Spatial-spectral blood cell classification with microscopic hyperspectral imagery

Qiong Ran, Lan Chang, Wei Li, Xiaofeng Xu

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

4 Citations (Scopus)

Abstract

Microscopic hyperspectral images provide a new way for blood cell examination. The hyperspectral imagery can greatly facilitate the classification of different blood cells. In this paper, the microscopic hyperspectral images are acquired by connecting the microscope and the hyperspectral imager, and then tested for blood cell classification. For combined use of the spectral and spatial information provided by hyperspectral images, a spatial-spectral classification method is improved from the classical extreme learning machine (ELM) by integrating spatial context into the image classification task with Markov random field (MRF) model. Comparisons are done among ELM, ELM-MRF, support vector machines(SVM) and SVMMRF methods. Results show the spatial-spectral classification methods(ELM-MRF, SVM-MRF) perform better than pixel-based methods(ELM, SVM), and the proposed ELM-MRF has higher precision and show more accurate location of cells.

Original languageEnglish
Title of host publicationAOPC 2017
Subtitle of host publicationOptical Spectroscopy and Imaging
EditorsWei Hang, Xiandeng Hou, Bing Zhao, Zhe Wang, Mengxia Xie, Tsutomu Shimura, Jin Yu
PublisherSPIE
ISBN (Electronic)9781510614031
DOIs
Publication statusPublished - 2017
Externally publishedYes
EventApplied Optics and Photonics China: Optical Spectroscopy and Imaging, AOPC 2017 - Beijing, China
Duration: 4 Jun 20176 Jun 2017

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume10461
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceApplied Optics and Photonics China: Optical Spectroscopy and Imaging, AOPC 2017
Country/TerritoryChina
CityBeijing
Period4/06/176/06/17

Keywords

  • Blood Cell Classification
  • Extreme Learning Machine
  • Microscpic Hyperspectral Image
  • Spatial-Spectral Classification

Fingerprint

Dive into the research topics of 'Spatial-spectral blood cell classification with microscopic hyperspectral imagery'. Together they form a unique fingerprint.

Cite this