HMM Based Handwritten Word Recognition System by Using Singularities

This paper presents a new approach for Handwritten Word Recognition based on Hidden Markov Model theory and the sliding window 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 window step are considered: Regular Step and Progressive Step. Experimental results showing the improvements obtained for basic word lexicon recognition are reported in the paper.

• Type: Journal
• Year: 2009
• Where: ICDAR
• Authors: Sebastiano Impedovo, Anna Ferrante, Raffaele Modugno
• Keywords: Document Analysis, Handwritten Word Recognition, Hidden Markov Model, ICDAR 2009, Word Lexicon Recognition