公开(公告)号：EP1553517A1

公开(公告)日：2005-07-13

申请号：EP03784485.9

申请日：2003-07-25

申请人： MATSUSHITA ELECTRIC INDUSTRIAL CO., LTD.

发明人： FUJITA, Yukihiro ,  SAWAMURA, Kouji ,  ITO, Katsuyuki

IPC分类号： G06K9/34 ,  G06K9/03 ,  G06K9/20 ,  H04M1/00 ,  H04M1/56

CPC分类号： G06K9/2054 ,  G06K9/228 ,  G06K2209/01

摘要： It is an object of the present invention to improve a rate of recognition and recognition speed, reduce a degree of a specification required for a device forming a photographing device or a system and lower consumed electric power and a cost. In a character recognition processing method according to the present invention, a character image as an object whose character is to be recognized is displayed on a display (12) together with a cursor of a character frame for recognizing a character. While the cursor is set to a character string as an object to be recognized, the character image is photographed by a photographing part (9). In an image fetching part (3), the image data of the photographed character image is fetched. In a layout analyzing part (5), the fetched image data of the character image and cursor position information from a cursor control part (4) corresponding to the character image are received. The image data is collated with the cursor position information to analyze the arrangement of the lines or characters of the character string as the object to be recognized. Then, in a character cutting part (6), the character is cut on the basis of the analyzed result. The character is recognized relative to the character image by a character recognizing part (7) to convert the image data to character data.

摘要翻译： 本发明的目的是提高识别速度和识别速度，降​​低形成拍摄装置或系统的装置所需的规格以及消耗的电力和成本。 在根据本发明的字符识别处理方法中，作为用于识别字符的字符的光标与显示器（12）一起显示作为要识别其角色的对象的字符图像。 当将光标设置为要被识别的对象的字符串时，由拍摄部分（9）拍摄字符图像。 在图像取出部（3）中，取出拍摄的字符图像的图像数据。 在布局分析部（5）中，接收与字符图像对应的来自光标控制部（4）的文字图像的取出图像数据和光标位置信息。 将图像数据与光标位置信息进行核对，以分析作为要识别的对象的字符串的行或字符的排列。 然后，在字符切割部（6）中，基于分析结果切断字符。 通过字符识别部（7）相对于字符图像识别字符，以将图像数据转换为字符数据。