AI-based inspection system for potato processors

A new AI-based vision inspection system from Smart Vision Works, a KPM Analytics brand, is designed to solve long-standing problems including inaccurate quality grading and detection of foreign objects during processing. 

The SiftAI^® Smart Table uses artificial intelligence (AI) to automatically detect and remove foreign objects and sort products in a single pass.  The system includes cameras, AI software, a conveyor, and automatic ejection mechanisms with dual drops (one for foreign material, one for culls) to ensure only ideal potatoes reach later process stages. 

Unlike others that use optical scanners, this system takes a full digital image and runs it through a neural network. Users receive detailed data for analysis. Beta customers report higher produce profit, fewer missed contaminants, and dramatically lower labor costs, according to KPM. Watch a video to see the system in action.

Designed to improve food processors’ profitability

The SiftAI Smart Table vision inspection system is competitively priced, according to KPM. Company managers can justify the investment by reallocating inspection workers to higher skill areas. Wages have risen sharply in recent years, so company managers will value the opportunity to shift workers away from low-skill activities.

In addition, the system helps processors avoid customer fines for contaminants. For some processors, these fines may cost $50,000 per incident and total hundreds of thousands of dollars per year.  Because of the speed of the advanced AI technology, conveyor speeds can be increased, giving operators more throughput per shift. 

The system precisely grades produce using sophisticated evaluation of bruises, rot, and green. According to Christopher Bryant, President of the Smart Vision Works AI Division within KPM Analytics, "we estimate that up to 20% of potatoes are typically diverted to the wrong value stream, reducing profitability and causing customer satisfaction issues." A more accurate sorting system diverts less produce to less profitable uses, and higher quality produce can command a higher price.

The AI-driven system addresses specific business and operational challenges potato processors face each day.

• Chip potatoes: Avoid penalties (charge backs) by immediately eliminating foreign materials from the process stream.
   
• Process potatoes: Also eliminate foreign materials while reliably sorting potatoes based on size, defect presence, and more.
   
• Fresh pack potatoes: Pre-sort to reduce potato volume through the facility, minimize foreign material risk, and deliver only the best potatoes to customers.

The SIftAI Smart Table system is available for order now with a 14-16-week lead time. Contact the factory for lead times on custom configurations having more tilt trays or other features.