Microsoft Technology Licensing, LLC

James A Pittman

Patrice Y Simard

Erik Michael Geidl

Patrick M Haluptzok

Mitica Manu

Angshuman Guha

Frank J Eisenhart

A system and method for labeling radicals in East Asian characters is described. The identity of the radical and the location of the radical in a character may be stored for future reference.

Radical-base classification of East Asian handwriting

Various technologies and techniques are disclosed that generate a teaching data set for use by a handwriting recognizer. Ink input is received from various ink sources, such as implicit field data, scripted untruthed ink, scripted truth ink, and/or ink from at least one other language in the same script as the target language for the recognizer. The ink input is used with various machine learning methods and/or other algorithmic methods to generate a teaching ink data set. Examples of the various machine learning methods include a character and/or word n-gram distribution leveling method, an allograph method, a subject diversity method, and a print and cursive data selection method. The teaching ink data is used by a handwriting trainer to produce the handwriting recognizer for the target language.

Handwriting teaching data selection system

New neural networks for handwriting recognition may be build from existing neural networks. An existing neural network pre-trained for a starting language is chosen based on a desired target language. The neural network is modified so that it may be used to recognize characters of the target language, and the modified neural network is used in a handwriting recognizer for the target language. Modification includes copying one or more of the primary outputs of the existing neural network. An appropriate starting language may be chosen based on the desired target language. In addition, a 'super network' may be provided that is a relatively large neural network configured to recognize characters from a number of different languages. One may customize a handwriting recognizer using such a super network by programming a mask to block outputs from the super network that are not necessary for the language desired to be recognized.

Handwriting recognition using neural networks

A method and system for recognizing user input information including cursive handwriting and spoken words. A time-delayed neural network having an improved architecture is trained at the word level with an improved method, which, along with preprocessing improvements, results in a recognizer with greater recognition accuracy. Preprocessing is performed on the input data and, for example, may include resampling the data with sample points based on the second derivative to focus the recognizer on areas of the input data where the slope change per time is greatest. The input data is segmented, featurized and fed to the time-delayed neural network which outputs a matrix of character scores per segment. The neural network architecture outputs a separate score for the start and the continuation of a character. A dynamic time warp (DTW) is run against dictionary words to find the most probable path through the output matrix for that word, and each word is assigned a score based on the least costly path that can be traversed through the output matrix. The word (or words) with the overall lowest score (or scores) are returned. A DTW is similarly used in training, whereby the sample ink only need be labeled at the word level.

Growing community of inventors

Issaquah, WA, United States of America

James A Pittman