专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09462175B2 Digital annotation-based visual recognition book pronunciation system and related method of operation 有权
标题翻译：基于数字注释的视觉识别书发音系统及相关操作方法
公开(公告)号：US09462175B2
公开(公告)日：2016-10-04
申请号：US14083251
申请日：2013-11-18
申请人： Heekwan Kim
发明人： Heekwan Kim
IPC分类号： G06K9/00 , G06K9/46 , H04N5/232
CPC分类号： H04N5/23206 , G06K9/00671 , H04N5/23216
摘要： A digital annotation-based visual recognition book pronunciation system and its method of operation are disclosed. In one embodiment, a mobile application program in the system extracts graphical feature points from a page image of a book captured by an integrated camera lens, transmits the graphical feature points to a digital annotation database executed in a cloud computing server, retrieves a book pronunciation content associated with the page image of the book, and superimposes an icon or a representation of the book pronunciation content on the page image of the book displayed as a real-time augmented application on the display panel of the mobile device. The system further includes the digital annotation database that stores relational data between the page image of the book and the book pronunciation content recited by a human narrator, and a related image analysis and matching program.
摘要翻译：公开了一种基于数字注释的视觉识别书发音系统及其操作方法。在一个实施例中，系统中的移动应用程序从集成摄像机镜头捕获的书籍的页面图像中提取图形特征点，将图形特征点发送到在云计算服务器中执行的数字注释数据库，检索书发音与本书的页面图像相关联的内容，并且在移动设备的显示面板上叠加显示为实时增强应用的书籍的页面图像上的图标或图书发音内容的表示。该系统还包括数字注释数据库，其存储书籍的页面图像与人类叙述者所述的书籍发音内容之间的关系数据，以及相关的图像分析和匹配程序。

2. 发明申请

US20150138385A1 DIGITAL ANNOTATION-BASED VISUAL RECOGNITION BOOK PRONUNCIATION SYSTEM AND RELATED METHOD OF OPERATION 有权
标题翻译：基于数字意图的视觉识别书发行系统及其相关操作方法
公开(公告)号：US20150138385A1
公开(公告)日：2015-05-21
申请号：US14083251
申请日：2013-11-18
申请人： Heekwan Kim
发明人： Heekwan Kim
IPC分类号： H04N1/21 , H04N5/232
CPC分类号： H04N5/23206 , G06K9/00671 , H04N5/23216
摘要： A digital annotation-based visual recognition book pronunciation system and its method of operation are disclosed. In one embodiment, a mobile application program in the system extracts graphical feature points from a page image of a book captured by an integrated camera lens, transmits the graphical feature points to a digital annotation database executed in a cloud computing server, retrieves a book pronunciation content associated with the page image of the book, and superimposes an icon or a representation of the book pronunciation content on the page image of the book displayed as a real-time augmented application on the display panel of the mobile device. The system further includes the digital annotation database that stores relational data between the page image of the book and the book pronunciation content recited by a human narrator, and a related image analysis and matching program.
摘要翻译：公开了一种基于数字注释的视觉识别书发音系统及其操作方法。在一个实施例中，系统中的移动应用程序从集成摄像机镜头捕获的书籍的页面图像中提取图形特征点，将图形特征点发送到在云计算服务器中执行的数字注释数据库，检索书发音与本书的页面图像相关联的内容，并且在移动设备的显示面板上叠加显示为实时增强应用的书籍的页面图像上的图标或图书发音内容的表示。该系统还包括数字注释数据库，其存储书籍的页面图像与人类叙述者所述的书籍发音内容之间的关系数据，以及相关的图像分析和匹配程序。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式