This study introduces a secure and accessible authentication approach that enables users to log in simply by blinking their eyes in a pattern similar to Morse code. This approach is designed especially for people with limited motor control or reduced hand mobility or traditional input devices. Instead of entering PINs or passwords, users can authenticate themselves through intentional eye blinks, making the system completely hands-free. The model uses OpenCV to track facial landmarks and dlib to calculate the Eye Aspect Ratio (EAR), which helps detect purposeful blinks accurately. These blinks are then converted into Morse code signals and compared with stored authentication patterns. Our experiments show that the system works reliably in normal lighting and responds with minimal delay, providing smooth interaction. Because it uses basic hardware and open-source tools, the solution is economical and can be deployed with minimal resources. The findings of this research indicate that eye-blink-based Morse code can be a practical, inclusive, and user-friendly alternative to conventional login mechanisms, especially for individuals who need assistive technology.

The Human Blink Sequence as a Morse Code Authentication System combines blink-based Morse code decoding, facial recognition, and password verification into a safe, user- friendly, and efficient multi-factor authentication framework. Hands-free and contactless authentication is made possible by the system’s successful demonstration of eye-blink patterns as a dependable behavioral biometric. Under typical operating conditions, the system achieves robust face recognition and accurate blink detection by utilizing real-time image processing, Haar Cascade classifiers, and facial encoding techniques. The findings show that the suggested method offers notable benefits over conventional password-based authentication, especially in terms of lowering vulnerabilities like impersonation, shoulder surfing, and password guessing. The combination of behavioral and biometric factors adds an additional layer of security, which significantly increases the difficulty of unauthorized access. Furthermore, the hands-free design improves accessibility for individuals with motor impairments and supports hygienic, touch-free login environments. Even though the system works well, some environmental elements, like dim lighting and fast involuntary blinks, may have an impact. However, the system’s overall viability is not compromised by these drawbacks. The study confirms that blink-based Morse code, when combined with facial recognition, can serve as a practical and innovative authentication method suitable for real-world applications. In conclusion, the work demonstrates a promising direction for future authentication technologies, offering enhanced security, improved usability, and inclusive design through the integration of computer vision and behavioural biometrics.

[1]P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2001. [2]G. Bradski, “The OpenCV Library,” Dr. Dobb’s Journal of Software Tools, 2000. [3]A. Krizhevsky, I. Sutskever, and G. Hinton, “ImageNet classification with deep convolutional neural networks,” Advances in Neural Information Processing Systems, vol. 25, 2012. [4]S. Liao, A. K. Jain, and S. Z. Li, “Partial face recognition: Alignment-free approach,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 5, pp. 1193– 1205, 2013. [5]A. Jain, A. Ross, and S. Prabhakar, “An introduction to biometric recognition,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 14, no. 1, pp. 4–20, 2004. [6]C. Rathgeb and A. Uhl, “A survey on biometric cryptosystems and cancelable biometrics,” EURASIP Journal on Information Security, vol. 2011, pp. 1–25, 2011. [7]International Telecommunication Union (ITU), “Morse Code Standard,” Recommendation ITU-R M.1677-1, 2009. [8]F. Ahmed, R. Bari, and M. R. Islam, “Eye-blink based communication system for physically impaired people,” International Journal of Computer Applications, vol. 180, no. 44, 2018. [9]D. Setu and M. Paul, “Human–computer interaction through blink detection using computer vision,” International Journal of Advanced Research in Computer Science, vol. 9, no. 3, 2018. [10]G. B. Huang, M. Ramesh, T. Berg, and E. Learned- Miller, “Labeled Faces in the Wild: A database for studying face recognition in unconstrained environments,” University of Massachusetts Amherst, Technical Report 07-49, 2007.