Virtual Control of PC using Facial and Voice Navigation

This paper presented a multimodal human-computer inter-action system for virtual PC control using facial navigation and voice commands. Its primary contribution lies in demon-strating that widely available hardware, together with contem-porary computer-vision and speech-processing methods, can be integrated into a low-cost hands-free interface for desktop interaction. The findings support the view that such systems can improve accessibility and practical functionality for users who face difficulty with conventional peripherals, while also offering contactless interaction in general-purpose settings. At the same time, the study confirms that technical feasibility alone is insufficient for a strong assistive-computing claim: future work must strengthen evaluation across larger and more diverse participant groups, compare unimodal and multimodal con-figurations, quantify robustness under noisy and low-light conditions, and address privacy, fairness, and personalization more explicitly. Accordingly, the next stage of this research should focus on reproducible benchmarking, adaptive calibration, multilingual and offline command recognition, and longitudinal user studies with people who have different motor impairments. With these additions, the system can be positioned not merely as an implementation project, but as a meaningful contribution to accessible multimodal computing.

[1]     M. Turk and A. Pentland, “Eigenfaces for recognition,” Journal of Cognitive Neuroscience, vol. 3, no. 1, pp. 71–86, 1991. [2]     G. G. Gordon, “Face recognition based on depth and curvature features,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1992. [3]     J. A. Bilmes et al., “The Vocal Joystick: A voice-based human-computer interface for users with motor impairments,” in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2006. [4]     A. Al-Qaysi and M. Zaidan, “A hybrid face and voice control system for human-computer interaction,” International Journal of Advanced Computer Science and Applications, vol. 10, no. 7, pp. 256–262, 2019. [5]     D. Chen et al., “Head-tracking mouse system for individuals with disabilities,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 12, no. 3, pp. 390–397, 2004. [6]     R. Sharma, “Assistive technology for improving accessibility in com-puting systems,” International Journal of Computer Applications, vol. 176, no. 12, pp. 15–20, 2020. [7]     A. Gaurav, “Voice recognition system using Python for human-computer interaction,” International Journal of Engineering Research and Tech-nology, vol. 10, no. 5, pp. 234–238, 2021. [8]     G. Bradski, “The OpenCV library,” Dr. Dobb’s Journal of Software Tools, 2000. [9]     P. K. Jain, “Real-time face detection and tracking using MediaPipe framework,” International Journal of Emerging Technologies, vol. 13, no. 2, pp. 45–50, 2022. [10]    A. Karpathy, “Large-scale video classification with convolutional neural networks,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.