Study on a system for adding a new utility value on Kana calligraphy images

2013 Fiscal Year Final Research Report

• Project/Area Number: 23650091
• Research Category: Grant-in-Aid for Challenging Exploratory Research
• Allocation Type: Multi-year Fund
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: The Institute of Statistical Mathematics
• Principal Investigator: MATSUI Tomoko 統計数理研究所, モデリング研究系, 教授 (10370090)
• Project Period (FY): 2011 – 2013
• Keywords: 機械学習 / サポートベクターマシン / かな書データ / 体調判定

Research Abstract

I studied two topics, (1) creation of a Kana calligraphy image database and (2) construction of a system for predicting the mood and physical conditions from Kana calligraphy images. For (1), Kana calligraphy images and survey responses on the mood and physical conditions by 5 subjects were collected once a week over 8 months. For (2), support vector machines with polynomial kernels were used to predict the mood and physical conditions from the Kana calligraphy images. It was found that especially for the body temperature and the eye strains, the average precisions were relatively high.