Modeling Flowchart Structure Recognition as a Max-Sum Problem

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F13%3A00212145" target="_blank" >RIV/68407700:21230/13:00212145 - isvavai.cz</a>
Result on the web
<a href="http://cmp.felk.cvut.cz/pub/cmp/articles/bresler/Bresler-Prusa-Hlavac-ICDAR-2013.pdf" target="_blank" >http://cmp.felk.cvut.cz/pub/cmp/articles/bresler/Bresler-Prusa-Hlavac-ICDAR-2013.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICDAR.2013.246" target="_blank" >10.1109/ICDAR.2013.246</a>

Result language
angličtina
Original language name
Modeling Flowchart Structure Recognition as a Max-Sum Problem
Original language description
This work deals with the on-line recognition of hand-drawn graphical sketches with structure. We present a novel approach, in which the search for a suitable interpretation of the input is formulated as a combinatorial optimization task -- the max-sum problem. The recognition pipeline consists of two main stages. First, groups of strokes possibly representing symbols of a sketch (symbol candidates) are segmented and relations between them are detected. Second, a combination of symbol candidates best fitting the input is chosen by solving the optimization problem. We focused on flowchart recognition. Training and testing of our method was done on a freely available benchmark database. We correctly segmented and recognized 82.7 prec. of the symbols having 31.5 prec. of the diagrams recognized without any error. It indicates that our approach has promising potential and can compete with the state-of-the-art methods.
Czech name
—
Czech description
—

Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
ICDAR 2013: Proceedings of the 12th International Conference on Document Analysis and Recognition
ISBN
—
ISSN
1520-5363
e-ISSN
—
Number of pages
5
Pages from-to
1215-1219
Publisher name
IEEE Computer Society
Place of publication
Los Alamitos
Event location
Washington DC
Event date
Aug 25, 2013
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)