Yıl: 2020 Cilt: 4 Sayı: 1 Sayfa Aralığı: 1 - 9 Metin Dili: İngilizce DOI: 10.26650/acin.763353 İndeks Tarihi: 03-12-2020

Baby Face Generation with Generative Adversarial Neural Networks: A Case Study

Öz:
Generative Adversarial Networks (GANs) are increasingly applied to train generative models with neuralnetworks, especially in computer vision studies. Since being introduced in 2014, many image generationstudies incorporating GANs have demonstrated promising results for producing highly convincing fakeimages of animals, landscapes, and human faces. We build a GAN structure to generate realistic baby faceimages from a small data set of 673 color 200×200 pixel images obtained from a Kaggle data set by followingprevious studies that demonstrated how GANs could be used for image generation from a limited number oftraining samples. The reason we limit especially as baby faces is that we aim to achieve success with a limitednumber of training data. For evaluation, experiments and case studies are one of the most consideredtechniques. The results of this study help identify issues requiring further investigation in comment analysisresearch. In this context, we presented the loss values of the generator and discriminator during the trainingprocess. The discriminator losses are around of 0.7 and the generator is between 0.7 and 0.9. The high qualityimages are produced about 300th epochs.
Anahtar Kelime:

Çekişmeli Üretici Sinir Ağları ile Bebek Yüz Üretimi: Bir Vaka Çalışması

Öz:
Çekişmeli Üretici Sinir Ağları (GAN) son zamanlarda özellikle bilgisayarlı görme çalışmalarında sinir ağlarına sahip üretken modelleri eğitmek için kullanılan popüler bir konudur. GAN’lar 2014 yılında araştırmacılara tanıtıldığından beri, özellikle GAN’larla görüntü oluşturma çalışmaları gittikçe artmaktadır. Bu çalışmalar, hayvanlar, manzaralar, insan yüzleri vb. gibi son derece ikna edici sahte görüntüler üretmek için umut verici sonuçlar elde etmiştir. Bu çalışmada gerçekçi yüz görüntüleri oluşturmak için bir GAN yapısı oluşturulması amaçlanmıştır. Daha az sayıda eğitim verisiyle gerçekçi resimler üretebilmek için veri seti içerisinde sadece bebek yüzleri kullanılmıştır. Çalışma kapsamında bir GAN yapısı inşa edilerek, Kaggle veri tabanından elde edilen 673 adet renkli 200x200 piksel boyutunda bebek yüz görüntüsü veri kümesinden yeni bebek yüzü görüntüleri oluşturulmaktadır. Önceki çalışmalar GAN’ların sınırlı sayıda eğitim örneği içeren veri kümeleri için görüntü oluşturmada kullanılabileceğini göstermektedir. Değerlendirme yöntemleri ile ilgili olarak, deneyler ve vaka çalışmaları en çok dikkate alınan tekniklerden biridir. Bu çalışmanın sonuçları, daha fazla araştırma yapılmasını gerektiren hususların belirlenmesine yardımcı olabilir.
Anahtar Kelime:

