Park, Soo Hyun Hong, Youngki Shuaibu, Mubarakat Kim, Sangcheol Lee, Won Suk 2024-01-19T18:01:08Z 2024-01-19T18:01:08Z 2021-09-04 2020-04 1000-0593 https://pubs.kist.re.kr/handle/201004/118823 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. English OFFICE SPECTROSCOPY & SPECTRAL ANALYSIS FRUIT-QUALITY DEFOLIATION GROWTH Detection of Apple Marssonina Blotch with PLSR, PCA, and LDA Using Outdoor Hyperspectral Imaging Article 10.3964/j.issn.1000-0593(2020)04-1309-06 1 SPECTROSCOPY AND SPECTRAL ANALYSIS, v.40, no.4, pp.1309 - 1314 SPECTROSCOPY AND SPECTRAL ANALYSIS 40 4 1309 1314 scie scopus 000534352300052 2-s2.0-85085251928 Spectroscopy Spectroscopy Article FRUIT-QUALITY DEFOLIATION GROWTH Apple Marssonina blotch Hyperspectral imaging PLSR PCA LDA