Automated computer vision system for quality assessment of meat-in-gravy and meat-in-jelly products
An AI-enabled computer-vision inspection platform that provides objective, repeatable, and fully recordable quality assessment for meat-in-gravy and meat-in-jelly products. It automates measurement of meat-piece size, shape, color, background color, and meat-to-background ratio, replacing subjective visual checks with traceable data for improved consistency and production efficiency.
Overview
An AI-enabled computer-vision inspection platform that delivers objective, repeatable, and fully recordable quality assessment for meat-in-gravy and meat-in-jelly products. The system replaces subjective, operator-dependent visual checks with automated measurement of the product attributes that determine appearance and consistency, including meat-piece size, shape, color, background (gravy or jelly) color, and meat-to-background ratio.
Technical specifications
The platform pairs high-resolution 2D/3D imaging with deep-learning image segmentation and calibrated colorimetric analysis. It is designed for at-line or near-line deployment immediately after filling, with an inline configuration available for later phases, enabling adoption with minimal disruption to existing production workflows.
Key capabilities:
- Automated quantification of meat-piece size, shape, and color
- Background gravy or jelly color and meat-to-background ratio measurement
- Annotated image capture with timestamps for full traceability
- Batch comparison and continuous model improvement from stored measurements
- Configurable tolerance ranges and deviation rules for quality control
Every measurement is stored with an annotated image and timestamp, supporting traceability, batch-to-batch comparison, and ongoing refinement of the segmentation and color models.
Technology readiness level
The platform is at the pilot-validation stage. The planned ten-week validation program begins with review of target products and existing quality standards together with collection of representative sample imagery, followed by calibration of the segmentation and color models on real product imagery and configuration of tolerance ranges. An on-site pilot then runs the system at a nominated production facility alongside current manual inspection for direct comparison, with accuracy, repeatability, and usability assessed against agreed success criteria. Upon successful sign-off, the system can be scaled to additional lines, products, and sites, including inline deployment.
About University of Illinois, Urbana-Champaign
The University of Illinois Urbana‑Champaign is a flagship public research university with large‑scale research capacity and a broad academic portfolio. An on‑campus Research Park co‑locates corporate R&D teams and startups with faculty, while the National Center for Supercomputing Applications provides advanced computing and data capabilities for collaboration. Integration with a regional health system and an engineering‑based college of medicine enables clinical translation, and a long‑standing extension network links campus innovation to partners statewide. Research is supported by competitive federal funding from NSF, NIH, DOE, USDA, and DoD. A technology transfer office streamlines IP, licensing, and startups, complemented by incubators and prototyping in the Research Park.
delivered to your inbox.