Batik Classification Using Convolutional Neural Network with Data Improvements

Meranggi, Dewa G. T.; Yudistira, Novanto; Sari, Yuita Arum

doi:10.30630/joiv.6.1.716

Cited by 8 publications

(5 citation statements)

References 14 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Employed the ResNet-18 architecture, which sped up training by using a pre-trained model. The new dataset's patch method of 88.88% 0.88 yielded the best test results [15]. Then there is also research conducted by Agastya et al.…”

Section: Introductionmentioning

confidence: 90%

Image Classification On Garutan Batik Using Convolutional Neural Network with Data Augmentation

Fitriani

Tresnawati

Sukriyansah

2023

JUITA

View full text Add to dashboard Cite

In Indonesia, Batik is one of the cultural assets in the field of textiles with various styles. There are many types of batik in Indonesia, one of which is Batik Garutan. Batik Garutan has different motifs that show the characteristics of Batik Garutan itself. Therefore, to distinguish the features of Batik Garutan from another batik, a system is needed to classify the types of batik patterns. Classification of batik patterns can be done using image classification. In image classification, there are methods to increase the size and quality of the limited training dataset by performing data augmentation. This study aims to obtain an image classification model by applying data augmentation. The image classification process is carried out using the Deep Learning method with the Convolutional Neural Network algorithm, which is expected to be helpful as a reference for research and can be applied to software development related to image classification. This study generated models from several experiments with different epoch parameters and dataset proportions. A system obtained the investigation with the best performance with a data proportion of 9:1, resulting in an accuracy value of 91 percent.

show abstract

Section: Introductionmentioning

confidence: 90%

Image Classification On Garutan Batik Using Convolutional Neural Network with Data Augmentation

Fitriani

Tresnawati

Sukriyansah

2023

JUITA

View full text Add to dashboard Cite

show abstract

“…Budaya Indonesia yang begitu kaya dan beragam menyebabkan begitu banyak terciptanya berbagai motif dan jenis batik tradisional yang berbeda-beda dan memiliki keunikannya sendiri-sendiri [2]. Namun sayangnya, masih begitu banyak masyarakat Indonesia yang masih belum dapat membedakan jenis-jenis batik berdasarakan motifnya [3].…”

Section: Pendahuluanunclassified

Use of Augmentation Data and Hyperparameter Tuning in Batik Type Classification using the CNN Model

Auliaddina,

Arifin

2024

SISTEMASI

View full text Add to dashboard Cite

Batik adalah salah satu budaya seni Indonesia yang paling dikenal di dunia dan memiliki motif serta jenis batik tradisional yang berbeda-beda dan memiliki keunikannya sendiri-sendiri. Namun sayangnya, masih begitu banyak masayarakat Indonesia yang belum dapat membedakan jenis-jenis batik berdasarakan motifnya. Karena itulah dibutuhkan sebuah cara untuk membantu masyarakat agar mudah untuk dapat membedakan jenis-jenis batik berdasarkan motifnya. Penelitian ini bertujuan untuk mengklasifikasikan jenis-jenis batik berdasarkan motifnya dengan menggunakan model deep learning Convolutional Neural Network dengan menggunakan Data Augmentation dan Hyperparameter Tuning. CNN termasuk dalam jenis Deep Neural Network karena kedalaman jaringannya yang tinggi dan banyak diterapkan pada data citra. Selain itu diterapkan pula Data Augmentation dan Hyperparameter Tuning untuk mengurangi overfitting. Hasil dari penelitian ini menunjukkan model CNN yang menggunakan optimasi Data Augmentation dan Hyperparameter Tuning mendapatkan nilai akurasi validasi, presisi dan recall jauh lebih tinggi yaitu sebesar 66,67% dibandingkan dengan mode CNN yang tidak menggunakan Data Augmentation dan Hyperparameter Tuning yang memiliki akurasi validasi, presisi, dan recall sebesar 28,15%. Selain itu diantara Data Augmentation dan Hyperparameter Tuning, Data Augmentation lah yang paling mempengaruhi peningkatan akurasi validasi, presisi, dan recall dibandingkan Hyperparameter Tuning dengan peningkatan akurasi validasi menjadi 64% dari akurasi validasi sebesar 28,15%.

show abstract

“…Of all scale distances obtained then searched the minimum distance or shortest distance. The result of this is the closest distance batik pattern image can be classified and identified in accordance with the group [19].…”

Section: Research About Batik By Adding a Discrete Wavelet Transform ...mentioning

confidence: 99%

Spatial and topology feature extraction on batik pattern recognition: a review

Kasim¹,

Bakri²,

Hendra³

et al. 2022

Jurnal Informatika

View full text Add to dashboard Cite

Batik is an Indonesian cultural heritage that has been recognized by UNESCO as an international cultural heritage on October 2, 2009. Patterns of batik produce geometric shapes unique, the number and name of the batik patterns make it difficult to recognize each motif. The objective classification of batik is split image into classes according to the pattern motif motive so easy to recognize in accordance with its feature. Batik can be classified based on the shape of the motive, namely geometric motifs, geometric motifs and motifs non specific. Spatial information is an important aspect of image processing such as computer vision and recognition structure / pattern in the context of modelling and resolution of the uncertainty caused by the ambiguity in the low-level features. Shortcomings inherent in combining two colours and spatial features are not adaptive pattern recognition process of the region across multiple images and histogram matching is not appropriate to capture the colours on the image content. This study discussed a model of spatial features and feature combinations topology with the aim to improve the validation batik image pattern recognition so that the level of the pattern recognition motif batik image could be better. Some of the features that have been used include colour features and spatial features. In addition, this paper discusses the possibility of combining the features in pattern recognition. This paper proposes a combination of features that will be able to improve the validation of image pattern recognition of batik.

show abstract

Batik Classification Using Convolutional Neural Network with Data Improvements

Cited by 8 publications

References 14 publications

Image Classification On Garutan Batik Using Convolutional Neural Network with Data Augmentation

Image Classification On Garutan Batik Using Convolutional Neural Network with Data Augmentation

Use of Augmentation Data and Hyperparameter Tuning in Batik Type Classification using the CNN Model

Spatial and topology feature extraction on batik pattern recognition: a review

Contact Info

Product

Resources

About