Towards determining syntactic complexity of visual stimuli used in art therapy

In the paper, we deal with the problem of automatic determining syntactic complexity of visual stimuli. This problem is important in case of using paintings in eye-tracking based diagnosis and therapy of some kinds of neuropsychological and emotional disorders. Our approach to solving the considered problem is based on the clustering procedure using Self Organizing Feature Maps. The clustering results are compared with the heat maps obtained in the eye-tracking process.