Lighting Variability Correction for Pill Identification

Seungtae Kang, Gil Jin Jang, Minho Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper proposes a novel method for the compensation of the illumination variations. To find accurate approximate of the shading conditions, class activation map (CAM) obtained by the output of convolutional neural networks (CNNs) provides weights for the shading parameter estimation. We applied the shading compensation to the pill images, and obtained improved surface images.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538658079
DOIs
StatePublished - 28 Nov 2018
Event2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018 - JeJu, Korea, Republic of
Duration: 24 Jun 201826 Jun 2018

Publication series

Name2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018

Conference

Conference2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018
Country/TerritoryKorea, Republic of
CityJeJu
Period24/06/1826/06/18

Keywords

  • Class activation map
  • Convolutional neural network
  • Illumination compensation
  • Object recognition

Fingerprint

Dive into the research topics of 'Lighting Variability Correction for Pill Identification'. Together they form a unique fingerprint.

Cite this