• DHIVYA SOBIYA M
• PADMASHREE T
• ZAINAB HIRA J
• PRABAKARAN G

The goal of the Hand Sign Recognition project is to create a reliable and effective system that can accurately read human hand motions. Through user-friendly gesture-based controls, this initiative seeks to improve human-computer interaction and bridge communication barriers for those who use sign language. In order to enhance model performance, the system first gathers a varied dataset of hand movements, after which preprocessing methods such frame extraction, hand detection, and data augmentation are applied. Convolutional neural networks (CNNs) and recurrent neural networks/long short-term memory (RNN/LSTM) networks are two examples of deep learning models that are taught to effectively recognize and categorize a variety of hand movements. In order to ensure accurate gesture interpretation, the system design also incorporates feature extraction techniques to record important hand characteristics. To enable smooth interaction and display recognized motions, an intuitive user interface is created. In order to make the solution inclusive and accessible to a broad spectrum of users, the project also places a strong emphasis on scalability, security, and privacy. Potential uses include virtual reality, gaming, smart home control, and sign language translation, demonstrating the adaptability and significance of the suggested technology.

Hand Gesture Recognition, Deep Learning, CNN and RNN/LSTM, Human-Computer Interaction

"Sign Language Interpreter Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.i670-i675, May-2025, Available :http://www.jetir.org/papers/JETIR2505972.pdf

"Sign Language Interpreter Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppi670-i675, May-2025, Available at : http://www.jetir.org/papers/JETIR2505972.pdf