Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 1, 2026

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Toward Intelligent and Deployable Seafood Quality Evaluation: A Review of Deep Learning-Assisted Computer Vision.

Yao Zheng¹, Liu Yang¹, Hanfeng Zheng¹

¹East China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Shanghai, China.

Comprehensive Reviews in Food Science and Food Safety

|June 30, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Gut Microbiomes of Rainbow Trout and Atlantic Salmon: Nutritional Modulation, Mucosal Immunity, and Resistome Risk.

Biology·2026

Same author

Genome-Wide Resequencing Reveals High Connectivity and Localized Adaptive Signals in Manila Clam (<i>Ruditapes philippinarum</i>) Populations Along the Southeastern Coast of China.

Animals : an open access journal from MDPI·2026

Same author

Comparative Response of <i>Ruditapes philippinarum</i> and <i>Mercenaria mercenaria</i> to Acute Heat and Hyposaline Stress.

Animals : an open access journal from MDPI·2026

Same author

Histological Observation and Functional Gene Expression Analysis of Gonadal Development in <i>Ruditapes philippinarum</i> Under Artificial Culture Conditions.

Animals : an open access journal from MDPI·2026

Same author

Image-Based Analysis of Morphometric Differences Between Sea-Caught and Farmed Large Yellow Croaker (<i>Larimichthys crocea</i>).

Animals : an open access journal from MDPI·2026

Same author

Body Coloration Characterization and Proteomic Analysis of Diurnal Color Variation in Farmed <i>Larimichthys crocea</i>.

Animals : an open access journal from MDPI·2026

Deep learning-assisted computer vision (DL-CV) offers a rapid, nondestructive method for assessing seafood quality. This technology shows great potential for industrial and consumer applications, improving accuracy and efficiency in quality control.

Area of Science:

Food Science and Technology
Artificial Intelligence
Computer Vision

Background:

Seafood quality deteriorates rapidly postharvest, necessitating efficient evaluation methods.
Traditional quality assessment techniques are often destructive, slow, and impractical for real-time industrial or consumer use.
Deep learning-assisted computer vision (DL-CV) presents a non-destructive and rapid alternative for seafood quality assessment.

Purpose of the Study:

To review recent advancements in DL-CV for seafood quality evaluation.
To explore both technical aspects and practical applications of DL-CV in the seafood industry.
To highlight DL-CV's potential for improving seafood quality control.

Main Methods:

Comparison of visible-light imaging with other modalities.

Keywords:

computer vision deep learning quality evaluation seafood

Related Experiment Videos

Last Updated: Jul 1, 2026

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Discussion of the shift from traditional machine learning to deep learning for feature extraction.

Summary of deep learning architectures (CNNs, Vision Transformers) and trends (lightweight design, interpretability).

Main Results:

DL-CV, particularly using visible-light imaging, shows significant potential for accurate, non-destructive seafood quality prediction.
Key applications include freshness evaluation (using storage time-based or indicator-based labeling), species identification, weight estimation, and defect detection.
Visible-light imaging systems are highlighted for their ease of deployment in practical settings.

Conclusions:

DL-CV is a powerful tool for revolutionizing seafood quality assessment, offering speed and non-destructive capabilities.
Future research should focus on enhancing quality differentiation, integrating multiple quality indicators, and scaling DL-CV for broader industrial and consumer adoption.