MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641106589 A) filed by Kkr & Ksr Institute Of Technology And Sciences on September 04, 2026, for A Brain Inspired Mathematical Approach To Volumetric Hand Gesture Textualization.
Inventors include Mr. Prof. Repudi Ramesh; Mrs. Dr. S. Srilakshmi Parvathi; K. Poojahimani; K. V. Vijayalakshmi; M. Spandana; and J. Pujitha.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: ABSTRACT [0012] Gesture recognition for air-writing has traditionally relied on deep learning models such as convolutional neural networks and recurrent neural networks, which require large training datasets, high computational power, and repeated retraining for personalization. These constraints limit their effectiveness in real- time, low-power, and assistive applications. To address these challenges, this invention presents a brain-inspired mathematical approach to volumetric hand-gesture textualization using spatio-temporal hyperdimensional computing. The proposed system captures three-dimensional hand-gesture trajectories using a camera-based hand-tracking framework and represents them as high-dimensional hypervectors, where information is encoded through orthogonality and temporal binding. Instead of complex neural network training, the system uses circular shift operations and superposition to preserve stroke order and construct word-level representations, enabling accurate recognition with one-shot learning. Gesture recognition is performed through associative memory lookup using lightweight bitwise operations, resulting in high speed, low latency, and energy-efficient computation. In addition to converting gestures into text, the system provides voice output, making it accessible to deaf, mute, blind, and physically challenged users. This approach offers a scalable and personalized alternative to conventional deep learning methods, suitable for deployment on resource-constrained devices such as wearables and assistive communication systems.
Disclaimer: Curated by HT Syndication.