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık
  • Antipov, G., Baccouche, M., & Dugelay, J. L. (2017). Face aging with conditional generative adversarial networks. In Proceedings of the IEEE International Conference on Image Processing (pp. 2089-2093).
  • Bao, J., Chen, D., Wen, F., Li, H., & Hua, G. (2017). CVAE-GAN: fine-grained image generation through asymmetric training. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2745-2754).
  • Bazrafkan, S., & Corcoran, P. (2018). Versatile auxiliary regressor with generative adversarial network (VAR+ GAN). arXiv preprint arXiv:1805.10864.
  • Chen, Z. L., He, Q. H., Pang, W. F., & Li, Y. X. (2018). Frontal face generation from multiple pose-variant faces with cgan in real-world surveillance scene. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 1308-1312).
  • Chen, H. Y., & Lu, C. J. (2019). Nested Variance Estimating VAE/GAN for Face Generation. In Proceedings of the International Joint Conference on Neural Networks (pp. 1-8).
  • Choe, J., Park, S., Kim, K., Hyun Park, J., Kim, D., & Shim, H. (2017). Face generation for low-shot learning using generative adversarial networks. In Proceedings of the IEEE International Conference on Computer Vision Workshops (pp. 1940-1948).
  • Duarte, A., Roldan, F., Tubau, M., Escur, J., Pascual, S., Salvador, A., ... & Giro-i-Nieto, X. (2019). Wav2Pix: Speech-conditioned Face Generation Using Generative Adversarial Networks. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (pp. 8633-8637).
  • Frid-Adar, M., Diamant, I., Klang, E., Amitai, M., Goldberger, J., & Greenspan, H. (2018). GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification. Neurocomputing, 321, 321-331.
  • Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N. D., & Weinberger, K. Q. (2014). Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems.
  • Günel, M., & Erkut Erdem, A. E. Kisi Görüntülerinin Nitelik Esaslı Üretilmesi Generating Person Images Based on Attributes.
  • Kdnuggets 2017, “Generative Adversarial Networks – Hot Topic in Machine Learning”. https://www.kdnuggets.com/2017/01/generative-adversarialnetworks- hot-topic-machine-learning.html (2017).
  • Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  • Li, W., Ding, W., Sadasivam, R., Cui, X., & Chen, P. (2019). His-GAN: A histogram-based GAN model to improve data generation quality. Neural Networks, 119, 31-45.
  • Liu, X., Kumar, B. V., Ge, Y., Yang, C., You, J., & Jia, P. (2018). Normalized face image generation with perceptron generative adversarial networks. In Proceedings of the IEEE International Conference on Identity, Security, and Behavior Analysis (pp. 1-8).
  • Lu, Y., Tai, Y. W., & Tang, C. K. (2018). Attribute-guided face generation using conditional cyclegan. In Proceedings of the European Conference on Computer Vision (pp. 282-297).
  • Lu, Y., Wu, S., Tai, Y. W., & Tang, C. K. (2018). Image generation from sketch constraint using contextual gan. In Proceedings of the European Conference on Computer Vision (pp. 205-220).
  • Mao, X., Li, Q., Xie, H., Lau, R. Y., Wang, Z., & Paul Smolley, S. (2017). Least squares generative adversarial networks. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2794-2802).
  • Peng, F., Zhang, L. B., & Long, M. (2019). Fd-gan: Face de-morphing generative adversarial network for restoring accomplice’s facial image. IEEE Access, 7, 75122-75131.
  • Seeliger, K., Güçlü, U., Ambrogioni, L., Güçlütürk, Y., & van Gerven, M. A. (2018). Generative adversarial networks for reconstructing natural images from brain activity. NeuroImage, 181, 775-785.
  • Shen, Y., Zhou, B., Luo, P., & Tang, X. (2018). Facefeat-gan: a two-stage approach for identity-preserving face synthesis. arXiv preprint arXiv:1812.01288.
  • Singh, V. K., Rashwan, H. A., Romani, S., Akram, F., Pandey, N., Sarker, M. M. K., ... & Torrents-Barrena, J. (2020). Breast tumor segmentation and shape classification in mammograms using generative adversarial and convolutional neural network. Expert Systems with Applications, 139, 112855.
