There is provided an image processing apparatus and an image processing method in which S/N can be improved. A class tap selection unit configures a class tap by selecting a pixel that is a class tap used in class classification of classifying a pixel to be processed of a first image obtained by adding a residual error of prediction encoding and a prediction image together, into any one class of a plurality of classes, from the first image. A class classification unit performs the class classification of the pixel to be processed by using the class tap, and a filter processing unit performs filter processing corresponding to class of the pixel to be processed, with respect to the first image, to generate a second image used in prediction of the prediction image. The class tap selection unit updates a tap structure of the class tap to a selected tap structure.