CCL: Molecule Image Dataset REQUIRED
- From: "Aniko Simon" <aniko^simbiosys.ca>
- Subject: CCL: Molecule Image Dataset REQUIRED
- Date: Wed, 16 Sep 2009 12:41:42 -0400
Sent to CCL by: "Aniko Simon" [aniko(_)simbiosys.ca]
Noureddin,
Prof. Peter Johnson's group at the University of Leeds, and his affiliates
SimBioSys, Inc. and Keymodule Ltd. are pioneers in this field (i.e. OCSR -
Optical Chemical Structure Recognition) since the early 90'ies. We do believe
that having a publicly available benchmarking test set is a great value to the
scientific community.
Please read this recent blog post:
http://www.simbiosys.ca/blog/2009/06/15/clide-for-converting-structure-images-to-structure-files/
which refers to the recent publication:
Aniko T. Valko, A. Peter Johnson: CLiDE Pro: The Latest Generation of CLiDE, a
Tool for Optical Chemical Structure Recognition
J. Chem. Inf. Model., 2009, 49 (4), pp 780-787
DOI: 10.1021/ci800449t
We offer two OCSR benchmarking test sets (the latest one is referred in the
above paper), they are both posted on our web-site and freely available:
http://www.simbiosys.ca/clide/validation.html
Best wishes,
Aniko
--
Aniko Simon, Ph.D. | SimBioSys Inc. | Tel: 1-416-741-4263
http://www.simbiosys.ca/
| blog: http://www.simbiosys.ca/blog/
On September 14, 2009, Noureddin Sadawi n.sadawi|*|gmail.com wrote:
> Sent to CCL by: "Noureddin Sadawi" [n.sadawi%gmail.com]
> Dear all,
> I am looking for a freely available molecule image dataset. I am looking
> for scanned images as I am developing a system to extract SMILES notation
> from such images.
>
> Any help is appreciated,
>
> Thanks
>