Efficient and Non-Invasive Grading of Chinese Mitten Crab Based on Fatness Estimated by Combing Machine Vision and Deep Learning

The Chinese mitten crab (<i>Eriocheir sinensis</i>) is a high-value seafood. Efficient quality-grading methods are needed to meet rapid increases in demand. The current grading system for crabs primarily relies on manual observations and weights; it is thus inefficient, requires large am...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiangtao Li, Hongbao Ye, Chengquan Zhou, Xiaolian Yang, Zhuo Li, Qiquan Wei, Chen Li, Dawei Sun
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Foods
Subjects:
Online Access:https://www.mdpi.com/2304-8158/14/11/1989
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850158947649978368
author Jiangtao Li
Hongbao Ye
Chengquan Zhou
Xiaolian Yang
Zhuo Li
Qiquan Wei
Chen Li
Dawei Sun
author_facet Jiangtao Li
Hongbao Ye
Chengquan Zhou
Xiaolian Yang
Zhuo Li
Qiquan Wei
Chen Li
Dawei Sun
author_sort Jiangtao Li
collection DOAJ
description The Chinese mitten crab (<i>Eriocheir sinensis</i>) is a high-value seafood. Efficient quality-grading methods are needed to meet rapid increases in demand. The current grading system for crabs primarily relies on manual observations and weights; it is thus inefficient, requires large amounts of labor, is costly, and no longer meets the requirements for the market. Here, we employed computer vision techniques combined with deep learning modeling to efficiently quantify key physiological traits, such as sex identification, carapace dimensions (length and width), and fatness assessment for quality classification. To this end, a YOLOv5-seg integrated with an SE attention model was developed using 2282 RGB images and manual measurements of the physiological traits of 300 crabs. The RGB dataset was further augmented by rotating and resizing. The results revealed that the accuracy of sex recognition was 100%, and the mAP for carapace segmentation was 0.995, which was superior to YOLOv8-seg and other variants. In addition, we proposed an improved conditional factor K to evaluate the fatness of crabs and classify their quality based on fatness. The consistency between the grading method proposed in this article and manual grading was 100%. This study could aid in developing precise and non-destructive grading systems for the aquaculture and food industries.
format Article
id doaj-art-b5a39d715440411fbb2636b3249e8e3e
institution OA Journals
issn 2304-8158
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Foods
spelling doaj-art-b5a39d715440411fbb2636b3249e8e3e2025-08-20T02:23:44ZengMDPI AGFoods2304-81582025-06-011411198910.3390/foods14111989Efficient and Non-Invasive Grading of Chinese Mitten Crab Based on Fatness Estimated by Combing Machine Vision and Deep LearningJiangtao Li0Hongbao Ye1Chengquan Zhou2Xiaolian Yang3Zhuo Li4Qiquan Wei5Chen Li6Dawei Sun7Huzhou Academy of Agricultural Sciences, Huzhou 313000, ChinaInstitute of Agricultural Equipment, Zhejiang Academy of Agricultural Sciences, Hangzhou 310021, ChinaInstitute of Agricultural Equipment, Zhejiang Academy of Agricultural Sciences, Hangzhou 310021, ChinaHuzhou Academy of Agricultural Sciences, Huzhou 313000, ChinaInstitute of Agricultural Equipment, Zhejiang Academy of Agricultural Sciences, Hangzhou 310021, ChinaInstitute of Agricultural Equipment, Zhejiang Academy of Agricultural Sciences, Hangzhou 310021, ChinaInstitute of Agricultural Equipment, Zhejiang Academy of Agricultural Sciences, Hangzhou 310021, ChinaInstitute of Agricultural Equipment, Zhejiang Academy of Agricultural Sciences, Hangzhou 310021, ChinaThe Chinese mitten crab (<i>Eriocheir sinensis</i>) is a high-value seafood. Efficient quality-grading methods are needed to meet rapid increases in demand. The current grading system for crabs primarily relies on manual observations and weights; it is thus inefficient, requires large amounts of labor, is costly, and no longer meets the requirements for the market. Here, we employed computer vision techniques combined with deep learning modeling to efficiently quantify key physiological traits, such as sex identification, carapace dimensions (length and width), and fatness assessment for quality classification. To this end, a YOLOv5-seg integrated with an SE attention model was developed using 2282 RGB images and manual measurements of the physiological traits of 300 crabs. The RGB dataset was further augmented by rotating and resizing. The results revealed that the accuracy of sex recognition was 100%, and the mAP for carapace segmentation was 0.995, which was superior to YOLOv8-seg and other variants. In addition, we proposed an improved conditional factor K to evaluate the fatness of crabs and classify their quality based on fatness. The consistency between the grading method proposed in this article and manual grading was 100%. This study could aid in developing precise and non-destructive grading systems for the aquaculture and food industries.https://www.mdpi.com/2304-8158/14/11/1989Chinese mitten crab<i>Eriocheir sinensis</i>gradingmachine learningYOLO
spellingShingle Jiangtao Li
Hongbao Ye
Chengquan Zhou
Xiaolian Yang
Zhuo Li
Qiquan Wei
Chen Li
Dawei Sun
Efficient and Non-Invasive Grading of Chinese Mitten Crab Based on Fatness Estimated by Combing Machine Vision and Deep Learning
Foods
Chinese mitten crab
<i>Eriocheir sinensis</i>
grading
machine learning
YOLO
title Efficient and Non-Invasive Grading of Chinese Mitten Crab Based on Fatness Estimated by Combing Machine Vision and Deep Learning
title_full Efficient and Non-Invasive Grading of Chinese Mitten Crab Based on Fatness Estimated by Combing Machine Vision and Deep Learning
title_fullStr Efficient and Non-Invasive Grading of Chinese Mitten Crab Based on Fatness Estimated by Combing Machine Vision and Deep Learning
title_full_unstemmed Efficient and Non-Invasive Grading of Chinese Mitten Crab Based on Fatness Estimated by Combing Machine Vision and Deep Learning
title_short Efficient and Non-Invasive Grading of Chinese Mitten Crab Based on Fatness Estimated by Combing Machine Vision and Deep Learning
title_sort efficient and non invasive grading of chinese mitten crab based on fatness estimated by combing machine vision and deep learning
topic Chinese mitten crab
<i>Eriocheir sinensis</i>
grading
machine learning
YOLO
url https://www.mdpi.com/2304-8158/14/11/1989
work_keys_str_mv AT jiangtaoli efficientandnoninvasivegradingofchinesemittencrabbasedonfatnessestimatedbycombingmachinevisionanddeeplearning
AT hongbaoye efficientandnoninvasivegradingofchinesemittencrabbasedonfatnessestimatedbycombingmachinevisionanddeeplearning
AT chengquanzhou efficientandnoninvasivegradingofchinesemittencrabbasedonfatnessestimatedbycombingmachinevisionanddeeplearning
AT xiaolianyang efficientandnoninvasivegradingofchinesemittencrabbasedonfatnessestimatedbycombingmachinevisionanddeeplearning
AT zhuoli efficientandnoninvasivegradingofchinesemittencrabbasedonfatnessestimatedbycombingmachinevisionanddeeplearning
AT qiquanwei efficientandnoninvasivegradingofchinesemittencrabbasedonfatnessestimatedbycombingmachinevisionanddeeplearning
AT chenli efficientandnoninvasivegradingofchinesemittencrabbasedonfatnessestimatedbycombingmachinevisionanddeeplearning
AT daweisun efficientandnoninvasivegradingofchinesemittencrabbasedonfatnessestimatedbycombingmachinevisionanddeeplearning