<title>Visual performance-based image enhancement methodology: an investigation of three Retinex algorithms</title>

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 develop a visual performance-based assessment methodology and apply it to assess three Retinex algorithms. The image enhancing algorithms used in this study are the two algorithms described in Funt, Ciurea, and McCann 1 as McCann99 Retinex and Frankle-McCann Retinex, and the multiscale Retinex with color restoration (MSRCR) 2 algorithm. This paper discusses the methodology developed to acquire objective human visual performance data as a means of evaluating various image enhancement algorithms. The basic approach is to determine whether or not standard objective performance metrics, such as response time and error rate, are improved when viewing the enhanced images versus the baseline, non-enhanced images. Four observers completed a visual search task using a spatial-forcedchoice paradigm. Observers had to search images for a target (a military vehicle) hidden among foliage and then indicate in which quadrant of the screen the target was located. Response time and percent correct were measured for each observer. Future directions and the viability of this technique are also discussed.

An investigation of image fusion algorithms using a visual performance-based image evaluation methodology

“…The whiskers represent the least significant difference value (as described above). The objective of this work was to use the assessment methodology developed in Neriani et al 1 to assess the degree of visual performance enhancement provided by four different fusion algorithms. Our original hypothesis was that response time and percent error would be improved by the use of fusion algorithms in a visual search task, as compared to the performance in the Visible unfused and Thermal unfused conditions.…”

“…The observer pressed the spacebar again as soon as they determined whether the target was present or absent and the displayed image was replaced with an image indicating the assignment of the four quadrants (see Figure 5). Then, the observer pressed the number on the keyboard that corresponded to the quadrant the target was located in (1)(2)(3)(4) or zero if there was no target in the image. Each trial had a time limit of 30 seconds.…”

“…Using the methodology developed in Neriani et al 1 , the research discussed in this paper is focused on the assessment of four different fusion algorithms. These algorithms are described in some detail in the next section.…”

Visual performance-based image enhancement methodology: an investigation of contrast enhancement algorithms

“…The objective of this work was to use the assessment methodology developed in Neriani et al 4 to assess the degree of contrast enhancement provided by six different algorithms. Based on the results discussed above, it would appear that both the RRF algorithm and (perhaps) the multiscale Retinex algorithm are promising algorithms in terms of contrast enhancement.…”

“…Using the methodology developed in Neriani et al 4 , the research discussed in this paper is focused on the assessment of six different algorithms designed to enhance the contrast of digital images. These algorithms are described in some detail in the next section.…”