EMAIL: PASSWORD:
Front Office
UPT. PERPUSTAKAAN
Institut Teknologi Sepuluh Nopember Surabaya


Kampus ITS Sukolilo - Surabaya 60111

Phone : 031-5921733 , 5923623
Fax : 031-5937774
E-mail : libits@its.ac.id
Website : http://library.its.ac.id

Support (Customer Service) :
timit_perpus@its.ac.id




Welcome..guys!

Have a problem with your access?
Please, contact our technical support below:
LIVE SUPPORT


Davi Wahyuni


Tondo Indra Nyata


Anis Wulandari


Ansi Aflacha




ITS » Undergraduate Theses » Matematika Ekstensi
Posted by system at 09/04/2010 15:45:15  •  3947 Views


PERANGKAT LUNAK PENGKONVERSI TEKS TULISAN TANGAN MENJADI TEKS DIGITAL

CONVERSION HANDWRITING TEXT TO DIGITAL TEXT SOFTWARE

Author :
ARIEF, ACHMAD FAUZI ( 1203109007 )




ABSTRAK

Teks digital adalah data yang terdiri dari karakter-karakter yang menyatakan kata-kata untuk berkomunikasi oleh manusia dalam bentuk tulisan di dalam sistem komputer. Di dalam sistem komputer terdapat data-data yang berupa teks dokumen dan citra. Data-data tersebut dapat diolah dalam berbagai macam perangkat lunak untuk kebutuhan kantor bisnis dan lain sebagainya. Apabila data yang dibutuhkan dalam kebutuhan kantor bisnis dan lainnya adalah data teks tulisan tangan berupa citra maka dibuat suatu perangkat lunak yang dapat mengolah data citra tersebut menjadi data teks tulisan berbentuk teks digital. Pada tugas akhir ini akan dibuat suatu perangkat lunak yang dapat mengolah teks tulisan tangan menjadi teks digital. Dalam proses pembuatan perangkat lunak ini menggunakan teks tulisan tangan sebagai citra masukan. Data tersebut diproses dan diwujudkan dalam pengolahan citra dengan proses segmentasi menggunakan thresholding kemudian hasil dari pengolahan citra dimasukan sebagai input unit pada jaringan syaraf tiruan standart backpropagation yang berfungsi sebagai pengambil keputusan dengan tujuan mengenali teks tulisan tangan tersebut dan selanjutnya diwujudkan dalam bentuk teks digital dalam sistem komputer berkode ASCII. Dari hasil uji coba yang telah dilakukan menunjukkan selama pengambilan data karakter didapat jumlah keseluruhan epoch 164000 jumlah keseluruhan squared error 01031610851753050 dan jumlah keseluruhan klasifikasi piksel error 54930 dengan neuron error 36032 dan jumlah output neuron 656000. Dan hasil uji coba pada pengenalan setiap karakter teks menunjukkan prosentasi rata-rata keberhasilan 6658 dan pengkonversian teks sebesar 5000.


ABSTRACT

Digital text is the data consisting of characters saying the words to communicate by humans in the form of writting in the computer system. In the computer system there is data in the form of text documents and images. Theses data can be processed in a variety of software for the needs of office businesses and others. If the data needed in the office businesses and others needs are handwriting text data in the form of images then created a software that can process the image data into text data written form of digital text. In this final project will be made a software that can process handwriting text into digital text. In the process of making this software using handwriting text as input image. The data is processed and embodied in image processing by using a thresholding segmentation process then the result of image processing as input unit included in the standard backpropagation neural networks that functioning as decision makers with the aim of recognizing the handwriting text and then realized in the form of digital text in the ASCII-coded of computer system. From the results that have been done showing for the character data acquisition obtained number of epoch 164000 total squared error 0.1031610851753050 and number of pixel classification error 5.4930 with 36032 neuron errors and number of output neurons 656000. And the test results to the recognition of each character shows the average percentage of success 66.58 and the conversion text 50.00.



KeywordsTeks Tulisan Tangan, Teks Digital, Pengolahan Citra Digital, Jaringan Syaraf Tiruan Backpropagation
 
Subject:  Program komputer
Contributor
  1. Drs. NURUL HIDAYAT, M.Kom
Date Create: 12/02/2010
Type: Text
Format: pdf
Language: Indonesian
Identifier: ITS-Undergraduate-3100010038451
Collection ID: 3100010038451
Call Number: RSMa 005.1 Ari p


Source
Undergraduate Theses, Mathematics, RSMa 005.1 Ari p, 2010

Coverage
ITS Community

Rights
Copyright @2010 by ITS Library. This publication is protected by copyright and per obtained from the ITS Library prior to any prohibited reproduction, storage in a re transmission in any form or by any means, electronic, mechanical, photocopying, reco For information regarding permission(s), write to ITS Library




[ Download - Open Access ]

  1.  ITS-Undergraduate-9291-Abstract_id.pdf - 22 KB
  2.  ITS-Undergraduate-9291-Abstract_en.pdf - 20 KB
  3.  ITS-Undergraduate-9291-Paper.pdf - 237 KB




 Similar Document...




! ATTENTION !

To facilitate the activation process, please fill out the member application form correctly and completely

Registration activation of our members will process up to max 24 hours (confirm by email). Please wait patiently

POLLING

Bagaimana pendapat Anda tentang layanan repository kami ?

Bagus Sekali
Baik
Biasa
Jelek
Mengecewakan





You are connected from 10.199.6.2
using CCBot/2.0 (https://commoncrawl.org/faq/)



Copyright © ITS Library 2006 - 2021 - All rights reserved.
Dublin Core Metadata Initiative and OpenArchives Compatible
Developed by Hassan