Poor man's OCR: need performance improvement tips

[D.Hering]

I thought I should correct and clarify the use of EMSL (even though
this isn't specific toward your request, qvx.)

http://esml.itsc.uah.edu/index.jsp

It's more for data format recognition and conversion. Here's a
description from the site. The sw was developed for earth science, but
is very useful for any domain.

ESML is an interchange technology that enables data (both structural
and semantic) interoperability with applications without enforcing a
standard format. Users can write external files using ESML schema to
describe the structure of the data file. Applications can utilize the
ESML Library to parse this description file and decode the data format.
As a result, software developers can now build data format independent
applications utilizing the ESML technology. Furthermore, semantic tags
can be added to the ESML files by linking different domain ontologies
to provide a complete machine understandable data description. This
ESML description file allows the development of intelligent
applications that can now understand and "use" the data.