會議論文
| 學年 | 101 |
|---|---|
| 學期 | 2 |
| 發表日期 | 2013-06-18 |
| 作品名稱 | Non-Visual Document Recognition for Blind Reading Assistant System |
| 作品名稱（其他語言） | |
| 著者 | Hsieh, Ching-Tang; Yeh, Cheng-Hsiang;Liu, Tsun-Te; Huang, Ku-Chen |
| 作品所屬單位 | 淡江大學電機工程學系 |
| 出版者 | AICIT, Korea(Rep. of) |
| 會議名稱 | 2013 9th International Conference on Computing Technology and Information Management(RNIS) |
| 會議地點 | Jeju Island, Republic of Korea |
| 摘要 | As time goes on, a huge mass of progressive knowledge is developed and then the e-book is built for paper reduction and environmental protection. Therefore, many historical documents over the past don’t exist. Research on blind reading aid device is a popular topic gradually, but there are some drawbacks on these methods. For example, electronic documents of many old dated of historical documents don’t read because format should be limited to e-document. Users can’t read any specified region of the document as he wishes. A novel blind reading aid device is proposed without e-document and the user only need to point the document with his finger. This system is composed of third parts. First, we use rectangle detection method to catch the region for document under the Microsoft Kinect. Next, dilation method and projection profile methods are used in order to execrate text and constructed coordinate database. Finally, skin detection, BEA method and depth image of Microsoft Kinect can get the coordinates of user’s finger when user wishes to read the document, and then match with constructed coordinate database to get the character. Then system output is obtained via text to speech. |
| 關鍵字 | Assistive Device;Braille;Document Recognition |
| 語言 | en |
| 收錄於 | |
| 會議性質 | 國際 |
| 校內研討會地點 | 無 |
| 研討會時間 | 20130618~20130620 |
| 通訊作者 | Hsieh, Ching-Tang |
| 國別 | KOR |
| 公開徵稿 | Y |
| 出版型式 | 紙本 |
| 出處 | Research Notes in Information Science (RNIS), pp.453-458 |
| 相關連結 |
機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/90438 ) |