A Study on Feature Extraction Method for Clock Drawing Images Using Weighted Direction Index Histogram

Abstract

Recently, the number of elderly persons with dementia has been increasing. In the past, we have proposed a dementia evaluation system using daily conversations and developed the system with a conversational robot. However, the current system is not sufficient for practical use because it can evaluate time/geographical orientation and short-term memory only, and the method to evaluate other orientations and functions is required as well as them. In this paper, we discussed a new dementia evaluation system using not only daily conversations but also drawing tests. The authors employed Clock Drawing Test (CDT) as new dementia evaluation test and implemented it in the tablet device. This paper discussed a feature extraction and recognition method to distinguish normal cases from dementia ones. After evaluation experiments, the proposed method could recognize 87.6% of the clock drawing images appropriately.