Gesture Recognition to Text and Voice

Abstract: Sign language is a main mode of communication for vocally disabled. This language uses a variety of symbols, including finger signs, expressions, and a combination of the two, to express information. This system offers a novel method for translating sign action analysis, recognition, and generation of a written description in Kannada language using mobile applications. Training and testing are two crucial procedures that are used. Each domain in the training set has 5 video samples, and each video sample has a class of words associated with it that will be stored in a database. Pre processing on the test sample is done using the median filter, the clever operator for edge detection, and the HOG for feature extraction.The text description will finally be produced in English. The performance efficiency over the traditional model is validated by the minimal average computation time, acceptable recognition rate, and performance.