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. 发明申请

WO2011128777A3 SEGMENTATION OF TEXTUAL LINES IN AN IMAGE THAT INCLUDE WESTERN CHARACTERS AND HIEROGLYPHIC CHARACTERS 审中-公开
标题翻译：在包括西方字符和等级字符的图像中的文本行的分割
公开(公告)号：WO2011128777A3
公开(公告)日：2012-02-02
申请号：PCT/IB2011001156
申请日：2011-03-25
申请人： MICROSOFT CORP
发明人： MITIC IVAN
IPC分类号： G06K7/10 , G06K9/18 , G06K9/46
CPC分类号： G06K9/346 , G06K9/342 , G06K9/344 , G06K2209/01
摘要： An image processing apparatus segments Western and hieroglyphic portions of textual lines. The apparatus includes an input component (102) that receives an input image having at least one textual line. The apparatus also includes an inter-character break identifier component (104) that identifies candidate inter-character breaks and an inter- character break classifier component. The inter-character break classifier component (104) classifies each of the candidate inter-character breaks as an actual break, a non-break or an indeterminate break. A character recognition component (108) recognizes the candidate characters based at least in part on a feature set extracted from each respective candidate character. A Western and hieroglyphic text classifier component (114) finds and classifies textual line segments as Western text segments or hieroglyphic text segments.
摘要翻译：图像处理装置分割文本行的西部和象形文字部分。该装置包括接收具有至少一个文本行的输入图像的输入部件（102）。该装置还包括识别候选字符间断符和字符间隔分类器组件的字符间中断标识符组件（104）。字符间间隔分类器组件（104）将每个候选字符间中断分类为实际中断，非中断或不确定中断。至少部分地基于从每个候选字符提取的特征集，字符识别组件（108）识别候选字符。西方和象形文字文本分类器组件（114）发现并将文本线段分类为西文本段或象形文字段。

IPRDB

热门服务

关于我们

友情链接

联系方式