This research aims to develop a banknote recognition system that can help people with special needs, especially people with visual impairments, in recognizing banknote denominations. This system uses image processing technology and machine learning models by utilizing the Create ML library which is integrated with Apple's operating system. By using the Create ML library, modeling the recognition of banknote nominal values can be made easily and without the need for special knowledge in developing machine learning models. The dataset used in this training comes from images of banknotes that have been previously collected and processed. Machine learning models are trained to recognize important features in images such as pictures, numbers and other signs and associate them with the appropriate denominations of money. The test results show that the model created can recognize banknote denominations with an accuracy rate of 71%. This shows that the use of the nominal recognition model for banknotes that is made can help the blind in identifying the nominal money more accurately and efficiently, thereby increasing the independence and quality of life of visual impaired person
Copyrights © 2023