A target recognition system based on the concept of fuzzy set theory and homomorphic system is proposed. It involves automatic threshold selection, feature extraction, and classification. An optimal threshold is selected by the fuzzy risk criterion, i.e. to separate a given image into meaningful grey level classes under the assumption that the object and pixel grey level values are normally distributed. An edge measure for evaluating thresholding methods is also presented. When an image is segmented, a set of invariant features called mean, variance, skewness, and kurtosis, which are derived from the spectrum histogram of the target image, is calculated. The classification is then accomplished using the membership function of the feature space of an image and stored patterns. By simulation results, we find that the fuzzy risk thresholding achieves significant performance according to the uniformity and edge measures, and the fuzzy filter with the invariant features has good performance even in low signal-to-noise ratio conditions.