STEMMER IMAGING

The MVTec experts have optimized a number of core technologies in HALCON 20.11.

• DotCode reading
  A new 2D code type known as DotCode has been added. It is based on a matrix of dots and can be printed very fast, which makes it especially suitable for high-speed applications, for instance in the tobacco industry.

• OCR and deep learning
  With another new feature called Deep OCR, MVTec introduces a holistic deep-learning-based approach for optical character recognition (OCR). Deep OCR can localize numbers and letters much more robustly, regardless of their orientation, font type, and polarity. The ability to group characters automatically allows the identification of whole words. This improves the recognition performance significantly and avoids the misinterpretation of characters with similar appearances.

• Improved user-friendliness and faster 3D matching
  The core technology shape-based matching was also optimized in HALCON 20.11. More parameters are now estimated automatically, which improves both user-friendliness and the matching rate in low contrast and high noise situations. The new release demonstrates significant improvements in the 3D environment as well. Edge-supported, surface-based 3D matching is now significantly faster for 3D scenes with many objects and edges. Usability has also been improved by removing the need to set a viewpoint.

• Improved functionality for developers
  HALCON 20.11 makes things much easier not only for users but also for developers. A new language interface enables programmers who work with Python to seamlessly access HALCON's powerful operator set. In addition, the integrated development environment HDevelop has been given a facelift. It now offers more options for individual configuration, such as a modern window docking concept. Moreover, themes are now available to improve visual ergonomics and adapt HDevelop to personal preferences.

• Precise edge detection with deep learning
  HALCON 20.11 includes a new and unique method for robustly extracting edges with the aid of deep learning. Especially for scenarios where a large number of edges are visible in an image, the deep-learning-based edge extraction function can be trained with only a few images to reliably extract only the desired edges. This greatly reduces the programming effort for processes of this type.
  
  Out of the box, the pretrained network is able to robustly detect edges in low contrast and high noise situations. This makes it possible to also extract edges that cannot be identified with conventional edge detection filters. In addition, "Pruning for Deep Learning” now enables users to subsequently optimize a fully trained deep learning network. They can now control the priority of the parameters speed, storage, and accuracy and thus modify the network precisely according to application-specific requirements.

HALCON 19.11 provides a wide range of new and improved machine vision features. Users benefit from massive simplifications for their applications. Particular emphasis was placed on the integration of further deep learning features.

• Deep Learning Anomaly Detection
  Automated surface inspection is an important task in many manufacturing industries and deep-learning-based solutions are becoming a standard tool which can be used to distinguish parts, detect and segment defects. However, it is often not easy to get enough images of the defect or the effort of labeling the available data is very high. HALCON's new Anomaly Detection feature gives you the possibility to perform an inspection using only a relatively low number of "good" images for the training. The inference results in the "anomaly" that was detected in the inspected image compared to the trained images. On the right, you can see an example of a defective bottleneck.

• ECC 200 Code Reader Speedup
  The code reader for ECC 200 codes has been significantly accelerated for multi-core systems. The biggest improvement was achieved for codes that are particularly hard to detect and read. For such codes a speedup of about 200% can be achieved. This speedup also greatly increases the viability of embedded-based code readers by making optimum use of existing hardware capacities.

• Generic Box Finder for pick and place applications
  The generic box finder allows the user to find boxes of different sizes based on 3D space, eliminating the need to train a model for each required box size. This makes many applications much more efficient – especially within the logistics and pharmaceutical industries, where usually boxes of a large variety of different sizes are used.

• ONNX-Support
  Many companies work with open source frameworks to train classifiers for deep learning models (CNN). These CNNs can be exported into the ONNX (Open Neural Network Exchange) format. HALCON is able to read data in ONNX format, allowing to use previously created 3rd party networks within HALCON.

In HALCON 19.05 the deep learning functionality can be applied to a broader range of applications. Please note that this update is only available with the progressive license model.

• Enhanced Object detection
  Users now have the option of aligning object detection boxes with the orientation of the object, enhancing the localised trained object classes.

• Inference on ARM Processors
  Inference for all three deep learning technologies – image classification, object detection, and semantic segmentation – runs out-of-the-box on Arm® processors. As this removes the need for special components like a powerful GPU or a desktop CPU, HALCON significantly broadens the range of possible deep learning applications. Execution times on Arm®-based platforms vary by complexity and the type of hardware, but MVTec benchmarks have shown them to be suitable for many conceivable applications.

• Shape Based Matching
  Shape-based matching is one of HALCON's most important core technologies and can be considered to be one of the most powerful matching tools on the market. MVTec continuously improves this technology to widen the application area even further. With HALCON 19.05, users can now, for example, specifically define so-called "clutter" regions (marked above in orange). These are areas within a search model that should not contain any contours.

