Department of Computer Science, Woldia Institute of Technology, Woldia University, Woldia, Ethiopia.
Department of Computer Science, Bahir Dar institute of technology, Bahir Dar University, Bahir Dar, Ethiopia.
Sci Rep. 2024 Oct 15;14(1):24172. doi: 10.1038/s41598-024-73895-7.
Braille, the most popular tactile-based writing system, uses patterns of raised dots arranged in cells to inscribe characters for visually impaired persons. Amharic is Ethiopia's official working language, spoken by more than 100 million people. To bridge the written communication gap between persons with and without eyesight, multiple Optical braille recognition systems for various language scripts have been developed utilizing both statistical and deep learning approaches. However, the need for half-character identification and character segmentation has complicated these systems, particularly in the Amharic script, where each character is represented by two braille cells. To address these challenges, this study proposed deep learning model that combines a CNN and a BiLSTM network with CTC. The model was trained with 1,800 line images with 32 × 256 and 48 × 256 dimensions, and validated with 200 line images and evaluated using Character Error Rate. The best-trained model had a CER of 7.81% on test data with a 48 × 256 image dimension. These findings demonstrate that the proposed sequence-to-sequence learning method is a viable Optical Braille Recognition (OBR) solution that does not necessitate extensive image pre and post processing. Inaddition, we have made the first Amharic braille line-image data set available for free to researchers via the link: https://github.com/Ne-UoG-git/Am-Br-line-image.github.io .
盲文是最流行的基于触觉的书写系统，它使用排列成单元格的凸起点模式来刻写字符，供视障人士使用。阿姆哈拉语是埃塞俄比亚的官方工作语言，有超过 1 亿人使用。为了弥合视力正常人和视障人士之间的书面交流差距，已经开发了多种光学盲文识别系统，用于各种语言脚本，利用统计和深度学习方法。然而，对半字符识别和字符分割的需求使这些系统变得复杂，特别是在阿姆哈拉语脚本中，每个字符由两个盲文单元格表示。针对这些挑战，本研究提出了一种深度学习模型，该模型结合了 CNN 和 BiLSTM 网络与 CTC。该模型使用具有 32×256 和 48×256 尺寸的 1800 行图像进行训练，并使用 200 行图像进行验证，并使用字符错误率进行评估。在具有 48×256 图像尺寸的测试数据上，最佳训练模型的 CER 为 7.81%。这些发现表明，所提出的序列到序列学习方法是一种可行的光学盲文识别（OBR）解决方案，不需要广泛的图像预处理和后处理。此外，我们通过以下链接免费向研究人员提供了第一个阿姆哈拉语盲文行图像数据集：https://github.com/Ne-UoG-git/Am-Br-line-image.github.io 。
