AI PEKAT VISION

Metal Screw Inspection (unsupervised anomaly detection)

PEKAT VISION© is able to check products or input raw materials which have an unstable look or shape.

It uses its own proprietary focused-learning algorithm which goes beyond deep-learning.

Focused-learning works like a human eye​. It is able to focus on detail and needs only a few images for learning and understanding the task.

Even from the few images it is able to recognize when an object or material is defect-free and when it is defective.

It can find anomalies​, detect and classify defects and check surface on materials and objects where current vision systems fail.

PEKAT VISION© is universal. It can be used with all kinds of materials such as wood, stone, metal, lacquer, castings, leather, rubber or fabrics.

• PEKAT VISION can work either in so called unsupervised mode. It is then able to find defects which it didn't see before​. It is even enough to train it on images of defect-free objects or material.
• Or it can work in a supervised mode - it can be trained to search for a specific defect or surface problem - e.g. scratches, rust, leaks, holes etc.
• It does not matter that each product or material is slightly different and it does not matter whether it is difficult or even impossible to describe what is a defect. PEKAT VISION is able to find it anyway.