In this paper we present an approach for image region classification that combines low-level processing with high-level scene understanding. For the low-level training, predefined image concepts are statistically modeled using wavelet features extracted directly from image pixels. For classification, features of a given test region compared with these statistical models provide probabilistic evaluations for all possible image concepts. Maximizing these values themselves already leads to a classification result (label). However, in our paper they are used as an input for the high-level approach exploiting explicitly represented spatial arrangements of labels, so called spatial prototypes. We formalize the problem using Fuzzy Constraint Satisfaction Problems and Linear Programming. They provide a model with explicit knowledge that is suitable to aid the task of region labeling. Results of experiments performed for more than 6000 test image regions show that using the combination of low-level and high-level image analysis increases the labeling accuracy significantly.