CLASSIFICATION BY DEEP LEARNING

What is deep learning?

It is an automatic hierarchical or structured algorithm that emulates human learning with the aim of achieving certain knowledge. The system is capable of learning by itself through a previous “training” phase, it is not necessary to be programmed.

Furthermore, it is characterized by processing information through the artificially intertwined neural networks of which it is composed. It is primarily used for the automation of predictive analytics.

artificial intelligence

Deep learning constitutes one of the fundamental bases of artificial intelligence (AI) and given the great boom that it has had in recent times, interest in deep learning has also increased.

Deep learning techniques have improved the ability to classify, recognize and detect, in short, have given a great boost to the ability to understand.

The classification of images based on Deep Learning, allows to carry out classification tasks of products or defects through artificial vision techniques.

Through previous learning of the system, and the configuration of a convolutional neural network, with relatively short configuration times, the classification of new products or effects is carried out quickly and efficiently.

By means of semantic segmentation, the trained defect classes can be located with pixel precision. This allows users, for example, to solve inspection tasks, which previously could not be done, or only with significant programming effort.

Today’s electronics make it possible to integrate classification software into embedded systems, enabling the development of compact, low-cost equipment.

Object and defect detection

deep learning

Object detection locates the classes of trained objects and identifies them with a surrounding rectangle (bounding box). Objects that touch or partially overlap are also separated, allowing for object counting.

We can align these rectangles according to the orientation of the object, which results in more accurate detection, as the rectangles are more closely aligned with the shape of the object.

This technology is very useful when classifying different products that do not have an identifying label or when identifying defects that follow random patterns of appearance and location.

Automatic product sorting and classification

Detection of defects and foreign body contamination in packaging

When it comes to the detection of defects that have a similar shade to that of the product or are difficult to detect using shade matching algorithms, such as:

  • Hairs (can be mistaken for shadows and reliefs of fillets)
  • Feathers (can be mistaken for pieces of fat)
  • Tray scraps (can be mistaken for glistening)
  • Bones and calves (can be mistaken for white shades of the product)
  • Wrinkles in the heat-sealing area
  • Rolling defects

Automatic detection by means of Deep Learning technology is chosen.

Previous
Next

Classification of carcasses by sex and detection of faecal contamination

Another of the multiple applications of Deep Learning technology is in solutions for slaughterhouses and cutting plants. INSPECTRA has developed through this technology the classification of carcasses by sex and the detection of faecal contamination by training neural networks with a large number of images captured online.

Detection of defects in cans

Deep Learning can defect detection is an advanced machine vision technique that uses deep neural networks to automatically identify and classify can defects accurately and efficiently.

This defect detection method uses a combination of image processing and deep learning technologies to analyse images of cans and detect any type of defect, such as dents, scratches, tears, stains, stains and more. The neural network is trained on a dataset of images of cans with and without defects to learn to identify patterns associated with the defects.

This is a highly customisable detection method that can be adapted to the specific needs and requirements of each customer:

  • Detection of dents or dings
  • Classification by shape or height
  • Detection of defects or tears in labels
  • High speed code reading and verification
  • Lithography inspection
  • Ring check: presence/absence, correct position, orientation and ring pattern