著者

清田 公保 島川 学 本田 幸代 江崎 修央 砂崎 由樹

出版者

一般社団法人情報処理学会

雑誌

情報処理学会研究報告ユビキタスコンピューティングシステム(UBI) (ISSN:09196072)

巻号頁・発行日

vol.2006, no.14, pp.139-143, 2006-02-16

被引用文献数

2

---

This paper proposes a text reading system by using active micro camera. This system is designed as information navigation for visually impaired person. The system is composed with a laptop PC Network Camera and a command input device. At first the system extracts character areas automatically and characters are recognized by offline-character recognition application. Next The text database of the layered structure is composed from captured menu image by using the system. A technical factor in this system is as follows. Because the user of the system is the blind the captured menu image is not certain whether to contain an appropriate character area. Some characters are transformed such as inclination too big or small. Therefore the proposed system extracts the character area including a small character first. The camera zooms to each candidate character area and then character area of high resolution is extracted. The proposed system can be used to check items of menu and prices. We apply this system to restaurant menu reading system for blind person. The user opens the first page of the menu and pushes [capture] button on the portable PC. In this time the camera turned in the direction of the menu. Then system tries to make database of the menu automatically. Then a menu item database is composed of the menu items that are extracted by offline character recognition. The database items are name of menu and its price. The system announces the menu items by voice synthesizer. The user is able to select the candidate item by using [yes] or [No] button on the control interface board in the system. This operation is very easy for the blind. From the viewpoint that the visually impaired person uses it we discuss that the system design of menu reading system and the presentation method of an efficient voice reading out.This paper proposes a text reading system by using active micro camera. This system is designed as information navigation for visually impaired person. The system is composed with a laptop PC, Network Camera and a command input device. At first, the system extracts character areas automatically, and characters are recognized by offline-character recognition application. Next, The text database of the layered structure is composed from captured menu image by using the system. A technical factor in this system is as follows. Because the user of the system is the blind, the captured menu image is not certain whether to contain an appropriate character area. Some characters are transformed such as inclination, too big or small. Therefore the proposed system extracts the character area including a small character first. The camera zooms to each candidate character area, and then character area of high resolution is extracted. The proposed system can be used to check items of menu and prices. We apply this system to restaurant menu reading system for blind person. The user opens the first page of the menu, and pushes [capture] button on the portable PC. In this time, the camera turned in the direction of the menu. Then system tries to make database of the menu automatically. Then, a menu item database is composed of the menu items that are extracted by offline character recognition. The database items are name of menu and its price. The system announces the menu items by voice synthesizer. The user is able to select the candidate item by using [yes] or [No] button on the control interface board in the system. This operation is very easy for the blind. From the viewpoint that the visually impaired person uses it, we discuss that the system design of menu reading system, and the presentation method of an efficient voice reading out.