1 publication
-
Published Subscription Original Research
Sign Language-enabled Offline IP-based Video Call Intercom System for the DeafBy Prakrati Bajpai, Soni M., Nikita Singh, Ravi Shankar Kumar, Sanjay B.R.
Abstract: Individuals who are deaf or hard of hearing frequently encounter major communication challenges on digital platforms because sign language support is often insufficient. This study presents a real-time, internet-independent sign language-to-text translation system embedded in an offline IP-based video intercom, designed to facilitate seamless communication. Leveraging TensorFlow’s Convolutional Neural Network (CNN) for classification and MediaPipe for hand tracking, the system achieved a training accuracy of 94.24% and a validation accuracy …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 12, Issue 1, 2025 · pp. 53–66 Read article →