Fractal based classification of Colon cancer tissue images

An attempt has been made to classify the histopathological images of colon cancer tissues from the normal tissues based only on fractal features. The tissue images are modelled as fractal sets in E
³
euclidian space. A new fractal feature estimation algorithm has been used. We call it true box counting method. It is seen that lacunarity features are important parameters and are more important in classification or segmentation than other fractal features like fractal dimension and mass dimension.