Classification of image data with adjustment of the degree of granulation

A system for classification of image data, the system comprising:

• at least one computer, the at least one computer being configured to implement:
• a trainable pre-processing unit configured to (i) receive the image data, (ii) transform the image data into a representation in a working space as a linear combination of basic functions of the working space characterized by a set of coefficients, (iii) retrieve, from a trained relationship, based on the image data, at least one specification regarding which of the coefficients are to be reduced in terms of magnitude or eliminated, the at least one specification defining an extent to which a level of detail of the image data is to be reduced, and (iv) (iii) generate detail-reduced image data by reducing or eliminating the coefficients of the representation in accordance with the at least one specification;
• and
• a trainable classifier configured to map the detail-reduced image data onto an assignment to one or more classes of a specified classification.