Incremental learning for interactive sketch recognition

Abstract : In this paper, we present the integration of a classfi er, based on an incremental learning method, in an interactive sketch analyzer. The classfi er recognizes the symbol with a degree of con dence. Sometimes the analyzer considers that the response is insu ficient to make the right decision. The decision process then solicits the user to explicitly validate the right decision. The user associates the symbol to an existing class, to a newly created class or ignores this recognition. The classifi er learns during the interpretation phase. We can thus have a method for autoevolutionary interpretation of sketches. In fact, the user participation has a great impact to avoid error accumulation during the analysis. This paper demonstrates this integration in an interactive method based on a competitive breadth- first exploration of the analysis tree for interpreting the 2D architectural floor plans.
Document type :
Book sections
Liste complète des métadonnées

Cited literature [8 references]  Display  Hide  Download

https://hal.inria.fr/hal-00959853
Contributor : Aurélie Lemaitre <>
Submitted on : Monday, March 17, 2014 - 10:42:32 AM
Last modification on : Thursday, February 7, 2019 - 4:16:05 PM
Document(s) archivé(s) le : Tuesday, June 17, 2014 - 11:25:46 AM

File

lncsGhorbel.pdf
Files produced by the author(s)

Identifiers

Citation

Achraf Ghorbel, Abdullah Almaksour, Aurélie Lemaitre, Eric Anquetil. Incremental learning for interactive sketch recognition. Young-Bin Kwon and Jean-Marc Ogier. Graphics Recognition New Trends and Challenges, 7423, Springer, pp.108-118, 2013, LNCS, 978-3-642-36823-3. ⟨10.1007/978-3-642-36824-0_11⟩. ⟨hal-00959853⟩

Share

Metrics

Record views

382

Files downloads

145