Qualitative Interpretation of Spectral Images: Reasoning with Uncertain Evidence

Interpreting spectral images requires comparing known patterns with input data (images) to identify which patterns are contained in the input data. In practice, however, it is hard to identify any pattern when the inaccuracy of input data is not slight. In this paper, we present a method for interpreting spectral images by using qualitative reasoning. First, we put forward a new concept called support coefficient function (SCF) which can be used to extract, represent, and calculate qualitative correlations among data. Then, we introduce an approach to determining dynamic shift intervals of inaccurate data on the basis of qualitative correlations. Finally, we discuss how to use qualitative correlations as evidence of enhancing or depressing hypotheses for inaccurate data. The method has been applied to a practical system for interpreting infrared spectral images. We have fully tested the system against several hundred real spectral images. The rate of identification (RI) and the rate of correctness (RC) are near 90% and 74% respectively, and the latter is the highest among known systems. 1 Introduction Interpreting spectral images is a special problem of diagnosis. The problem requires comparing known patterns with input spectral images to identify which patterns may be contained by the images [Anand et a/., 1991; Sadtler, 1988]. Because spectral data are always inaccurate , one difficult task is to deal with uncertain evidence. Currently known methods and systems of spectral image interpretation are primarily based on quantitative analysis [Culthup et a/., 1990; Sadtler, 1988]. The essential principle of quantitative analysis is to determine the possibility that a pattern may be contained by an image by calculating the difference between the pattern and the parts of the image. In practice, however, a critical problem of applying quantitative analysis is that it is hard to identify any pattern when the inaccuracy of input data is not slight. Fuzzy logic and probability theory can partially solve the problem [Duda and Nilsson, 1976; Zadeh, 1978], but they can not consider qualitative correlations among data 1 which are very important and effective in spectral image interpretation. We present a novel method for interpreting spectral images by using qualitative reasoning. The method draws inferences on the basis of qualitative features of spectral images, and uses qualitative correlations among data as evidence when input data are inaccurate. We put forward a new concept called support coefficient function (SCF). SCF can be used to extract, represent, and calculate qualitative …