Abstract:
Sign language serves as the primary means of communication for the deaf and voiceless community. However, a significant challenge they face is the limited understanding of sign language among the general population. The objective of this system is to bridge the communication gap between communities, enabling the voiceless community to interact effectively with others. Hand motions in sign language exhibit variations in shape and position, posing challenges for accurate recognition. Recent advancements in the field have introduced various methods and techniques to address this issue and develop effective sign language recognition systems. Previous approaches involved decoding hand gestures using algorithms such as K-Nearest Neighbors (KNN), Multi-class Support Vector Machine (SVM), and trials with hand gloves. This study compares the performance of KNN, SVM, and Convolutional Neural Network (CNN) algorithms to determine the most accurate approach. The dataset, comprising approximately 29,000 images, is divided into test and train data, preprocessed, and used to achieve accuracy rates of 93.83%, 88.89%, and 98.49% for the KNN, SVM, and CNN models, respectively.
At Smart AI Technologies, a leading project center in Bangalore, we specialize in providing comprehensive support for final year engineering projects based on IEEE papers. If you choose our project center, you can expect the following components for your project:
Complete documentation support to ensure a well-documented project.
Implementation of working hardware/software in your environment.
Customized classes and guidance to meet your project requirements.
By selecting our project center in Bangalore, you can be assured that your final year engineering project on sign language recognition using machine learning will be one of the best IEEE projects for computer science. Contact us now to avail of our services and receive expert guidance throughout your project development process.