Can expressiveness of a drawing be traced with a computer? In this study a neural network (perceptron) and a support vector machine are used to classify line drawings. To do this the line drawings are attributed values according to a kinematic model and a diffusion model for the lines they consist of. The values for both models are related to looking times. Extreme values according to these models, that is both extremely short and extremely long looking times, are interpreted as indicating expressiveness. The results strongly indicate that expressiveness in this sense can be detected, at least with a neural network.
View on arXiv