FIGURE 1 - available via license: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Content may be subject to copyright.
Source publication
People with vision impairment use Braille language for reading, writing, and communication. The basic structure of the Braille language consists of six dots arranged in three rows and two column cells, which are identified by visually impaired people using finger touch. However, it is difficult to memorize the pattern of dots that form the Braille...
Contexts in source publication
Context 1
... is hard for these visually impaired people to read and write text, so they use Braille, a system of raised dots that can be read by the sense of finger touch [2]. The basic structure of Braille system is matrix of six dots aligned in 3x2 order as shown in Figure 1a. Each character in a Braille cell is formed by arrangement of these six dots in a special manner. ...
Context 2
... a dot may be raised at any combination for the six positions hence, in total 64 combinations are available (2 ^6 = 64). In Braille, every character is identified by pattern formed by the dots that are raised in cell, The codes of Braille characters, alphabets, and symbols formed through different combinations of Braille dots are shown in Figure 1b. Due to its effectiveness, Braille system is used worldwide by visually impaired for written communication. ...
Citations
... In recent years, the classification of Braille patterns is predominantly performed using various deep learning models and few works used SVM (Support Vector Machine) which have also shown accuracy over 90%. A lightweight CNN model with IRB(Inverted Residual Block) was used to identify Braille patterns from two datasets; one consisting of English Braille and the other one was of Chinese Braille in [4]. Different types of image preprocessing techniques were also used for aligning and enhancing the training images. ...
... It was found that a tilt of 1.5 degrees would make the system unable to recognize the pattern. Similar to the previously mentioned paper [4], they have also used various preprocessing techniques like cropping, thresholding, dilation, erosion and greyscale image preprocessing techniques. In [6], a deep neural network was proposed to identify the Braille characters. ...
... Method Accuracy (%) Kausar et al. [4] CNN 95.2 Subur et al. [5] FC + ANN 99 Kawabe et al. [7] AlexNet In conclusion, the BrailleSense system represents a significant leap forward in assisting visually impaired individuals in learning and utilizing the Braille system. Through the deployment of a custom Convolutional Neural Network (CNN) model on a Raspberry Pi, our system achieves an impressive accuracy of 97.44%, showcasing its potential for real-world applications. ...
Individuals with visual impairments face challenges accessing written information. Braille is one of many solutions that only requires the reader to sense the depth of the paper with their hand to comprehend written information without the need to look at the text. However, learning Braille, especially for those losing sight later in life, presents difficulties. This research introduces the BrailleSense system, a technological solution designed to assist visually impaired individuals in learning and utilizing the Braille system effectively. The system features a virtual prototype of hand gloves equipped with a camera, aiming to alleviate challenges associated with Braille pattern memorization. Key contributions include the development of a custom lightweight Convolutional Neural Network (CNN) model for Braille pattern classification coined as the BrailleNet. This model is then deployed on a Raspberry Pi to investigate the feasibility of working with resource-limited portable devices, BrailleNet achieves an impressive accuracy of 97.44% under real-world constraints. The research outlines the conceptual design through a 3D model of the gloves, addressing spatial allocation. Acknowledging challenges in user comfort and alignment, BrailleSense presents a pioneering step towards empowering visually impaired individuals, enhancing literacy, and fostering independence. The dataset and code for the BrailleSense system are available on GitHub-https://github.com/faiyazabdullah/BrailleNet
... To leverage a small dataset, the study used data augmentation to train their CNN model and achieved a test accuracy of 97.74%. A number of other studies [12][13][14]16,[30][31][32][33][34][35] used the data augmentation technique to overcome the data deficiency problem and to get commendable accuracy in the task of character recognition or classification. Another study [13] used a Multi-Augmentation Technique and Adaptive Gaussian Convolutional Autoencoder (MAT-AGCA) to recognize lontar manuscript characters, the ancient Balinese letter written on palm leaves. ...
... The model has three maxpooling layers after each convolution layer with a 2 × 2 kernel and two fully connected layers at the end, producing a test accuracy of 94%. A great deal of studies [1,2,[21][22][23]28,[31][32][33][37][38][39][40] confirmed that the CNN model outperformed in character recognition tasks compared to other existing deep learning models. In particular, Sakib, Nazmus et al. [1] used the CNN model to perform handwritten character recognition on two open source datasets (Kagle and MNIST) achieving higher accuracy than using other performant models. ...
