Radiometric correction and feature extraction of molecular hyperspectral imaging data

Hongying Liu*, Qingli Li, Jingao Liu, Yongqi Xue

*Corresponding author for this work

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

Abstract

Some molecular hyperspectral images of retina sections were collected. Due to the infection of lamp, a spectral curve extracted directly from the original hyperspectral data can not truly present biochemical character. The main preprocessing step of the hyperspectral data is radiometric correction. The paper provides the gray correction coefficient algorithm to eliminating the influence. Because hyperspectral data cube includes a great deal of single band image, data redundancy is very serious. The paper cites that PCA(Principal Component Analysis) algorithm can validly extract feature information and eliminate data redundancy and achieve dimensionality reduction.

Original languageEnglish
Title of host publication2012 Symposium on Photonics and Optoelectronics, SOPO 2012
DOIs
StatePublished - 2012
Event2012 International Symposium on Photonics and Optoelectronics, SOPO 2012 - Shanghai, China
Duration: 21 May 201223 May 2012

Publication series

Name2012 Symposium on Photonics and Optoelectronics, SOPO 2012

Conference

Conference2012 International Symposium on Photonics and Optoelectronics, SOPO 2012
Country/TerritoryChina
CityShanghai
Period21/05/1223/05/12

Keywords

  • PCA
  • dimensionality reduction (DR)
  • feature extraction
  • molecular hyperspctral imaging(MHSI)
  • radiometric correction

Fingerprint

Dive into the research topics of 'Radiometric correction and feature extraction of molecular hyperspectral imaging data'. Together they form a unique fingerprint.

Cite this