Newest HALCON Features
Preview: HALCON 20.11
Here we publish gradually the coming main features of the new version of MVTec HALCON, which will be published on November 20, 2020.
Deep Learning Edge Extraction
Deep learning edge extraction is a new and unique method to robustly extract edges (e.g., object boundaries) that comes with two major use cases.
Especially for scenarios where a variety of edges is visible in an image, it can be trained with only few images to reliably extract the desired edges. Hence, the programming effort to extract specific kinds of edges is highly reduced with this version of MVTec HALCON. Besides, the pretrained network is innately able to robustly detect edges in low contrast and high noise situations. This makes it possible to extract edges that usual edge detection filters cannot detect.
HALCON 20.11 introduces a new HALCON/Python interface. This enables developers who work with Python to easily access HALCON's powerful operator set.
Current version: HALCON 20.05
On this page, you will find information on the newest features of MVTec's standard machine vision software HALCON.
The latest HALCON version was released in May 2020:
Subpixel Bar Code Reader
The bar code reader has been improved by an advanced decoding algorithm. Thanks to this, the bar code reader in HALCON 20.05 is even capable of reading codes with an element size smaller than 1 pixel.
More robust Surface-Based 3D Matching
With HALCON 20.05, surface-based 3D matching is more robust in case of almost symmetric objects.
Especially in the assembly industry, workpieces must be located robustly and accurately to allow for further processing. Often, properties like small holes are the only unique feature to find the correct orientation of the object.
HALCON's surface-based 3D matching can now make use of these features to increase accuracy and robustness of the matching result.
Deep Learning Training on CPU
With HALCON 20.05, training for all deep learning technologies can be performed on the CPU. By removing the need for a dedicated GPU, standard industrial PCs (that could not house powerful GPUs) can now be used for training as well. This greatly increases customers' flexibility in implementing deep learning, because training can now be performed directly on the production line, making it possible to adjust the application to changing external conditions "on the fly".
More robust Generic Box Finder
The generic box finder, which was released with HALCON 19.11, allows users to locate boxes of different sizes within a predefined range of height, width, and depth, removing the need to train a model. With HALCON 20.05, it was improved in terms of robustness, performance, speed, and usability. Now, it is much easier to find a wide range of different sizes of various boxes in a robust way.
Anomaly Detection Improvements
The anomaly detection significantly facilitates the automated surface inspection by only requiring a low number of high quality "good" images for training. With HALCON 20.05, training a network for anomaly detection is now up to 10 times faster. Combined with an also faster inference, this opens up entirely new possibilities for trying deep learning on new and existing applications: Training a new network can now mostly be done in a matter of seconds, allowing users to perform many iterations to fine-tune their application without sacrificing a lot of precious time. Trained networks now also require less memory and disk space, which makes HALCON's anomaly detection more viable for the use on embedded devices.
CPU Support for Grad-CAM-based Heatmap
The Grad-CAM-based heatmap (Gradient-weighted Class Activation Mapping) supports you in analyzing which parts of an image influence the classification decision. In HALCON 20.05, the heatmap calculation can also be performed on the CPU. Since this can be done without significant speed drops, customers are now able to analyze their deep learning network's class prediction "on the fly".