UNIPEN project of on-line data exchange and recognizer benchmarks

TLDR

The UNIPEN project, initiated by the International Association of Pattern Recognition’s Technical Committee 11 two years ago, aims to standardize online handwriting data exchange and recognizer benchmarks. Its goal is to provide solutions for the increasing demand for handwriting samples to train and evaluate online handwriting recognizers on pen‑based computers. Researchers from industry and academia have defined a common data format, exchange platform, and benchmark protocol, with data—including handprints, cursive, signatures, and gestures from multiple alphabets—to be compiled by the Linguistic Data Consortium and benchmarked under NIST arbitration.

Abstract

We report the status of the UNIPEN project of data exchange and recognizer benchmarks started two years ago at the initiative of the International Association of Pattern Recognition (Technical Committee 11). The purpose of the project is to propose and implement solutions to the growing need of handwriting samples for online handwriting recognizers used by pen-based computers. Researchers from several companies and universities have agreed on a data format, a platform of data exchange and a protocol for recognizer benchmarks. The online handwriting data of concern may include handprint and cursive from various alphabets (including Latin and Chinese), signatures and pen gestures. These data will be compiled and distributed by the Linguistic Data Consortium. The benchmarks will be arbitrated the US National Institute of Standards and Technologies. We give a brief introduction to the UNIPEN format. We explain the protocol of data exchange and benchmarks.