문자 인식의 왜곡을 보정하는 방법
    1.
    发明公开
    문자 인식의 왜곡을 보정하는 방법 有权
    用于补偿文本识别中的失真的方法

    公开(公告)号:KR1020100092778A

    公开(公告)日:2010-08-23

    申请号:KR1020090012070

    申请日:2009-02-13

    CPC classification number: G06K9/32 G06K9/342 G06K2009/363 G06K2209/01

    Abstract: PURPOSE: A method for revising distortion of character recognition is provided to normally recognize the characteristic area even if an image including characteristic area is photographed distortedly, thereby preventing decline of the recognition rate of the character recognition. CONSTITUTION: A control unit extracts character area from an image(S202). The control unit presumes the figure of upper side of the extracted character area(S203). The control unit presumes the figure of lower side of the extracted character area(S204). The control unit presumes the figure of the left/right sides of the extracted characteristic area(S205). The control unit presumes the figure(S206). The figure comprises the characteristic area in the minimum area. The control unit converts the characteristic area into rectangular figure through affine transform(S207).

    Abstract translation: 目的:提供一种用于修改字符识别失真的方法,即使包含特征区域的图像被失真地拍摄,从而防止字符识别的识别率的下降,也可以正常识别特征区域。 构成:控制单元从图像中提取字符区域(S202)。 控制单元假设提取的字符区域的上侧的图形(S203)。 控制单元假设提取的字符区域的下侧的图形(S204)。 控制单元假设提取的特征区域的左/右侧的图形(S205)。 控制单元假定该图(S206)。 该图包括最小区域中的特征区域。 控制单元通过仿射变换将特征区域转换成矩形图(S207)。

Patent Agency Ranking