• NISCHITHA C B

This research paper introduces "Vision" an Android application tailored to enhance accessibility and independence for visually impaired individuals in India. Nayan integrates cutting-edge machine learning techniques, including YOLOv8 for currency identification and Convolutional Neural Networks (CNN) for currency recognition, enabling users to accurately identify, sum, and convert Indian currency notes into audible speech. Through intuitive swipe gestures, users can initiate currency identification, summation, and text-to-speech conversion functionalities. The development process involved the collection and annotation of a diverse dataset of Indian currency notes, followed by model training and integration into the Android application. Evaluation results demonstrate Vision's efficacy, achieving an 87% accuracy rate in currency identification using the YOLOv8 algorithm. Vision stands as a promising tool for promoting inclusivity and accessibility in financial transactions and daily tasks for the visually impaired community in India.

"VISUAL ASSISTANCE FOR BLIND PEOPLES USING DEEP LEARNING TECHNOLOGY", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.h883-h923, December-2024, Available :http://www.jetir.org/papers/JETIRTHE2164.pdf

"VISUAL ASSISTANCE FOR BLIND PEOPLES USING DEEP LEARNING TECHNOLOGY", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. pph883-h923, December-2024, Available at : http://www.jetir.org/papers/JETIRTHE2164.pdf