MAHARANI, DWI and Saparudin, Saparudin and Satria, Hadipurnawan (2016) PENGENALAN KARAKTER KOREA (HANGEUL) TULISAN TANGAN MENGGUNAKAN ZONE CENTROID AND ZONE (ZCZ) DAN BACKPROPAGATION. Undergraduate thesis, Sriwijaya University.
Text
RAMA_ 55201 _ 09111002063.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy |
|
Preview |
Text
RAMA_ 55201 _ 09111002063_0012046906_0018048003_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (387kB) | Preview |
Text
RAMA_ 55201 _ 09111002063_0012046906_0018048003_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (450kB) | Request a copy |
|
Text
RAMA_ 55201 _ 09111002063_0012046906_0018048003_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy |
|
Text
RAMA_ 55201 _ 09111002063_0012046906_0018048003_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (948kB) | Request a copy |
|
Text
RAMA_ 55201 _ 09111002063_0012046906_0018048003_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (86kB) | Request a copy |
|
Text
RAMA_ 55201 _ 09111002063_0012046906_0018048003_06_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (116kB) | Request a copy |
Abstract
Research in Handwritten charcter recognition is popular for various practical application in daily life activity but research in latin character is more than in nonlatin character. Korean character (Hangul) is composed in two dimensional space which is horizontal and vertical while Latin is composed in one dimensional space only. This research using Zone Centroid and Zone (ZCZ) as feature extractor and backpropagation as training and testing method. Training stage is started by choosing the training data, then the data is computed in preprocessing stage such as scaling, grayscaling, thresholding, and thinning. Next, the data’s feature will be obtained using Zone Centroid and Zone, so the feature could be the input of the training and testing phase using backpropagation. We obtained 100% recognition rate of training data and 89% recognition rate of testing data in italic and straight variation of data
Item Type: | Thesis (Undergraduate) |
---|---|
Uncontrolled Keywords: | Pengenalan karakter tulisan tangan, backpropagation, Zone Centroid and Zone (ZCZ), dan Hangul |
Subjects: | T Technology > T Technology (General) > T58.5-58.64 Information technology > T58.5 General works Management information systems Cf. HD30.213 Industrial management Cf. HF5549.5.C6+ Communication in personnel management Cf. TS158.6 Automatic data collection systems (Production control) |
Divisions: | 09-Faculty of Computer Science > 55201-Informatics (S1) |
Depositing User: | Mr Halim Sobri |
Date Deposited: | 22 Nov 2019 02:14 |
Last Modified: | 22 Nov 2019 02:14 |
URI: | http://repository.unsri.ac.id/id/eprint/17790 |
Actions (login required)
View Item |