SIGN LANGUAGE TRANSLATOR USING MACHINE LEARNING

Computer Science and Engineeering

Sign Language is the only means of communication for the deaf and mute people. But many of the normal people do not know sign language. Thus, it is difficult for the the people who speak in sign language to communicate with those who don’t speak the sign language to communicate. This paper extends the previously proposed Convolutional Neural Network (CNN) model for predicting Sign Language using a MobileNetV2-based transfer learning model. The proposed system aims to enable efficient communication for hearing-impaired users by translating sign language gestures into text or speech. The TensorFlow K-NN Image Classifier is used to train the model on the training set. The classifier involves a k-nearest neighbor classifier. The number of classes is determined by the number of unique signs in the dataset, and each class is associated with one sign. The MobileNet model is pre-trained on a large-scale image dataset and fine-tuned on ASL hand sign images to learn discriminative features. After extracting features from the MobileNet model, a KNN classifier is employed for sign language recognition. KNN is a simple yet effective algorithm that assigns a label to an input sample based on the majority class of its k-nearest neighbors in the feature space. In this case, the neighbors correspond to previously seen sign language gestures. The proposed sign language translator system has numerous practical applications, such as aiding individuals with hearing or speech impairments during everyday interactions. Additionally, it can be integrated into educational platforms to support sign language learners and provide inclusive linguistic education opportunities

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.