New optical sensor reads Braille at the speed of touch

WASHINGTON — Researchers have developed a fast and accurate flexible optical skin that can be used to read Braille. The advance could not only improve access to information for people who are blind but also helps move us closer to a future where accessible and adaptable technology can benefit everyone.

“Braille, which is made of tiny raised dots, requires very precise sensors to be read correctly,” said research team leader Zhuo Wang from Beijing Normal University in China. “Traditional sensors struggle with this, especially for dynamic tasks like reading Braille as a person moves their finger over it in real-time. Our sensor can handle tiny Braille details accurately and quickly.”

In the Optica Publishing Group journal Optics Express, the researchers describe the new sensor, which consists of an optical fiber ring resonator embedded in soft PDMS material that acts like a flexible optical skin. When pressure is applied, the sensor measures the resulting frequency changes in the light and converts them into readable data. In tests, they showed that the system, when combined with neural network data processing methods, could quickly and accurately read Braille letters, numbers and punctuation.

“This technology could lead to faster, more accurate smart readers that read Braille and convert it to speech or text without the user having to learn Braille,” said Heng Wang, a research team member from Shenyang Aerospace University in China. “This could help Braille become more widespread in public spaces, on digital platforms and in education. The impact could also extend to other fields where sensitive tactile sensing is needed, from smart medical devices to the next generation of robots.”

Creating a flexible Braille reader

Learning and reading Braille can be challenging, making automated Braille readers essential, especially for older individuals who lose their vision later in life. Optical tactile sensors are precise, flexible and resistant to interference, but their tactile detection sensitivity and issues with environmental disturbances limit their ability to accurately recognize smaller Braille dots.

To create a sensitive and reliable touch sensor, the researchers embedded an optical fiber ring resonator — a device made from a loop of optical fiber with light circulating through it — into a soft material known as PDMS. This provided flexibility similar to skin, allowing the sensor to bend and feel pressure. When a user presses the sensor onto Braille dots, the pressure slightly bends the fiber, which changes the resonant frequency of the resonator.

The researchers used a technique called Pound-Drever-Hall (PDH) frequency locking to convert the small frequency changes into readable data. This approach keeps the light signal stable even in dynamic environments so that readings are accurate no matter what else is happening around the sensor.

They also drew on machine learning to enhance the device's accuracy. They used a Multilayer Perceptron Neural Network, which is used to perform complex tasks like pattern recognition, to help with recognition of specific Braille patterns. A Long Short-Term Memory network, which is designed to effectively learn and retain long-term dependencies in sequential data, aided in turning sequences of Braille into readable text or words.

Reading Braille in real-time

The researchers tested the sensor by having it read Braille with different levels of pressure and touch. The sensor identified eight different Braille patterns with 98.57% accuracy. It also recognized Braille characters in dynamic settings, such as when the sensor slides over a Braille board, mimicking real-world usage. The sensor could respond to pressure in less than 0.1 seconds and could read an entire Braille word correctly, even with slight variations in each character.

“This system is far more precise than older Braille-reading technologies that might miss imperfectly pressed dots,” said Rui Min from Beijing Normal University, coauthor of the paper with Lin Ma from Shenyang Aerospace University. “The flexible optical fiber resonator detects very small pressure differences, and PDH frequency locking ensures stability and accuracy, even with changing light or power fluctuations. Machine learning further enhances the system, allowing it to recognize Braille despite minor errors or pressure variations.”

The researchers are now working to make the sensor even more robust for real-world use. This involves optimizing it for different devices, reducing costs and improving its durability. They are also improving the integration of machine learning models to manage more complex Braille reading tasks.

Paper: H. Wang, L. Ma, Q. Nie, X. Hu, X. Li, R. Min, Z. Wang, “Optical tactile sensor based on flexible optical fiber ring resonator for intelligent Braille recognition,” Opt. Express 33, 2512-2528 (2025).

DOI: https://doi.org/10.1364/OE.546873

About Optica Publishing Group

Optica Publishing Group is a division of the society, Optica, Advancing Optics and Photonics Worldwide. It publishes the largest collection of peer-reviewed and most-cited content in optics and photonics, including 18 prestigious journals, the society’s flagship member magazine, and papers and videos from more than 835 conferences. With over 400,000 journal articles, conference papers and videos to search, discover and access, our publications portfolio represents the full range of research in the field from around the globe.

About Optics Express

Optics Express reports on scientific and technology innovations in all aspects of optics and photonics. The bi-weekly journal provides rapid publication of original, peer-reviewed papers. It is published by Optica Publishing Group and led by Editor-in-Chief James Leger of the University of Minnesota, USA. Optics Express is an open-access journal and is available at no cost to readers online.  For more information, visit Optics Express.

Media Contact

mediarelations@optica.org