Characterizing Hyperspectral Microscope Imagery for Classification of Blueberry Firmness with Deep Learning Methods
Firmness is an important quality indicator of blueberries. Firmness loss (or softening) of postharvest blueberries has posed a challenge in its shelf-life quality control and can be delineated with its microstructural changes. To investigate spatial and spectral characteristics of microstructures ba...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-12-01
|
Series: | Agronomy |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4395/12/1/85 |
_version_ | 1797496663305093120 |
---|---|
author | Bosoon Park Tae-Sung Shin Jeong-Seok Cho Jeong-Ho Lim Ki-Jae Park |
author_facet | Bosoon Park Tae-Sung Shin Jeong-Seok Cho Jeong-Ho Lim Ki-Jae Park |
author_sort | Bosoon Park |
collection | DOAJ |
description | Firmness is an important quality indicator of blueberries. Firmness loss (or softening) of postharvest blueberries has posed a challenge in its shelf-life quality control and can be delineated with its microstructural changes. To investigate spatial and spectral characteristics of microstructures based on firmness, hyperspectral microscope imaging (HMI) was employed for this study. The mesocarp area with 20× magnification of blueberries was selectively imaged with a Fabry–Perot interferometer HMI system of 400–1000 nm wavelengths, resulting in 281 hypercubes of parenchyma cells in a resolution of 968 × 608 × 300 pixels. After properly processing each hypercube of parenchyma cells in a blueberry, the cell image with different firmness was examined based on parenchyma cell shape, cell wall segment, cell-to-cell adhesion, and size of intercellular spaces. Spectral cell characteristics of firmness were also sought based on the spectral profile of cell walls with different image preprocessing methods. The study found that softer blueberries (1.96–3.92 N) had more irregular cell shapes, lost cell-to-cell adhesion, loosened and round cell wall segments, large intercellular spaces, and cell wall colors that were more red than the firm blueberries (6.86–8.83 N). Even though berry-to-berry (or image-to-image) variations of the characteristics turned out large, the deep learning model with spatial and spectral features of blueberry cells demonstrated the potential for blueberry firmness classification with Matthew’s correlation coefficient of 73.4% and accuracy of 85% for test set. |
first_indexed | 2024-03-10T03:06:50Z |
format | Article |
id | doaj.art-ac02fdec9f4849fcb600600ea0743d09 |
institution | Directory Open Access Journal |
issn | 2073-4395 |
language | English |
last_indexed | 2024-03-10T03:06:50Z |
publishDate | 2021-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Agronomy |
spelling | doaj.art-ac02fdec9f4849fcb600600ea0743d092023-11-23T12:38:01ZengMDPI AGAgronomy2073-43952021-12-011218510.3390/agronomy12010085Characterizing Hyperspectral Microscope Imagery for Classification of Blueberry Firmness with Deep Learning MethodsBosoon Park0Tae-Sung Shin1Jeong-Seok Cho2Jeong-Ho Lim3Ki-Jae Park4U.S. National Poultry Research Center, United States Department of Agriculture, Agricultural Research Service, 950 College Station Road, Athens, GA 30605, USAU.S. National Poultry Research Center, United States Department of Agriculture, Agricultural Research Service, 950 College Station Road, Athens, GA 30605, USAKorea Food Research Institute, Sungnam-si 55365, KoreaKorea Food Research Institute, Sungnam-si 55365, KoreaKorea Food Research Institute, Sungnam-si 55365, KoreaFirmness is an important quality indicator of blueberries. Firmness loss (or softening) of postharvest blueberries has posed a challenge in its shelf-life quality control and can be delineated with its microstructural changes. To investigate spatial and spectral characteristics of microstructures based on firmness, hyperspectral microscope imaging (HMI) was employed for this study. The mesocarp area with 20× magnification of blueberries was selectively imaged with a Fabry–Perot interferometer HMI system of 400–1000 nm wavelengths, resulting in 281 hypercubes of parenchyma cells in a resolution of 968 × 608 × 300 pixels. After properly processing each hypercube of parenchyma cells in a blueberry, the cell image with different firmness was examined based on parenchyma cell shape, cell wall segment, cell-to-cell adhesion, and size of intercellular spaces. Spectral cell characteristics of firmness were also sought based on the spectral profile of cell walls with different image preprocessing methods. The study found that softer blueberries (1.96–3.92 N) had more irregular cell shapes, lost cell-to-cell adhesion, loosened and round cell wall segments, large intercellular spaces, and cell wall colors that were more red than the firm blueberries (6.86–8.83 N). Even though berry-to-berry (or image-to-image) variations of the characteristics turned out large, the deep learning model with spatial and spectral features of blueberry cells demonstrated the potential for blueberry firmness classification with Matthew’s correlation coefficient of 73.4% and accuracy of 85% for test set.https://www.mdpi.com/2073-4395/12/1/85blueberry firmnesshyperspectral microscopy imagingdeep learningcell characterization |
spellingShingle | Bosoon Park Tae-Sung Shin Jeong-Seok Cho Jeong-Ho Lim Ki-Jae Park Characterizing Hyperspectral Microscope Imagery for Classification of Blueberry Firmness with Deep Learning Methods Agronomy blueberry firmness hyperspectral microscopy imaging deep learning cell characterization |
title | Characterizing Hyperspectral Microscope Imagery for Classification of Blueberry Firmness with Deep Learning Methods |
title_full | Characterizing Hyperspectral Microscope Imagery for Classification of Blueberry Firmness with Deep Learning Methods |
title_fullStr | Characterizing Hyperspectral Microscope Imagery for Classification of Blueberry Firmness with Deep Learning Methods |
title_full_unstemmed | Characterizing Hyperspectral Microscope Imagery for Classification of Blueberry Firmness with Deep Learning Methods |
title_short | Characterizing Hyperspectral Microscope Imagery for Classification of Blueberry Firmness with Deep Learning Methods |
title_sort | characterizing hyperspectral microscope imagery for classification of blueberry firmness with deep learning methods |
topic | blueberry firmness hyperspectral microscopy imaging deep learning cell characterization |
url | https://www.mdpi.com/2073-4395/12/1/85 |
work_keys_str_mv | AT bosoonpark characterizinghyperspectralmicroscopeimageryforclassificationofblueberryfirmnesswithdeeplearningmethods AT taesungshin characterizinghyperspectralmicroscopeimageryforclassificationofblueberryfirmnesswithdeeplearningmethods AT jeongseokcho characterizinghyperspectralmicroscopeimageryforclassificationofblueberryfirmnesswithdeeplearningmethods AT jeongholim characterizinghyperspectralmicroscopeimageryforclassificationofblueberryfirmnesswithdeeplearningmethods AT kijaepark characterizinghyperspectralmicroscopeimageryforclassificationofblueberryfirmnesswithdeeplearningmethods |