TY - GEN
T1 - Blood cell segmentation based on the hybrid algorithm of spectral angle mapping and spectral information divergence
AU - Xue, Yingying
AU - Wang, Qian
AU - Li, Qingli
AU - Zhou, Mei
AU - Liu, Hongying
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2017/2/13
Y1 - 2017/2/13
N2 - Hyperspectral remote sensing is a frontier field of the remote sensing technology, and it has broad applications. In the clinical field, the use of hyperspectral images to make blood cell segmentation and identification can avoid shortcomings of the traditional optical detection. Also, the study of blood cell segmentation using hyperspectral images is limited. Spectral angle mapping (Sam) and spectral information divergence (SID) are supervised classification algorithms, which can be used for segmentation and recognition of blood cell images. This paper aims to use the combined algorithm SAM-SID to make blood cell segmentation which is based on hyperspectral images. The hybrid algorithm can make up the defects of these two algorithms, so that the segmentation effect is more accurate. Experimental results show that the proposed method improves the accuracy of cell segmentation, which shows the advantage of hyperspectral images in the biomedical field.
AB - Hyperspectral remote sensing is a frontier field of the remote sensing technology, and it has broad applications. In the clinical field, the use of hyperspectral images to make blood cell segmentation and identification can avoid shortcomings of the traditional optical detection. Also, the study of blood cell segmentation using hyperspectral images is limited. Spectral angle mapping (Sam) and spectral information divergence (SID) are supervised classification algorithms, which can be used for segmentation and recognition of blood cell images. This paper aims to use the combined algorithm SAM-SID to make blood cell segmentation which is based on hyperspectral images. The hybrid algorithm can make up the defects of these two algorithms, so that the segmentation effect is more accurate. Experimental results show that the proposed method improves the accuracy of cell segmentation, which shows the advantage of hyperspectral images in the biomedical field.
KW - Spectral Angle Mapping (SAM)
KW - Spectral Information Divergence (SID)
KW - cell segmentation
KW - hyperspectral imaging
UR - https://www.scopus.com/pages/publications/85016055404
U2 - 10.1109/CISP-BMEI.2016.7852733
DO - 10.1109/CISP-BMEI.2016.7852733
M3 - 会议稿件
AN - SCOPUS:85016055404
T3 - Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016
SP - 341
EP - 345
BT - Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016
Y2 - 15 October 2016 through 17 October 2016
ER -