NURFAJRI, ROBBY BIRHAM (2022) KLASIFIKASI JENIS BATIK DAERAH MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK BERBASIS TELEGRAM BOT. Undergraduate thesis, Universitas Stikubank.
![[thumbnail of HALAMAN JUDUL]](/style/images/fileicons/application_pdf.png) |
PDF (HALAMAN JUDUL)
Download (2MB) |
|
PDF (ABSTRAK)
Download (141kB) |
|
PDF (BAB I)
Download (195kB) |
|
PDF (BAB II)
Restricted to Repository staff only Download (257kB) |
|
PDF (BAB III)
Restricted to Repository staff only Download (872kB) |
|
PDF (BAB IV)
Restricted to Repository staff only Download (2MB) |
|
PDF (BAB V)
Restricted to Repository staff only Download (125kB) |
|
PDF (DAFTAR PUSTAKA)
Download (84kB) |
|
PDF (LAMPIRAN)
Restricted to Repository staff only Download (3MB) |
Abstract
Batik pada setiap daerah di Nusantara memiliki ragam hias dengan ciri khusus pada tiap daerah. Saat ini yang sering terjadi dalam mengenal pola motif batik dari daerah tertentu sering mengalami kesulitan karena beragamnya motif batik yang dimiliki oleh setiap daerah. Sedemikian beragamnya motif batik dari berbagai daerah diperlukan identifikasi satu motif yang dapat mencirikan kekhasan satu daerah. Menyikapiahal-halatersebut, diperlukan satu aplikasi yang bisa melakukan deteksiadanaklasifikasi motif batik berdasarkan daerah asal melalui telegram bot. Metode yang digunakan untuk mengidentifikasi keberagaman motif menggunakan ConvolutionalaNeuralaNetwork (CNN) dengan arsitekturaResNet 50. Hasil dari training model klasifikasi Convolutional Neural Network diuji dengan data test menghasilkan hasil yang cukup baik dengan nilai akurasi 96%. Hasil uji klasifikasi data test berupa data lain berjumlah 1180 gambar dengan masing-masing kelas terdiri dari 60-70 gambar diperoleh akurasi yang cukup baik sebesar 69%. Aplikasi ini harapannya dapat membantu masyarakat untuk mengenali dan mengidentifikasi jenis batik daerah menggunakan telegram bot. Batik in each region in the archipelago has a variety of decorations with special characteristics in each region. Currently, what often happens in recognizing patterns of batik motifs from certain regions is that they often experience difficulties because of the variety of batik motifs owned by each region. With such a variety of batik motifs from various regions, it is necessary to have a motif that can characterize the uniqueness of a region. In response to these things, we need an application that can detect and classify batik motifs based on the region of origin via a telegram bot. The method used to identify the diversity of motifs using Convolutional Neural Network (CNN) with ResNet 50 architecture. The results of the Convolutional Neural Network classification training model were tested with data testing yielding fairly good results with an accuracy value of 96%. The results of the test data classification test in the form of other data found 1180 images with each class consisting of 60-70 images obtained a fairly good accuracy of 69%. It is hoped that this application can help the community to recognize and identify the types of regional batik using telegram bots.
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Additional Information: | SKR.I.05.01.2191 NIM.17.01.53.0101 |
| Uncontrolled Keywords: | Convolutional Neural Network, KlasifikasiaJenis Batik Daerah Deep Learning, Arsitektur ResNet50. Convolutional Neural Network, Deep Learning, ResNet50 Architecture,Classification of Regional Batik Types. |
| Subjects: | Q Science > QA Mathematics > QA76 Computer software |
| Faculty / Institution: | Fakultas Teknologi Informasi > Program Studi Teknik Informatika |
| Depositing User: | Teteh Hayati |
| Date Deposited: | 27 Sep 2022 03:13 |
| Last Modified: | 27 Sep 2022 03:13 |
| URI: | https://eprints.unisbank.ac.id/id/eprint/8719 |
Actions (login required)
 |
View Item |
