The document analysis community spends substantial resources towards computer recognition of any type of text (e.g. characters, handwriting, document structure etc.). In this paper, we introduce a new paradigm focusing on recognizing the activities and habits of users while they are reading. We describe the differences to the traditional approaches of document analysis. We present initial work towards recognizing reading activities. We report our initial findings using a commercial, dry electrode Electroencephalography (EEG) system. We show the feasibility to distinguish reading tasks for 3 different document genres with one user and near perfect accuracy. Distinguishing reading tasks for 3 different document types we achieve 97 % with user specific training. We present evidence that reading and non-reading related activities can be separated over 3 users using 6 classes, perfectly separating reading from non-reading. A simple EEG system seems promising for distinguishing the reading of different document genres.
|ジャーナル||Proceedings of the International Conference on Document Analysis and Recognition, ICDAR|
|出版ステータス||Published - 2013 12 11|
|イベント||12th International Conference on Document Analysis and Recognition, ICDAR 2013 - Washington, DC, United States|
継続期間: 2013 8 25 → 2013 8 28
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition