Detection of Apple Marssonina Blotch with PLSR, PCA, and LDA Using Outdoor Hyperspectral Imaging
Soo Hyun Park1, 3, Youngki Hong2, Mubarakat Shuaibu1, Sangcheol Kim2, Won Suk Lee1*
1. Department of Agricultural and Biological Engineering, University of Florida, Gainesville, FL 32611, United States
2. Department of Agricultural Engineering, National Academy of Agricultural Science, RDA, Jeonju 55365, South Korea
3. Smart Farm Research Center, Korea Institute of Science and Technology (KIST) Gangneung-si, Gangwon-do 25451, South Korea
Detection of Apple Marssonina Blotch with PLSR, PCA, and LDA Using Outdoor Hyperspectral Imaging
Soo Hyun Park1, 3, Youngki Hong2, Mubarakat Shuaibu1, Sangcheol Kim2, Won Suk Lee1*
1. Department of Agricultural and Biological Engineering, University of Florida, Gainesville, FL 32611, United States
2. Department of Agricultural Engineering, National Academy of Agricultural Science, RDA, Jeonju 55365, South Korea
3. Smart Farm Research Center, Korea Institute of Science and Technology (KIST) Gangneung-si, Gangwon-do 25451, South Korea
摘要: In this study, hyperspectral images were used to detect a fungal disease in apple leaves called Marssonina blotch (AMB). Estimation models were built to classify healthy, asymptomatic and symptomatic classes using partial least squares regression (PLSR), principal component analysis (PCA), and linear discriminant analysis (LDA) multivariate methods. In general, the LDA estimation model performed the best among the three models in detecting AMB asymptomatic pixels, while all the models were able to detect the symptomatic class. LDA correctly classified asymptomatic pixels and LDA model predicted them with an accuracy of 88.0%. An accuracy of 91.4% was achieved as the total classification accuracy. The results from this work indicate the potential of using the LDA estimation model to identify asymptomatic pixels on leaves infected by AMB.
Abstract:In this study, hyperspectral images were used to detect a fungal disease in apple leaves called Marssonina blotch (AMB). Estimation models were built to classify healthy, asymptomatic and symptomatic classes using partial least squares regression (PLSR), principal component analysis (PCA), and linear discriminant analysis (LDA) multivariate methods. In general, the LDA estimation model performed the best among the three models in detecting AMB asymptomatic pixels, while all the models were able to detect the symptomatic class. LDA correctly classified asymptomatic pixels and LDA model predicted them with an accuracy of 88.0%. An accuracy of 91.4% was achieved as the total classification accuracy. The results from this work indicate the potential of using the LDA estimation model to identify asymptomatic pixels on leaves infected by AMB.
Soo Hyun Park, Youngki Hong, Mubarakat Shuaibu, Sangcheol Kim, Won Suk Lee. Detection of Apple Marssonina Blotch with PLSR, PCA, and LDA Using Outdoor Hyperspectral Imaging[J]. 光谱学与光谱分析, 2020, 40(04): 1309-1314.
Soo Hyun Park, Youngki Hong, Mubarakat Shuaibu, Sangcheol Kim, Won Suk Lee. Detection of Apple Marssonina Blotch with PLSR, PCA, and LDA Using Outdoor Hyperspectral Imaging. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(04): 1309-1314.
[1] Yin L, Wang P, Li M, et al. J. Pineal Res., 2013, 54(4): 426.
[2] Sagong D H, Kweon H J, Song Y Y, et al. Korean J. Hortic. Sci., 2011, 29(6): 531.
[3] Lee D H, Back C G, Win N K K, et al. Mycobiology, 2011, 39(3): 200.
[4] Sharma N, Thakur V S, Sharma S, et al. Indian Phytopath., 2011, 64(4): 358.
[5] Lee C H, Lee S Y, Jung H Y, et al. J. Opt. Soc. Korea, 2012, 16(2): 133.
[6] Park M Y, Sagong D H, Kweon H J, et al. Korean J. Hortic. Sci., 2013, 31(5): 523.
[7] Min H, Cho B K. J. of Biosystems Eng., 2015, 40(1): 67.
[8] Lefcourt A M, Beck E A, Lo Y M, et al. J. of Biosystems Eng., 2015, 40(2): 145.
[9] Mahesh S, Jayas D S, Paliwal J, et al. J. Stored Products Res., 2015, 61: 17.
[10] XIE Chuan-qi, SHAO Yong-ni, GAO Jun-feng,et al. Spectroscopy and Spectral Analysis, 2015, 35(12): 3431.
[11] Bulanon D M, Burks T F, Kim D G, et al. Agric. Eng. Int.: CIGR Journal , 2013, 15(3): 171.
[12] Kim D, Burks T F, Ritenour M A, et al. Int. J. Agric. & Biol. Eng., 2014, 7(6): 20.
[13] Senthilkumar T, Jayas D S, White N D G. J. Stored Products Res., 2015, 63: 80.
[14] Tallada J G, Wicklow D T, Pearson T C, et al. Trans. ASABE, 2011, 54(3): 1151.
[15] Williams P J, Geladi P, Britz T J, et al. J. Cereal Sci., 2012, 55(3): 272.
[16] Barbedo J G, Tibola C S, Fernandes J M. Biosyst. Eng., 2015, 131: 65.
[17] Tekle S, Mge I, Segtnan V H, et al. Cereal Chem., 2015, 92(1): 73.
[18] Qin J, Burks T F, Ritenour M A, et al. J. Food Eng., 2009, 93(2): 183.
[19] Cetó X, Gutiérrez-Capitán M, Calvo D, et al. Food Chem., 2013, 141(3): 2533.