Abstract

Abstract: People communicate using sign language by visually conveying sign patterns to portray purpose. One method of communicating with deaf-mute people is to use sign language mechanisms. One of the nonverbal communication strategies used in sign language is the hand gesture. Many manufacturers all over the world have created various sign language systems, but they are neither adaptable nor cost-effective for end users. We present a design that can recognize various American sign language static hand motions in real-time using transfer learning, Python, and OpenCV in this paper. “Hello, Yes, No, Thank You, and I Love You" are all prevalent sign language terms that our system correctly acknowledges. The following are the key steps in system design; we created our own dataset taking prominent gestures of the American Sign Language, captured images with OpenCV and webcam, the images were then labelled for object detection, training and testing of dataset was done with transfer learning using SSD MobileNet, and eventually the gestures were successfully determined in real-time.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.