EUVIMEDEUVIMED entdecken
Crossref

Recognition of Handwritten Meitei Mayek Script Based on Texture Feature

Sanasam Inunganbi, Prakash Choudhary

International Journal on Natural Language Computing · 30.10.2018 · 7 (5) · 105-114

DOI: 10.5121/ijnlc.2018.7510 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal on Natural Language Computing, erschienen am 30.10.2018. Verfasst von Sanasam Inunganbi und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recognition of Manipuri Script called Meitei Mayek is still in the infant stage due to its complex structure. In this paper, an attempt has been made to develop an offline Meitei Mayek handwritten character recognition model by exploiting the texture feature, Local Binary Pattern (LBP). The system has been developed and evaluated on a large dataset consisting of 3,780 characters which are collected from different people of varying age group. The highest recognition rate achieved by the proposed method is 93.33% using Support Vector Machine (SVM). So, the contribution of this paper is bi-fold: firstly, a collection of a large handwritten corpus of Meitei Mayek Script and secondly developing character recognition model on the collected dataset.

Zitieren

APA

Inunganbi, S., & Choudhary, P. (2018). Recognition of Handwritten Meitei Mayek Script Based on Texture Feature. International Journal on Natural Language Computing, 7(5), 105-114. https://doi.org/10.5121/ijnlc.2018.7510

Vancouver

Inunganbi S, Choudhary P. Recognition of Handwritten Meitei Mayek Script Based on Texture Feature. International Journal on Natural Language Computing. 2018;7(5):105-114. doi:10.5121/ijnlc.2018.7510

BibTeX
@article{Inunganbi2018,
  author = {Inunganbi, Sanasam and Choudhary, Prakash},
  title = {Recognition of Handwritten Meitei Mayek Script Based on Texture Feature},
  journal = {International Journal on Natural Language Computing},
  year = {2018},
  volume = {7},
  number = {5},
  pages = {105--114},
  doi = {10.5121/ijnlc.2018.7510}
}
Kostenlos starten →