How an AI application is helping improve quality control in the egg farming industry

People typically open a carton of eggs before buying it to be sure none of the eggs are cracked. No one wants to deal with the mess of cracked eggs. For egg farmers, one “bad egg” in a carton means the retail store must be credited for the entire carton. That could potentially waste as many as 23 good eggs, depending on carton size. It’s in farmers’ best interest to detect egg cracks before the eggs enter the supply chain.
Plus, if an egg is cracked, there’s a risk that the egg is in bad condition for consumers. Egg farmers typically perform egg inspection manually, which is time consuming. Pixelabs, a digital solutions provider and IBM Business Partner in Spain, has developed an innovative artificial intelligence (AI) quality control application that optimizes and automates the egg inspection process.
Creating the quality control app at the Watson Build Challenge
Pixelabs developed its “Deteggtor” egg quality control application on IBM Cloud with IBM Watson Visual Recognition technology. The solution uses machine learning to detect egg cracks and provide visual feedback. We gathered thousands of images of cracked and uncracked eggs to train Deteggtor. Following this training, cracked egg detection with the Deteggtor application was 97 percent accurate in a fraction of the time.
We developed Deteggtor during participation in the Watson Build Challenge. Our close collaboration with IBM on both the technology and business fronts helped us understand that beyond just participating in a competition, we could actually develop a viable product and bring it to market. We have appreciated the feedback and support from IBM. We’ve always had someone by our side to help us, not only learn how to use the Watson technology, but also to discover what is possible with Watson.
Helping deliver faster, more accurate egg quality control
The benefits we have seen in our initial pilot are related to quality control and speed of production. Egg crack detection is more accurate and quicker with Deteggtor than with a human.
Another benefit I envision is that egg farmers won’t have to teach new employees how to distinguish which egg is broken or not. Deteggtor has modernized that process.
Additionally, by not introducing cracked eggs into the supply chain, egg farmers have less waste, reduced worry about selling cracked eggs and more confidence that they’re complying with industry regulations. The system is scalable and replicable, thus can adjust to industry demand.
Read the case study for more details.
The post How an AI application is helping improve quality control in the egg farming industry appeared first on Cloud computing news.
Quelle: Thoughts on Cloud