Generative Adversarial Networks를 이용한 Face Morphing 기법 연구

다국어 초록 (Multilingual Abstract)

Recently, with the explosive development of computing power, various methods such as RNN and CNN have been proposed under the name of Deep Learning, which solve many problems of Computer Vision have. The Generative Adversarial Network, released in 2014, showed that the problem of computer vision can be sufficiently solved in unsupervised learning, and the generation domain can also be studied using learned generators. GAN is being developed in various forms in combination with various models. Machine learning has difficulty in collecting data. If it is too large, it is difficult to refine the effective data set by removing the noise. If it is too small, the small difference becomes too big noise, and learning is not easy. In this paper, we apply a deep CNN model for extracting facial region in image frame to GAN model as a preprocessing filter, and propose a method to produce composite images of various facial expressions by stably learning with limited collection data of two persons.

참고문헌 (Reference)

1 X. Sun, "meProp: Sparsified back propagation for accelerated deep learning with reduced overfitting" 3299-3308, 2017

2 A. Radford, "Unsupervised representation learning with deep convolutional generative adversarial networks" 1-15, 2016

3 A. Radford, "Unsupervised representation learning with deep convolutional generative adversarial networks" 1-15, 2016

4 J. T. Springenberg, "Striving for simplicity: The all convolutional net" 1-14, 2015

5 R. Tachibana, "Semisupervised learning using adversarial networks" 1-6, 2016

6 L. C. Yang, "MidiNet: A convolutional generative adversarial network for symbolicdomain music generation" 324-331, 2017

7 E. L. Miller, "Labeled faces in the wild: A survey" 189-248, 2016

8 X. Chen, "InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets" 2180-2188, 2016

9 Y. Le Cun, "Gradientbased learning applied to document recognition" 86 (86): 2278-2324, 1998

10 I. J. Goodfellow, "Generative adversarial networks" 2672-2680, 2014

11 M. S. Ko, "GANMOOK: Generative adversarial network to stylize images like ink wash painting" 793-795, 2017

12 S. Lawrence, "Face recognition: A convolutional neural-network approach" 8 (8): 98-113, 1997

13 J. Areeyapinan, "Face morphing using critical point filters" 283-288, 2012

14 D. Triantafyllidou, "Face detection based on deep convolutional neural networks exploiting incremental facial part learning" 3560-3565, 2016

15 Y. LeCun, "Deep learning" 521 (521): 436-444, 2015

16 최승호, "CNN 기반 서명인식에서 시간정보를 이용한 위조판별 성능 향상" 한국디지털콘텐츠학회 19 (19): 205-212, 2018