Batik Clothes Auto-Fashion using Conditional Generative Adversarial Network and U-Net

Tirtawan, Timothius; Susanto, Evan Kusuma; Zaman, P. C. S.W Lukman; Kristian, Yosi

doi:10.1109/eiconcit50028.2021.9431867

Cited by 5 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concurrently, there is a demand for innovative approaches to enhance the diversity of batik motifs, thus facilitating the creation of new designs. To address these challenges, various research efforts focusing on generating new motif using generative adversarial networks [ [2] , [3] , [4] , [5] , [6] ] and diffusion [ 7 ] have been initiated. Although the Batik Nitik 960 dataset, introduced by Minarno [ 8 ], is valuable, it lacks comprehensive identification motif pairs.…”

Section: Introductionmentioning

confidence: 99%

Dataset of Batik Nitik Sarimbit 120

Minarno,

Soesanti,

Nugroho

2024

Data in Brief

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Dataset of Batik Nitik Sarimbit 120

Minarno,

Soesanti,

Nugroho

2024

Data in Brief

View full text Add to dashboard Cite

“…Batik is generally created by craftsmen using specific techniques, including dyeing, printing, stamping, and dabbing. Each technique has a different difficulty level, thereby depicting imperfection in drawing Batik pattern [3], [4]. Every craftsman who draws Batik can also not necessarily draw various types of Batik.…”

Section: Introductionmentioning

confidence: 99%

Generation of Batik Patterns Using Generative Adversarial Network with Content Loss Weighting

Minarno¹,

Antoko²,

Azhar³

2023

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

Every craftsman who draws Batik can also not necessarily draw various types of Batik. On the other hand, it takes a long time ranging from weeks to months, to make Batik. Image generation is regarded as an essential part of the field of computer vision. One of the popular methods includes the Generative Adversarial Network, commonly implemented to generate a new data set from an existing one. One model of the Generative Adversarial Network is BatikGAN SL generating batik images by inserting the two Batik patterns to produce a new Batik image. Currently, the generated Batik image does not maintain the input of the Batik pattern. Therefore, this study proposes a GAN model of BatikGAN SL, with the addition of a content loss function using hyperparameters to weight the content loss function. The content loss function is added from the Neural Transfer Style method. Previously, the style loss function in this method has been implemented in BatikGAN SL, and the dataset consists of Batik patches (326 images) and real Batik (163 images). This paper compares the BatikGAN SL model from previous studies with the BatikGAN SL model by implementing hyperparameters on the content loss function. The evaluation is conducted with FID, containing FID Local and FID Global. The results obtained in this study include a collection of Batik images, test evaluation value of 42 on FID Global and 16 on FID Local. These results are obtained by implementing the content loss function with a weight value of 1.

show abstract