Face image generation system using attribute information with DCGANs

Yurika Sagawa, Masafumi Hagiwara

研究成果: Conference contribution

1 引用 (Scopus)

抜粋

In this paper, we propose an attribute added face image generation system using Deep Convolutional Generative Adversarial Networks(DCGANs). Convolutional Neural Networks(CNNs) can extract important features of an image and attain high precision in image classification tasks. In the proposed system, image features are extracted using CNNs, and attribute features added to image features, and attributes added images are generated by DCGANs. Specifically, we use the attributes of "smile" and "male", and work on a task of generating smile images from non-smile images, and a task of generating male images from female images. Since the training of the proposed system requires image pairs including with and without attributes, we use two extraction methods, 1)Usage of attribute label attached dataset, 2)Usage of cosine similarity. To obtain attribute features, we trained 4-layer CNNs which are the same architecture as Discriminator of GANs, to classify images into two classes, with and without attributes. Here, attribute features are defined as the averaged difference between image features with and without attributes, more specifically, the values in the final convolution layer in the 4-layer CNNs. We performed two kinds of evaluation experiments: the first one is a subjective evaluation experiment on items such as "whether generated images have attributes", the second one is a quantitative evaluation experiment for measuring whether the people shown in the input image and the generated image are the same person. As the results, excellent characteristics were obtained.

元の言語English
ホスト出版物のタイトル2nd International Conference on Machine Learning and Soft Computing, ICMLSC 2018
出版者Association for Computing Machinery
ページ109-113
ページ数5
ISBN(電子版)9781450363365
DOI
出版物ステータスPublished - 2018 2 2
イベント2nd International Conference on Machine Learning and Soft Computing, ICMLSC 2018 - Phu Quoc Island, Viet Nam
継続期間: 2018 2 22018 2 4

Other

Other2nd International Conference on Machine Learning and Soft Computing, ICMLSC 2018
Viet Nam
Phu Quoc Island
期間18/2/218/2/4

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

フィンガープリント Face image generation system using attribute information with DCGANs' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    Sagawa, Y., & Hagiwara, M. (2018). Face image generation system using attribute information with DCGANs. : 2nd International Conference on Machine Learning and Soft Computing, ICMLSC 2018 (pp. 109-113). Association for Computing Machinery. https://doi.org/10.1145/3184066.3184071