A rapid, low-cost deep learning system to classify squid species and evaluate freshness based on digital images
文献类型： 外文期刊
作者： Hu, Jun 1 ; Zhou, Chengquan 1 ; Zhao, Dandan 1 ; Zhang, Linnan 2 ; Yang, Guijun 3 ; Chen, Wenxuan 1 ;
作者机构： 1.Zhejiang Acad Agr Sci, Food Sci Inst, Hangzhou, Zhejiang, Peoples R China
2.Ningbo Frirui Marine Biotechnol Co Ltd, Ningbo, Zhejiang, Peoples R China
3.Minist Agr PR China, Key Lab Quantitat Remote Sensing Agr, Beijing Res Ctr Informat Technol Agr, Beijing, Peoples R China
关键词： Squid species classification; Freshness evaluation; Deep learning; Low-cost system
期刊名称：FISHERIES RESEARCH （ 影响因子：2.422； 五年影响因子：2.594 ）
ISSN： 0165-7836
年卷期： 2020 年 221 卷
页码：
收录情况： SCI
摘要： We developed and evaluated a rapid, low-cost system to classify squid in industrial production. This involved designing an easy-to-use handheld image-acquisition system combined with an automated, labor-saving, and efficient deep learning model (named "improved faster recurrent convolutional neural network") to identify three squid species from the North Pacific Ocean. Three indicators, Accuracy, Intersection-over-Union, and Average Running Time, are used to evaluate the classification, and the average results for the test samples are 85.7%, 80.1%, and 0.144 s, respectively. The proposed network provides better squid classification compared with four other approaches. In addition, to ensure quality, the freshness of the selected squid is also evaluated using global threshold segmentation analysis. This proposed method is demonstrated to be a robust, noninvasive, and high-throughput system for squid classification and can also be expanded to other fine processing of aquatic products.
- 相关文献
作者其他论文 更多>>
-
An automated lightweight approach for detecting dead fish in a recirculating aquaculture system
作者：Zhou, Chengquan;Wang, Chenye;Sun, Dawei;Hu, Jun;Ye, Hongbao;Wang, Chenye
关键词：YOLO; Dead fish; RAS; Image processing; Lightweight framework
-
Insights into the Metabolite Differentiation Mechanism Between Chinese Dry-Cured Fatty Ham and Lean Ham Through UPLC-MS/MS-Based Untargeted Metabolomics
作者：Xie, Ruoyu;Liu, Yaqiong;Wu, Xiaoli;Hu, Jun;Chen, Wenxuan;Zhao, Ke;Li, Huanhuan;Chen, Lihong;Zhang, Jin;Du, Hongying
关键词：fatty ham; lean ham; Chinese dry-cured ham; untargeted metabolomics; UPLC-MS/MS; differential metabolite
-
Efficient and Non-Invasive Grading of Chinese Mitten Crab Based on Fatness Estimated by Combing Machine Vision and Deep Learning
作者：Li, Jiangtao;Yang, Xiaolian;Ye, Hongbao;Zhou, Chengquan;Li, Zhuo;Wei, Qiquan;Li, Chen;Sun, Dawei;Ye, Hongbao;Zhou, Chengquan;Li, Chen;Sun, Dawei
关键词：Chinese mitten crab;
Eriocheir sinensis ; grading; machine learning; YOLO -
CNN-Transformer-BiGRU: A Pump Fault Detection Model for Industrialized Recirculating Aquaculture Systems
作者：Shao, Wei;Shao, Wei;Zhou, Chengquan;Sun, Dawei;Li, Chen;Ye, Hongbao;Zhou, Chengquan;Sun, Dawei;Li, Chen;Ye, Hongbao
关键词：aquaculture; BiGRU; convolutional neural network (CNN); fault detection; transformer
-
Nondestructive detection of multiple dried squid qualities by hyperspectral imaging combined with 1D-KAN-CNN
作者：Hu, Jun;Sun, Dawei;Zhou, Hongkui;Lou, Weidong;Zhang, Jin;Zhou, Chengquan;Chen, Wenxuan;Jiang, Yuanhao;Zhou, Chengquan;Chen, Wenxuan
关键词：Dried squid; Quality assessment; Kolmogorov-Arnold network; Wavelength selection; Hyperspectral imaging
-
A Novel Multinozzle Targeting Pollination Robot for Clustered Kiwifruit Flowers Based on Air-Liquid Dual-Flow Spraying
作者：Gao, Changqing;He, Leilei;Ding, Yusong;Murengami, Bryan Gilbert;Li, Rui;Fu, Longsheng;Chen, Jinyong;Chen, Jinyong;Zhou, Chengquan;Ye, Hongbao;Zhou, Chengquan;Ye, Hongbao
关键词：clustered kiwifruit flowers; multinozzle end-effector-optimal; pollination robot; spray parameters
-
Fd-CasBGRel: A Joint Entity-Relationship Extraction Model for Aquatic Disease Domains
作者：Ye, Hongbao;Lv, Lijian;Ye, Hongbao;Lv, Lijian;Zhou, Chengquan;Sun, Dawei;Ye, Hongbao;Zhou, Chengquan;Sun, Dawei
关键词：relational extraction; aquatic diseases; Casrel; fine-tuned pretrained model; self-attention mechanisms; relative position coding; BiLSTM; GHM loss function
