In this study, fluorescent spectral imaging technology combined with principal component analysis (PCA) and artificial neural networks (ANNs) was used to identify Cistanche deserticola, Cistanche tubulosa and Cistanche sinensis, which are traditional Chinese medicinal herbs. The fluorescence spectroscopy imaging system acquired the spectral images of 40 cistanche samples, and through image denoising, binarization processing to make sure the effective pixels. Furthermore, drew the spectral curves whose data in the wavelength range of 450-680 nm for the study. Then preprocessed the data by first-order derivative, analyzed the data through principal component analysis and artificial neural network. The results shows: Principal component analysis can generally distinguish cistanches, through further identification by neural networks makes the results more accurate, the correct rate of the testing and training sets is as high as 100%. Based on the fluorescence spectral imaging technique and combined with principal component analysis and artificial neural network to identify cistanches is feasible.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Cistanches identification based on fluorescent spectral imaging technology combined with principal component analysis and artificial neural network


    Contributors:
    Dong, Jia (author) / Huang, Furong (author) / Li, Yuanpeng (author) / Xiao, Chi (author) / Xian, Ruiyi (author) / Ma, Zhiguo (author)

    Conference:

    Selected Papers from Conferences of the Photoelectronic Technology Committee of the Chinese Society of Astronautics 2014, Part I ; 2014 ; China,China


    Published in:

    Publication date :

    2015-03-04





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English





    Nonlinear Principal Component Analysis Based on Hierarchical Input-training Neural Network

    Zhao, Z.-g. / Liu, F. / Xu, B.-g. | British Library Online Contents | 2005


    Modal Parameter Identification with Principal Component Analysis

    Wang, C. / Gou, J. / Bai, J. et al. | British Library Online Contents | 2013