The new version enables customers to conduct training of convolutional neural networks (CNNs) based on deep learning algorithms themselves for the first time. The trained networks can then be used to automatically classify the image data corresponding to the pre-defined classes. The best part: The future-proof deep learning features are seamlessly integrated into a professional and established standard machine vision library. As a result, users benefit from all advantages offered by a standard software package, such as high quality, continuous updates, and expert support.
Users have been able to use deep-learning-based OCR classifiers since version 13 of MVTec HALCON, which has been released in November 2016. This technology alone already leads to impressive recognition rates in numerous applications.
Less effort through self-trained networks
Johannes Hiltner, product manager HALCON at MVTec, states: "With the new HALCON version, we are specifically addressing a current trend and strong market need for machine vision. By using their self-trained networks, customers save a great deal of effort, time, and money. For example, defect classes can be identified solely through reference images. Tedious programming for identifying different defect classes is therefore no longer necessary. In the industrial machine vision environment, deep learning is mainly used for classification tasks which appear in many applications areas, e.g., in the inspection of industrial goods or the recognition of components."