HUMAN PERFORMANCE EVALUATIONS OF SELECTED IMAGE ENHANCEMENT/RESTORATION TECHNIQUES

Recently, the number of digital imaging systems incorporated into information display applications, such as military and industrial aerial reconnaissance, has increased rapidly. These imaging systems provide considerable flexibility for the processing and enhancement of information that otherwise might be unnoticed in conventional imaging systems. Many of the digital enhancement techniques, however, have not been subject to systematic evaluations to examine their influence upon operationally relevant human task performance. This paper reports the findings of a segment of an ongoing research program designed to establish a digital image database, to standardize a set of experimental procedures of obtaining human performance data, and to relate these performance measures to various image display conditions.; The image database consists of low-altitude aerial scenes of various military and civilian installations. Original transparencies were digitized with a microdensitometer to generate the image database for magnetic tape storage. The digitized images were then degraded by blur and noise to simulate various levels of system resolution and system signal-to-noise ratio, respectively.; Two experimental tasks were developed to assess the effects of digital image quality upon human performance characteristics of interest to the military reconnaissance community. An information extraction task required the human observers to answer a series of questions pertaining to the essential elements of information with each image. A subjective rating task required observers to estimate the extent of image interpretability.; Using military photointerpreters as subjects, studies were conducted to assess the effects of image degradations (blur and noise) and image enhancement/restoration processing on human performance. The studies employed high-resolution, black-and-white CRT monitors to display the digital images. Results indicated that both blue and noise image degradations impaired interpretability of the imagery and that several enhancement/restoration processing techniques substantially improved interpretability of the imagery. These results provide useful information for users of digital imaging systems and for researchers to aid future developments of digital image processes.