image deblurring algorithms is typically evaluated via a certain discrepancy measure between the reconstructed image and the ideal sharp image. The choice of metric, however, has been a source of debate and has also led to alternative metrics based on human visual perception. While fixed metrics may fail to capture some small but visible artifacts, perception-based metrics may favor reconstructions with artifacts that are visually pleasant. To overcome these limitations, we propose to assess the quality of reconstructed images via a task-driven metric. In this paper we consider object classification as the task and therefore use the rate of classification as the metric to measure deblurring performance. In our evaluation we use data with different types of blur in two cases: Optical Character Recognition (OCR), where the goal is to recognise characters in a black and white image, and object classification with no restrictions on pose, illumination and orientation. Finally, we show how off-the-shelf classification algorithms benefit from working with deblurred images.

Paper Details

Date Published: 19 November 2012
PDF: 8 pages
Proc. SPIE 8542, Electro-Optical Remote Sensing, Photonic Technologies, and Applications VI, 854215 (19 November 2012); doi: 10.1117/12.979199
Show Author Affiliations
Daniele Perrone, Univ. Bern (Switzerland)
David Humphreys, SELEX Galileo Ltd. (United Kingdom)
Robert A. Lamb, SELEX Galileo Ltd. (United Kingdom)
Paolo Favaro, Univ. Bern (Switzerland)

Published in SPIE Proceedings Vol. 8542:
Electro-Optical Remote Sensing, Photonic Technologies, and Applications VI
Gary W. Kamerman; Gary J. Bishop; Mark T. Gruneisen; Keith L. Lewis; Miloslav Dusek; Richard C. Hollins; Ove Steinvall; John Gonglewski; John G. Rarity; Thomas J. Merlet, Editor(s)

© SPIE. Terms of Use
Back to Top