Conversion of Speaker's Face Image Using PCA and Animation Unit for Video Chatting

Yuki Saito, Takashi Nose, Takahiro Shinozaki, Akinori Ito

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

Video chat is a good way of personal communication, however, there is a privacy issue in the video chat because we need to disclose one's identity such as face or voice when chatting. In this paper, we propose two methods by which face image of a speaker is converted into that of different person to conceal the speaker's identity. In the first method, we first prepare the speech and video data of the original and target speakers for training the conversion model. The face image features are calculated using the PCA to the whole pixels of the image. In the second method, the animation units extracted by Kinect are used as an intermediate feature, and we train a model that converts the animation unit to the target speaker's face image. In both methods, we used a neural network as the conversion model. We conducted experiments, and the first method could convert the whole shape of the speakers, while small movements such as mouth movement cannot be converted. The second method could convert both the whole shape of the face and mouth movement, however, the quality of face image was deteriorated.

本文言語English
ホスト出版物のタイトルProceedings - 2015 International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2015
編集者Jeng-Shyang Pan, Ching-Yu Yang, Hsiang-Cheh Huang, Ivan Lee
出版社Institute of Electrical and Electronics Engineers Inc.
ページ433-436
ページ数4
ISBN(電子版)9781509001880
DOI
出版ステータスPublished - 2016 2 19
イベント11th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2015 - Adelaide, Australia
継続期間: 2015 9 232015 9 25

出版物シリーズ

名前Proceedings - 2015 International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2015

Other

Other11th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2015
国/地域Australia
CityAdelaide
Period15/9/2315/9/25

ASJC Scopus subject areas

  • 情報システム
  • 信号処理
  • 人工知能
  • コンピュータ ネットワークおよび通信
  • 安全性、リスク、信頼性、品質管理

フィンガープリント

「Conversion of Speaker's Face Image Using PCA and Animation Unit for Video Chatting」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル