DocumentCode :
2140813
Title :
Spectral feature extraction of blood cells based on hyperspectral data
Author :
Chunni Dai ; Jingao Liu
Author_Institution :
Sch. of Inf. Technol., Shanghai Jianqiao Coll., Shanghai, China
fYear :
2013
fDate :
23-25 July 2013
Firstpage :
1439
Lastpage :
1443
Abstract :
The aim of this paper is to investigate how to extract spectral features of five kinds of blood cells before they are classified and counted. Here the hyperspectral images of blood cells are taken from leukemic patients and healthy persons. Different from traditional methods which are usually based on morphology, the method of feature extraction based on hyperspectral imaging technique is mainly from spectral pattern traits and similarity measures. The spectral pattern traits in this paper includes characteristics of troughs or crests in spectral patterns such as spectral absorption index, location, intensity, symmetry. Similarity measures are to measure two pattern´s relationship using spectral angle mapping, correlation coefficient and covariance. Altogether these features contain more than thirty characteristics, which would be of great use to segment and classify blood cells in later work.
Keywords :
blood; cellular biophysics; correlation methods; covariance analysis; feature extraction; hyperspectral imaging; image classification; medical image processing; blood cells classification; correlation coefficient; covariance; crests characteristics; healthy persons; hyperspectral data; hyperspectral imaging technique; leukemic patients; pattern relationship; similarity measures; spectral absorption index; spectral angle mapping; spectral feature extraction; spectral pattern traits; troughs characteristics; Cells (biology); Feature extraction; Hyperspectral imaging; Imaging; Vectors; White blood cells; blood cell; feature extraction; similarity measure; spectrum;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Natural Computation (ICNC), 2013 Ninth International Conference on
Conference_Location :
Shenyang
Type :
conf
DOI :
10.1109/ICNC.2013.6818206
Filename :
6818206
Link To Document :
بازگشت