Conventional color sorters let near-colored insects and plastic fragments pass while ejecting blemished but edible produce as defects — detection and false-reject move against each other. This plant rebuilt the decision logic with DaoAI deep-learning models.
This fresh-produce processor supplies prepared vegetables and frozen fruit-and-veg ingredients to retail and food-service channels, handling over a hundred tons per day. Conventional photoelectric color sorters rely on fixed color thresholds and are nearly helpless against foreign objects close in color to the raw material — dark insect bodies, translucent plastics, same-colored grit. To avoid misses, operators tightened thresholds, which in turn ejected large volumes of naturally blemished or slightly off-color but perfectly edible produce, keeping good-product loss stubbornly high.
DaoAI deployed an AI-AOI inspection system to replace the rule-based color sorter. The deep-learning model no longer looks at color alone; it combines texture, shape, edge and context to separate true foreign objects from natural raw-material variation — faced with a dark patch, it tells a moldy contaminant apart from a varietal dark spot. For occasional rare contaminant types, APDT few-shot learning lets the line adapt to new raw-material batches from just dozens of samples, with no need to re-annotate massive datasets.
Solution Architecture
- AI-AOI high-speed line-scan imaging plus deep-learning defect/FO models, interfaced to the existing air-jet ejectors
- A grading model concurrently outputs size, color and damage grade, so removal and grading complete in one pass
- APDT few-shot onboarding of new raw-material batches, cutting annotation effort by about 80%
- All decisions are logged, enabling per batch traceback of contaminant types and ejection records
Detection and false-reject no longer trade off — the model learned to tell true contaminants from the raw material's natural variation.
After go-live, foreign-object detection rose from roughly 88% on the old color sorter to above 97%, while false-reject fell from 4–6% to under 1% — hundreds of kilograms of good material saved every hour. The line runs stably at 6.5 t/h throughput, with grading and FO removal merged into a single station, manual re-inspection headcount reduced, and overall yield meaningfully recovered.
FAQ
What are the problems of traditional color sorters in fresh food processing?
Traditional photoelectric color sorters rely on fixed color thresholds and have difficulty identifying foreign objects with similar colors. To avoid missing detections, tightening the thresholds leads to a large number of qualified raw materials being wrongly removed, with high loss of good products and a trade-off between detection and false removal rates.
What are the advantages of DaoAI's solution?
DaoAI deploys an AI-AOI system. The deep-learning model distinguishes foreign objects from natural differences in raw materials by considering multiple factors. The APDT few-shot learning ability adapts to new raw materials. The foreign object detection rate exceeds 97% and the false removal rate is below 1%, improving the overall yield.
How does this solution improve production line efficiency?
The solution combines high-speed line-scan imaging and deep-learning models, and connects with the air-blowing removal mechanism. Quality grading and foreign object removal are completed in one step, reducing manual re-inspection positions. The production line runs stably at a throughput of 6.5 tons per hour.