Lucent Technologies Inc.

At&t Bell Laboratories

Quen-Zong Wu

Yann Andre LeCun

Data samples describing a plurality of micro-segments that compose a symbol to be recognized are received from a device such as an electronic pad. A preprocessor 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 is trained to identify symbols from a different group of symbols. A sorter 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 that communicates the cell values to the proper neural network.

Method and apparatus for symbol recognition using multidimensional

Data samples describing a plurality of micro-segments that compose a symbol to be recognized are received from a device such as an electronic pad. Preprocessors map the micro-segments into cells of a plurality of feature arrays with different resolutions. Preprocessors assign 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 comparators that compare the feature arrays with reference arrays. The results of comparisons involving lower resolution feature arrays and reference arrays, are used to limit the number of comparisons involving higher resolution feature arrays and reference arrays. The highest resolution comparison selects the reference array that identifies the symbol to be recognized.

Growing community of inventors

Lincroft, NJ, United States of America

Quen-Zong Wu