Cargando…
Citrus disease detection using convolution neural network generated features and Softmax classifier on hyperspectral image data
Identification and segregation of citrus fruit with diseases and peel blemishes are required to preserve market value. Previously developed machine vision approaches could only distinguish cankerous from non-cankerous citrus, while this research focused on detecting eight different peel conditions o...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9768035/ https://www.ncbi.nlm.nih.gov/pubmed/36570926 http://dx.doi.org/10.3389/fpls.2022.1043712 |
_version_ | 1784854087329644544 |
---|---|
author | Yadav, Pappu Kumar Burks, Thomas Frederick, Quentin Qin, Jianwei Kim, Moon Ritenour, Mark A. |
author_facet | Yadav, Pappu Kumar Burks, Thomas Frederick, Quentin Qin, Jianwei Kim, Moon Ritenour, Mark A. |
author_sort | Yadav, Pappu Kumar |
collection | PubMed |
description | Identification and segregation of citrus fruit with diseases and peel blemishes are required to preserve market value. Previously developed machine vision approaches could only distinguish cankerous from non-cankerous citrus, while this research focused on detecting eight different peel conditions on citrus fruit using hyperspectral (HSI) imagery and an AI-based classification algorithm. The objectives of this paper were: (i) selecting the five most discriminating bands among 92 using PCA, (ii) training and testing a custom convolution neural network (CNN) model for classification with the selected bands, and (iii) comparing the CNN’s performance using 5 PCA bands compared to five randomly selected bands. A hyperspectral imaging system from earlier work was used to acquire reflectance images in the spectral region from 450 to 930 nm (92 spectral bands). Ruby Red grapefruits with normal, cankerous, and 5 other common peel diseases including greasy spot, insect damage, melanose, scab, and wind scar were tested. A novel CNN based on the VGG-16 architecture was developed for feature extraction, and SoftMax for classification. The PCA-based bands were found to be 666.15, 697.54, 702.77, 849.24 and 917.25 nm, which resulted in an average accuracy, sensitivity, and specificity of 99.84%, 99.84% and 99.98% respectively. However, 10 trials of five randomly selected bands resulted in only a slightly lower performance, with accuracy, sensitivity, and specificity of 98.87%, 98.43% and 99.88%, respectively. These results demonstrate that an AI-based algorithm can successfully classify eight different peel conditions. The findings reported herein can be used as a precursor to develop a machine vision-based, real-time peel condition classification system for citrus processing. |
format | Online Article Text |
id | pubmed-9768035 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-97680352022-12-22 Citrus disease detection using convolution neural network generated features and Softmax classifier on hyperspectral image data Yadav, Pappu Kumar Burks, Thomas Frederick, Quentin Qin, Jianwei Kim, Moon Ritenour, Mark A. Front Plant Sci Plant Science Identification and segregation of citrus fruit with diseases and peel blemishes are required to preserve market value. Previously developed machine vision approaches could only distinguish cankerous from non-cankerous citrus, while this research focused on detecting eight different peel conditions on citrus fruit using hyperspectral (HSI) imagery and an AI-based classification algorithm. The objectives of this paper were: (i) selecting the five most discriminating bands among 92 using PCA, (ii) training and testing a custom convolution neural network (CNN) model for classification with the selected bands, and (iii) comparing the CNN’s performance using 5 PCA bands compared to five randomly selected bands. A hyperspectral imaging system from earlier work was used to acquire reflectance images in the spectral region from 450 to 930 nm (92 spectral bands). Ruby Red grapefruits with normal, cankerous, and 5 other common peel diseases including greasy spot, insect damage, melanose, scab, and wind scar were tested. A novel CNN based on the VGG-16 architecture was developed for feature extraction, and SoftMax for classification. The PCA-based bands were found to be 666.15, 697.54, 702.77, 849.24 and 917.25 nm, which resulted in an average accuracy, sensitivity, and specificity of 99.84%, 99.84% and 99.98% respectively. However, 10 trials of five randomly selected bands resulted in only a slightly lower performance, with accuracy, sensitivity, and specificity of 98.87%, 98.43% and 99.88%, respectively. These results demonstrate that an AI-based algorithm can successfully classify eight different peel conditions. The findings reported herein can be used as a precursor to develop a machine vision-based, real-time peel condition classification system for citrus processing. Frontiers Media S.A. 2022-12-07 /pmc/articles/PMC9768035/ /pubmed/36570926 http://dx.doi.org/10.3389/fpls.2022.1043712 Text en Copyright © 2022 Yadav, Burks, Frederick, Qin, Kim and Ritenour https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Plant Science Yadav, Pappu Kumar Burks, Thomas Frederick, Quentin Qin, Jianwei Kim, Moon Ritenour, Mark A. Citrus disease detection using convolution neural network generated features and Softmax classifier on hyperspectral image data |
title | Citrus disease detection using convolution neural network generated features and Softmax classifier on hyperspectral image data |
title_full | Citrus disease detection using convolution neural network generated features and Softmax classifier on hyperspectral image data |
title_fullStr | Citrus disease detection using convolution neural network generated features and Softmax classifier on hyperspectral image data |
title_full_unstemmed | Citrus disease detection using convolution neural network generated features and Softmax classifier on hyperspectral image data |
title_short | Citrus disease detection using convolution neural network generated features and Softmax classifier on hyperspectral image data |
title_sort | citrus disease detection using convolution neural network generated features and softmax classifier on hyperspectral image data |
topic | Plant Science |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9768035/ https://www.ncbi.nlm.nih.gov/pubmed/36570926 http://dx.doi.org/10.3389/fpls.2022.1043712 |
work_keys_str_mv | AT yadavpappukumar citrusdiseasedetectionusingconvolutionneuralnetworkgeneratedfeaturesandsoftmaxclassifieronhyperspectralimagedata AT burksthomas citrusdiseasedetectionusingconvolutionneuralnetworkgeneratedfeaturesandsoftmaxclassifieronhyperspectralimagedata AT frederickquentin citrusdiseasedetectionusingconvolutionneuralnetworkgeneratedfeaturesandsoftmaxclassifieronhyperspectralimagedata AT qinjianwei citrusdiseasedetectionusingconvolutionneuralnetworkgeneratedfeaturesandsoftmaxclassifieronhyperspectralimagedata AT kimmoon citrusdiseasedetectionusingconvolutionneuralnetworkgeneratedfeaturesandsoftmaxclassifieronhyperspectralimagedata AT ritenourmarka citrusdiseasedetectionusingconvolutionneuralnetworkgeneratedfeaturesandsoftmaxclassifieronhyperspectralimagedata |