Off-line handwritten signature verification based on machine learning
U. Yu. AkhundjanovFerghana branch of Tashkent university of information technologies named after Muhammad al-Kwarizmi., Ferghana, UzbekistanBakhrom SoliyevFerghana branch of Tashkent university of information technologies named after Muhammad al-Kwarizmi., Ferghana, UzbekistanNurmakhamad JuraevFerghana branch of Tashkent university of information technologies named after Muhammad al-Kwarizmi., Ferghana, UzbekistanKhurshid MusayevFerghana branch of Tashkent university of information technologies named after Muhammad al-Kwarizmi., Ferghana, UzbekistanMuhammadyunus NorinovFerghana branch of Tashkent university of information technologies named after Muhammad al-Kwarizmi., Ferghana, UzbekistanZarina ErmatovaFerghana branch of Tashkent university of information technologies named after Muhammad al-Kwarizmi., Ferghana, UzbekistanRakhmatullo ZaynabidinovFerghana branch of Tashkent university of information technologies named after Muhammad al-Kwarizmi., Ferghana, Uzbekistan
ABI
Аннотация
This paper describes the results of recognizing handwritten signatures. For the experiments, the database of handwritten signatures BHSig260-Bengali, BHSig260-Hindi, CEDAR and TUIT was used. For classification, four options were used to reduce the signatures to sizes: 200×120, 250×150, 300×150 and 400×200 pixels. These images served as input for the proposed network architecture. As a result of testing the proposed approach, the average accuracy of correct classification of signatures on images of size 250×150 was achieved: for the CEDAR database it was 94.38%, for the BHSig260-Hindi database it was 95.63%, for the BHSig260-Bengali database it was 97.50% and for TUIT base is 90.04%.
Темы
Идентификаторы
Цитирования и источники
Показатели — AkademScholar · Скоро