| Presentation | 2017-09-15 Face Image Generation System Using Attribute information with DCGANs Yurika Sagawa, Masafumi Hagiwara, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we propose an attribute added face image generation system using Deep Convolutional Generative Adversarial Networks(DCGANs). Convolution Neural Network(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, attribute features to image feature are added, 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 women 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. Here, attribute features is defined as the averaged difference between two images using the image pairs with and without attributes. In order to generate a similar person in the input image, the generated images are input to Reconstruction Generator to obtain the final reconstructed images. We performed two kinds of evaluation experiment: the first one is a subjective evaluation experiment on items such as ``whether generated images has attributes'' or something else, the second one is a quantitative evaluation experiment for measuring whether the persons shown in the input image and generated image are the same person. As the results, excellent characteristics were obtained. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Image Generation / Deep Convolutional Generative Adversarial Networks / Convolutional Neural Networks |
| Paper # | PRMU2017-52,IBISML2017-24 |
| Date of Issue | 2017-09-08 (PRMU, IBISML) |
| Conference Information | |
| Committee | PRMU / IBISML / IPSJ-CVIM |
|---|---|
| Conference Date | 2017/9/15(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinichi Sato(NII) / Kenji Fukumizu(ISM) |
| Vice Chair | Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) / Masashi Sugiyama(Univ. of Tokyo) |
| Secretary | Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) / Masashi Sugiyama(Kyoto Univ.) / (Univ. of Tokyo) |
| Assistant | Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) / Ichiro Takeuchi(Nagoya Inst. of Tech.) / Toshihiro Kamishima(AIST) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Computer Vision and Image Media |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Face Image Generation System Using Attribute information with DCGANs |
| Sub Title (in English) | |
| Keyword(1) | Image Generation |
| Keyword(2) | Deep Convolutional Generative Adversarial Networks |
| Keyword(3) | Convolutional Neural Networks |
| 1st Author's Name | Yurika Sagawa |
| 1st Author's Affiliation | Keio University(Keio Univ.) |
| 2nd Author's Name | Masafumi Hagiwara |
| 2nd Author's Affiliation | Keio University(Keio Univ.) |
| Date | 2017-09-15 |
| Paper # | PRMU2017-52,IBISML2017-24 |
| Volume (vol) | vol.117 |
| Number (no) | PRMU-210,IBISML-211 |
| Page | pp.pp.107-112(PRMU), pp.107-112(IBISML), |
| #Pages | 6 |
| Date of Issue | 2017-09-08 (PRMU, IBISML) |