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 SVM-MRF 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.
基金:
Beijing Nova ProgramBeijing Municipal Science & Technology Commission [Z171100001117050]; Beijing Natural Science FoundationBeijing Natural Science Foundation [4172043]; National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [NSFC-61501017]; Fundamental Research Funds for the Central UniversitiesFundamental Research Funds for the Central Universities [BUCTRC201615]
语种:
外文
被引次数:
WOS:
第一作者:
第一作者机构:[1]Beijing Univ Chem Technol, Coll Informat Sci & Technol, 15 East Rd, Beijing, Peoples R China
通讯作者:
推荐引用方式(GB/T 7714):
Ran Qiong,Chang Lan,Li Wei,et al.Spatial-spectral Blood Cell Classification with Microscopic Hyperspectral Imagery[J].AOPC 2017: OPTICAL SPECTROSCOPY AND IMAGING.2017,10461:doi:10.1117/12.2281268.
APA:
Ran, Qiong,Chang, Lan,Li, Wei&Xu, Xiaofeng.(2017).Spatial-spectral Blood Cell Classification with Microscopic Hyperspectral Imagery.AOPC 2017: OPTICAL SPECTROSCOPY AND IMAGING,10461,
MLA:
Ran, Qiong,et al."Spatial-spectral Blood Cell Classification with Microscopic Hyperspectral Imagery".AOPC 2017: OPTICAL SPECTROSCOPY AND IMAGING 10461.(2017)