Hyperspectral Imaging System with Rotation Platform for Investigation of Jujube Skin Defects
A novel object rotation hyperspectral imaging system with the wavelength range of 468–950 nm for investigating round-shaped fruits was developed. This system was used to obtain the reflection spectra of jujubes for the application of surface defect detection. Compared to the traditional linear scan...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-04-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/8/2851 |
id |
doaj-cee29c4645794b34bd1fbb98b68f5339 |
---|---|
record_format |
Article |
spelling |
doaj-cee29c4645794b34bd1fbb98b68f53392020-11-25T02:29:51ZengMDPI AGApplied Sciences2076-34172020-04-01102851285110.3390/app10082851Hyperspectral Imaging System with Rotation Platform for Investigation of Jujube Skin DefectsQuoc Thien Pham0Nai-Shang Liou1Department of Mechanical Engineering, Southern Taiwan University of Science and Technology, Tainan 710, TaiwanDepartment of Mechanical Engineering, Southern Taiwan University of Science and Technology, Tainan 710, TaiwanA novel object rotation hyperspectral imaging system with the wavelength range of 468–950 nm for investigating round-shaped fruits was developed. This system was used to obtain the reflection spectra of jujubes for the application of surface defect detection. Compared to the traditional linear scan system, which can scan about 49% of jujube surface in one scan pass, this novel object rotation scan system can scan 95% of jujube surface in one scan pass. Six types of jujube skin condition, including rusty spots, decay, white fungus, black fungus, cracks, and glare, were classified by using hyperspectral data. Support vector machine (SVM) and artificial neural network (ANN) models were used to differentiate the six jujube skin conditions. Classification effectiveness of models was evaluated based on confusion matrices. The percentage of classification accuracy of SVM and ANN models were 97.3% and 97.4%, respectively. The object rotation scan method developed for this study could be used for other round-shaped fruits and integrated into online hyperspectral investigation systems.https://www.mdpi.com/2076-3417/10/8/2851hyperspectral imagingrotation scanpostharvest processsingjujube skinsurface defect detection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Quoc Thien Pham Nai-Shang Liou |
spellingShingle |
Quoc Thien Pham Nai-Shang Liou Hyperspectral Imaging System with Rotation Platform for Investigation of Jujube Skin Defects Applied Sciences hyperspectral imaging rotation scan postharvest processsing jujube skin surface defect detection |
author_facet |
Quoc Thien Pham Nai-Shang Liou |
author_sort |
Quoc Thien Pham |
title |
Hyperspectral Imaging System with Rotation Platform for Investigation of Jujube Skin Defects |
title_short |
Hyperspectral Imaging System with Rotation Platform for Investigation of Jujube Skin Defects |
title_full |
Hyperspectral Imaging System with Rotation Platform for Investigation of Jujube Skin Defects |
title_fullStr |
Hyperspectral Imaging System with Rotation Platform for Investigation of Jujube Skin Defects |
title_full_unstemmed |
Hyperspectral Imaging System with Rotation Platform for Investigation of Jujube Skin Defects |
title_sort |
hyperspectral imaging system with rotation platform for investigation of jujube skin defects |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2020-04-01 |
description |
A novel object rotation hyperspectral imaging system with the wavelength range of 468–950 nm for investigating round-shaped fruits was developed. This system was used to obtain the reflection spectra of jujubes for the application of surface defect detection. Compared to the traditional linear scan system, which can scan about 49% of jujube surface in one scan pass, this novel object rotation scan system can scan 95% of jujube surface in one scan pass. Six types of jujube skin condition, including rusty spots, decay, white fungus, black fungus, cracks, and glare, were classified by using hyperspectral data. Support vector machine (SVM) and artificial neural network (ANN) models were used to differentiate the six jujube skin conditions. Classification effectiveness of models was evaluated based on confusion matrices. The percentage of classification accuracy of SVM and ANN models were 97.3% and 97.4%, respectively. The object rotation scan method developed for this study could be used for other round-shaped fruits and integrated into online hyperspectral investigation systems. |
topic |
hyperspectral imaging rotation scan postharvest processsing jujube skin surface defect detection |
url |
https://www.mdpi.com/2076-3417/10/8/2851 |
work_keys_str_mv |
AT quocthienpham hyperspectralimagingsystemwithrotationplatformforinvestigationofjujubeskindefects AT naishangliou hyperspectralimagingsystemwithrotationplatformforinvestigationofjujubeskindefects |
_version_ |
1724831291958886400 |