Classification of Sign Language Gestures using CNN with Adam Optimizer
Aadershi Mohan, Daivik Mohan, Satvik Vats, Vikrant Sharma, Vinay Kukreja
Abstract
In this paper, we have worked on to improve the overall accuracy and the individual accuracies of the given gestures before developing the sign language gestures prediction system for that we have taken a dataset of pre-processed images from Kaggle and further applied CNN model with four layers of relu activation function, has three layers of pooling and has a layer of softmax activation and after execution we have got and overall accuracy of 99.95%.
Topics & Concepts
GestureComputer scienceSign languageSign (mathematics)Gesture recognitionNatural language processingArtificial intelligenceSpeech recognitionLinguisticsPhilosophyMathematicsMathematical analysisHand Gesture Recognition Systems