A deep learning model is developed for classifying sign language images to corresponding sign words by transfer learning of the Inception V3 architecture and it is extended to videos for generating simple English sentences
-
The sign language data set is created for 30 sign words and 25 alphabets which could be classified using just one image frame and our model is trained using it.
-
An accuracy of 62.5% is achieved on the test set under normal lighting conditions.