Deep Learning Extends the Power of Machine Vision
Artificial intelligence and specifically deep learning is getting more and more powerful. Deep learning solutions can serve very specific requirements.
In machine vision, deep learning enables an increasing number of applications that weren’t possible before. Moreover, the performance of existing applications can be significantly improved. Especially in the field of data classification, deep learning is a very efficient technology. Many industries and sectors are already benefiting from the new opportunities, such as agriculture, mechanical engineering, pharmaceuticals, logistics, etc.
MVTec software products offer a large selection of operators, functions and methods that either are based on deep learning technologies or allow customers to use deep learning technologies in their own applications.
Learn more about deep learning methods, the differences to classic machine vision and how to start with deep learning.
Deep Learning Takes Data Classification to the Next Level
The machine vision software products from MVTec come with pre-trained CNNs (Convolutional Neural Networks), that allow applications to be developed with a relatively small number of training images. By using these networks, users can train their own classifier to classify new data. Provided with a sufficient amount of images, the training process automatically extracts each class’ distinct features. HALCON and MERLIC then analyze these images and automatically learn which features can be used to identify the given classes.
Deep Learning Methods in MVTec Products
Deep learning is a powerful technology that complements MVTec’s comprehensive machine vision toolkit. Customers can develop holistic applications using deep learning in combination with conventional machine vision.
The training for these deep learning methods can be performed on GPUs, as well as on CPUs. This greatly increases your flexibility in implementing deep learning, because training can also be performed directly on the production line. This makes it possible to adjust the application to changing conditions of the environment. The inference can be performed on GPUs, on x86 CPUs and on Arm® processors.
Based on our AI² interface, we also support a growing number of AI inference accelerators to increase the speed using dedicated hardware.
Advantages of Deep Learning
- Automatic feature extraction
- Reduced effort of programming
- Big amounts of data can be used
- Reduced development time
More to know about Deep Learning
Application Examples
Logistics
Whether you need to classify packages or control an unmanned pallet truck, deep learning solutions enable you to solve machine vision tasks faster and more cost-effectively.
Example: Identification of empty rack spaces
The implemented deep-learning-based solution works with 2D image data, replacing a complex hardware setup with 3D sensors. This accelerated the classification process and reduced costs.
Agriculture & Food
From classifying fruits, feeding animals, picking ripe vegetables, packing fruits in bags, or producing frozen goods – deep learning technologies will enhance your automation, whether in the greenhouse, in the field, in the barn, or in the production plant.
Example: Identification of plants
With deep learning, new plant types could be programmed twice as fast as before. Moreover, the error rate was significantly reduced.
Electronics & Semiconductors
Machine vision plays a big role for, e.g., the identification and inspection of electronic components. With deep learning, complex inspection tasks that were previously performed manually can be automated.
Example: Quality check of circuit board printing
The classification of good and bad images of different circuit board parts could be significantly accelerated with deep learning.
Medical & Pharma
If you are looking for a tool that takes your quality control to the next level, deep learning technologies are the right choice. Whether you need to detect defects on pills, sort tablets correctly, fill, inspect or package bottles or labels – machine vision with deep learning improves your processes.
Example: Detection of defects on pills
New types of defects could be trained automatically, which means enormous time and costs savings.
