DIGITAL IMAGE PROCESSING NOMINAL DETECTION ON BANKNOTE FOR THE BLIND PERSON USING THE CONVOLUTIONAL NEURAL NETWORK (CNN) METHOD

AZINDHA, FILLAH SYAKUR (2024) DIGITAL IMAGE PROCESSING NOMINAL DETECTION ON BANKNOTE FOR THE BLIND PERSON USING THE CONVOLUTIONAL NEURAL NETWORK (CNN) METHOD. Tugas Akhir thesis, Informatics.

[img] Text
5200411522_Fillah Syakur Azindha_Abstrak.pdf
Download (11kB)

Abstract

ABSTRACT Money is a valuable tool as a means of payment in carrying out transactions or buying and selling in human life. Based on the material used to create it, money can be divided into 2 types, namely paper money and metal money. On banknotes there is writing to differentiate the value or nominal value between one money and another. However, it is difficult for blind people to distinguish the nominal value on banknotes. This research aims to create a system that can help blind people distinguish the nominal value of banknotes. Stages and methods used in designing the system: image processing such as changing RGB images into greyscale images. In designing the model, the model used uses the Convolutional Neural Network method. The model is trained to detect uniqueness in each banknote image. The results of the processing are visualized in the form of sound through the speakers. From the results of research trials, the designed system can identify and detect the uniqueness of money in the input image of banknotes and visualize the output in the form of sound that can be heard by blind people. It is hoped that the research that has been carried out can help blind people in distinguishing the value of banknotes, and can help other researchers who want to design devices and provide references for their research. Keywords: Banknotes, Image, Image processing, RGB Image, Binary Image, Thresholding, and Convolutional Neural Network.

Item Type: Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Sains Dan Teknologi > S1 Informatika
Depositing User: Kaprodi S1 Informatika UTY
Date Deposited: 07 Aug 2024 06:14
Last Modified: 07 Aug 2024 06:14
URI: http://eprints.uty.ac.id/id/eprint/15875

Actions (login required)

View Item View Item
UTY Open Access is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.