• Surface Based Matching
  Edge-supported surface-based matching is now more robust against noisy point clouds: Users can control the impact of surface and edge information via multiple min-scores. Additionally, in case that no xyz-images are available, a new parameter now allows switching off 3D edge alignment entirely. This enables users to eliminate the influence of insufficient 3D data on matching results, while keeping the valuable 2D information for surface and 2D edge alignment.

• Speedups
  Various operators in HALCON have been sped up. For example, depending on image type and settings, affine_trans_image is now up to 230 % faster on AVX2 processors. Furthermore, polar_trans_image_ext can be executed up to 160 % faster, depending on the interpolation method.

HALCON 18.11 will be available in two editions: Steady and Progress. While the latter is available as a subscription with a six-month release cycle, the Steady edition – as successor of HALCON 13 – is offered for regular purchase.

• Deep Learning
  The new version 18.11 further expands the deep learning capabilities of HALCON. Even more powerful deep learning algorithms now allow users to locate objects within an image with pixel-precision or bounding box accuracy. There is no need to start from scratch, as our standard machine vision software comes with various pretrained Convolutional Neural Networks (CNNs), that have been highly optimized for industrial applications.

• Semantic Segmentation
  With HALCON 18.11, object- or error classes trained with deep learning can now be segmented pixel-precisely. Combined with the multitude of possibilities that HALCON offers for further processing extracted regions, this paves the way for an entirely new range of applications, which previously could not be realized, or only with significant programming effort. For example: recognising objects with a very heterogeneous texture (e.g., plants) or detecting defects on various types of objects and materials, e.g., pills, glass or leather.

• Object Detection
  HALCON 18.11 introduces deep-learning-based object detection, which allows customers to localise trained object- or error classes in an image. In contrast to semantic segmentation, objects are marked by a surrounding rectangle (bounding box). The object detection also separates instances of the same class, even if the objects touch each other or partially overlap. This is especially useful when the exact amount of objects is needed, e.g., when checking pill bags for correct filling.

• New Data Structure "Dictionaries"
  HALCON 18.11 introduces a new data structure, "dictionary", which is an associative array that opens up various new ways to work with complex data. It is possible, for example, to bundle various complex data types (e.g., an image, corresponding ROIs, and parameters) into a single dictionary: This helps to structure programs when, e.g., passing many parameters to a procedure.

• Handle Variable Inspect in HDevelop
  With HALCON 18.11, HDevelop can display detailed information on most important handle variables. This allows developers to easily inspect the current properties of complex data structures at a glance, which is extremely useful for debugging. Double-clicking a handle variable now returns all parameters associated with the handle and their current settings.

• ECC 200 Code Reader Improvements
  The data code reader for ECC 200 codes has been improved.

• HALCON in Your Industrial Network
  HALCON 18.11 introduces the Hilscher-cifX interface. This allows HALCON to communicate with almost all industrial field bus protocols via Hilscher cards.

• Improved Barcode Reader
  HALCON 18.05 features optimized edge detection, which improves the ability to reliably read bar codes with very small line widths as well as strongly blurred codes. Moreover, the quality of the bar codes is also verified in accordance with the most recent version of the ISO/IEC 15416 standard.

• Enhanced Deflectometry The deflectometry functionality introduced in HALCON 17.12 now includes a new pattern type that improves the precision and robustness of error detection especially on partially specular surfaces like varnished metal sheets.

• 3D Improvements HALCON 18.05 offers optimized functions for surface-based 3D matching. These can be used to determine the position of objects in 3D space more reliably, making development of 3D applications easier. In addition, HALCON now also includes a new helper procedure that allows developers to quickly inspect and debug parameters and results of a surface-based matching application.

• Automatic Handle Clearing HALCON 18.05 makes it much more comfortable to work with handles by clearing these automatically once they are no longer required. This significantly reduces the risk of creating memory leaks because you no longer have to manually release unused memory. This way, writing "safe code" is now much simpler.

• HDevEngine improvements The HDevelop library export feature has been expanded: Developers can now access HDevelop procedures not just in C++, but also in .NET via an exported wrapper – as easily and intuitively as a native function. This significantly facilitates the development process.

• Support for Hypercentric Lenses A new camera model within HALCON now allows the corrections of distortions in images that were recorded with hypercentric (also known as pericentric) camera lenses. These lenses can depict several sides of an object simultaneously, thus enabling a convergent view of the test object. With this technology, users only need a single camera system for inspection and identification tasks, e.g., the inspection of cylindrical objects

• Deep Learning
  With MVTec HALCON 17.12, you are able to train your own CNN classifier (Convolutional Neural Network). After training the CNN, the network can be used to classify new data with HALCON.

• Deflectometry
  In order to address the special challenges imposed by inspecting specular reflecting surfaces for defects like dents and scratches, HALCON now enables you to apply the principle of deflectometry. This method uses 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