This paper deals with the analysis of eroded surfaces obtained from cavitation-erosion experiments on stainless steel in water and oil-in-water (o/w) emulsions using image processing. Two analysis techniques that are very promising in this respect are the wavelet decomposition transform and fractals. These can be used to extract parameters that characterize the cavitation intensity in a similar manner to that of the mean depth of erosion (MDP). The extracted parameters are the wavelet energy and entropy as well as the fractal dimension. Both of the image feature parameters and the MDP decrease with adding oil to water. Also, it was found that the variation of image feature parameters versus concentration of oil-in-water emulsions has a general trend that does not depend on magnification factor. The cavitation erosion behavior and mechanism for water and o/w emulsions were analyzed and it was found that the predominant failure mode was fatigue for water and o/w emulsions. The results show that a corrosive effect appears at 5 and 10 wt% o/w emulsions.