Loading...

Talk

Scroll

Previous Case Study: QSL
Next Case Study: Restos Plaisirs

HOW TO BE 25% MORE EFFICIENT IN QUALITY CONTROL WITH AI

Patates Dolbec

Patates Dolbec is the largest potato producer in eastern Canada. The company cultivates nearly 10,000 acres of land in the Portneuf region and has vertically integrated itself over the years. Today, Patates Dolbec cultivates, transforms and packages a wide variety of potatoes destined to the North American market.

Founded 50 years ago, the Saint-Ulbade company has always relied on innovation to improve its performance. Following the automation of its production line, Patates Dolbec decided to reach for Vooban in order to improve their quality assurance process using artificial intelligence.

Statistics

Potato varieties

White, russet, red, etc.

15

Defects identified by the algorithm

21

Challenges

The objective was to be able to detect all types of imperfections affecting the potatoes’ quality (more than 20) and to provide a solution that would give Patates Dolbec the freedom of choosing the quality level of their product according to the varying needs of their customers (restaurants, grocery stores, etc.).

An additional challenge was to surpass the performance of the detection algorithm of their industrial sorting machine, which is the market benchmark for this sort of task, to allow Patates Dolbec to reallocate its quality assurance team towards higher value jobs and activities.

Solution

  

Patates Dolbec was not satisfied with the performance (30% error rate) of their legacy optical sorting machine, causing them to have to manually remove the remaining defects and losing a large number of good potatoes and the profits associated with it. In an industry with chronic labor shortage, a better solution was crucial. With the ever-changing nature of grown products, they needed an evolutive solution to be able to adapt to the changes in the base product.

We, therefore, retrofitted their optical sorting machine with high-definition cameras and a state-of-the-art deep-neural-network computer vision model to leverage recent development in AI and computer vision. To allow for periodic retraining of the model, a machine learning pipeline was developed in the AWS cloud. From datastore, labeling, and training to model registry and edge deployment, the AWS cloud is the foundational backbone of the upgraded sorting machine.

In the end, the implementation of AI in the quality control process had allowed Patates Dolbec to gain no less than 25% in efficiency as the error rate went from 30% to 5% in just a few months. Patates Dolbec, with the help of the AWS cloud, is now fully autonomous in their capacity to retrain and deploy new models that are trained using knowledge from their own workforce. This allows them to adapt the model to new varieties or changes in the base product. Furthermore, they can customise the behaviour of the sorting to a level unattainable by their legacy machine, indeed this allows them to precisely tune the sorting characteristic to address the needs of different customers.