Patent · US Active

Compact handwriting recognition

US8369611B2 · kind B2 · utility

0Cited by

2References

20Claims

0Family size

Assignee

Microsoft Corporation · US

Inventors

Qiang Huo · Beijing, CN
Yongqiang Wang · Shanghai, CN

Key dates

Filing date	Apr 22, 2010
Grant date	Feb 5, 2013
Priority date	—
Expiry date	Jul 14, 2031

Classification

Technology area (CPC G)Physics
CPC primaryG06V30/287
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

One or more techniques and/or systems are disclosed for constructing a compact handwriting character classifier. A precision constrained Gaussian model (PCGM) based handwriting classifier is trained by estimating parameters for the PCGM under minimum classification error (MCE) criterion, such as by using a computer-based processor. The estimated parameters of the trained PCGM classifier are compressed using split vector quantization (VQ) (e.g., and in some embodiments, scalar quantization) to compact the handwriting recognizer in computer-based memory.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.