Home
Angelina Dataset (see "links" section) consists of 240 labeled images with Braille text (colored, 96 dpi, usually 1024x1344 or 1024x1376 pixels), divided into a train set (212 pictures) and a validation set (28 pictures). Braille text is written in a 6-dot code, each letter is formed by 1 to 6 raized dots located in a 2*3 cell. A label corresponds to a single character; the character location is defined by two points (its upper left and lower right corners). An image may contain recto as well as verso dots; only recto dots should be detected.
| Double-sided Braille book | Single-sided Braille writing |
|---|---|
 |
 |
The primary goal is to build a detector that recognizes Braille characters on validation images with high accuracy (in accordance with the IoU loss), presumably using the training dataset.
The next goal, which I will aim only if I succeed in the first one, is to add more images to the Angelina Dataset which contain Braille characters not only from books and Braille paper sheets but also those from Braille plates and other materials such as Braille Contraction cards used by students; then build a new detection system that will perform well on the new data, too.
In addition, I plan to combine the dataset with unlabeled images that I will shoot at home, in the Library for the Blind, Rehabilitation Center For The Blind, etc., in order to improve the detection performance using semi-supervised learning (e.g. semi-supervised data mining).
Examples of Braille text recognition (pages from the book by V. V. Golubina)
Raw input images are on the left and corresponding results (produced by AngelinaReader software) are on the right.
There are few mistakes but in general the result reflects the true mapping.
- Angelina Braille Reader, the state-of-the-art Braille OCR system | GitHub
- Angelina Dataset | GitHub
- DataSet of Braille Images mod. Ilya Ovodov | GitHub
- Elena Fomina's Flutter cross-platform Braille OCR app | git.asi.ru
- Braille data collection | git.asi.ru
- Braille OCR system | GitHub
- Braille Character Dataset | Kaggle
- Braille Classifier (Keras) | Kaggle
- Braille tiles recognition (R-CNN, PyTorch) | GitHub + Jupyter Notebook Viewer
- Optical Braille recognition | Wikipedia
- Optical Braille Recognition Using Object Detection CNN | Ilya G. Ovodov | ArXiV, 2020
- Optical Braille Recognition Based on Semantic Segmentation Network with Auxiliary Learning Strategy | Xiandong Wang et al | ResearchGate, 2020 (the same people that made DSBI)
- Smart OCR for Visually Challenged People| Devarsh Bhupatkar et al | SemanticScholar, 2019
- DSBI: Double-Sided Braille Image Dataset and Algorithm Evaluation for Braille Dots Detection | Renqiang Li et al | ArXiV, 2018
- A Novel and Efficient Algorithm to Recognize Any Universally Accepted Braille Characters: A Case with Kannada Language | C.N. Ravi Kumar | IEEEXplore, 2014
- Software algorithm prototype tor optical recognition of embossed Braille | L. Wong et al | ResearchGate, 2004
- A BRAILLE O.C.R. FOR BLIND PEOPLE | X. F. Hermida et al | SemanticScholar, 2003
- A Braille O.C.R. for Blind People | X. F. Hermida et al | ResearchGate, 1996
- List of papers on SSL for object detection (part of Awesome SSL) | GitHub, updated in 2021
- Consistency-based Semi-supervised Learning for Object detection | Jisoo Jeong et al | NeurIPS proceedings, 2019
- Watch and Learn: Semi-Supervised Learning of Object Detectors from Videos | Ishan Misra et al | ArXiV, 2015