Multimodal biometric systems have gained broad acceptance in recent years due to their superior accuracy and resilience compared to unimodal approaches (Bokhari et al., 2022; Al-Hazaimeh et al., 2021). This article presents an integrated system that combines facial recognition and hand gesture recognition to enhance authentication procedures and human- computer interaction. Real-time facial feature detection and classification are achieved using a pre-trained VGG19 convolutional neural network (CNN), while MediaPipe is employed for rapid hand gesture recognition (Xu et al., 2023). To enable seamless, touchless control, the system utilizes OpenCV and PyAutoGUI for efficient image processing and input simulation. Experimental evaluations were conducted under varying conditions, including changes in lighting, partial occlusion, and user movement. Results demonstrate that the combined multimodal approach significantly improves authentication accuracy and user engagement over traditional single- modal systems. This research contributes to the advancement of unified facial-gesture authentication frameworks that are both high performing and responsive. The proposed system opens new opportunities for secure, contactless interfaces in critical environments and assistive technologies. Future enhancements may include the integration of additional biometric modalities and deployment across mobile and embedded platforms to broaden applicability and accessibility.