Published Paper Details:

Communication between hearing-impaired individuals and people who do not understand sign language is often difficult. Sign language is the primary method used by deaf and mute individuals to express their thoughts and emotions, but many people are not familiar with it. This communication gap creates challenges in education, healthcare, and daily interactions. The Telugu Sign Language Translator using Deep Learning aims to bridge this gap by automatically recognizing hand gestures used in Telugu sign language and converting them into readable text or speech. The system uses computer vision techniques to capture hand gesture images through a webcam and processes them using a deep learning model. A Convolutional Neural Network (CNN) is trained to identify and classify different Telugu sign gestures accurately. Once the gesture is recognized, the system translates it into corresponding Telugu text and optionally generates voice output using text-to-speech technology. This allows normal users to understand the message conveyed by the sign language user in real time. The proposed system helps improve accessibility and communication for hearing-impaired individuals. By integrating deep learning, computer vision, and speech technologies, the model provides an intelligent and efficient solution for translating Telugu sign language. This technology can be further extended to mobile applications, real-time translation systems, and multilingual sign language recognition platforms. The system is designed to capture hand gestures using a webcam or camera device and process the input images through image preprocessing techniques such as resizing, normalization, and background removal. These processed images are then fed into a trained deep learning model that extracts important features of the hand gestures and classifies them into predefined Telugu sign language categories. The deep learning architecture, primarily based on Convolutional Neural Networks (CNN), is capable of learning complex patterns from gesture images and providing accurate predictions. The recognized gestures are mapped to their corresponding Telugu characters, words, or phrases. The output is displayed as Telugu text on the screen and can also be converted into speech using a text-to-speech module, allowing users to hear the translated message. This system can be highly beneficial in educational institutions, public service centers, hospitals, and workplaces where effective communication with hearing-impaired individuals is essential. By providing real-time gesture recognition and translation, the model reduces dependency on human interpreters and improves communication efficiency. Furthermore, the project highlights the potential of artificial intelligence in building inclusive technologies that support people with disabilities. Future improvements may include expanding the dataset to cover more gestures, improving model accuracy using advanced architectures, supporting continuous sign language sentences, and developing mobile or web-based applications for wider accessibility. Overall, the Telugu Sign Language Translator using Deep Learning represents an important step toward enhancing accessibility, promoting social inclusion, and leveraging modern AI technologies to solve real-world communication challenges.