TY - JOUR
T1 - Modélisation de HMM en contexte avec des arbres de décision pour la reconnaissance de mots manuscrits
AU - Bianne-Bernard, Anne Laure
AU - Kermorvant, Christopher
AU - Likforman-Sulem, Laurence
AU - Mokbel, Chafic
PY - 2011/9/1
Y1 - 2011/9/1
N2 - This paper presents an HMM-based recognizer for the off-line recognition of handwritten words. Word models are the concatenation of context-dependent character models: the trigraphs. Due to the large number of possible context-dependent models to compute, a clustering is applied on each state position, based on decision trees. Our system is shown to perform better than a baseline context independent system, and reaches an accuracy higher than 80% on the publicly available Rimes database.
AB - This paper presents an HMM-based recognizer for the off-line recognition of handwritten words. Word models are the concatenation of context-dependent character models: the trigraphs. Due to the large number of possible context-dependent models to compute, a clustering is applied on each state position, based on decision trees. Our system is shown to perform better than a baseline context independent system, and reaches an accuracy higher than 80% on the publicly available Rimes database.
KW - Decision trees
KW - Off-line handwriting recognition
KW - State position clustering
UR - https://www.scopus.com/pages/publications/80053082353
U2 - 10.3166/dn.14.2.29-52
DO - 10.3166/dn.14.2.29-52
M3 - Article
AN - SCOPUS:80053082353
SN - 1279-5127
VL - 14
SP - 29
EP - 52
JO - Document Numerique
JF - Document Numerique
IS - 2
ER -