Implementasi algoritma learning vector quantization dalam pengenalan tulisan tangan aksara Sunda

Mustofa, Dede Rizal (2019) Implementasi algoritma learning vector quantization dalam pengenalan tulisan tangan aksara Sunda. Diploma thesis, UIN Sunan Gunung Djati Bandung.

[img]
Preview
Text (COVER)
1_cover.pdf

Download (53kB) | Preview
[img]
Preview
Text (ABSTRAK)
2_abstrak.pdf

Download (45kB) | Preview
[img]
Preview
Text (DAFTAR ISI)
3_daftarisi.pdf

Download (1MB) | Preview
[img]
Preview
Text (BAB I)
4_bab1.pdf

Download (209kB) | Preview
[img] Text (BAB II)
5_bab2.pdf
Restricted to Registered users only

Download (679kB) | Request a copy
[img] Text (BAB III)
6_bab3.pdf
Restricted to Registered users only

Download (1MB) | Request a copy
[img] Text (BAB IV)
7_bab4.pdf
Restricted to Registered users only

Download (748kB) | Request a copy
[img] Text (BAB V)
8_bab5.pdf
Restricted to Registered users only

Download (109kB) | Request a copy
[img] Text (DAFTAR PUSTAKA)
9_daftarpustaka.pdf
Restricted to Registered users only

Download (115kB) | Request a copy

Abstract

INDONESIA Pengenalan tulisan tangan aksara Sunda merupakan bagian dari proses pengenalan pola, dimana dalam setiap proses pengenalan aksara ini lebih mengutamakan pada pola-pola setiap aksara. Untuk proses pengenalan pola aksara secara umum diterapkan proses pembelajaran atau pelatihan pada sebuah mesin komputer agar dapat mengenali aksara berdasarkan pola aksara dan ciri-ciri yang dimiliki aksara tersebut sesuai dengan contoh data aksara yang diberikan pada komputer tersebut. Dilihat dari sisi kebudayaan, aksara Sunda merupakan salahsatu bagian kebudayaan Sunda dan sudah menjadi ciri khas dan kebanggaan masyarakat Sunda (Jawa Barat). Aksara Sunda merupakan bagian dari tata tulis atau sistem pengaksaraan dalam bahasa Sunda. Aksara Sunda itu sendiri terdiri dari 7 aksara Swara dan 25 aksara Ngalagena (konsonan) sehingga total aksara Sunda berjumlah 32 aksara, dimana setiap aksara mempunyai bentuk dan pola yang berbeda antara satu dengan yang lainnya. Hal yang berkaitan dengan pola bertambah rumit ketika pada umumya aksara itu berupa tulisan tangan, dimana variasi tulisan dari setiap individu pasti berbeda dengan yang lainnya. Untuk mengatasi perubahan pola dalam pengenalan tulisan tangan aksara Sunda oleh sebuah mesin komputer, maka diterapkanlah metode Learning Vector Quantization (LVQ) berdasarkan hasil ektrasi ciri dari Gray Level Co-Occurrence (GLCM) yang diimplementasikan pada pemrograman matlab. Pada hasil akhir pengujian diperoleh hasil pengenalan tulisan tangan aksara Sunda dengan ketepatan akurasi sebesar 65,7143%. ENGLISH The introduction of handwriting Sundanese is part of the pattern recognition process, where each process of introducing this script prioritizes the patterns of each script. For the process of character recognition in general a learning or training process is needed on a computer machine in order to be able to recognize characters based on the patterns and characteristics of the characters in accordance with the examples given on the computer. In terms of Sundanese script culture is one part of Sundanese culture and is a characteristic and pride of Sundanese society (West Java). Sundanese script is part of the writing system or literary system in Sundanese. Sundanese characters consist of 7 Swara characters and 25 Ngalagena consonant characters so that the total Sundanese characters are 32, where each script has a shape and pattern that is different from one another. In general, things related to the pattern will get more complicated when the script is in the form of handwriting, where the writing of each individual must have different variations from one another. To overcome the changing pattern in the introduction of Sundanese script handwriting by a computer machine, the method Learning Vector Quantization (LVQ) is applied. Based on the results of feature extraction from Gray Level Co-Occurrence (GLCM), which is implemented in matlab programming. At the end of the test the results of the Sundanese script handwriting recognition are obtained with an accuracy of 65,7143%.

Item Type: Thesis (Diploma)
Uncontrolled Keywords: lvq; glcm; aksara sunda; citra; matlab;
Subjects: Indonesia
Educational Institutions, Schools and Their Activities > School Laboratories
Educational Institutions, Schools and Their Activities > Special Education
Divisions: Fakultas Sains dan Teknologi > Program Studi Teknik Informatika
Depositing User: dede rizal mustofa
Date Deposited: 17 May 2019 08:05
Last Modified: 17 May 2019 08:05
URI: http://digilib.uinsgd.ac.id/id/eprint/20400

Actions (login required)

View Item View Item