Autor: |
J Rethna Virgil Jeny, A Mamatha, Thandu Sumanth, Karnati Monica, A Anjana |
Rok vydání: |
2021 |
Předmět: |
|
Zdroj: |
2021 5th International Conference on Trends in Electronics and Informatics (ICOEI). |
DOI: |
10.1109/icoei51242.2021.9453072 |
Popis: |
Speech disorder is a condition which affects one's ability to speak and hear. Those people use the separate language that is sign language, using that they can communicate with normal people. In this paper we developed a system which can translate sign language to text and then to audio, thus can improve communication with sign language. The system takes image data using the webcam of the computer, then preprocessing of the image is done using masking technique where the hand is masked to recognize the signed alphabet. Using Convolutional neural network algorithm features are mapped and classification is performed to classify the images accordingly, now image that is given as input is predicted and the translation is done in the form of text, then converted to audio. English alphabet are used as the data set for this system that is all the 26 alphabet are taken in the form of masked images. We've used 45500 images for training and 6500 images for testing. |
Databáze: |
OpenAIRE |
Externí odkaz: |
|