Performance of the Kullback-Leibler information gain for predicting image fidelity

This paper presents a new method for characterizing information of a compressed image relative to the original one. We show how the Kullback-Leibler information gain is based on three basic postulates which are natural for image processing and thus desirable. As an example of the proposed measure, we analyze the effects of lossy compression on the identification of breast cancer microcalcifications. We also show the comparative results of the Kullback-Leibler information gain and various quantitative measures for predicting image fidelity in the sense of diagnostic usefulness.