Li, CYan, Wei Qi2021-11-282021-11-282021-08-132021-08-13In 2021 4th International Conference on Control and Computer Vision (ICCCV'21). Association for Computing Machinery, New York, NY, USA, 30–35. DOI:https://doi.org/10.1145/3484274.3484280https://hdl.handle.net/10292/14743Text is the media to convey and transmit information. Braille is extremely important for vision impaired people to exchange information through reading and writing. A braille translator is crucial tool for aiding people to understand braille messages. In this paper, we implement character-based braille translator using ResNet, there are three versions of ResNet we implement for braille classifiers, including ResNet-18, ResNet-34, and ResNet-50. We also implement a word-based braille detector using a novel solution called Adaptive Bezier-Curve Network (ABCNet), which is a Scene Text Recognition (STR) method for detecting word-based text in natural scenes. A comparison is present to evaluate the performance of ABCNet.© ACM, 2021. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in PUBLICATION (see Citation), (see Publisher’s Version).Braille recognitionDeep learningConvolutional neural networkNatural scene text detectionConference ContributionOpenAccess10.1145/3484274.3484280