Study on Fast Image Retrieval and Recognition Using Visual Big Data

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K00248
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perceptual information processing
• Research Institution: Waseda University
• Principal Investigator: Kamata Seiichiro 早稲田大学, 理工学術院(情報生産システム研究科・センター), 教授 (00204602)
• Research Collaborator: SUGIMOTO Kenjiro ; ZHANG Qieshi ; RYU Jegoon ; HAO Pengyi ; WU Renjie ; OKUTANI Ryo ; YE Xiaoxi ; LAI Yongwen ; LIM Xueting ; QIU Fan ; TANG Kaihua ; WU Xinhui ; NI Shoucheng ; YANO Koichi ; TIAN Li ; MA Lizhuang ; BRECKON Toby
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: 画像検索 / 画像認識 / スパースグラフ / ニューラルネットワーク / ビジュアルビッグデータ / ディープラーニング / 圧縮可能性 / 基底関数分解

Outline of Final Research Achievements

Big data from visual media, which is called visual big data, was utilized in this study, and new methodologies in image retrieval and recognition were established based on a concept of compressibility which is focusng on reduction of computational complexity in information theory. Especially combining with state-of-the-art deep learning, a new research direction of sparse graph neural network was developed using face visual big data.

Free Research Field

知覚情報処理