<![CDATA[Blind and low vision individuals experience difficulties in independently recognizing Indonesian banknote denominations, which may lead to errors in daily financial transactions. This study aims to develop an Internet of Things-based smart assistive device to identify Indonesian banknote denominations in real-time. The proposed system employs Raspberry Pi 4 as the processing unit, an OV5647 camera for image acquisition, an HC-SR04 ultrasonic sensor for distance measurement, YOLOv8 Nano for banknote detection, and fuzzy logic as a decision-making mechanism based on the confidence score and object distance. The detection results are delivered through audio output and stored in Firebase Realtime Database, allowing monitoring through a web-based dashboard. The dataset consists of seven Indonesian banknote denominations, namely Rp1,000, Rp2,000, Rp5,000, Rp10,000, Rp20,000, Rp50,000, and Rp100,000. Experimental results show that the proposed system achieves a detection accuracy of 91.43% with an average response time of 1.36 seconds. Therefore, the developed system is expected to improve the independence of blind and low vision individuals in conducting daily financial transactions.]]>
Copyrights © 2026
