发明名称 |
A method and apparatus for symbol recognition using multidimensional preprocessing and symbol sorting |
摘要 |
<p>Data samples describing a plurality of micro-segments that compose a symbol to be recognized are received from a device (160) such as an electronic pad. A preprocessor (162) maps the micro-segments into cells of an array that has several feature dimensions. The preprocessor assigns values to the cells based on the length of a micro-segment associated with the cell, and how well the features of the associated micro-segment correspond to the feature label of the cell. The cell values are used as inputs to at least one of a plurality of neural networks, where each neural network (168) is trained to identify symbols from a different group of symbols. A sorter (164) examines the symbol to determine which neural network should be used to recognize the symbol. An output produced by the sorter controls a switching means (166) that communicates the cell values to the proper neural network. <IMAGE></p> |
申请公布号 |
EP0593204(B1) |
申请公布日期 |
2001.08.22 |
申请号 |
EP19930307960 |
申请日期 |
1993.10.07 |
申请人 |
AT&T CORP.;TELECOMMUNICATION LABORATORIES, DGT, MOTC |
发明人 |
LECUN, YANN ANDRE;WU, QUEN-ZONG |
分类号 |
G06K9/66;G06K9/68;G06T7/00;(IPC1-7):G06K9/68;G06K9/46 |
主分类号 |
G06K9/66 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|