• Syed Afiya Tazin
• Dr. Sugandha Nandedkar

The project titled “Medicine Assistance Application for Visually Impaired People using Deep Learning” focuses on developing an intelligent and accessible system that helps visually impaired individuals identify and manage their medicines safely and independently. The application uses deep learning techniques, mainly Convolutional Neural Networks (CNN) and Optical Character Recognition (OCR), to accurately detect medicine names, expiry dates, and dosage information from captured images of medicine strips or bottles. Once the text is recognized, it is converted into clear audio output using a text-to-speech engine, allowing users to hear the medicine details instantly. The system is designed to recognize various fonts, lighting conditions, and packaging styles to ensure high accuracy and reliability in real-world conditions. It also features a medicine reminder system that alerts users about their scheduled dosages and helps prevent missed doses. The application maintains a secure database to store medicine information and user history, enabling easy tracking and management. It can also warn users about expired or incorrect medicines, thus preventing potential health hazards. The deep learning model is trained using a large and diverse dataset of medicine images to enhance performance. Moreover, the system supports multilingual audio assistance, ensuring accessibility for users from different linguistic backgrounds. The user-friendly interface allows simple navigation through voice commands, eliminating the need for visual input. The proposed system bridges the gap between healthcare and accessibility, empowering visually impaired individuals to handle medicines without external help. It represents an innovative application of artificial intelligence in assistive technology, improving quality of life and independence. This solution promotes inclusivity, safety, and convenience through the integration of modern deep learning and speech technologies. Ultimately, the project aims to create a smarter, more empathetic, and accessible healthcare ecosystem for visually challenged individuals.

Deep Learning, Optical Character Recognition (OCR), Convolutional Neural Networks (CNN), Assistive Technology, Text-to-Speech, Accessibility, Visually Impaired, Medicine Identification, Healthcare Application, Artificial Intelligence.

"A Review on Medicine Assistance Application for Visually Impaired People using Deep Learning ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.b681-b687, November-2025, Available :http://www.jetir.org/papers/JETIR2511185.pdf

"A Review on Medicine Assistance Application for Visually Impaired People using Deep Learning ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppb681-b687, November-2025, Available at : http://www.jetir.org/papers/JETIR2511185.pdf