A Deep Learning-Based Recognition Approach for the Conversion of Multilingual Braille Images

作     者：Abdulmalik AlSalman Abdu Gumaei Amani AlSalman Suheer Al-Hadhrami 

作者机构：Department of Computer ScienceCollege of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Department of Special EducationCollege of EducationKing Saud UniversityRiyadh11543Saudi Arabia 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2021年第67卷第6期

页      面：3847-3864页

核心收录：

学科分类：0711[理学-系统科学] 07[理学] 08[工学] 081101[工学-控制理论与控制工程] 0811[工学-控制科学与工程] 071102[理学-系统分析与集成] 081103[工学-系统工程] 

基　　金：funded by the National Plan for Science Technology and Innovation(MAARIFAH) King Abdulaziz City for Science and Technology Kingdom of Saudi Arabia Award Number(5-18-03-001-0004) 

主　　题：Optical Braille recognition OBR Braille cells blind sighted deep learning deep convolutional neural network 

摘      要：Braille-assistive technologies have helped blind people to write,read,learn,and communicate with sighted individuals for many *** technologies enable blind people to engage with society and help break down communication barriers in their *** Optical Braille Recognition(OBR)system is one example of these *** plays an important role in facilitating communication between sighted and blind people and assists sighted individuals in the reading and understanding of the documents of Braille ***,a clear gap exists in current OBR systems regarding asymmetric multilingual conversion of Braille *** systems allow sighted people to read and understand Braille documents for self-learning *** this study,we propose a deep learning-based approach to convert Braille images into multilingual *** is achieved through a set of effective steps that start with image acquisition and preprocessing and end with a Braille multilingual mapping *** develop a deep convolutional neural network(DCNN)model that takes its inputs from the second step of the approach for recognizing Braille *** experiments are conducted on two datasets of Braille images to evaluate the performance of the DCNN *** rst dataset contains 1,404 labeled images of 27 Braille symbols representing the alphabet *** second dataset consists of 5,420 labeled images of 37 Braille symbols that represent alphabet characters,numbers,and *** proposed model achieved a classication accuracy of 99.28%on the test set of the rst dataset and 98.99%on the test set of the second *** results conrm the applicability of the DCNN model used in our proposed approach for multilingual Braille conversion in communicating with sighted people.