Abstract:Study on identification of seed varieties is an important means of ensuring seed quality. The paper uses hyperspectral image technology and fusing image feature to identify different varieties of delinted cottonseeds. Hyperspectral image data (400~1000nm) of 4 types a total of 240 delinted cottonseeds samples were acquired. In addition, the spectral information and 12 morphological characteristics such as length width area,and circularity were extracted. Moreover, 11 effective wave-lengths(EWs) were to be selected by successive projection algorithm(SPA). And then 11 EWs of the calibration set were used as input to build a partial least quares discriminant analysis(PLS-DA),soft independent modeling of class analogy(SIMCA),K-nearest neighbor algorithm(KNN),principal component analysis was combined with linear discriminant analysis (PCA-LDA) and quadratic discriminant analysis (PCA-QDA) were used to build models. The results showed that the total identification rate of the PLS-DA model were 93% for the calibration set and 90% for the prediction set, respectively. When using image information modeling analysis,the overall recognition rate of the model is not high,which showed that the effect of classification is not good when only using morphological characteristics of hyperspectral images. Then,we fused the spectral and morphological information of the feature band as input,and established the data fusion model based on the analysis of PLS-DA,SIMCA,KNN,PCA-LDA and PCA-QDA. It suggested that the data fusion model showed better performance than the individual image model and spectral model,PLS-DA model had the best recognition effect,the overall recognition rate of calibration set and prediction set was 98% and 97% respectively. The experimental results indicated that fusing the spectral and image information of hyperspectral images could effectively improved discrimination accuracy for delinted cottonseeds at the case of a small amount of wavebands.
Key words:Hyperspectral image; Delinted cottonseeds; Classification; Data fusion
黄蒂云,李景彬,尤 佳,坎 杂. 基于高光谱技术融合图像信息的脱绒棉种品种分类检测研究[J]. 光谱学与光谱分析, 2018, 38(07): 2227-2232.
HUANG Di-yun, LI Jing-bin, YOU Jia, KAN Za. The Classification of Delinted Cottonseeds Varieties by Fusing Image Information Based on Hyperspectral Image Technology. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(07): 2227-2232.
[1] WANG Li-jun(王立军). Seed Storage Processing and Inspection(种子贮藏加工与检验). Beijing:Chemical Industry Press(北京:化学工业出版社),2009,181.
[2] Wang L,Sun D W,Pu H,et al. Food Analytical Methods,2016,9(1):1.
[3] SHAO Lu-hao,KAN Za,LI Jing-bin,et al(邵鲁浩,坎 杂,李景彬,等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报),2011,27(S2):86.
[4] SHANG Lian-guang,LI Jun-hui,WANG Yu-mei,et al(商连光,李军会,王玉美,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2015,35(3):609.
[5] XU Peng, GUO Ting-ting, ZHANG Gui-xiang, et al(徐 鹏,郭婷婷,张桂香,等). China Cotton(中国棉花),2010,37(1):17.
[6] Barbedo J G A,Tibola C S,Fernandes J M C. Biosystems Engineering,2015,(131):65.
[7] Singh C B,Jayas D S,Paliwal J,et al. Journal of Stored Products Research,2009,45(3):151.
[8] Han S I,Chae J H,Bilyeu K,et al. Journal of the American Oil Chemists’ Society,2014,91(2):229.
[9] Tan K,Chai Y,Song W,et al. Transactions of the Chinese Society of Agricultural Engineering,2014,30(9):235.
[10] Hai V,Tachtatzis C,Murray P,et al. Rich Seed Varietal Purity Inspection Using Hyperspectral Imaging, Hyperspectral Imaging and Applications Conference,Coventry, United Kingdom,2016.
[11] Deng X,Zhu Q,Huang M. Laser & Optoelectronics Progress,2015,(2):122.
[12] Wang Q,Huang M,Zhu Q,et al. Journal of Food Science & Biotechnology,2014,33(2):163.
[13] Yang S,Zhu Q B,Huang M,et al. Food Analytical Methods,2017,10(2):424.
[14] SUN Jun,JIN Xia-ming,MAO Han-ping,et al(孙 俊,金夏明,毛罕平,等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报),2014,30(10):167.
[15] WEI Zi-fu,BI Du-yan,MA Shi-ping(危自福,毕笃彦,马时平). Journal of Data Acquisition and Processing(数据采集与处理),2010,25(3):347.
[16] Majumdar S,Jayas D S. Transactions of the ASAE,2000,43(6):1681.