Indonesian Journal of Electrical Engineering and Computer Science Vol. 30, No. 1, April 2023, pp. 545~556 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v30.i1.pp545-556  545 Journal homepage: http://ijeecs.iaescore.com Real-time recognition of American sign language using long- short term memory neural network and hand detection Reham Mohamed Abdulhamied 1,2 , Mona M. Nasr 2 , Sarah N. Abdulkader 2 1 Department of Software Engineering, Faculty of Computers Science, October University for Modern Science and Arts, Cairo, Egypt 2 Faculty of Computers and Artificial Intelligence, Helwan University, Cairo, Egypt Article Info ABSTRACT Article history: Received Feb 23, 2022 Revised Dec 5, 2022 Accepted Dec 10, 2022 Sign language recognition is very important for deaf and mute people because it has many facilities for them, it converts hand gestures into text or speech. It also helps deaf and mute people to communicate and express mutual feelings. This paper's goal is to estimate sign language using action detection by predicting what action is being demonstrated at any given time without forcing the user to wear any external devices. We captured user signs with a webcam. For example; if we signed “thank you”, it will take the entire set of frames for that action to determine what sign is being demonstrated. The long short-term memory (LSTM) model is used to produce a real-time sign language detection and prediction flow. We also applied dropout layers for both training and testing dataset to handle overfitting in deep learning models which made a good improvement for the final result accuracy. We achieved a 99.35% accuracy after training and implementing the model which allows the deaf and mute communicate more easily with society. Keywords: Action detection Hand gesture LSTM model MediaPipe Sign language This is an open access article under the CC BY-SA license. Corresponding Author: Reham Mohamed Abdulhamied Department of Software Engineering, Faculty of Computers Science October University for Modern Science and Arts Kairo, Egypt Email: reham.abdulhamied@gmail.com 1. INTRODUCTION The earliest forms of communication for the deaf and mute people provided by the use of sign language, which appeared in Spain during the 17th century to assist people who could not speak or hear. This is one of the languages in which each letter of the alphabet is generated by putting the hands on certain signs. Hand movements are only one component of sign language; other aspects include facial expressions, lip movements, and body movements. Sign language assists deaf and mute people with special abilities in developing their mental, verbal, and sign skills, as well as the reduction of internal and psychological pressures experienced by the deaf and mute, and the development of social, cognitive, and cultural relations among deaf and mute people [1]. Several schools were established in a variety of countries around the world to help the deaf and mute to learn sign language, but it needs more work to be expanded, particularly in Arab societies. It is critical to integrate deaf and mute children with other students in schools, as well as to provide them with dedicated classes within schools, in order to provide them with a better social and educational life, as well as to raise their self- confidence levels. There are over 300 different sign languages in use worldwide [2]. Different sign languages use various sign language alphabets. For instance, the alphabets of Indian sign language and Italian sign language are very different from those of American sign language (ASL) as shown in Figure 1. Thus, regional differences in sign