Individuals primarily communicate with one another. Blind and deaf people use sign language to communicate with others. These individuals have difficulty communicating their message to ordinary people. Deaf and blind people believe they are unable to communicate because of a lack of communication skills, and as a result, they are unable to express their emotions. Because most individuals aren’t educated in sign language, communicating in an emergency can be extremely challenging. As a consequence, the challenge may be solved by converting hand gestures into human-hearing sounds and text. Vision and non-vision approaches are two of the most commonly used methods for detecting hand movements or gestures. In a vision-based approach, a camera will be used for gesture detection, whereas sensors will be employed in a non-vision-based technique. In this study, a vision-based technique was used. This device detects and locates hand motions in order to keep a communication channel open with others. Using convolutional neural networks and artificial neural networks, this research develops a gesture recognition system. This study looks into the advantages and disadvantages of hand motion recognition.