ScholarWorks@숙명여자대학교

초록

From simple scribbles of children to paintings by world-class artists, human psychology is melted into drawings. They express the concept, experience, desire, and attitude to the environment they have acquired, and can identify the person's tendency and personalities. This can be used as a medium for psychotherapy, called "art therapy." We devise an efficient scheme to analyze the hand drawings based on a hierarchical structure, which allows us to produce certain results. First, we extract some separated parts which is consisted of whole objects by object detection. With the extracted parts, we perform the classification task based on 2D CNN to define key attribute. For the given image, the analyzed report is constructed based on the key attributes. The proposed algorithm is applied to "tree test" and "cat test" among many drawing psychological tests, and achieves an analysis accuracy of about 93% and 96%, respectively.

키워드