AUGMENTASI DATA MENGGUNAKAN DCGAN  PADA GAMBAR TANAH

PATMAWATI PATMAWATI; Andi Sunyoto; Emha Taufiq Luthfi

doi:10.46764/teknimedia.v4i1.100

PATMAWATI PATMAWATI Universitas Amikom Yogyakarta
Andi Sunyoto Universitas Amikom Yogyakarta
Emha Taufiq Luthfi Universitas Amikom Yogyakarta

DOI: https://doi.org/10.46764/teknimedia.v4i1.100

Keywords: : Deep Convolutional Generative Adversarial Networks (DCGAN), Latent space dimension, Evaluation, Fr´echet Inception Distance (FID), Image synthesis

Abstract

Several studies related to soil type classification have been conducted. However, each of these studies uses different datasets. Only a small number of researchers share soil image datasets publicly. In addition, published datasets have an imbalance in the amount of data in each class which will result in poor model performance or over fit, especially deep learning. With data augmentation, new data variations can be formed that can handle the limited number of datasets. One of the modern augmentation models is DCGAN which is an extension of GAN. DCGAN is considered a good model in improving the stability of GAN training and the quality of image results. The resulting synthesized image is the result of mapping randomized latent vectors in an n-dimensional latent space. A meaningful image transformation is generated from the latent vector through arithmetic operations in the latent space dimension. The size of the latent space dimension is very important in enabling accurate reconstruction of the training data. To test the effect of latent space dimension on images, a quantitative evaluation using Fre'chet Inception Distance (FID) is used. The following results were obtained, for the best image quality in the alluvial soil category using latent space dimension 10 with FID score = 322.0. For clay soil category, the best image quality is generated using latent space dimension 100 with score FID = 332.84 and 512 with score FID = 322.08. In the black soil category, the best latent space dimension is 128 with FID score = 360.80. And for red soil, the best image quality is generated with the use of 512 latent spaces that have a FID score = 256.67.

References

[1] M. G. Lanjewar and O. L. Gurav, “Convolutional Neural Networks based classifications of soil images,” Multimed. Tools Appl., vol. 81, no. 7, pp. 10313–10336, 2022, doi: 10.1007/s11042-022-12200-y.
[2] R. Thakur, “Recent Trends Of Machine Learning In Soil Classification : A Review,” no. November, pp. 25–32, 2018.
[3] U. Barman and R. D. Choudhury, “Soil texture classification using multi class support vector machine,” Inf. Process. Agric., vol. 7, no. 2, pp. 318–332, 2020, doi: 10.1016/j.inpa.2019.08.001.
[4] B. Bhattacharya and D. P. Solomatine, “Machine learning in soil classification,” Neural Networks, vol. 19, no. 2, pp. 186–195, 2006, doi: 10.1016/j.neunet.2006.01.005.
[5] X. Ying, “An Overview of Overfitting and its Solutions,” J. Phys. Conf. Ser., vol. 1168, no. 2, 2019, doi: 10.1088/1742-6596/1168/2/022022.
[6] I. Marin, S. Gotovac, M. Russo, and D. Božić-Štulić, “The effect of latent space dimension on the quality of synthesized human face images,” J. Commun. Softw. Syst., vol. 17, no. 2, pp. 124–133, 2021, doi: 10.24138/jcomss-2021-0035.
[7] A. Radford, L. Metz, and S. Chintala, “Unsupervised representation learning with deep convolutional generative adversarial networks,” 4th Int. Conf. Learn. Represent. ICLR 2016 - Conf. Track Proc., pp. 1–16, 2016.
[8] K. M. N. and M. Hwang, “Finding the best k for the dimension of the latent space in autoencoders,” in International Conference on Computational Collective Intelligence, 2020, pp. 453–464. doi: 10.1007/978-3-030-63007-2 35.
[9] M. Of, T. H. E. Latent, S. On, T. O. Fit, T. H. E. Distribution, and T. H. E. A. Of, “Impact of the latent space on the ability of GANs to fit the distribution,” no. 2014, pp. 1–13, 2020.
[10] M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, and S. Hochreiter, “GANs trained by a two time-scale update rule converge to a local Nash equilibrium,” Adv. Neural Inf. Process. Syst., vol. 2017-Decem, no. Nips, pp. 6627–6638, 2017.
[11] E. Secada Purba, “IMPLEMENTATION OF GENERATIVE ADVERSARIAL NETWORKS FOR CREATING DIGITAL ARTWORK IN THE FORM OF ABSTRACT IMAGES.”
[12] B. Liu, J. Lv, X. Fan, J. Luo, and T. Zou, “Application of an Improved DCGAN for Image Generation,” Mob. Inf. Syst., vol. 2022, 2022, doi: 10.1155/2022/9005552.
[13] A. Borji, “Pros and cons of GAN evaluation measures,” Comput. Vis. Image Underst., vol. 179, pp. 41–65, 2019, doi: 10.1016/j.cviu.2018.10.009.
[14] S. K. Venu and S. Ravula, “Evaluation of deep convolutional generative adversarial networks for data augmentation of chest x-ray images,” Futur. Internet, vol. 13, no. 1, pp. 1–13, 2021, doi: 10.3390/fi13010008.
[15] “pytorch-fid,” 2023. https://pypi.org/project/pytorch-fid/