Visual Performance-Based Image Enhancement Methodology: An Investigation of Contrast Enhancement Algorithms
Abstract
While vast numbers of image enhancing algorithms have already been developed, the majority of these algorithms have not been assessed in terms of their visual performance-enhancing effects using militarily relevant scenarios. The goal of this research was to apply a visual performance-based assessment methodology to assess six algorithms that were specifically designed to enhance the contrast of digital images. The image enhancing algorithms used in this study included three different histogram equalization algorithms, the Autolevels function, the Recursive Rational Filter technique described in Marsi, Ramponi, and Carrato and the multiscale Retinex algorithm described in Rahman, Jobson and Woodell. The methodology used in the assessment has been developed to acquire objective human visual performance data as a means of evaluating the contrast enhancement algorithms. The basic approach is to use standard objective performance metrics, such as response time and error rate, to compare algorithm enhanced images versus two baseline conditions, original non-enhanced images and contrast-degraded images. Observers completed a visual search task using a spatial-forced-choice paradigm. Observers searched images for a target (a military vehicle) hidden among foliage and then indicated in which quadrant of the screen the target was located.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 2006
- Accession Number
- ADA444614
Entities
People
- Alan R. Pinkus
- Charles D. Goodyear
- George A. Reis
- Kelly E. Neriani
- Travis J. Herbranson
Organizations
- General Dynamics