Cargando…

Research on Pepper External Quality Detection Based on Transfer Learning Integrated with Convolutional Neural Network

A pepper quality detection and classification model based on transfer learning combined with convolutional neural network is proposed as a solution for low efficiency of manual pepper sorting at the current stage. The pepper dataset was amplified with data pre-processing methods including rotation,...

Descripción completa

Detalles Bibliográficos
Autores principales: Ren, Rui, Zhang, Shujuan, Sun, Haixia, Gao, Tingyao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8398717/
https://www.ncbi.nlm.nih.gov/pubmed/34450747
http://dx.doi.org/10.3390/s21165305
_version_ 1783744905910157312
author Ren, Rui
Zhang, Shujuan
Sun, Haixia
Gao, Tingyao
author_facet Ren, Rui
Zhang, Shujuan
Sun, Haixia
Gao, Tingyao
author_sort Ren, Rui
collection PubMed
description A pepper quality detection and classification model based on transfer learning combined with convolutional neural network is proposed as a solution for low efficiency of manual pepper sorting at the current stage. The pepper dataset was amplified with data pre-processing methods including rotation, luminance switch, and contrast ratio switch. To improve training speed and precision, a network model was optimized with a fine-tuned VGG 16 model in this research, transfer learning was applied after parameter optimization, and comparative analysis was performed by combining ResNet50, MobileNet V2, and GoogLeNet models. It turned out that the VGG 16 model output anticipation precision was 98.14%, and the prediction loss rate was 0.0669 when the dropout was settled as 0.3, learning rate settled as 0.000001, batch normalization added, and ReLU as activation function. Comparing with other finetune models and network models, this model was of better anticipation performance, as well as faster and more stable convergence rate, which embodied the best performance. Considering the basis of transfer learning and integration with strong generalization and fitting capacity of the VGG 16 finetune model, it is feasible to apply this model to the external quality classification of pepper, thus offering technical reference for further realizing the automatic classification of pepper quality.
format Online
Article
Text
id pubmed-8398717
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83987172021-08-29 Research on Pepper External Quality Detection Based on Transfer Learning Integrated with Convolutional Neural Network Ren, Rui Zhang, Shujuan Sun, Haixia Gao, Tingyao Sensors (Basel) Article A pepper quality detection and classification model based on transfer learning combined with convolutional neural network is proposed as a solution for low efficiency of manual pepper sorting at the current stage. The pepper dataset was amplified with data pre-processing methods including rotation, luminance switch, and contrast ratio switch. To improve training speed and precision, a network model was optimized with a fine-tuned VGG 16 model in this research, transfer learning was applied after parameter optimization, and comparative analysis was performed by combining ResNet50, MobileNet V2, and GoogLeNet models. It turned out that the VGG 16 model output anticipation precision was 98.14%, and the prediction loss rate was 0.0669 when the dropout was settled as 0.3, learning rate settled as 0.000001, batch normalization added, and ReLU as activation function. Comparing with other finetune models and network models, this model was of better anticipation performance, as well as faster and more stable convergence rate, which embodied the best performance. Considering the basis of transfer learning and integration with strong generalization and fitting capacity of the VGG 16 finetune model, it is feasible to apply this model to the external quality classification of pepper, thus offering technical reference for further realizing the automatic classification of pepper quality. MDPI 2021-08-05 /pmc/articles/PMC8398717/ /pubmed/34450747 http://dx.doi.org/10.3390/s21165305 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ren, Rui
Zhang, Shujuan
Sun, Haixia
Gao, Tingyao
Research on Pepper External Quality Detection Based on Transfer Learning Integrated with Convolutional Neural Network
title Research on Pepper External Quality Detection Based on Transfer Learning Integrated with Convolutional Neural Network
title_full Research on Pepper External Quality Detection Based on Transfer Learning Integrated with Convolutional Neural Network
title_fullStr Research on Pepper External Quality Detection Based on Transfer Learning Integrated with Convolutional Neural Network
title_full_unstemmed Research on Pepper External Quality Detection Based on Transfer Learning Integrated with Convolutional Neural Network
title_short Research on Pepper External Quality Detection Based on Transfer Learning Integrated with Convolutional Neural Network
title_sort research on pepper external quality detection based on transfer learning integrated with convolutional neural network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8398717/
https://www.ncbi.nlm.nih.gov/pubmed/34450747
http://dx.doi.org/10.3390/s21165305
work_keys_str_mv AT renrui researchonpepperexternalqualitydetectionbasedontransferlearningintegratedwithconvolutionalneuralnetwork
AT zhangshujuan researchonpepperexternalqualitydetectionbasedontransferlearningintegratedwithconvolutionalneuralnetwork
AT sunhaixia researchonpepperexternalqualitydetectionbasedontransferlearningintegratedwithconvolutionalneuralnetwork
AT gaotingyao researchonpepperexternalqualitydetectionbasedontransferlearningintegratedwithconvolutionalneuralnetwork