Smart Reader for Blind People

• Published in: 2025 International Conference in Advances in Power, Signal, and Information Technology (APSIT) pp. 1 - 4
• Main Authors: S R, Deepthi, Gowda, Vijeth K, Rai R, Rishitha, Kumar S, Sudarshan, K P, Vineeth
• Format: Conference Proceeding
• Language: English
• Published: IEEE 23.05.2025
• Subjects: Accuracy; Cameras; Image capture; Libraries; Multilingual; Optical character recognition; Optical Character Recognition component; Optical switches; Reliability; Text to speech; Visual impairment
• DOI: 10.1109/APSIT63993.2025.11086193

The system is dedicated to the development of an innovative smart reading table designed specifically for individuals with visual impairments. This technology aims to facilitate the reading of printed materials for people with visual challenges by integrating advanced technologies such as optical character recognition (OCR) and text-to-speech (TTS). The system is comprised of a Raspberry Pi, a 5MP camera module, a speaker, and mechanical push buttons to enhance user interaction. Despite significant advancements in existing text-tospeech conversion technologies, many users continue to depend on external computing resources or internet connectivity. This project addresses the essential need for a self-contained, costeffective, and user-friendly system that functions independently of external devices, thereby alleviating issues related to accessibility and practicality. The methodology implemented involves capturing images with the Raspberry Pi camera module, processing these images to extract text using OCR, and converting the extracted text into audible speech through offline TTS tools such as pyttsx3. A mechanical switch allows for image capture, and controls for audio playback are integrated into the system. The system offers multilingual support with Kannada and English voice output. Experimental results demonstrate 95% text extraction accuracy from clear images and an average processing time of 26.06 seconds, confirming its reliability in real-world applications. Future developments will concentrate on enhancing image processing capabilities for deburring, implementing multilingual support, optimizing hardware for improved performance, and incorporating additional features such as braille output. The technology exhibits considerable potential for implementation in educational institutions, libraries, and as personal reading aids for individuals with visual impairments.