Your browser is out of date. It may not display all features of this websites. Learn how to update your browser.

OK
Start configuring your vision system now Webshop

Vision Systems for Deep Learning

Deep learning is rapidly spreading across computer vision applications. The benefits of artificial neural networks (ANNs) are twofold. ANNs have the potential to improve the accuracy and robustness for applications in factory automation, robotics or retail. At the same time, ANNs have the capability to solve image-based application problems that could not be solved in the past, such as pathology detection in microscopy or complex pattern classification in surface detection.

Comparison of classical image processing with deep learning

Deep learning-based image processing

First image
Second image

Classical image processing

Classical image processing

Possible applications:

  • Recognition of simple shapes and structures
  • Rectification and coordinate conversions
  • Measurements of positions, distances, sizes
  • Preprocessing of images
  • Code reading

Advantages:

  • Fast and easy setup
  • Sophisticated, traceable algorithms

Deep learning-based image processing

Possible applications:

  • Recognition of elements with varying shapes and sizes
  • Classification of complex elements and structures
  • Recognition with varying backgrounds
  • Recognition under varying light conditions
  • Text recognition

Advantages:

  • Robust setup
  • High performance for recognition of complex elements
Frame Grabber-based Systems for Deep Learning: Fastest Inference

FPGA frame grabber-based systems for deep learning: fastest inference and highest reliability

Best performance, fastest inference per second, highest reliability – if your application demands high throughput, the FPGA frame grabber-based vision system for deep learning is the right fit for you. The microEnable 5 marathon deepVCL from Silicon Software, together with the FPGA configuration software VisualApplets, let you deploy your ANN on FPGAs with just a few clicks!

More about FPGA frame grabber-based systems for deep learning

PC-based systems for deep learning: fast time-to-market with lowest integration costs

Lowest integration costs and fastest time-to-market: PC-based systems score with an easy design-in. Use our plug-and-play hardware and software components to build your PC-based deep learning vision system. Our broad ace camera portfolio and the pylon Camera Software Suite make it easy to deploy your ANN without spending too much integration effort.

More about PC-based systems for deep learning

Embedded Vision for Deep Learning

Embedded vision for the most compact and cost-effective deep learning solutions

The most compact and cost-effective vision systems can be designed using embedded technology. The combination of board level cameras and embedded processing units ensures the lowest cost per unit. Intelligent edge devices deliver fast runtimes, low latency and advanced privacy and security. From camera modules to concept studies and ready-to-use solutions – let us take care of your embedded vision system for deep learning.

More about embedded vision systems for deep learning

Would you like more information about deep learning?

Then browse through our knowledge base. In our White Papers you will get expert knowledge, in the Product Insights we present selected products suitable for deep learning applications, in our Use Cases and Customer Stories you will get to know fictional as well as real application examples and the Vision Campus area offers you basic knowledge for the perfect introduction to the topic of deep learning.

Neural networks conquer image processing

Neural networks conquer image processing

Deep learning increasingly takes over tasks handled by conventional algorithm-based image processing, as this approach yields better image processing results in many applications. For some applications, deep neural networks such as convolutional neural networks (CNN) are particularly well suited.

Read Product Insight
Neural networks on FPGAs in the industrial sector

Neural networks on FPGAs in the industrial sector

Neural networks such as convolutional neural networks (CNN) on FPGAs take over classical image processing tasks in industry. If these are exclusively, more easily or better solvable with deep learning, it displaces classical image processing – especially in the case of disturbances such as reflective surfaces.

Read Product Insight
Deep vision becomes reality with CNN

Deep vision becomes reality with CNN

Small neural networks are sufficient for many vision applications. Processors such as FPGAs can therefore be used for convolutional neural networks (CNN). This opens up a wide range of applications far beyond classification tasks and also enables use in embedded vision systems.

Read Product Insight
Automating Thought – Opportunities & Risks

Automating thought – opportunities & risks

Billions are being invested worldwide in the use of artificial intelligence (AI) in a wide range of social areas. At the same time, laws, standards and ethical guidelines are being enacted to ensure sensible use of this technology – and also to emphasize its benefits to society.

Read Product Insight
Smart payment terminal with AI software and Basler cameras for retail

Smart payment terminal with AI software and Basler cameras for retail

Basler has developed an automated retail payment terminal made of embedded technology and artificial intelligence (AI) software. It identifies and classifies products in a shopping cart and displays the prices.

Read Use Case

AI-based bacteria classification with an embedded vision system

Embedded technologies are finding their way into diagnostics and analytics. They are powerful, space-saving and inexpensive. Add an artificial neural network (ANN) and bacteria can be classified in a split second.
Watch Use Case video

3D vision combined with deep learning software for automated fruit recognition

3D vision combined with deep learning software for automated fruit recognition

Basler and Data Spree have developed an accurate and robust real-time solution for sorting fruit. The vision system is based on a Basler blaze time-of-flight camera and a deep learning platform from Data Spree.

Read Use Case
Deep learning in action: vision sensor “at the edge” with Amazon Web Services

Deep learning in action: vision sensor “at the edge” with Amazon Web Services

Do you want to develop an embedded vision sensor to detect and classify objects? Basler has set up a convolutional neural network (CNN) with a deep learning framework and is using this in an embedded device.

Read Use Case
What is deep learning?

What is deep learning?

Terms such as machine learning, deep learning or artificial intelligence (AI) are being used in more and more areas of everyday life. What exactly does this mean, how does it all work and what are its application areas?

Read Vision Campus article

How do machines learn?

How do you teach a machine to learn autonomously? How does a machine become an “intelligent” machine with the help of neural networks and what can we use this called artificial intelligence (AI) for?
Watch Vision Campus Video

Do you need help?

Do you need help with choosing the right hardware system for your deep learning application?

Contact us!

Back to Webshop