AI System for Routing Produce Images to Quality Review

The problem

In day-to-day operations, samples requiring inspection may be missed when produce volumes are high. When produce images, batch, variety, imaging conditions and the quality checklist are scattered across sensors, documents, field records or team systems, issues do not become visible in time.

This fragmented data delays preparation of the quality review queue and forces teams to search for supporting evidence again by hand. Before making a decision, the food engineer or quality control specialist must complete missing records and verify each conflict individually.

A common exception is that natural differences between varieties and lighting conditions can resemble defects. Without this context check, incomplete or incorrect automation could reject suitable produce or accept a defective batch, so no physical or operational action can be applied directly.

What we set out to improve

• Proportion of review candidates confirmed by the quality specialist
• Proportion of outputs corrected or rejected by the food engineer or quality control specialist
• Time between the source event and the inspection output

How the system works

1. 01 Define the review scope and the authorised food engineer or quality control specialist role
2. 02 Retrieve inputs: produce images, batch, variety, imaging conditions and quality checklist
3. 03 Check source identity, date, calibration or version, and data recency
4. 04 Check image quality and batch identity
5. 05 Preclassify visible differences against the checklist
6. 06 Check for an exception: natural differences between varieties and lighting conditions can resemble defects
7. 07 Route low-confidence or conflicting records to a separate specialist queue
8. 08 Write the source identity, rule, output and timestamp to the audit trail
9. 09 Have the food engineer or quality control specialist approve, correct, defer or reject the output

Methods we used

• Image preclassification without deciding product grade or acceptance
• Source, format, timing and required-field checks for produce images, batch, variety, imaging conditions and the quality checklist
• A missing-data warning instead of an estimate when inputs are incomplete or conflicting
• Separate evaluation of exceptions and the main rule
• Combined retention of the source, rule result, quality review queue and human decision

Where people stay involved

Data and security

Access to produce images, batch, variety, imaging conditions and the quality checklist is limited to the minimum permissions required for the task. Commercial, location and employee information is masked where possible, and only the necessary subset of the raw dataset is passed to the model. Access, outputs and the food engineer's or quality control specialist's decisions are logged; the system is not released to production until the organisation approves the retention period and data location.

Who this suits

Frequently asked questions