TY - JOUR
T1 - Blurred Shape Model for binary and grey-level symbol recognition
AU - Escalera, Sergio
AU - Fornés, Alicia
AU - Pujol, Oriol
AU - Radeva, Petia
AU - Sánchez, Gemma
AU - Lladós, Josep
PY - 2009/11/1
Y1 - 2009/11/1
N2 - Many symbol recognition problems require the use of robust descriptors in order to obtain rich information of the data. However, the research of a good descriptor is still an open issue due to the high variability of symbols appearance. Rotation, partial occlusions, elastic deformations, intra-class and inter-class variations, or high variability among symbols due to different writing styles, are just a few problems. In this paper, we introduce a symbol shape description to deal with the changes in appearance that these types of symbols suffer. The shape of the symbol is aligned based on principal components to make the recognition invariant to rotation and reflection. Then, we present the Blurred Shape Model descriptor (BSM), where new features encode the probability of appearance of each pixel that outlines the symbols shape. Moreover, we include the new descriptor in a system to deal with multi-class symbol categorization problems. Adaboost is used to train the binary classifiers, learning the BSM features that better split symbol classes. Then, the binary problems are embedded in an Error-Correcting Output Codes framework (ECOC) to deal with the multi-class case. The methodology is evaluated on different synthetic and real data sets. State-of-the-art descriptors and classifiers are compared, showing the robustness and better performance of the present scheme to classify symbols with high variability of appearance. © 2009 Elsevier B.V. All rights reserved.
AB - Many symbol recognition problems require the use of robust descriptors in order to obtain rich information of the data. However, the research of a good descriptor is still an open issue due to the high variability of symbols appearance. Rotation, partial occlusions, elastic deformations, intra-class and inter-class variations, or high variability among symbols due to different writing styles, are just a few problems. In this paper, we introduce a symbol shape description to deal with the changes in appearance that these types of symbols suffer. The shape of the symbol is aligned based on principal components to make the recognition invariant to rotation and reflection. Then, we present the Blurred Shape Model descriptor (BSM), where new features encode the probability of appearance of each pixel that outlines the symbols shape. Moreover, we include the new descriptor in a system to deal with multi-class symbol categorization problems. Adaboost is used to train the binary classifiers, learning the BSM features that better split symbol classes. Then, the binary problems are embedded in an Error-Correcting Output Codes framework (ECOC) to deal with the multi-class case. The methodology is evaluated on different synthetic and real data sets. State-of-the-art descriptors and classifiers are compared, showing the robustness and better performance of the present scheme to classify symbols with high variability of appearance. © 2009 Elsevier B.V. All rights reserved.
KW - Adaboost
KW - Error-Correcting Output Codes
KW - Multi-class classification
KW - Symbol description
KW - Symbol recognition
U2 - 10.1016/j.patrec.2009.08.001
DO - 10.1016/j.patrec.2009.08.001
M3 - Article
SN - 0167-8655
VL - 30
SP - 1424
EP - 1433
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
IS - 15
ER -