MVTec and Datavision deepen partnership
Datavision expands MVTec's machine vision ecosystem: Halcon and the cloud-based data management platform Beeyard are linked
MVTec and Datavision will work more closely together in the future. The aim of the cooperation is to offer users of the MVTec Halcon image processing software additional options for collecting, managing, analyzing and processing their image data in line with Industry 4.0. For this purpose, an interface between MVTec Halcon and the data management platform BeeYard from Datavision was developed as part of the partnership.
Deep learning applications in particular benefit from data management systems: Powerful platforms for data management offer advantages for almost every method of industrial image processing. These are particularly large for deep learning applications. Beeyard supports users in two ways:
- On the one hand, the data management platform facilitates the handling of very large amounts of data, which arise from deep learning. This data is compiled from various sources, can be provided with user rights and managed with keywords and labels.
- On the other hand, improvements can be made both for the machine vision application and for the production process. By analyzing and labeling additional images, conclusions can be drawn as to whether and at what point the deep learning network needs to be retrained. Training or post-training can be done on the platform with Halcon. In addition, if the same error always occurs, deductions can be made for the production process.
As part of the partnership, the Halcon machine vision software library was expanded to include data management functions. With the Extension Package for Halcon, it is possible to set up an image database and enrich the images with additional information such as a time stamp, lot number, product number, temperature or vibration data. The image data is then evaluated and analyzed using the BeeYard data management platform from Datavision. The cloud-based or server-based platform allows customization to meet storage needs, location-independent accessibility, cost-efficiency - especially for large amounts of data - integration of a variety of other cloud-based tools and services, and high processing speed.
