摘要
利用由液晶可调谐滤光片(LCTF)和CCD相机组成的多光谱成像系统在450~1 000 nm光谱范围内每隔10 nm采集人体指甲样本,得到包含56个波段的人体指甲多光谱图像。通过参考白板比较测量法进行反射率反演,得到指甲的准确反射率信息,分别利用主成分分析法(PCA)和波段指数法实现样本图像的降维,得到两个特征空间,并利用光谱角度填图法(SAM)在两个特征空间内对人体指甲进行分类,分类准确度分别为92.5%及82.9%。因此,由主成分分析法得到的特征空间可以作为人体指甲的特征光谱,为指甲多光谱图谱分析和人体健康评估提供了可靠的依据。
A multispectral imaging system consisting of liquid crystal tunable filter(LCTF) and charge coupled device(CCD) camera was used to collect the images of fingernail samples at intervals of 10 nm during the spectral range of 450-1 000 nm, and a multispectral image of human fingernails containing 56 bands was obtained. The accurate reflectivity information of fingernails was obtained through referring whiteboard comparative measurement method. Principal component analysis(PCA) and band index method were used to reduce the dimension of the sample images respectively and two feature spaces were obtained. Spectral angle mapping(SAM) was used to classify human fingernails in these two feature spaces. The classification accuracy were above 92.5% and 82.9% respectively. Therefore, the feature space obtained by the PCA can be used as the characteristic spectrum of human fingernails, which provides a reliable basis for the analysis of multispectral spectrum of fingernails and human health assessment in the future.
引文
[1] Lee S H,Yang C S.Fingernail analysis management system using microscopy sensor and blockchain technology.International Journal of Distributed Sensor Networks,2018,14(3):1-13.
[2] Niu H F,Zhao K H,Yu G C,et al.Clinical application of hand diagnosis.Clinical Journal of Chinese Medicine,2016,8(5):135-138.
[3] Li X L,Shi Q,Jin W L,et al.Uric acid quantification in fingernail of gout patients and healthy volunteers using HPLC-UV.Biomedical Chromatography,2016,30(8):1338-1342.
[4] Zhu N.FTIR spectra of finger nails of normal people and cancer patients.Research and Exploration in Laboratory,2013,31(10):246-247.
[5] Dong Q,Liu G,Liu T H.FTIR study on the finger nail with carcinoma of nasopharynx.Spectroscopy and Spectral Analysis,2004,24(12):1543-1545.
[6] Zeng W J,Li Z H,Wen Y X,et al.Advance of multispectral image application in the biomedicine.Progress in Modern Biomedicine,2012,12(5):968-971.
[7] Liu M,Zhao J,Li G,et al.Tongue coat information extraction of the traditional Chinese medicine with hyperspectral image.Spectroscopy and Spectral Analysis,2017,37(1):162-165.
[8] Wang W L,Li C Y,Tollner E W,et al.A liquid crystal tunable filter based shortwave infrared spectral imaging system:design and integration.Computers and Electronics in Agriculture,2012,80(1):126-134.
[9] Wang X,Liao N F,Li Y S,et al.The research on reconstruction spectral reflectance in LCTF image system based on comparative measurement.Spectroscopy and Spectral Analysis,2018,38(1):290-295.
[10] Bajorski P,Member S.Statistical inference in PCA for hyperspectral images.IEEE Journal of Selected Topics in Signal Processing,2011,5(3):438-445.
[11] Cao P F,Li H N,Luo Y L,et al.Selection of feature bands for phaseolus vulgaris leaves based on multi-spectral imaging.Laser and Optoelectronics Progress,2014,51(1):011101.
[12] Zu Q,Zhang S F,Cao Y,et al.Research on identification of cabbages and weeds combining spectral imaging technology and SAM taxonomy.Spectroscopy and Spectral Analysis,2015,35(2):479-485.