Dr. Abhishek Mandal, Ph.D.

Founder, Vision Science Academy, London, U.K.


Vision Science Academy Exclusive


Many efforts have been done to interface the human eye with the machines in a seamless way and much progress has been made in this field. Innovations like eye tracking were present as early as the 1980s and now even more practical and advanced technologies are being integrated into this development. The introduction of smartphones and portable devices have rendered the use of this interface technology even more successful and tremendous data is collected each day which guarantees even further innovations in the future.

How interfacing is achieved?

Interfacing with the eye gaze can be achieved in many ways (Santos, Santos, Jorge, & Abrantes, 2014). The earliest ways of interfacing included using physical implantation of electrodes surrounding the eye. The contraction of the muscles produces an electric current which is sensed by these electrodes and helps registers the eye movements. These signals can then be integrated with algorithms in the computer or machines to perform specific functions. In this way, the user achieves freedom from physical input and can control the interface with the mere blink of his eyes. This whole technique is called electrooculography (EOG) and forms the basis of modern day AI interfacing (Iáñez, Azorin, & Perez-Vidal, 2013).

The interfacing systems have now become largely independent of invasive approaches and use optical trackers instead. High-quality cameras are now able to detect intentional blinks and specific eye movements from the users. These actions are interpreted by means of algorithms and as a result, perform different actions. In a trial, people were able to navigate web pages and were able to emulate the functions of the keyboard and mouse just with the help of their vision. This interfacing holds great prospects for people who cannot speak or use their hands like in motor neuron disease, or paraplegia.

How can the data help improve AI?

As this technology becomes incorporated more and more into our daily lives, the data collected will be immense for the deep learning of new algorithms. The innovations are already making a large leap in eye care by early diagnosis of fatal diseases like age-related macular degeneration and diabetic retinopathy (Jacko et al., 2000). Eye-tracking and interfacing will help detect human behavior and can even be used to detect complex facial expressions and human emotions (Bozomitu, Păsărică, Tărniceriu, & Rotariu, 2019).

Apart from that, the AI algorithms can interpret the eye movements of psychiatric patients and help in their evaluation as well. AI has considerable success in detecting symptoms of anxiety in patients with attention deficit hyperactivity disorder (ADHD), autism, and bulimia nervosa.

On the retail side of things, big brands and stores are already using this technology to judge consumer behavior. They use similar methods of interfacing and try to see what the consumers are looking for when they are shopping for groceries.

In summary, the prospects of vision-based AI are outstanding, and only time will tell its true limits.



Bozomitu, R. G., Păsărică, A., Tărniceriu, D., & Rotariu, C. (2019). Development of an Eye Tracking-Based Human-Computer Interface for Real-Time Applications. 19(16), 3630.

Iáñez, E., Azorin, J. M., & Perez-Vidal, C. (2013). Using eye movement to control a computer: a design for a lightweight electro-oculogram electrode array and computer interface. PLoS One, 8(7), e67099. doi:10.1371/journal.pone.0067099

Jacko, J. A., Barreto, A. B., Chu, J. Y. M., Scott, I. U., Rosa, R. H., & Pappas, C. C. (2000). Macular Degeneration and Visual Search: What We Can Learn from Eye Movement Analysis. 44(29), 116-119. doi:10.1177/154193120004402931

Santos, R., Santos, N., Jorge, P. M., & Abrantes, A. (2014). Eye Gaze as a Human-computer Interface. Procedia Technology, 17, 376-383. doi:https://doi.org/10.1016/j.protcy.2014.10.247