2019 年 85 巻 5 号 p. 463-468
In this paper, we propose a system for estimating reading content in a booklet from an indoor surveillance camera. Here, we assume that a reading content can be specified by estimating the following two; which booklet/page, and which region in the page. We implement a reading booklet/page estimation method based on image search, and propose a reading region estimation method based on the slight difference of body pose of the reader. We evaluated the method as a 44 classes classification problem, which consists of eleven pages of booklets and four regions in each pages. We confirmed that the system achieved 25.6% in accuracy of the reading content estimation in our evaluation setting.