Creation of Uyghur offline handwritten database

Ubul, Kurban; Zunun, Mavjuda; Aysa, Alim; Yadikar, Nurbiya; Yunus, Umut

doi:10.1109/wosspa.2013.6602378

Cited by 2 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although, so far it has been established Uyghur handwritten document image database [16], but there is no a standard database for Uyghur handwritten signature. So, there is still much research space for creating or developing standard database that suitable for Uyghur handwriting signature recognition and verification field.…”

Section: E Cedar Databasementioning

confidence: 99%

Creation of Uyghur Off-Line Handwritten Signature Database

Yimin¹,

Gheni²,

Mahpirat³

et al. 2016

Proceedings of the 2016 2nd International Conference on Artificial Intelligence and Industrial Engineering (AIIE 2016)

Self Cite

View full text Add to dashboard Cite

Until now, there has not been any major international effort that aims at comparing different signature verification methods systematically. However, most of the disclosed handwritten signature database is based on Latin, Chinese, Arabic and other languages. So creation of Uyghur off-line signature database plays very important role in estimating and comparing research results that was achieved by different groups of researcher. In this paper, the signature samples are collected by different age's people. For off-line Uyghur signature recognition and verification research, there are 500 persons genuine signature. (20 samples of each person), 185 persons simple forgery signature and skilled forgery signature (20 samples of each person), in total 17400 signature samples were collected. Each handwriting signature samples is scanned, stored with bmp file, and pre-processed (such as graying, noise reduction and binarization etc).The Uyghur signatures database very useful for designing a signature recognition and verification system that is optimized to verify Uyghur signatures.

show abstract

Section: E Cedar Databasementioning

confidence: 99%