  • Song, Y., Zhu, J., Li, D., Wang, X., & Qi, H. (2018). Talking face generation by conditional recurrent adversarial network. arXiv preprint arXiv:1804.04786.
  • Tian, Y., Peng, X., Zhao, L., Zhang, S., & Metaxas, D. N. (2018). CR-GAN: learning complete representations for multi-view generation. arXiv preprint arXiv:1806.11191.
  • Wan, L., Wan, J., Jin, Y., Tan, Z., & Li, S. Z. (2018). Fine-grained multi-attribute adversarial learning for face generation of age, gender and ethnicity. In Proceedings of the International Conference on Biometrics (pp. 98-103).
  • Wang, F., Zhang, Z., Liu, C., Yu, Y., Pang, S., Duić, N., ... & Catalão, J. P. (2019). Generative adversarial networks and convolutional neural networks based weather classification model for day ahead short-term photovoltaic power forecasting. Energy conversion and management, 181, 443-462.
  • Ye, L., Zhang, B., Yang, M., & Lian, W. (2019). Triple-translation GAN with multi-layer sparse representation for face image synthesis. Neurocomputing, 358, 294-308.
  • Zhu, L., Chen, Y., Ghamisi, P., & Benediktsson, J. A. (2018). Generative adversarial networks for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 56(9), 5046-5063.
  • Zhang, Z., Pan, X., Jiang, S., & Zhao, P. (2019). High-quality Face Image Generation based on Generative Adversarial Networks. Journal of Visual Communication and Image Representation, 102719.
APA ORTAÇ G, DOGAN Z, Orman Z, ŞAMLI R (2020). Baby Face Generation with Generative Adversarial Neural Networks: A Case Study. , 1 - 9. 10.26650/acin.763353
Chicago ORTAÇ GİZEM,DOGAN ZELIHA,Orman Zeynep,ŞAMLI RÜYA Baby Face Generation with Generative Adversarial Neural Networks: A Case Study. (2020): 1 - 9. 10.26650/acin.763353
MLA ORTAÇ GİZEM,DOGAN ZELIHA,Orman Zeynep,ŞAMLI RÜYA Baby Face Generation with Generative Adversarial Neural Networks: A Case Study. , 2020, ss.1 - 9. 10.26650/acin.763353
AMA ORTAÇ G,DOGAN Z,Orman Z,ŞAMLI R Baby Face Generation with Generative Adversarial Neural Networks: A Case Study. . 2020; 1 - 9. 10.26650/acin.763353
Vancouver ORTAÇ G,DOGAN Z,Orman Z,ŞAMLI R Baby Face Generation with Generative Adversarial Neural Networks: A Case Study. . 2020; 1 - 9. 10.26650/acin.763353
IEEE ORTAÇ G,DOGAN Z,Orman Z,ŞAMLI R "Baby Face Generation with Generative Adversarial Neural Networks: A Case Study." , ss.1 - 9, 2020. 10.26650/acin.763353
ISNAD ORTAÇ, GİZEM vd. "Baby Face Generation with Generative Adversarial Neural Networks: A Case Study". (2020), 1-9. https://doi.org/10.26650/acin.763353
APA ORTAÇ G, DOGAN Z, Orman Z, ŞAMLI R (2020). Baby Face Generation with Generative Adversarial Neural Networks: A Case Study. Acta Infologica, 4(1), 1 - 9. 10.26650/acin.763353
Chicago ORTAÇ GİZEM,DOGAN ZELIHA,Orman Zeynep,ŞAMLI RÜYA Baby Face Generation with Generative Adversarial Neural Networks: A Case Study. Acta Infologica 4, no.1 (2020): 1 - 9. 10.26650/acin.763353
MLA ORTAÇ GİZEM,DOGAN ZELIHA,Orman Zeynep,ŞAMLI RÜYA Baby Face Generation with Generative Adversarial Neural Networks: A Case Study. Acta Infologica, vol.4, no.1, 2020, ss.1 - 9. 10.26650/acin.763353
AMA ORTAÇ G,DOGAN Z,Orman Z,ŞAMLI R Baby Face Generation with Generative Adversarial Neural Networks: A Case Study. Acta Infologica. 2020; 4(1): 1 - 9. 10.26650/acin.763353
Vancouver ORTAÇ G,DOGAN Z,Orman Z,ŞAMLI R Baby Face Generation with Generative Adversarial Neural Networks: A Case Study. Acta Infologica. 2020; 4(1): 1 - 9. 10.26650/acin.763353
IEEE ORTAÇ G,DOGAN Z,Orman Z,ŞAMLI R "Baby Face Generation with Generative Adversarial Neural Networks: A Case Study." Acta Infologica, 4, ss.1 - 9, 2020. 10.26650/acin.763353
ISNAD ORTAÇ, GİZEM vd. "Baby Face Generation with Generative Adversarial Neural Networks: A Case Study". Acta Infologica 4/1 (2020), 1-9. https://doi.org/10.26650/acin.763353