Grid-Calibrated Patch Learning for Braille Multi-Character Recognition
DOI:
https://doi.org/10.12928/biste.v8i1.15199Keywords:
Braille Recognition, Deep Learning, Multi-Braille Character (MBC), Grid Alignment, ResNet-101Abstract
The approach presents a multi braille character (MBC) recognition system for Indonesian syllablesdesigned to address real-world imaging variations. The proposed framework formulates 105-class visual classification task, where each class represents a two-character Braille unit. This design aims to preserve inter-character spatial relationships and reduce error propagation commonly found in single-character segmentation approaches. A carefully constructed dataset undergoes spatial pre-processing stages, including rotation normalization, grid assignment, and multicell cropping, resulting in uniform 89×89 pixel image patches that ensure geometric consistency across samples. To enhance model generalization under varying illumination conditions, single-dimension photometric augmentation is applied exclusively during training, including brightness (±25%), exposure (±20%), saturation (±40%), and hue (±30%). ResNet-101 is adopted as the backbone architecture based on prior comparative studies conducted on the same dataset, demonstrating its effectiveness in capturing fine-grained Braille dot shadow patterns. The network is trained for 300 epochs with a batch size of 32 under consistent experimental settings, and performance is evaluated using a confusion-matrix-based framework with overall accuracy as the primary metric. Experimental results indicate that moderate photometric reductions significantly improve recognition performance by preserving critical micro-contrast cues. In particular, an exposure reduction of −20% achieves the best balance between accuracy (86.13%) and training efficiency (14.12 minutes), outperforming the non-augmented baseline (74.37%, 22.10 minutes). A hue reduction of −30% further improves robustness to ambient color variations, while aggressive positive adjustments degrade performance due to structural distortion. These findings confirm the effectiveness of the proposed MBC framework for practical Braille recognition in real-world environments.
References
T. Kausar, S. Manzoor, A. Kausar, Y. Lu, M. Wasif, and M. A. Ashraf, “Deep Learning Strategy for Braille Character Recognition,” IEEE Access, vol. 9, pp. 169357–169371, 2021, https://doi.org/10.1109/ACCESS.2021.3138240.
A. AlSalman, A. Gumaei, A. AlSalman, and S. Al-Hadhrami, “A Deep Learning-Based Recognition Approach for the Conversion of Multilingual Braille Images,” Computers, Materials & Continua, vol. 67, no. 3, pp. 3847–3864, 2021, https://doi.org/10.32604/cmc.2021.015614.
K. Banerjee, A. Singh, N. Akhtar, and I. Vats, “Machine-Learning-Based Accessibility System,” SN Comput Sci, vol. 5, no. 3, p. 294, 2024, https://doi.org/10.1007/s42979-024-02615-9.
R. Li, H. Liu, X. Wang, and Y. Qian, “Effective Optical Braille Recognition Based on Two-Stage Learning for Double-Sided Braille Image,” In Pacific Rim International Conference on Artificial Intelligence, pp. 150–163, 2019, https://doi.org/10.1007/978-3-030-29894-4_12.
S. Kumari, A. Akole, P. Angnani, Y. Bhamare, and Z. Naikwadi, “Enhanced Braille Display Use of OCR and Solenoid to Improve Text to Braille Conversion,” in 2020 International Conference for Emerging Technology (INCET), pp. 1–5, 2020, https://doi.org/10.1109/INCET49848.2020.9153996.
I. G. Ovodov, “Optical Braille Recognition Using Object Detection Neural Network,” in 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 1741–1748, 2021, https://doi.org/10.1109/ICCVW54120.2021.00200.
Z. Khanam and A. Usmani, “Optical Braille Recognition using Circular Hough Transform,” arXiv preprint arXiv:2107.00993, 2021, https://doi.org/10.48550/arXiv.2107.00993.
Ramiati, S. Aulia, Lifwarda, and S. N. Nindya Satriani, “Recognition of Image Pattern To Identification Of Braille Characters To Be Audio Signals For Blind Communication Tools,” IOP Conf Ser Mater Sci Eng, vol. 846, no. 1, p. 012008, 2020, https://doi.org/10.1088/1757-899X/846/1/012008.
B. Meneses-Claudio, W. Alvarado-Diaz, and A. Roman-Gonzalez, “Classification System for the Interpretation of the Braille Alphabet through Image Processing,” Advances in Science, Technology and Engineering Systems Journal, vol. 5, no. 1, pp. 403–407, 2020, https://doi.org/10.25046/aj050151.
