MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202641112937 A) filed by R. Prithiviraj; Dr. S. Umarani; Mohankumar. S; Karpagavalli. S. M; Kiruthika. S; Raghapriya. N. R; Gokul. K; Girija Vasumathi. G. G; Kiruthikaa. K. V; Arjun. E; Thulasi Raman. S; and Dharani. P. V on September 21, 2026, for Gesture Yolo: Free Hand Alexa For Individuals With Disabilities.
Inventors include R. Prithiviraj; Dr. S. Umarani; Mohankumar. S; Karpagavalli. S. M; Kiruthika. S; Raghapriya. N. R; Gokul. K; Girija Vasumathi. G. G; Kiruthikaa. K. V; Arjun. E; Thulasi Raman. S; and Dharani. P. V.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: The present invention relates to an artificial intelligence-based multimodal human-computer interaction system that enables touchless and hands-free control of computers and software applications using real-time hand gestures and voice commands. The system comprises a web camera [1], hand tracking module [2], gesture recognition module [3], Gmail interface [4], YouTube interface [5], Google search interface [6], shopping interface [7], product page interface [8], microphone [9], voice processing module [10], and speech-to-text module [11] for capturing, processing, and converting user inputs into executable computer operations. The web camera [1] captures the user's hand movements, while the hand tracking module [2] detects and tracks hand landmarks and finger positions. The gesture recognition module [3] analyses the detected hand information to recognize predefined gestures for performing operations including cursor movement, clicking, right-clicking, scrolling, volume control, window manipulation, navigation, and application control. The microphone [9] receives spoken commands, which are processed by the voice processing module [10], and the speech-to-text module [11] converts the spoken input into text for performing operations including web searching, text entry, application navigation, and email-related activities. The system further provides interaction with a Gmail interface [4], YouTube interface [5], Google search interface [6], shopping interface [7], and product page interface [8] through recognized hand gestures and voice commands. The multimodal interaction mechanism enables gesture-based and voice-based commands to operate independently or in combination according to the application context. The invention operates using commonly available input devices such as the web camera [1] and microphone [9], without requiring wearable devices or specialized physical input hardware, thereby providing an accessible, convenient, flexible, and touchless human-computer interaction solution for general computing and accessibility-oriented applications.
Disclaimer: Curated by HT Syndication.
