Prototipe Detektor Mata Uang Kertas Untuk Modul Vending Machine Automatic Cash Money Menggunakan Rapsberry Pi

Sigit Anggoro, Tacbir Hendro


Vending Machines are strategic trading machines when it comes to social and physical distancing policies during the current Covid 19 pandemic. The ability to trade independently in trading without a physical meeting is one of its advantages. On the other hand, the Vending Machine payment system has developed with many variations ranging from payment models using coins, banknotes, payment gateway systems capable of serving debit and credit payments and the ability to make payments via fintech. This study focuses on the banknote detection module using the Oriented FAST and Rotated BRIEF (ORB) algorithm. In order to become a prototype that is ready to be developed in the future, the banknote detection module needs to be made in a concise and independent form. The use of the Rapsberry Pi and the ability to work on complex algorithms is one of the goals that will be achieved from this research. This research is expected to be able to apply the ORB algorithm for the classification of Rupiah banknotes and at the same time be able to further develop it to sort (sort) for banknotes that meet the requirements (accept) and reject those that do not meet the requirements (reject).


Vending Machine; Klasifikasi ; mata uang kertas ;ORB; Rapsberry Pi

Full Text:



Gruber S, Buber R, Ruso B, Gadner J. The commodity vending machine. Vol. 02, Internationale Gesellschaft für Warenwissenschaften und Technologie. 2016. p. 0–10.

Prasad V, Ramya G, Sandeep G, Laxmareddy K. A Research on the Design of FSM Based Vending Machine. Int J Innov Technol Explor Eng. 2019;8(12S2):356–60.

Bodhale AP, Kulkarni PJS. Case Study on Different Vending Machines. Int Res J Eng Technol [Internet]. 2017;4(4):3531–5. Available from:

Thakwani D, Tripathi N. PLC Based Change Dispensing Vending Machine Using Image Plc Based Change Dispensing Vending Machine Using Image Processing Technique for Identifying and Verifying. Int Res J Eng Technol. 2017;03(November 2016):454–8.

Sarfraz M. An Intelligent Paper Currency Recognition System. Procedia Comput Sci [Internet]. 2015;65(Iccmit):538–45. Available from:

Zhang Q. Currency Recognition Using Deep Learning. Auckland University of Technology; 2018.

Swami G, Naveen J. Nitte Conference on Advances in Electrical Engineering NCAEE-2016 Identification of Counterfeit currency and denomination using Raspberry pi. IJIREEICE. 2016;4(2):142–6.

Bojanic D, Bartol K, Pribanic T, Petkovic T, Donoso YD, Mas JS. On the comparison of classic and deep keypoint detector and descriptor methods. Int Symp Image Signal Process Anal ISPA. 2019;2019-Septe:64–9.

Khoharja G, Eng M, Purbowo AN, Mt M, Studi P, Informatika T, et al. Aplikasi Deteksi Nilai Uang pada Mata Uang Indonesia dengan Metode Feature Matching. 2017;2–6.

Yousry A, Taha M, Selim MM. Currency Recognition System for Blind people using ORB Algorithm. Int Arab J e-Technology. 2018;5(1):34–40.

Calonder M, Lepetit V, Strecha C, Fua P. BRIEF: Binary robust independent elementary features. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics). 2010;6314 LNCS(PART 4):778–92.

R R, B S. Motion Detection in Moving Background using ORB Feature Matching and Affine Transform. 2015;17–8.

Rublee E, Rabaud V, Konolige K, Bradski G. ORB: An efficient alternative to SIFT or SURF. Proc IEEE Int Conf Comput Vis. 2011;2564–71.

Karami E, Prasad S, Shehata M. Image matching using SIFT, SURF, BRIEF and ORB: Performance comparison for distorted images. arXiv. 2017;

Luo C, Yang W, Huang P, Zhou J. Overview of Image Matching Based on ORB Algorithm. J Phys Conf Ser. 2019;1237(3)


  • There are currently no refbacks.