M. Mukhiddinov and S.-Y. Kim, “A Systematic Literature Review on the Automatic Creation of Tactile Graphics for the Blind and Visually Impaired,” Processes, vol. 9, no. 10, p. 1726, 2021, https://doi.org/10.3390/pr9101726.
Jonnatan Arroyo, Ramiro Velazquez, Mehdi Boukallel, Nicola Ivan Giannoccaro, and Paolo Visconti, “Design and Implementation of a Low-Cost Printer Head for Embossing Braille Dots on Paper,” International Journal of Emerging Trends in Engineering Research, vol. 8, no. 9, pp. 6183–6190, 2020, https://doi.org/10.30534/ijeter/2020/206892020.
L. N. Hayati et al., “Improving Indonesian Sign Alphabet Recognition for Assistive Learning Robots Using Gamma-Corrected MobileNetV2,” Buletin Ilmiah Sarjana Teknik Elektro, vol. 7, no. 3, pp. 350–361, 2025, https://doi.org/10.12928/biste.v7i3.13300.
A. Mujahid et al., “Real-Time Hand Gesture Recognition Based on Deep Learning YOLOv3 Model,” Applied Sciences, vol. 11, no. 9, p. 4164, 2021, https://doi.org/10.3390/app11094164.
A. Kloska, M. Tarczewska, A. Giełczyk, S. M. Kloska, and A. Michalski, “Influence of augmentation on the performance of double ResNet-based model for chest X-rays classification,” Pol J Radiol, vol. 88, pp. 244–250, 2023, https://doi.org/10.5114/pjr.2023.126717.
B. Li, Y. Hou, and W. Che, “Data augmentation approaches in natural language processing: A survey,” AI Open, vol. 3, pp. 71–90, 2022, https://doi.org/10.1016/j.aiopen.2022.03.001.
M. Ayu et al., “Generalized Deep Learning Approach for Multi Braille Character (MBC) Recognition,” Buletin Ilmiah Sarjana Teknik Elektro, vol. 7, no. 3, pp. 434–449, 2025, https://doi.org/10.12928/biste.v7i3.13891.
I Made Agus Dwi Suarjaya, B. A. Wiratama, and Ayu Wirdiani, “Sistem Pengenalan Huruf Braille Menggunakan Metode Deep Learning Berbasis Website,” JITSI : Jurnal Ilmiah Teknologi Sistem Informasi, vol. 5, no. 3, pp. 93–99, 2024, https://doi.org/10.62527/jitsi.5.3.244.
A. A. Wicaksana and A. N. Handayani, “Comparation Analysis of Otsu Method for Image Braille Segmentation : Python Approaches,” Indonesian Journal of Data and Science, vol. 6, no. 2, pp. 175–183, 2025, https://doi.org/10.56705/ijodas.v6i2.268.
Y. Xia, R. Xie, X. Wu, Y. Zhao, P. Sun, and H. Chen, “The role of phonological awareness, morphological awareness, and rapid automatized naming in the braille reading comprehension of Chinese blind children,” Learn Individ Differ, vol. 103, p. 102272, 2023, https://doi.org/10.1016/j.lindif.2023.102272.
G. Liu, S. Tian, Y. Mo, R. Chen, and Q. Zhao, “On the Acquisition of High-Quality Digital Images and Extraction of Effective Color Information for Soil Water Content Testing,” Sensors, vol. 22, no. 9, p. 3130, 2022, https://doi.org/10.3390/s22093130.
S. Shokat, R. Riaz, S. S. Rizvi, I. Khan, and A. Paul, “Characterization of English Braille Patterns Using Automated Tools and RICA Based Feature Extraction Methods,” Sensors (Basel), vol. 22, no. 5, 2022, https://doi.org/10.3390/s22051836.
S. S. M., S. A., J. Raju, and R. M. George, “BrailleSegNet: A novel methodology for Braille dataset generation and character segmentation,” Displays, vol. 90, p. 103145, 2025, https://doi.org/10.1016/j.displa.2025.103145.
A. Al-Salman and A. AlSalman, “Fly-LeNet: A deep learning-based framework for converting multilingual braille images,” Heliyon, vol. 10, no. 4, p. e26155, 2024, https://doi.org/10.1016/j.heliyon.2024.e26155.
N. Elaraby, S. Barakat, and A. Rezk, “A generalized ensemble approach based on transfer learning for Braille character recognition,” Inf Process Manag, vol. 61, no. 1, p. 103545, 2024, https://doi.org/10.1016/j.ipm.2023.103545.
