Cursive Arabic Handwriting Recognition System Without Explicit Segmentation Based on Hidden Markov Models

Abstract : In this paper we present a system for offline recognition cursive Arabic handwritten text which is analytical without explicit segmentation based on Hidden Markov Models (HMMs). Extraction features preceded by baseline estimation are statistical and geometric to integrate both the peculiarities of the text and the pixel distribution characteristics in the word image. These features are modelled using hidden Markov models. The HMM-based classifiercontains a training module and a recognition module. The training module estimates the parameters of each of the character HMMs uses the Baum-Welchalgorithm. In the recognition phase, feature vectors extracted from an image are passed to a network of word lexicon entries formed of character models. The character sequence providing the maximumlikelihood identifies the recognized entry. If required, the recognition can generate N best output hypotheses rather than just the single best one. To determine the best output hypotheses, the Viterbi algorithm is used.The experiments on images of the benchmark IFN/ENIT database show that the proposed system improves recognition.
Document type :
Journal articles
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01458216
Contributor : Mouhcine Rabi <>
Submitted on : Thursday, February 9, 2017 - 7:41:21 PM
Last modification on : Thursday, July 4, 2019 - 3:50:16 PM
Long-term archiving on : Wednesday, May 10, 2017 - 12:19:12 PM

Files

VSST paper.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-01458216, version 1

Collections

Citation

Mouhcine Rabi, Mustapha Amrouch, Zouhair Mahani. Cursive Arabic Handwriting Recognition System Without Explicit Segmentation Based on Hidden Markov Models. Journal of Data Mining and Digital Humanities, Episciences.org, 2018, Special Issue on Scientific and Technological Strategic Intelligence (2016). ⟨hal-01458216⟩

Share

Metrics

Record views

869

Files downloads

1070