28 Nov 2018
Further development of deep learning and convolutional neural networks (CNNs) allows object-, feature-, or error classes that have been trained with deep learning to be segmented with pixel accuracy. Segmentation, like classification, can be performed on a GPU as well as a CPU. These object-, feature-, or error classes can also be localized in the new software. By marking the required objects within a rectangle, a wide range of complex machine vision localization tasks can be re-evaluated and performed with far less effort than using conventional methods. This feature can also be used to reliably identify and count objects that touch each other or partially overlap.
To facilitate the use of deep learning, pre-trained networks based on millions of royalty-free images are provided. These allow the training of new objects more easily by eliminating the need for hundreds of thousands of application-specific images, and have no limitations for use in commercial applications.
For embedded vision applications, the new software now also runs on the increasingly popular 64-bit ARM® architecture.
A USB3 Vision interface for both 32 and 64 bit is provided. A further improvement is that the reading of data codes has been optimized and made more flexible. For example, the ECC200 data code reader is much faster and capable of reading codes with missing or damaged/disrupted "quiet zones”. In addition, codes against complex backgrounds can be found and read faster and more robustly.
The field bus connection is another useful feature for developers. The Hilscher CifX interface allows communication with almost all industrial field bus protocols including Profibus, ProfiNet, and Ethernet/IP. HALCON 18.11 also fully supports UTF-8 encoding, for use of the software in multiple languages simultaneously. Western alphabets and Asian characters are now displayed in the same encoding and no longer have to be converted from one to another, reducing error rates.
HALCON 18.11 is available in two editions. The ‘Progress’ edition is a subscription version on a six-month release cycle, while the ‘Steady’ edition can be purchased with a release cycle of two years.
München , Germany
MVTec is a leading international manufacturer of standard software products for machine vision. Their industrially proven software products HALCON and MERLIC are used in a large variety of application areas, such as semiconductor industry, inspection applications, medicine, and surveillance. Besides, MVTec provides customized solutions from feasibility studies to the complete software part of customer's application.
HALCON is a comprehensive standard software for machine vision with an integrated development environment (IDE) that serves all industries. It provides outstanding performance and a comprehensive support of multi-core platforms and special instructions sets like AVX2, as well as GPU acceleration.