Sparse Fourier Transform for High-dimensional Images and Accelerating Deep Learning

2017 Fiscal Year Final Research Report

• Project/Area Number: 16K16092
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Perceptual information processing
• Research Institution: Waseda University
• Principal Investigator: Sugimoto Kenjiro 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), 次席研究員 (00773483)
• Research Collaborator: KAMATA Sei-ichiro 早稲田大学, 理工学術院, 教授 (00204602) ; FUKUSHIMA Norishige 名古屋工業大学, 工学系研究院, 准教授 (80550508) ; KYOCHI Seisuke 北九州市立大学, 国際環境工学部, 准教授 (70634616) ; KUROKI Yoshimitsu 久留米工業高等専門学校, 教授 (60290847) ; HIRAKAWA Keigo Dayton大学, 准教授 ; Breckon Toby P. Durham大学, 教授
• Project Period (FY): 2016-04-01 – 2018-03-31
• Keywords: スパースフーリエ変換 / 定数時間ガウシアンフィルタ / 定数時間バイラテラルフィルタ / 深層学習

Outline of Final Research Achievements

The Fast Fourier Transform (FFT) is an essential tool in many applications of engineering. This research has tried to establish a more efficient FFT algorithm for sparse signals, called Sparse Fourier Transform (SFT), and also has developed more elaborated techniques related to the SFT, called constant-time image filters. During the research period (two years, 2016/4-2017/3), we published 1 journal paper, 16 conference papers (7 international and 9 domestic), and 3 awards. Many of our conference papers were accepted to worldwide flagship conferences in signal/image processing fields and also some of our domestic papers won research awards. From these highly-evaluated outcomes, our research showed high impacts and potentials in signal/image processing communities.

Free Research Field

信号処理、画像処理、機械学習