International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 08 Issue: 07 | July 2021 www.irjet.net p-ISSN: 2395-0072 © 2021, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 1578 SIGN LANGUAGE DETECTION Pavitra Kadiyala 1 1 SCOPE, Vellore Institute of Technology, Vellore, India ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - Communication through signs has consistently been a significant way for communication among hearing and speech impaired humans, generally called deaf and dumb. It is the only mode of communicating for such individuals to pass on their messages to other human beings, and hence other humans need to comprehend their language. In this project, a sign language detection or recognition web framework is proposed with the help of image processing. This application would help in recognizing Sign Language. The dataset used is the Indian Sign Language dataset. This application could be used in schools or any place, which would make the communication process easier between the impaired and non- impaired people. The proposed method can be used for the ease of recognition of sign language. The method used is Deep Learning for image recognition and the data is trained using Convolution Neural Network. Using this method, we would recognize the gesture and predict which sign is shown. Key Words: Sign Language, Convolution Neural Network, Image Processing, Framework, Gestures 1.INTRODUCTION Sign language is the most significant way of communication between the impaired people. Establishing an easy way of communication with deaf and dumb people is very important. Everyone should be able to understand sign language as it would be useful in case of any emergency. These individuals communicate through hand signals or gestures. Signals are essentially the actual activity structure performed by an individual to pass on the important data. People trained to know sign language would be able to communicate efficiently but this would be a problem for the untrained ones. Communicating using signs is using gestures and using hands or expressions to depict a particular sign. Few people use signs for communicating when they are busy for example in a meeting or so. There are many types of signs depending on the language and region. This paper proposes a method for identifying the Indian Sign Language. We know the field of Machine Learning, Artificial Intelligence, Image Processing is advancing and can be used for multiple domains nowadays. In this paper, Deep Learning is used. There are many factors that as taken into consideration when it comes to signing language recognition. The angle of the gesture also plays a very important role. The type of dataset also plays a very vital role in the recognition model. 1.1 Existing Solutions There are a few ways which are being used. 1. Searching in a book or online for the matching image of the sign represented. But this is a time- consuming method for searching. 2. To have an experienced and educated translator every time with you. But this is a very tough method to find a translator everywhere you go. 3. Non-vision-based which uses Sensor and Hardware-based devices for detecting. 1.2 Motivation of the Topic Keeping in mind the above drawbacks of the existing method, this paper proposes a solution to it by using Deep Learning. Also, this method would help the ease of understanding, and even in public areas the communication is easy. 2. LITERATURE REVIEW In this paper [1], a gesture-based communication fingerspelling letters in order ID framework was created by utilizing image processing and Artificial Intelligence. Specifically, they introduced 24 sequential images by a few blends. Histogram of Oriented Gradients (HOG) and Local Binary Pattern (LBP) highlights of each motion were taken from the training dataset. Then, they applied Multiclass Support Vector Machines (SVMs) to prepare this separated information. Additionally, Convolutional Neural Network (CNN) design has been used in the training dataset for correlation. The Massey Dataset is used in the training and testing periods of the entire