Non-Alcohol Liver Disease (NAFLD) is nowadays the most common liver disease in Western Countries. It is the chronic condition of fat expansion in liver, which is not associated with alcohol consumption. Quantitating steatosis in liver biopsies could provide objective measurement of the severity of the disease, instead of using semi-quantitative scoring systems. The current work, introduces an automated method for measuring steatosis in liver biopsies, using both machine learning and classical image processing techniques. Clustering is employed for tissue specimen detection, while an iterative morphological procedure is used for steatosis revealing. The method has been evaluated in a set of 20 liver biopsy images and the obtained results present ~1% mean percentage error.