Understanding the Scattering Transform Using Univariate Signals

Youngmi Hur, Hyojae Lim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we review the scattering transform in the univariate setting. After reviewing its properties including translation invariance, stability under small diffeomorphism, and ability to carry high-frequency information, we investigate how these properties can be used in understanding the effect of the scattering transform when various types of signal deformation are considered. We find that, together with the Fourier transform modulus, the scattering transform can be used in classifying some of these deformations.

Original languageEnglish
Title of host publicationProceedings - 2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2018
EditorsQingli Li, Wei Li, Lipo Wang
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538676042
DOIs
Publication statusPublished - 2019 Feb 1
Event11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2018 - Beijing, China
Duration: 2018 Oct 132018 Oct 15

Publication series

NameProceedings - 2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2018

Conference

Conference11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2018
Country/TerritoryChina
CityBeijing
Period18/10/1318/10/15

Bibliographical note

Funding Information:
ACKNOWLEDGMENT This research was supported in part by the National Research Foundation of Korea (NRF) [Grant Number 20151009350].

Publisher Copyright:
© 2018 IEEE.

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Health Informatics

Fingerprint

Dive into the research topics of 'Understanding the Scattering Transform Using Univariate Signals'. Together they form a unique fingerprint.

Cite this