APPARATUS, PROGRAM, AND RECORDING MEDIUM FOR LEARNING DATA TO FORM A SELF-ORGANIZING MAP COMPRISED OF REFERENCE VECTORS CORRESPONDING TO FEATURES OF AN IMAGE AND USED FOR DETERMINING OBJECTS IN AN IMAGE

A temporary self-organizing map in which classes are associated with respective vector points is first derived by a first learning section of a data learning apparatus. Thereafter, by use of, for example, an improved method incorporating concept of vicinity learning intp learning vector quantization, a second learning section modifies the temporary self-organizing map and obtains a final self-organizing map. By use of the final self-organizing map thus derived, image meaning determining processing is performed.