+7 8202 20-21-17
Mon-Fri 9:00AM – 6:00PM (MSK)

Defects detection

For 20 years, the specialists of the company Mallenom Systems have developed and successfully implemented dozens of machine vision systems. In our solutions, we use both our own unique developments in the field of image analysis, as well as proven algorithms from the world leader - the company Cognex.

In recent years, many new, interesting and at the same time complex tasks have appeared, for which deterministic algorithms do not give a satisfactory result. Therefore, we began to actively use artificial neural networks that allow to successfully solve the problem of localization and classification of complex objects in undefined, changing external conditions.

Detection of substandard vegetables

A batch of fresh vegetables may contain spoiled or rotten products, infected products, frozen or diseased vegetables. Even a few substandard vegetables can lead to the loss of the entire batch.

The quality control system for fresh fruits and vegetables developed by the Mallenom Systems analyzes the look of products and determines their maturity, caliber and defects presence. Based on the analysis, a conclusion is made about the product quality category, and if necessary, it is automatically sorted.

Detection of foreign particles in plastic bottles

In production of plastic bottles for drinking yoghurt, it is the likelihood that small pieces of plastic fall inside the bottle, which is unacceptable for further use of such bottles. Therefore, it is crucial to control bottles for purity and detect foreign particles.

Variable marking is embossed at the bottle bottom, and the inclusions can be of arbitrary shape. Therefore, to solve the problem, neural networks were used that made it possible to identify all inclusions with high accuracy.

Defects detection on roofing material

The surface of roofing material may contain obvious defects, such as holes, and as well as hard-to-see defects, such as riffles or defects in the binding layer. Defects may appear both on the top (front) and on the bottom (back) side of the canvas. Additional complications arise due to the canvas movement speed - up to 7 m/s and the presence of water drops on the material.

Neural networks successfully cope with such a challenge, which makes it possible to detect deviations from qualitative material even for roofing material of various categories.

Defects detection on ceramic bricks 

In ceramic brick production, various defects can be formed on its surface: cracks, chipping, spalling, scaling, etc.

The system created by Mallenom Systems allows to detect and classify surface defects of bricks. At the same time, all defects differ substantially in shape and size.

For additional information, please contact:

Tsareva Ekaterina, Project Manager
e-mail: tsareva@mallenom.ru
phone: +7 (8202) 20-16-39, cell: +7-921-251-62-96