• Pranav Patil
• Prathamesh Mate
• Pritesh Wadile
• Gaurav Wani
• Prof. Pallavi Chaudhari

The Blind people may not be able to see or count money. Therefore, a framework called "Image Based Money Recognition and Counting System" is required to solve this problem. Although results analysis methods help blind and visually impaired people analyze results, they are not sufficient. Also, they represent only one currency at a time, and not the total amount, depending on the volume of production. Therefore, it is difficult for a blind person to judge all the money. In this article, we propose a method to confirm results using an efficient and quick method to identify results after finding it will save all results found and benefit the blind. The proposed method was used to identify seven different Indian currencies. At first, the first method is used on paper money. After that, complete the ROI and OCR and then provide the main annotation. Finally, the Hamming distance algorithm is used to match key identifiers from the extraction process. The results show that the proposed method can be implemented in real-time conditions with an accuracy of 93.71% and a running time of 1.2 seconds.

Raspberry Pi, Sensor, Camera, neural network, currency, deep learning, visually impaired, CNN

"PHYSICAL CURRENCY DETECTOR FOR VISUALLY IMPAIRED PERSON ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.g650-g653, May-2023, Available :http://www.jetir.org/papers/JETIR2305695.pdf

"PHYSICAL CURRENCY DETECTOR FOR VISUALLY IMPAIRED PERSON ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppg650-g653, May-2023, Available at : http://www.jetir.org/papers/JETIR2305695.pdf