HBF49 feature set: A first unified baseline for online symbol recognition - Archive ouverte HAL
Article Dans Une Revue Pattern Recognition Année : 2013

HBF49 feature set: A first unified baseline for online symbol recognition

Résumé

As the rise of pen-enabled interfaces is accompanied with an increased number of techniques for recognition of pen-based input, recent trends in symbol recognition show an escalation in systems complexity (number of features, classifiers combination) or the over-specialization of systems to specific datasets or applications. Despite the importance of representation space in feature-based methods, few works focus on the design of feature sets adapted to a large variety of symbols, and no universal representation space was proposed as a benchmarking reference. We introduce in this work HBF49, a unique set of features for the representation of hand-drawn symbols to be used as a reference for evaluation of symbol recognition systems. An empirical constructive approach is adopted for designing this set of 49 simple features, able to handle a large diversity of symbols in various experimental contexts. An original effort is made for guaranteeing transparency of features design and reproducibility of experiments. We demonstrate that using off-the-shelf statistical classifiers, the HBF49 representation performs comparably or better than state-of-the-art results reported on eight databases of hand-drawn objects. We also obtain a good recognition performance for user-defined gestures that further attests the ability of HBF49 to deal with a great variety of symbols.
Fichier principal
Vignette du fichier
preprint_HBF49_v2.pdf (619.39 Ko) Télécharger le fichier
convex_hull.pdf (7.67 Ko) Télécharger le fichier
cvc_12L.tif (24.46 Ko) Télécharger le fichier
definitions.pdf (10.31 Ko) Télécharger le fichier
hhreco_12L.tif (22.07 Ko) Télécharger le fichier
ironoff_12L.tif (18.96 Ko) Télécharger le fichier
laviola_12L.tif (20.65 Ko) Télécharger le fichier
loustic_12L.tif (28.42 Ko) Télécharger le fichier
meubles_12L.tif (30.67 Ko) Télécharger le fichier
nicicon_12L.tif (24.88 Ko) Télécharger le fichier
resampled.pdf (8.78 Ko) Télécharger le fichier
sign_12L.tif (19.96 Ko) Télécharger le fichier
zoning2.pdf (10.56 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Format Autre
Format Autre
Format Autre
Format Autre
Format Autre
Format Autre
Format Autre
Format Autre
Format Autre
Format Autre
Format Autre
Format Autre
Loading...

Dates et versions

hal-00933509 , version 1 (02-02-2014)

Identifiants

Citer

Adrien Delaye, Eric Anquetil. HBF49 feature set: A first unified baseline for online symbol recognition. Pattern Recognition, 2013, 46 (1), pp.117-130. ⟨10.1016/j.patcog.2012.07.015⟩. ⟨hal-00933509⟩
651 Consultations
813 Téléchargements

Altmetric

Partager

More