Pattern recognition based on neural network for sign language interpretation system using flexes sensor

Author(s):  
D.A. Kadhim ◽  
O. Obaid
Author(s):  
Pias Paul ◽  
Moh. Anwar-Ul-Azim Bhuiya ◽  
Md. Ayat Ullah ◽  
Molla Nazmus Saqib ◽  
Nabeel Mohammed ◽  
...  

2014 ◽  
Vol 6 (37) ◽  
pp. 170
Author(s):  
Yulia Sergeevna Manueva ◽  
Mikhail Gennadyevich Grif ◽  
Andrei Nikolaevich Kozlov

Author(s):  
SARGUR N. SRIHARI

A gradation of pattern discrimination problems is encountered in interpreting handwritten postal addresses. There are several multiclass discrimination problems, including handwritten numeral recognition with 10 classes, alphanumeral recognition with 36 classes, and touching-digit pair recognition with 100 classes. Word recognition with a lexicon is a problem where the number of classes varies from a few to about a thousand. Some of the discrimination techniques, particularly those with few classes, lend themselves well to neural network classification, while others are better handled by Bayesian polynomial and nearest-neighbor methods. This paper describes each of the discrimination problems and the performances of each of the subsystems in a handwritten address interpretation system developed at CEDAR.


2019 ◽  
Vol 7 ◽  
pp. 38-41
Author(s):  
Artem Sharapov ◽  
Ruslan Grishin

The possibility of using computer vision libraries for sign language interpretation. The specialized software required for the development of sign language interpretation system is analyzed. The configuration and testing of public libraries of computer vision are carried out.


2019 ◽  
Vol 1362 ◽  
pp. 012034 ◽  
Author(s):  
Golda Jeyasheeli P ◽  
Annapoorani K Miss

Sign in / Sign up

Export Citation Format

Share Document