PENGENALAN TULISAN HIRAGANA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK

HARAHAP, IRFAN WIJAYA and Fachrurrozi, Muhammad (2021) PENGENALAN TULISAN HIRAGANA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_55201_09021381520058.pdf] Text
RAMA_55201_09021381520058.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (63MB) | Request a copy
[thumbnail of RAMA_55201_09021381520058_TURNITIN.pdf] Text
RAMA_55201_09021381520058_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (73MB) | Request a copy
[thumbnail of RAMA_55201_09021381520058_0222058001_01_front_ref.pdf]
Preview
Text
RAMA_55201_09021381520058_0222058001_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (5MB) | Preview
[thumbnail of RAMA_55201_09021381520058_0222058001_02.pdf] Text
RAMA_55201_09021381520058_0222058001_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (2MB) | Request a copy
[thumbnail of RAMA_55201_09021381520058_0222058001_03.pdf] Text
RAMA_55201_09021381520058_0222058001_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (6MB) | Request a copy
[thumbnail of RAMA_55201_09021381520058_0222058001_04.pdf] Text
RAMA_55201_09021381520058_0222058001_04.pdf - Accepted Version
Restricted to Repository staff only

Download (47MB) | Request a copy
[thumbnail of RAMA_55201_09021381520058_0222058001_05.pdf] Text
RAMA_55201_09021381520058_0222058001_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (2MB) | Request a copy
[thumbnail of RAMA_55201_09021381520058_0222058001_06.pdf] Text
RAMA_55201_09021381520058_0222058001_06.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (126kB) | Request a copy
[thumbnail of RAMA_55201_09021381520058_0222058001_07_ref.pdf] Text
RAMA_55201_09021381520058_0222058001_07_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (87kB) | Request a copy
[thumbnail of RAMA_55201_09021381520058_0222058001_08_lamp.pdf] Text
RAMA_55201_09021381520058_0222058001_08_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (222kB) | Request a copy

Abstract

In the last few decades the Convolutional Neural Network has had outstanding results in various fields related to pattern recognition, one of which is the recognition of Hiragana's writing. For foreigners, hiragana characters are difficult to understand because they have similar characteristics. This study aims to develop software that can recognize hiragana writing using the Convolutioanal Neural Network method. The most optimal architecture for recognizing hiragana writing has a filter size of 3x3 and a learning rate of 0.005. From these results it can be concluded that the Convolutional Neural Network can be used to recognize Hiragana's writing.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Pengenalan Tulisan, Convolutional Neural Network
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics > TA1632.A48 Image processing.
T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics > TA1632.B35 Image processing--Digital techniques. Pattern recognition systems
Divisions: 09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User: Irfan Wijaya Harahap
Date Deposited: 14 Oct 2021 04:59
Last Modified: 14 Oct 2021 04:59
URI: http://repository.unsri.ac.id/id/eprint/55865

Actions (login required)

View Item View Item