Feature Preview - HALCON 22.05 is just around the corner!

Here you can see a preview of some features included in the next release, HALCON 22.05, which will be published in May 2022.

Deep OCR Training

HALCON`s Deep OCR enables users to efficiently solve text reading applications in a multitude of use cases. With HALCON 22.05, this technology is extended by training functionality, enabling application specific training on the user's own application dataset. This allows you to solve even most complex applications like reading text with bad contrast (e.g., on tires). Another advantage is that very rarely used special characters or printing styles can also be trained. Training for Deep OCR significantly improves the performance and usability and makes applications run even more robust.

Global Context Anomaly Detection

Global Context Anomaly Detection

HALCON 22.05 opens up completely new application possibilities with the detection of logical anomalies in images. This is the further development of the deep learning technology anomaly detection. Until now, it was possible to detect local, structural anomalies. The new “Global Context Anomaly Detection” is a one-of-a-kind technology, which is able to "understand" the logical content of the entire image. Just like HALCON`s existing anomaly detection the new “Global Context Anomaly Detection” only requires "good images" for training, eliminating the need of data labeling.

This technology makes it possible to detect entirely new variants of anomalies like missing, deformed, or incorrectly arranged components. It opens up completely new possibilities: For example, the inspection of printed circuit boards in the semiconductor production or the inspection of imprints.

Improved Print Quality Inspection for ECC 200 Codes

Print Quality Inspection (PQI) refers to the evaluation and grading of certain aspects of printed bar and data codes according to international standards. For example, it indicates how reliable a code can be read by various code readers or how stable the print quality is in a manufacturing process. HALCON supports various standards for grading the print quality of 1D and 2D codes. With HALCON 22.05, the PQI of data codes has been further improved. It is now up to 150% faster. In addition, the module grid determination for print quality inspection of ECC 200 has been improved. Last but not least, the usability of the PQI of data codes has been improved by introducing a new procedure that provides the grades.

Quality-of-Life Improvements and Speed-Ups

With HALCON 22.05, various improvements are released. One example is a new operator that performs adaptive histogram equalization to improve contrast locally in an image. This helps to extract significantly more information from images with low contrast, especially in case of inhomogeneous gray value gradient. Besides, the HALCON library has been extended with a new operator which allows image smoothing with arbitrarily shaped regions. Furthermore, another new operator allows you to transform 3D points using a rigid 3D transformation that is specified as a dual quaternion. And finally, HDevelop’s Matching Assistant now generates the code based on Generic Shape Matching.


Previous Features

Have a look at the features from previous releases. All features listed below are available for HALCON Progress or Steady users with a version 20.11 and higher.

HALCON 21.11

Features included in this version:

 

  • Deep Learning Instance Segmentation
  • Improved Bar Code Reader for Code 128
  • Improved Dictionary Handling
  • Future-Proof Interface for Shape Matching

Get more information

HALCON 21.05

Features included in this version:

 

  • Deep OCR improvements
  • Generic Shape Matching
  • HDevelop usability improvements
  • HALCON Deep Learning Framework
  • Subpixel bar code reader improvements

Get more information

HALCON 20.11

(Steady Version)

Features included in this version:

 

  • Improved Surface-based 3D-Matching

  • DotCode and Data Matrix Rectangular Extension

  • Deep OCR

  • Improved Shape-based Matching

  • HDevelop Facelift

  • Deep Learning Edge Extraction

Get more information

HALCON 20.05

Features included in this version:

 

  • Subpixel Bar Code Reader
  • More robust Surface-Based 3D Matching

  • Deep Learning Training on CPU

  • Further Improvements

    • More robust Generic Box Finder

    • Anomaly Detection Improvements

    • CPU Support for Grad-CAM-based Heatmap

Get more information

HALCON 19.11

Features included in this version:

 

  • Deep Learning Anomaly Detection
  • ECC 200 Code Reader Speedup

  • Generic Box Finder

  • ONNX-Support

Get more information

HALCON 19.05

Features included in this version:

 

  • Deep Learning Inference on Arm Processors
  • Enhanced Object Detection

  • Improved Surface-based Matching

  • Enhanced Shape-based Matching

Get more information