公开(公告)号：US20070009155A1

公开(公告)日：2007-01-11

申请号：US11358436

申请日：2006-02-21

申请人： Wesley Potts ,  Brian Anderson ,  Jason Rogers ,  Humayun Khan ,  Scott Coons

发明人： Wesley Potts ,  Brian Anderson ,  Jason Rogers ,  Humayun Khan ,  Scott Coons

IPC分类号： G06K9/18 ,  G06K9/62

CPC分类号： G06K9/00

摘要： A process for intelligent importation of information from a foreign application user interface includes extraction of raster data from a pre-designated region of a screen displayed in the foreign application, segmentation of the raster data into prospective sets of character raster data; application of the character raster data and a feature data set and a vector data set derived from the character raster data as inputs to respective raster, feature, and vector artificial neural networks to generate candidate characters; using a voting process to identify a character represented by the character raster data from the candidate characters; assembly of the remaining characters as recognized by the neural networks into a key; and association of the key with an external data file which may be stored and thereafter retrieved in association with the screen displayed in the foreign application.

摘要翻译： 用于从外部应用程序用户界面智能导入信息的过程包括从在外部应用中显示的屏幕的预先指定的区域提取光栅数据，将光栅数据分割成预期的字符光栅数据组; 将字符光栅数据和特征数据组以及从字符光栅数据导出的矢量数据集应用于相应的光栅，特征和矢量人造神经网络，以产生候选字符; 使用表决过程从候选人物识别由字符栅格数据表示的字符; 将由神经网络识别的剩余字符组合成键; 以及密钥与外部数据文件的关联，该外部数据文件可以与在外部应用中显示的屏幕相关联地被存储并随后检索。