HALCON 20.11 Feature-Preview: Deep Learning Edge Extraction

The next version of HALCON will be released on November 20, 2020. We're happy to turn the spot on one of the upcoming features:
Screenshot of a commong edge extraction filer application and one with deep learning edge extractor after applicatioin-specific training
MVTec's deep learning edge extraction can distinguish between parquet joints and the wood grain.

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.