Application of Hyperspectral Imaging for Watermelon Seed Classification Using Deep Learning and Scoring Mechanism

Watermelon seeds are a significant source of nutrition in the diet. To assess the potential of near-infrared hyperspectral imaging technology for swift and nondestructive identification of watermelon seed varieties, near-infrared hyperspectral imaging (NIR-HSI) technology was used. The Savitzky–Gola...

Full description

Saved in:
Bibliographic Details
Main Authors: Hengnian Qi, Mengbo He, Zihong Huang, Jianfang Yan, Chu Zhang
Format: Article
Language:English
Published: Wiley 2024-01-01
Series:Journal of Food Quality
Online Access:http://dx.doi.org/10.1155/2024/7313214
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849306462424137728
author Hengnian Qi
Mengbo He
Zihong Huang
Jianfang Yan
Chu Zhang
author_facet Hengnian Qi
Mengbo He
Zihong Huang
Jianfang Yan
Chu Zhang
author_sort Hengnian Qi
collection DOAJ
description Watermelon seeds are a significant source of nutrition in the diet. To assess the potential of near-infrared hyperspectral imaging technology for swift and nondestructive identification of watermelon seed varieties, near-infrared hyperspectral imaging (NIR-HSI) technology was used. The Savitzky–Golay (SG) smoothing algorithm and standard normal variable (SNV) algorithm were combined to preprocess the extracted spectral data. The successive projections algorithm (SPA) was used to reduce the dimensionality of the spectral data. Subsequently, three deep learning models (LeNet, GoogLeNet, and ResNet) were used to classify 10 common watermelon seeds. SPA was used to reduce the dimensionality of hyperspectral data. In terms of full band, the ResNet model achieved a classification accuracy of 86.77% on the test set. By using characteristic bands, the GoogLeNet model achieved a classification accuracy of 83.85% on the test set. The ensemble fusion model based on a scoring mechanism achieved accuracy rates of 99.56%, 90.88%, and 87.97% on the training, validation, and test sets, respectively. The results indicated that the ensemble fusion model based on a scoring mechanism can enhance accuracy. Combining deep learning with NIR-HSI can effectively distinguish different varieties of watermelon seeds.
format Article
id doaj-art-31f83f4efae9430394c8c2aa2adddcfb
institution Kabale University
issn 1745-4557
language English
publishDate 2024-01-01
publisher Wiley
record_format Article
series Journal of Food Quality
spelling doaj-art-31f83f4efae9430394c8c2aa2adddcfb2025-08-20T03:55:03ZengWileyJournal of Food Quality1745-45572024-01-01202410.1155/2024/7313214Application of Hyperspectral Imaging for Watermelon Seed Classification Using Deep Learning and Scoring MechanismHengnian Qi0Mengbo He1Zihong Huang2Jianfang Yan3Chu Zhang4School of Information EngineeringSchool of Information EngineeringSchool of Information EngineeringZhejiang Provincial Seed Management StationSchool of Information EngineeringWatermelon seeds are a significant source of nutrition in the diet. To assess the potential of near-infrared hyperspectral imaging technology for swift and nondestructive identification of watermelon seed varieties, near-infrared hyperspectral imaging (NIR-HSI) technology was used. The Savitzky–Golay (SG) smoothing algorithm and standard normal variable (SNV) algorithm were combined to preprocess the extracted spectral data. The successive projections algorithm (SPA) was used to reduce the dimensionality of the spectral data. Subsequently, three deep learning models (LeNet, GoogLeNet, and ResNet) were used to classify 10 common watermelon seeds. SPA was used to reduce the dimensionality of hyperspectral data. In terms of full band, the ResNet model achieved a classification accuracy of 86.77% on the test set. By using characteristic bands, the GoogLeNet model achieved a classification accuracy of 83.85% on the test set. The ensemble fusion model based on a scoring mechanism achieved accuracy rates of 99.56%, 90.88%, and 87.97% on the training, validation, and test sets, respectively. The results indicated that the ensemble fusion model based on a scoring mechanism can enhance accuracy. Combining deep learning with NIR-HSI can effectively distinguish different varieties of watermelon seeds.http://dx.doi.org/10.1155/2024/7313214
spellingShingle Hengnian Qi
Mengbo He
Zihong Huang
Jianfang Yan
Chu Zhang
Application of Hyperspectral Imaging for Watermelon Seed Classification Using Deep Learning and Scoring Mechanism
Journal of Food Quality
title Application of Hyperspectral Imaging for Watermelon Seed Classification Using Deep Learning and Scoring Mechanism
title_full Application of Hyperspectral Imaging for Watermelon Seed Classification Using Deep Learning and Scoring Mechanism
title_fullStr Application of Hyperspectral Imaging for Watermelon Seed Classification Using Deep Learning and Scoring Mechanism
title_full_unstemmed Application of Hyperspectral Imaging for Watermelon Seed Classification Using Deep Learning and Scoring Mechanism
title_short Application of Hyperspectral Imaging for Watermelon Seed Classification Using Deep Learning and Scoring Mechanism
title_sort application of hyperspectral imaging for watermelon seed classification using deep learning and scoring mechanism
url http://dx.doi.org/10.1155/2024/7313214
work_keys_str_mv AT hengnianqi applicationofhyperspectralimagingforwatermelonseedclassificationusingdeeplearningandscoringmechanism
AT mengbohe applicationofhyperspectralimagingforwatermelonseedclassificationusingdeeplearningandscoringmechanism
AT zihonghuang applicationofhyperspectralimagingforwatermelonseedclassificationusingdeeplearningandscoringmechanism
AT jianfangyan applicationofhyperspectralimagingforwatermelonseedclassificationusingdeeplearningandscoringmechanism
AT chuzhang applicationofhyperspectralimagingforwatermelonseedclassificationusingdeeplearningandscoringmechanism