Penerapan Algoritma Faster R-CNN dalam Pengenalan Uang Kertas Rupiah

Muhammad, Zuhdi Hanif (2024) Penerapan Algoritma Faster R-CNN dalam Pengenalan Uang Kertas Rupiah. Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

	Text Cover.pdf Download (1MB)
	Text Abstrak.pdf Download (9kB)
	Text Abstract.pdf Download (9kB)
	Text BAB I.pdf Download (95kB)
	Text BAB II.pdf Download (726kB)
	Text BAB III.pdf Download (300kB)
	Text BAB IV.pdf Restricted to Registered users only Download (1MB)
	Text BAB V.pdf Download (75kB)
	Text DAFTAR PUSTAKA.pdf Download (105kB)

Abstract

Money is an important part of human life. Humans are never separated from activities related to money. In the modern era, the use of money has increasingly developed. One of the conveniences that the public can feel is the existence of technology or a system that can recognize the nominal value of banknotes. Therefore, we need a technology that can differentiate banknotes based on their nominal value; one that can be used is object detection. Object detection is one of the most popular branches of computer vision. There are many methods for carrying out object detection, such as Faster R-CNN. Faster R-CNN has been widely used in various fields to perform object detection tasks. Faster R-CNN has advantages over its predecessor because it uses a Region Proposal Network (RPN) as a substitute for selective search, which requires less compilation time. This research aims to apply the Faster R-CNN algorithm with ResNet-50 architecture to recognize rupiah banknotes. The dataset used is 1120 images consisting of 8 classes. The model gets an accuracy of 87.5% in the RGB scheme and 82.1% in the HSV scheme with HOG. Even though they show good numbers, the two models cannot predict class well. Keywords: Faster R-CNN, Object Detection, Rupiah Banknotes, ResNet-50, Deep Learning.

Actions (login required)

View Item