Quantitative analysis and visualization of live spotted seabass (Lateolabrax maculatus) flesh texture using hyperspectral imaging and machine learning
values of 0.552 and 0.341, and RPD values of 1.494 and 1.134, respectively. Visualization maps generated from the optimal models facilitated the direct assessment of TPA parameters distribution in the muscle. This study demonstrated that HSI combined with machine learning offers an effective and non-invasive method for assessing flesh quality in live spotted seabass, thereby accelerating the selection of germplasm with superior textural attributes.
Authors
- Changting An (ORCID: https://orcid.org/0000-0003-4181-7423)
- Qiyou Tao
- Shufang Liu (ORCID: https://orcid.org/0000-0002-5522-8024)
- Ang Li (ORCID: https://orcid.org/0000-0001-7578-1911)
- Qing Wang (ORCID: https://orcid.org/0000-0002-9840-6492)
- Xiang Fang
- Changlin Liu
- Zhimeng Zhuang
- Yun Li
- Shuai Che
- Huan Wang
Institutions
- Qingdao National Laboratory for Marine Science and Technology (CN)
- Ningde Normal University (CN)
- Chinese Academy of Fishery Sciences (CN)
- Ocean University of China (CN)
Publication Details
- Journal
- Food Chemistry X
- Published
- 2026-03-31
- DOI
- https://doi.org/10.1016/j.fochx.2026.103773
- Primary Topic
- Spectroscopy and Chemometric Analyses
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Ministry of Science and Technology of the People's Republic of China
- Qingdao Municipal Science and Technology Bureau
- Ministry of Agriculture and Rural Affairs of the People's Republic of China
- Polit National Laboratory for Marine Science and Technology
- National Key Research and Development Program of China