E. M. Torralba, “Fibonacci Numbers as Hyperparameters for Image Dimension of a Convolu-tional Neural Network Image Prognosis Classification Model of COVID X-ray Images,” International Journal of Multidisciplinary: Applied Business and Education Research, vol. 3, no. 9, pp. 1703–1716, 2022, https://doi.org/10.11594/ijmaber.03.09.11.
S. Roy et al., “Fibonacci-Net: A Lightweight CNN model for Automatic Brain Tumor Classification,” Mar. 2025, https://doi.org/10.48550/arXiv.2503.13928.
K. Panetta, F. Sanghavi, S. Agaian, and N. Madan, “Automated Detection of COVID-19 Cases on Radiographs using Shape-Dependent Fibonacci-p Patterns,” IEEE J Biomed Health Inform, vol. 25, no. 6, pp. 1852–1863, 2021, https://doi.org/10.1109/JBHI.2021.3069798.
B.-M. Hsu, “Braille Recognition for Reducing Asymmetric Communication between the Blind and Non-Blind,” Symmetry (Basel), vol. 12, no. 7, p. 1069, 2020, https://doi.org/10.3390/sym12071069.
V. P. Revelli, G. Sharma, and S．Kiruthika devi, “Automate extraction of braille text to speech from an image,” Advances in Engineering Software, vol. 172, p. 103180, 2022, https://doi.org/10.1016/j.advengsoft.2022.103180.
C. Li and W. Yan, “Braille Recognition Using Deep Learning,” in 2021 4th International Conference on Control and Computer Vision, pp. 30–35, 2021, https://doi.org/10.1145/3484274.3484280.
L. Lu, D. Wu, J. Xiong, Z. Liang, and F. Huang, “Anchor-Free Braille Character Detection Based on Edge Feature in Natural Scene Images,” Comput Intell Neurosci, vol. 2022, pp. 1–11, 2022, https://doi.org/10.1155/2022/7201775.
Z. Tian et al., “A Survey of Deep Learning-Based Low-Light Image Enhancement.,” Sensors (Basel), vol. 23, no. 18, 2023, https://doi.org/10.3390/s23187763.
Z. Jingchun, G. Eg Su, and M. Shahrizal Sunar, “Low-light image enhancement: A comprehensive review on methods, datasets and evaluation metrics,” Journal of King Saud University - Computer and Information Sciences, vol. 36, no. 10, p. 102234, 2024, https://doi.org/10.1016/j.jksuci.2024.102234.
K. Alomar, H. I. Aysel, and X. Cai, “Data Augmentation in Classification and Segmentation: A Survey and New Strategies,” J Imaging, vol. 9, no. 2, p. 46, 2023, https://doi.org/10.3390/jimaging9020046.
J. Wu, B. Ding, B. Zhang, and J. Ding, “A Retinex-based network for image enhancement in low-light environments,” PLoS One, vol. 19, no. 5, p. e0303696, 2024, https://doi.org/10.1371/journal.pone.0303696.
L. Lu, D. Wu, J. Xiong, Z. Liang, and F. Huang, “Anchor-Free Braille Character Detection Based on Edge Feature in Natural Scene Images,” Comput Intell Neurosci, vol. 2022, pp. 1–11, 2022, https://doi.org/10.1155/2022/7201775.
S. Shokat, R. Riaz, S. S. Rizvi, A. M. Abbasi, A. A. Abbasi, and S. J. Kwon, “Deep learning scheme for character prediction with position-free touch screen-based Braille input method,” Human-centric Computing and Information Sciences, vol. 10, no. 1, p. 41, 2020, https://doi.org/10.1186/s13673-020-00246-6.
W. Hassan, J. B. Joolee, and S. Jeon, “Establishing haptic texture attribute space and predicting haptic attributes from image features using 1D-CNN,” Sci Rep, vol. 13, no. 1, p. 11684, 2023, https://doi.org/10.1038/s41598-023-38929-6.
J. Huang, K. Zhou, W. Chen, and H. Song, “A pre-processing method for digital image correlation on rotating structures,” Mech Syst Signal Process, vol. 152, p. 107494, May 2021, https://doi.org/10.1016/j.ymssp.2020.107494.
Y. Ho and A. Mostafavi, “Multimodal Mamba with multitask learning for building flood damage assessment using synthetic aperture radar remote sensing imagery,” Computer-Aided Civil and Infrastructure Engineering, vol. 40, no. 26, pp. 4401–4424, 2025, https://doi.org/10.1111/mice.70059.
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Made Ayu Dusea Widyadara, Anik Nur Handayani, Heru Wahyu Herwanto, Tony Yu; Marga Asta Jaya Mulya
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
This journal is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
