<![CDATA[Braille letters are used as a written language for people with visual impairments. To this day, Braille letters are used in in inclusive schools where they are taught to disabled students. However, there are physical capability barriers faced by teachers when correcting Braille answer sheets written by visually impaired students. The ability to read Braille letters is also important for family members to support the students' learning process. This research’s purpose was to create a system that can transliterate Braille letters into the Latin alphabet using deep learning methods. The proposed deep learning methods include Base Convolutional Neural Network (CNN), ResNet50, VGG-16, and Inception-v3. The Braille Character image dataset used consists of 12,641 data divided into 37 classes from the AEyeAlliance repository. The Base CNN model used achieved 98% training accuracy, 99% validation accuracy, and 99.1% testing accuracy.]]>
Copyrights © 2024
