MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641106600 A) filed by Kkr & Ksr Institute Of Technology And Sciences on September 04, 2026, for Sign Language Recognition System By Using Artificial Intelligence And Deep Learning.
Inventors include Mr. Prof. Repudi Ramesh; Mrs. Dr. Chittineni Aruna; Mr. Dr. B. Tarakeswara Rao; M. Bhuvanesh Babu; K. Srinivas; N. Chaitanya; and L. Jaya Sankar.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: ABSTRACT [0011] Communication between hearing and speech-impaired individuals and normal people is difficult due to the lack of a common communication medium. Sign language is widely used by deaf and mute people, but most people cannot understand it. This invention proposes a sign language translation system that converts text or audio input into corresponding sign language images or video output using convolutional neural networks and YOLOv7. The system accepts text input from the user or audio input through a microphone. The audio input is converted into text using speech recognition technology. The processed text is then mapped to sign language gestures stored in the dataset. YOLOv7 is used for efficient detection and localization of sign gesture components, while the convolutional neural network is used for feature extraction and classification of sign language images. Based on the recognized text, the system retrieves and displays the corresponding sign language image or video sequence as output. Convolutional neural networks provide high accuracy in recognizing and classifying gesture patterns, and YOLOv7 ensures fast and efficient object detection, making the system suitable for real-time applications. The proposed system is cost-effective, accurate, and easy to deploy on computers and mobile devices. It helps improve communication for deaf and mute individuals, promotes accessibility, and reduces the need for human interpreters.
Disclaimer: Curated by HT Syndication.
