Machine vision for rapid quality assessment of meat in gravy or jelly
A compact, color-calibrated imaging station for routine quality assessment of meat products in gravy or jelly beside a production line. Machine-vision software measures visible meat-piece size, shape, color, matrix color, and meat-to-background area ratio, with segmentation models and uncertainty flags. Designed for minimal sample preparation, cleanable hardware, and a sub-five-minute turnaround, it delivers annotated images, size distributions, and specification-based alerts.
Overview
A compact machine vision station for routine quality assessment of meat products in gravy or jelly, for use beside a production line. It combines a color-calibrated RGB camera, enclosed lighting, and image-analysis software to measure visible meat-piece size, shape, color, gravy or jelly color, and meat-to-background area ratio, enabling rapid quality decisions against agreed specifications.
The station is engineered for practical manufacturing use, with minimal sample preparation, cleanable hardware, and a target turnaround under five minutes. Outputs include annotated images, size distributions, and automated alerts.
Technical specifications
System components:
- Color-calibrated RGB camera with enclosed lighting for glare-controlled image capture
- Segmentation models distinguish visible meat pieces from the surrounding gravy or jelly matrix
- Automated measurement of piece size, shape, color, matrix color, and meat-to-background ratio
- Uncertainty flags for ambiguous measurements requiring human review
Analytical approach:
- Models trained and validated on independent production batches
- Benchmarking against reference measurements for accuracy and repeatability
- Robustness to overlapping pieces and glare
- Annotated images, size distributions, and deviation alerts against product specifications
Technology readiness level
Early-stage development and validation. UC Davis research combines food-quality assessment, analytical chemistry, and machine learning for model development and analytical validation. A proposed three-month pilot would assemble the prototype, standardize calibration and sample presentation, collect labeled images across production batches, and develop segmentation and measurement models. The final phase validates accuracy, repeatability, missed defects, and false alarms in a supervised line-side trial, assessing operator usability, cleaning needs, and turnaround time. Deliverables include a validated performance report, operating protocol, and deployment recommendations.
About University of California, Davis
UC Davis is a comprehensive public research university in Northern California, combining a land-grant heritage with an integrated academic health system and a veterinary teaching hospital. Industry engages through co-located clinical and translational facilities in Sacramento, a campus-adjacent research park, pilot-scale food and bioprocessing facilities, and a statewide extension network for field-to-market deployment. Proximity to the Bay Area and California's Central Valley enables rapid collaboration with startups and established enterprises, while corporate relations staff streamline access to faculty, talent, and core labs. Research is supported by competitive federal funding from agencies such as NIH, NSF, USDA, and DOE. A dedicated technology transfer office and venture support programs provide IP management, licensing, and startup formation pathways for industry partnerships.
delivered to your inbox.