Adaptive gray level run length features from class distance matrices

We have constructed class distance matrices for the Gray Level Run Length texture analysis method. For a four-class problem of liver cell nuclei, we have found that there exist areas of consistently high values in the class distance matrices. We have combined the information from the entries of the normalized run length matrix, based on the class distance matrices, to obtain adaptive features for texture classification. Using this procedure, we have extracted only two features, which halved the classification error when compared to the best pair of classical GLRLM features.