MVTec HALCON 17.12

Introducing HALCON 17.12, boasting an extensive set of cutting-edge deep learning functions, which can be instantly applied in industrial settings. Users are now able to raise their machine vision processes to an entirely new level using self-learning algorithms. This allows companies to simplify and accelerate programming processes significantly. In addition, they also benefit from even more robust detection rates and better classification results.

Training a CNN

Training a CNN in HALCON is done simply by providing a sufficient amount of labeled training images. E.g., to be able to differentiate between samples that show scratches or contamination and good samples, training images for all three classes must be provided: Images showing scratches must be labeled “scratch”, images showing some sort of contamination must carry the label “contamination”, and images showing a good sample must be in the category “OK”.

HALCON then analyses these images and automatically learns which features can be used to identify defective and good samples. This is a big advantage compared to all previous classification methods, where these features had to be “handcrafted” by the user – a complex and cumbersome undertaking that requires skilled engineers with programming and vision knowledge.

Using the Trained Network

Once the network has learned to differentiate between the given classes, e.g., tell if an image shows either a scratched, a contaminated or a good sample, the network can be put to work. This means, users can then apply the newly created CNN classifier to new image data which the classifier then matches to the classes it has learned during training.

Typical application areas for deep learning include defect classification (e.g., for circuit boards, bottle mouths or pills), or object classification (for example, identifying the species of a plant from one single image).

Inspecting Specular Surfaces with Deflectometry

Inspecting specular reflecting surfaces imposes special challenges, because the observer does not see the surface itself, but the mirror image of the environment.

This poses significant problems for most surface inspection methods such as triangulation or shape from shading, because these usually rely on diffuse reflection.

HALCON 17.12 includes new operators, which enable the user to inspect specular and partially specular surfaces to detect defects by applying the principle of deflectometry. This method uses the aforementioned specular reflections by observing mirror images of known patterns and their deformations on the surface.

Automatic Text Reader

HALCON 17.12 features an improved version of the automatic text reader, which now detects and separates touching characters more robustly.

Surface Fusion For Multiple 3D Point Clouds

HALCON now offers a new method that fuses multiple 3D point clouds into one watertight surface. This new method is able to combine data from various 3D sensors, even from different types like a stereo camera, a time of flight camera, and fringe projection. This technology is especially useful for reverse engineering.


HDevEngine Improvements

With the new HDevelop library export included in HALCON 17.12, calling HDevelop procedures from C++ is as easy and intuitive as calling any other C++ function. This new library export also generates CMake projects, which can easily be configured to output project files for many popular IDEs, such as Visual Studio.


PROGRESS VS STEADY – What’s the difference?

HALCON 17.12 will be the first release of the new HALCON Progress Edition. From version 17.12 onwards, MVTec HALCON is available in two different software editions:

  • HALCON Progress Edition
  • HALCON Steady Edition (The first HALCON Steady Edition is scheduled for release by the end of 2018. Until then, customers who are interested in HALCON Steady can purchase HALCON 13 and benefit from the same advantages.)

Models Available

  • HALCON 17.12 Brochure
  • Euresys
  • IO Industries
  • Moritex
  • Imperx
  • FingerLake Instruments
  • Basler