Title :
HMM Based Handwritten Word Recognition System by Using Singularities
Author :
Impedovo, Sebastiano ; Ferrante, Anna ; Modugno, Raffaele
Author_Institution :
Dipt. di Inf., Univ. di Bari, Bari, Italy
Abstract :
This paper presents a new approach for handwritten word recognition based on hidden Markov model theory and the sliding windows technique. The new approach uses specific singularity markers to support the recognition phase: the static marker and the dynamic marker. Moreover, different strategies for sliding windows step are considered: regular step and progressive step. Experimental results showing the improvements obtained for basic word lexicon recognition are reported in the paper.
Keywords :
handwritten character recognition; hidden Markov models; image recognition; HMM; dynamic marker; handwritten word recognition system; hidden Markov model theory; progressive step; regular step; singularity marker; sliding window technique; static marker; Character recognition; Computer networks; Handwriting recognition; Hidden Markov models; Histograms; Humans; Impedance; Prototypes; Speech recognition; Text analysis; Basic Words; Hidden Markov Models; Pattern Recognition; Singularities; Sliding Windows;
Conference_Titel :
Document Analysis and Recognition, 2009. ICDAR '09. 10th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
978-1-4244-4500-4
Electronic_ISBN :
1520-5363
DOI :
10.1109/ICDAR.2009.73
