• Arathi M
• Harshini C M
• Niharika S
• Tejasvi Kannan
• Suraj Kumar B P

Sign Language is a form of communication used primarily by people hard of hearing or deaf. This language enables you to interact with a variety of hearing, hard-of-hearing, and deaf people and forms of difficulties caused by hearing issues. Hence, these types of gesture-based languages allow people to convey ideas and thoughts by easily overcoming these barriers that may arise. In this study, methods of deep learning have been deployed to build a system that can detect facial expressions and signs. The system will use a camera to capture the live video of a person to analyse both signs and facial expressions. The sign language gesture recognition module will be designed to recognize individual signs and translate them into text. The facial expression recognition module will detect emotions in real-time, such as happiness, sadness, anger, surprise, fear, disgust, and neutral. The model is developed using Python, OpenCV, and deep learning frameworks such as TensorFlow and Keras. The accuracy of the system will be evaluated using real-world data, and its usability will be assessed through user testing. The main aim is to develop an effective and dependable system that can improve the standard of communication for people with speech and hearing impairments.

Sign Language Recognition, Hand Gestures, Computer Vision, Deep Learning, Emotion Recognition, Neural Networks, LSTM.

"Recognition of Sign Language in Real -Time: A Deep Learning Based Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 4, page no.m637-m639, April-2023, Available :http://www.jetir.org/papers/JETIR2304C85.pdf

"Recognition of Sign Language in Real -Time: A Deep Learning Based Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 4, page no. ppm637-m639, April-2023, Available at : http://www.jetir.org/papers/JETIR2304C85.pdf