Skip to main content
ARS Home » Northeast Area » Leetown, West Virginia » Cool and Cold Water Aquaculture Research » Research » Publications at this Location » Publication #428627
Research Project: Innovating New Technologies that Improve Efficiencies of Recirculating Aquaculture Systems

Location: Cool and Cold Water Aquaculture Research

Title: FilletCam AI: A handheld tool for precise fillet color profiling of Atlantic salmon and rainbow trout

Author
item RANJAN, RAKESH - Freshwater Institute
item SHROFF, HARSH - University Of Maryland
item SHARRER, KATA - Freshwater Institute
item TSUKUDA, SCOTT - Freshwater Institute
item GOOD, CHRISTOPHER - Freshwater Institute

Submitted to: Journal of Agriculture and Food Research
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 10/11/2024
Publication Date: 10/12/2024
Citation: Ranjan, R., Shroff, H., Sharrer, K., Tsukuda, S., Good, C. 2024. FilletCam AI: A handheld tool for precise fillet color profiling of Atlantic salmon and rainbow trout. Journal of Agriculture and Food Research. 18. Article 101461. https://doi.org/10.1016/j.jafr.2024.101461.
DOI: https://doi.org/10.1016/j.jafr.2024.101461

Interpretive Summary: Customers often associate the vibrant pink-red pigmentation of salmon and trout fillets with freshness and superior quality and are willing to pay higher prices for such products. Suboptimal fillet pigmentation can diminish the product's economic value. Besides color intensity, the uniformity of color is also a key quality parameter. Therefore, reliable, repeatable, and objective fish fillet color measurement and profiling are crucial for ensuring production quality and establishing pricing benchmarks. This proof-of-concept study focused on developing a hand-held smart device (FilletCam) for rapid fish fillet color scoring. The research prototype leverages computer vision and artificial intelligence to enable highthroughput, real-time fillet color scoring. Additionally, the developed GUI provides an intuitive interface to collect, analyze, visualize, and share data with authorized users. FilletCam performed satisfactorily with consistent accuracy and repeatability in fillet color measurements. With appropriate refinements for commercial use, the demonstrated technology has the potential to become a valuable tool for color-related quality inspection in fish processing lines, seafood retail outlets, and grocery stores.

Technical Abstract: High-throughput and objective color measurements of fish fillets are crucial for quality control and establishing pricing benchmarks. While fillet color scoring traditionally relies on subjective visual inspection using color reference cards or labor-intensive color measurement using a colorimeter, this study aims to develop a smart handheld device (FilletCam) for precise and rapid profiling of fish fillet color. FilletCam comprises an imaging sensor integrated with an embedded computing unit for image acquisition. A graphical user interface (GUI) was developed to streamline data collection, analysis, visualization, compilation, and data sharing with authorized users. An Artificial Intelligence (AI) model was developed and deployed on the edge for region-of-interest (ROI) detection. A single-stage YOLOv8 model was trained on a custom image dataset comprised of Atlantic salmon (Salmo salar) and rainbow trout (Oncorhynchus mykiss) fillet images to detect the fillet and color palette with their respective SalmonFan™ (SF) score on the reference card. Delta E metric was adopted to compare the color of the fillet and reference color shades on the SF card. The SF score corresponding to the lowest Delta E value was assigned to the fillet. The object detection model performed well and achieved a mean average precision (mAP0.5) of 99.5% and an F1 score of 0.99. The FilletCam-predicted fillet color scores were compared with the expert ratings and colorimeter scores to evaluate the performance of the developed tool. The minimum Delta E values for FilletCam were consistently lower than those for the colorimeter, indicating FilletCam’s ability to detect minor color differences accurately. FilletCam exactly predicted the color scores at 73% of instances compared to 30% of instances for the colorimeter. Additionally, for only 3% of instances, the predicted SF score deviated by more than two points. Overall, the developed research prototype shows promise as a valuable digital tool for the fish processing and retail industries.