Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{200302,
        author = {R. CAROL PRAVEEN and A.NIKCY JOSEPH and A.NAVEEN KUMAR and U.OM SRINATH and M.PARTHASARATHY RAJ},
        title = {Touchless Gesture-Controlled Smart Interface Using Computer Vision and ESP32},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {8260-8265},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200302},
        abstract = {The proliferation of shared digital surfaces in public infrastructure has renewed urgent interest in contactless interaction paradigms, particularly within healthcare, banking, transportation, and smart-home ecosystems. This paper presents a low-cost, real-time Touchless Gesture-Controlled Smart Interface that enables users to navigate and activate menu-driven systems using bare-hand gestures, entirely eliminating the need for physical contact. A standard USB webcam feeds continuous video into an OpenCV pipeline that pre-processes frames and forwards them to MediaPipe Hands, which localises 21 skeletal landmarks per hand at inference speeds exceeding 30 fps. The normalised coordinates of the index-fingertip landmark drive a virtual cursor across an interactive menu rendered on the host screen; sustained hover over a virtual button for a configurable dwell interval—typically two seconds—confirms the selected command. Upon confirmation, a PySerial link transmits the command string over USB-UART to an ESP32 microcontroller, which decodes the payload and updates a 0.96-inch SSD1306 OLED display with a human-readable status message. Experimental evaluation under varied indoor lighting conditions demonstrates gesture classification accuracy exceeding 94%, end-to-end latency below 180 ms, and stable serial throughput at 115,200 baud. The prototype employs entirely open-source software and commodity hardware, keeping the bill-of-materials cost under USD 15. Results affirm the feasibility of deploying gesture-driven interfaces in resource-constrained environments, and the modular architecture readily accommodates future enhancements such as deep-learning gesture classifiers, Wi-Fi/BLE wireless control, and cloud telemetry integration.},
        keywords = {Gesture Recognition, MediaPipe Hands, Computer Vision, Human-Machine Interface, ESP32, OLED Display, Contactless Interaction.},
        month = {May},
        }