MVTec Software GmbH (www.mvtec.com), a leading international provider of machine vision software, will release the new version (22.05) of its HALCON machine vision software on May 25, 2022. The highlight is the new technology "Global Context Anomaly Detection", which is available in HALCON 22.05 in this form as a world`s first. As an expansion of the long-established anomaly detection technology, this new feature raises deep-learning-based fault detection to a whole new level. The new release also includes significant expansions such as new features as well as new improvements to HALCON’s core technologies. As a result, the software now enables the practical implementation of software solutions for even more demanding applications across a wide range of industries. Companies using this machine vision software benefit from more efficient production, especially in application areas like quality assurance.
“With Global Context Anomaly Detection, we’re providing an impressive demonstration of our technological market leadership in the field of machine vision software. The new technology provides our customers with brand-new possibilities, such as for inspection activities. We’ve also added a deep-learning-based training option to the Deep OCR feature. With HALCON 22.05, we’ve once again managed to implement new features as well as useful enhancements of existing technologies,” explains Mario Bohnacker, Technical Product Manager for HALCON at MVTec Software GmbH.
Understanding an image’s logical content
By detecting logical anomalies in images, HALCON 22.05 opens up completely new application areas and represents a further development of the deep learning technology of anomaly detection. Until now, it has only been possible to detect structural anomalies strictly on a local level. The new Global Context Anomaly Detection feature is currently the only technology that can “understand” the logical content of the entire image. Like the existing anomaly detection in HALCON, Global Context Anomaly Detection requires only “good images” for training. The training data does not need to be labeled. The technology can thus detect completely new anomaly variants, such as missing, deformed, or incorrectly arranged components of an assembly, for example. This opens up possibilities in brand-new areas, such as the inspection of printed circuit boards in semiconductor manufacturing or the verification of printing.
Individualized training for OCR applications
Using HALCON’s Deep OCR, users can efficiently address OCR applications for a variety of application areas. The release of version 22.05 now expands this technology to include a training function that allows users to perform individualized training based on their own application dataset. This makes it possible to handle even the most complex applications, such as reading text with poor contrast (on tires, for example). As a further benefit, it is possible to train special characters and print styles that are very rarely used. Ultimately, training for Deep OCR significantly improves performance and user-friendliness and makes applications even more robust.
Optimized print quality inspection of ECC200 codes
HALCON supports various standards for evaluating the print quality of 1D and 2D codes. This ensures that all readers will have no trouble reading the printed code in actual practice. Version 22.05 brings further improvements to the print quality inspection (PQI) of bar codes and data codes, making the determination of the module grid for the print quality inspection of the ECC200 code much more robust. Moreover, the PQI of 2D data codes is now up to 150 percent faster. And finally, the user-friendliness of the PQI of 2D data codes has been improved through the addition of a new method for calculating the evaluations.
Additional improvements, thanks to new operators
HALCON 22.05 offers still more improvements – for example, a new operator that helps to optimize image contrast locally. Another new operator permits image smoothing with randomly shaped regions.
Automate exhibition
MVTec Software is further expanding its involvement in the US. The company is underscoring its intentions with a larger presence at this year’s Automate show in Detroit. From June 6 to 9, 2022, MVTec will present its comprehensive machine vision software product portfolio at booth #4715. Dr. Olaf Munkelt, MVTec Managing Director, and Heiko Eisele, President of MVTec USA, will personally welcome visitors at the booth. “We’re excited to once again take part in Automate, the largest solution-based trade show for automation in North America. We’ve been at Automate since the very beginning. This year, a larger booth will enable us to present our comprehensive product portfolio to customers and partners with an even greater visual impact,” says Eisele, commenting on the company’s trade show exhibit.
MVTec presents state-of-the-art deep learning technologies at Automate
At the booth, MVTec will demonstrate how machine vision, acting as the “eye of production,” optimizes and automates processes in Industry 4.0. With deep learning technology, for example, MVTec offers a wide range of capabilities with the flexibility and optimization features needed to help customers confidently and efficiently integrate deep learning into their own applications. In addition, MVTec’s software can run on almost any embedded platform. Users of MVTec’s machine vision software not only benefit from a rich feature set but also MVTec’s services such as application evaluations, training documentation, and technical support. Last but not least, two new software versions, HALCON 22.05 and MERLIC 5.1, will also be presented at Automate.
Exciting live demos deliver transparent practical insights
MVTec experts will use live demos to deliver practical insights into efficiently solving many common types of machine vision applications. A showcase, for example, will vividly demonstrate how all common bar and data codes can be read using MVTec’s software, regardless of orientation – even when the element width is less than one pixel or when the code is partially obscured. Another demo using the MERLIC software will show how easily and effectively deep-learning-based anomaly detection facilitates automated surface inspection. Only a small number of high-quality images are required for training because a wide variety of defects can be identified without prior knowledge or labeling effort.
MVTec represented in the US for 15 years
MVTec established its first global subsidiary in the US back in 2007. Since then, MVTec USA (Boston, Massachusetts), has grown steadily and positioned itself as a trusted leader in the North American machine vision industry. “Our goal is to provide customers with the best possible machine vision software experience at all times,” says Martin Krumey, Vice President of Sales at MVTec Software GmbH. “For us, this means we offer outstanding products like HALCON, MERLIC, and the Deep Learning Tool, while establishing very close relationships with our customers through our local services and support. Besides boosting our presence at the Automate we are also actively increasing our footprint in the North American Market by hiring additional personnel for our Boston office.”
