HALCON 12
Back to MVTec
Back to Machine Vision Software
Back to Manufacturers

HALCON 12 sets new standards
for performance and usability

HALCON's general features
HALCON is the comprehensive standard software for machine vision with an integrated development environment (IDE) that is used worldwide enabling cost savings and improved time to market. HALCON's flexible architecture facilitates rapid development of machine vision, medical imaging, and image analysis applications and provides outstanding performance and a comprehensive support of multi-core platforms, SSE2 and AVX, as well as GPU acceleration.

It serves all industries with a library of more than 1800 operators for blob analysis, morphology, matching, measuring, identification, and 3D vision, among others and supports Windows, Linux, and Mac OS X, The full library is accessable from common programming languages like C, C++, C#, Visual Basic .NET, and Delphi.

HALCON guarantees hardware independence by providing interfaces to hundreds of industrial cameras and frame grabbers and also for standards like GenICam, GigE Vision, USB3 Vision, and IIDC 1394.

HALCON's sample-based identification is capable of differentiating a large number of items and can recognize trained objects solely based on characteristic features like colour or texture. Consequently, there is no need to use special imprints like bar codes or data codes for object identification purposes; the user merely needing to train the software to identify objects from several different directions.

HALCON offers a variety of 3D vision methods, and, in particular, the 3D surface comparison between expected and measured shape of a 3D object surface is an outstanding technology of the software. The object's surface can be reconstructed by any 3D technology available in HALCON such as multi-view stereo, sheet of light, or by ready-to-run 3D hardware scanners (also directly supported by Halcon). Additionally, improved photometric stereo is offered for special use in surface inspection.

Provided are many methods for 3D object processing, such as registration and triangulation of point clouds, calculation of features like shape and volume, segmentation of point clouds by cutting planes, and many more, all supported by GPU processing. HALCON automatically splits the data into multiple threads running on all available processing cores and then merges the output into one result with no input required from the user. Likewise, depth from focus, Fast Fourier Transformation, and HALCON’s local deformable matching are significantly accelerated.

Click here to learn more about Halcon's general features

Highlights of HALCON 12
SPEEDUP With version 12, HALCON utilizes AVX2, so running significantly faster on state-of- the-art processors. Further speedup is achieved in HDevelop and HDevEngine where the execution of procedures has become considerably faster by utilizing a just-in-time compiler.	3D VISION With the new local deformable surfaced-based matching, bent or stretched objects like pretzels can be found reliably, and so expanding the possibilities of 3D vision applications. HALCON’s surfaced-based 3D matching in version 12 has become more robust when processing noisy image data, e.g., from time-off-light cameras.	IDE HALCON’s highly interactive programming environment (IDE) HDevelop has been enhanced with support of parallel programming and thus allows concurrency. For this, HALCON 12 now also supports event-based processing. As a special key feature for software developers, a new extension allows to inspect HALCON variables (tuples and iconic) directly within Visual Studio, thus easing debugging tasks tremendously.
IDENTIFICATION HALCON 12 eases OCR applications with a new technology for automatic text reading. Characters of any size are found robustly, in most cases without the need to adjust parameters. The new technology has an impressive capability to distinguish characters from background texture even under challenging conditions.		USABILITY By means of its new calibration plates, HALCON 12 reaches the same accuracy by using considerably fewer images. Furthermore, it is no longer necessary that the new calibration plates are completely visible in the image.