The automatic character recognition of historic documents gained more attention from scholars recently, due to the big improvements in computer vision, image processing, and digitization. While Neural Networks, the current state-of-the-art models used for image recognition, are very performant, they typically suffer from using large amounts of training data. In our study we manually built our own relatively small dataset of 404 characters by cropping letter images from a popular historic manuscript, the Electronic Beowulf. To compensate for the small dataset we use ImageDataGenerator, a Python library was used to augment our Beowulf manuscript’s dataset. The training dataset was augmented once, twice, and thrice, which we call resampling 1, resampling 2, and resampling 3, respectively. To classify the manuscript’s character images efficiently, we developed a customized Convolutional Neural Network (CNN) model. We conducted a comparative analysis of the results achieved by our proposed model with other machine learning (ML) models such as support vector machine (SVM), K-nearest neighbor (KNN), decision tree (DT), random forest (RF), and XGBoost. We used pretrained models such as VGG16, MobileNet, and ResNet50 to extract features from character images. We then trained and tested the above ML models and recorded the results. Moreover, we validated our proposed CNN model against the well-established MNIST dataset. Our proposed CNN model achieves very good recognition accuracies of 88.67%, 90.91%, and 98.86% in the cases of resampling 1, resampling 2, and resampling 3, respectively, for the Beowulf manuscript’s data. Additionally, our CNN model achieves the benchmark recognition accuracy of 99.03% for the MNIST dataset.
People with normal vision can easily see the world around them and can read and write without difficulty. For those who are visually impaired, the Braille script enables them to read and write just like sighted individuals. According to WHO data from 2023, about 15 million people worldwide have significant vision loss. The Braille system uses cells with six raised dots, each dot numbered from one to six, arranged in two columns. This system is crucial for visually impaired individuals to keep up with the world around them. Providing Braille-assisted technology and incorporating it into daily life is essential to make life more comfortable and efficient for visually impaired people, enabling better communication with others. Key Words: Braille script, OBR.
Braille letters are letters used by blind people to exchange and get information from written media. Because Braille letters are different from the usual alphabet, it requires the ability to read Braille letters where the role of teachers is needed to teach Braille letters to the blind. This paper aims to facilitate prospective teachers and people who want to learn braille letters. The system designed is a website that classifies braille letters using deep learning with the convolutional neural network (CNN) method with the activation functions used, namely ReLU and Softmax. In this research, the input is an image of braille letters with grayscale elements. The output of the data is a regular alphabet letter. Most of this research data consists of training and testing data, which is 2,722 pieces. The accuracy results obtained in the data training process using Max Pooling and epoch 30 for data is 92.15%, epoch 50 is 94.58%, and for training data with epoch 100 is 96.64%. The test results using the system produce an accuracy value of all braille letter image data of 92.30%. Furthermore, for better system development, it is recommended to use hyperparameter tuning to minimize classification uncertainty in braille letter images.
Braille character recognition(BCR) is a basic step in building and designing any Braille assistive
technology. Each Braille character is represented by a 2 × 3 matrix of raised dots (called a cell),
which can be read by touch. This study introduces a generalized recognition approach based on
an ensemble of transfer learning models for BCR. The study experiments are performed on two
benchmark English Braille datasets (handwritten Braille – Omniglot (HBO), and Braille character
(BC)), and a new dataset of Arabic Braille characters collected by our group called Arabic Braille
(AB). First, we investigate the performance of 17- transfer learning models on the three datasets.
Then, we build three ensemble approaches based on majority voting from the most effective two,
three, and four models in each dataset. The experimental results reveal that the ensemble of
DarkNet-53, GoogleNet, SqueezeNet, and DenseNet-201 is a more generalizable ensemble
approach for BCR. It achieves a higher F1 score and lesser generalization error (Etest) value than
each individual transfer learning model. The F1 scores of the introduced ensemble reached
89.42%, 99.58%, and 97.11% on the HBO, BC, and AB datasets, respectively, with Etest values of
10.47%, 0.43%, and 3.23%. While the F1 scores of the DarkNet-53 which is the most effective
single model on the three datasets are 87.54%, 99.14%, and 94.73, with Etest values of 12.79%,
0.85%, and 5.31%, respectively.
