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

Öz

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

Anahtar Kelimeler

• GANs
• Image Generation
• Face Generation

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 Kelimeler

• Çekişmeli Üretici Ağlar
• Resim Sentezleme
• Yüz Resmi Sentezleme

Kaynakça

1. Antipov, G., Baccouche, M., & Dugelay, J. L. (2017, September). Face aging with conditional generative adversarial networks. In 2017 IEEE international conference on image processing (ICIP) (pp. 2089-2093). IEEE.
2. 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).
3. Bazrafkan, S., & Corcoran, P. (2018). Versatile auxiliary regressor with generative adversarial network (VAR+ GAN). arXiv preprint arXiv:1805.10864.
4. Chen, Z. L., He, Q. H., Pang, W. F., & Li, Y. X. (2018, April). Frontal face generation from multiple pose-variant faces with cgan in real-world surveillance scene. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1308-1312). IEEE.
5. Chen, H. Y., & Lu, C. J. (2019, July). Nested Variance Estimating VAE/GAN for Face Generation. In 2019 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.
6. 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).
7. Duarte, A., Roldan, F., Tubau, M., Escur, J., Pascual, S., Salvador, A., ... & Giro-i-Nieto, X. (2019, March). Wav2Pix: Speech-conditioned Face Generation Using Generative Adversarial Networks. In ICASSP (pp. 8633-8637).
8. 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.

9. 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 2014, December 8-13 2014. Montreal, Quebec, Canada.
10. 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”.
11. https://www.kdnuggets.com/2017/01/generative-adversarial- networks-hot-topic-machine-learning.html (2017).
12. Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
13. 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.
14. Liu, X., Kumar, B. V., Ge, Y., Yang, C., You, J., & Jia, P. (2018, January). Normalized face image generation with perceptron generative adversarial networks. In 2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis (ISBA) (pp. 1-8). IEEE.
15. 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 (ECCV) (pp. 282-297).
16. 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 (ECCV) (pp. 205-220).
17. 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).
18. 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.
19. 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.
20. 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.
21. 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.
22. Song, Y., Zhu, J., Li, D., Wang, X., & Qi, H. (2018). Talking face generation by conditional recurrent adversarial network. arXiv preprint arXiv:1804.04786.
23. 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.
24. Wan, L., Wan, J., Jin, Y., Tan, Z., & Li, S. Z. (2018, February). Fine-grained multi-attribute adversarial learning for face generation of age, gender and ethnicity. In 2018 International Conference on Biometrics (ICB) (pp. 98-103). IEEE.
25. 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.
26. Wei, G., Luo, M., Liu, H., Zhang, D., & Zheng, Q. (2020). Progressive generative adversarial networks with reliable sample identification. Pattern Recognition Letters, 130, 91-98.
27. 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.
28. 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.
29. 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.