<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Image transformation is a hot topic in the field of computer vision. Its purpose is to use the existing similar or semblable images to learn the mapping between the input image and the output image. Generative Adversarial Networks model is a powerful generative model with the idea of Zero-sum game theory, Co-training the two through the confrontation learning method of the generator and the discriminator, so as to estimate the potential distribution of data samples and generate new data samples. This paper is based on the generative adversarial networks and the existing network, the image transformation is realized by combining the two network structures of DCGAN and Cycle GAN. Experimental results show that this method not only effectively solves the problem that paired images are not easy to obtain, but also fully demonstrates the superiority of the generated adversarial networks in image transformation.</p>
</abstract>

Image transformation is a hot topic in the field of computer vision. Its purpose is to use the existing similar or semblable images to learn the mapping between the input image and the output image. Generative Adversarial Networks model is a powerful generative model with the idea of Zero-sum game theory, Co-training the two through the confrontation learning method of the generator and the discriminator, so as to estimate the potential distribution of data samples and generate new data samples. This paper is based on the generative adversarial networks and the existing network, the image transformation is realized by combining the two network structures of DCGAN and Cycle GAN. Experimental results show that this method not only effectively solves the problem that paired images are not easy to obtain, but also fully demonstrates the superiority of the generated adversarial networks in image transformation.

Image Transformation Based on Generative Adversarial Networks

International Journal of Advanced Network, Monitoring and Controls

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"Image Transformation Based on Generative Adversarial Networks"}

Image transformation is a hot topic in the field of computer vision. Its purpose is to use the existing similar or semblable images to learn the mapping...

operation	Convolution kernel size	pace	Convolution kernel number	Batch normalization	activation function
convolution	4×4	2	64	No	Leaky Relu
convolution	4×4	2	128	Yes	Leaky Relu
convolution	4×4	2	256	Yes	Leaky Relu
convolution	4×4	2	512	Yes	Leaky Relu

operation	Convolution kernel size	pace	Convolution kernel number	Batch normalization	activation function
convolution	7×7	1	32	No	Relu
convolution	3×3	2	64	Yes	Relu
convolution	3×3	2	128	Yes	Relu
convolution	3×3	2	128	Yes	Relu
convolution	3×3	2	128	Yes	Relu
convolution	3×3	2	128	Yes	Relu
convolution	3×3	2	128	Yes	Relu
convolution	3×3	2	128	Yes	Relu
deconvolution	3×3	1/2	128	Yes	Relu
deconvolution	3×3	1/2	128	Yes	Relu
deconvolution	3×3	1/2	128	Yes	Relu
deconvolution	3×3	1/2	128	Yes	Relu
deconvolution	3×3	1/2	128	Yes	Relu
deconvolution	3×3	1/2	64	Yes	Relu
deconvolution	3×3	1/2	32	Yes	Relu
deconvolution	7×7	1	3	Yes	Relu

Image Transformation Based on Generative Adversarial Networks

Publicado en línea: 08 oct 2019

Páginas: 93 - 98

DOI: https://doi.org/10.21307/ijanmc-2019-053

Palabras clave
Image Transformation, GAN, Deep Learning, CNN, Adversarial Training

© 2019 Chen Jie et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

NETWORK STRUCTURE OF THE DISCRIMINATOR

NETWORK STRUCTURE OF THE GENERATOR

Image Transformation Based on Generative Adversarial Networks

Publicado en línea: 08 oct 2019

Páginas: 93 - 98

DOI: https://doi.org/10.21307/ijanmc-2019-053

Palabras claveImage Transformation, GAN, Deep Learning, CNN, Adversarial Training

© 2019 Chen Jie et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

NETWORK STRUCTURE OF THE DISCRIMINATOR

NETWORK STRUCTURE OF THE GENERATOR

Palabras clave
Image Transformation, GAN, Deep Learning, CNN, Adversarial Training