NeuroCheck Deep-Learning

NeuroCheck as a Platform

The Basis for your Deep Learning Application

Deep learning is becoming an increasingly important technology in the manufacturing industry. That‘s why NeuroCheck has been providing in-house developed backpropagation networks for image content and object feature classification for over 25 years. The necessary neural network structures have been an integral part of the NeuroCheck image processing software since 1994. With increasing computing power, cloud computing and fast Internet connections, new possibilities for the use of Deep Learning in industrial vision open up. Hard-to-solve inspection tasks become feasible.

Technology Partner for Deep-Learning with NeuroCheck (Image © NeuroCheck)
NeuroCheck AI-Xtension gives the user the opportunity to use his own deep learning know-how productively. Self-developed and trained models can be quickly and easily integrated into production processes.

Neural networks can be integrated directly into NeuroCheck in the TensorFlow and ONNX format. Other model formats such as CNTK, Pytorch, Keras, Watson, and others are also possible. As a basis for your deep learning application, process integration (Profibus, Profinet, EthernetIP etc.), hardware support (2D, 3D cameras), and data acquisition (image data, XML, data base) have already been part of the standard functionality of NeuroCheck for a long time.

Main areas of application » Successful use when it really makes sense

Sample application » Inspect a rubber sleeve » Pseudo error rate reduced many times over

As part of an automated production step, a rubber sleeve is affixed to a carrier. This can cause pinches and back folding, which in turn may compromise leak tightness and thus the proper working of the assembly group. The challenging part of this inspection task is the high variety of fault appearances that can occur and that it is impossible to establish a quantitative classification of the faults. In addition, the component images differ in size, position, contrast, and brightness due to the production process. Traditional image procession produces a high rate of false alarms with an additional high risk for errors going undetected.

Inspection Rubber Sleeve » Correct » OK

Rubber Sleeve - NeuroCheck Inspection OK (Image © NeuroCheck)

Inspection Rubber Sleeve » Incorrect » NOK

Rubber Sleeve - NeuroCheck Inspection NOK (Image © NeuroCheck)

Further examples of error patterns

Rubber Sleeve - Examples of error pattern (01) - (Image © NeuroCheck)
Rubber Sleeve - Examples of error pattern (02) - (Image © NeuroCheck)
Rubber Sleeve - Examples of error pattern (03) - (Image © NeuroCheck)
Rubber Sleeve - Examples of error pattern (04) - (Image © NeuroCheck)
Rubber Sleeve - Examples of error pattern (05) - (Image © NeuroCheck)
Rubber Sleeve - Examples of error pattern (06) - (Image © NeuroCheck)
Rubber Sleeve - Examples of error pattern (07) - (Image © NeuroCheck)
Rubber Sleeve - Examples of error pattern (08) - (Image © NeuroCheck)

Example Application » Identification and Localization of Screws

Neural Network solves Inspection Task

To control an automated screwing process, precise identification and localization of the screws is necessary. The station processes a high number of various assembly groups with varying numbers of screws, surfaces and geometries. In addition, the screws may be slightly covered or absent, which must lead to a termination of the screwing process. With this application as well, a number of complex environmental conditions need to be dealt with. The example images show various levels of brightness, various sizes of assembly parts, positions and levels of focus.

NeuroCheck Deep-Learning - Fittings Overexposure (Image © NeuroCheck)
Variations in brightness because of overexposure
NeuroCheck Deep-Learning - Example of another type (Image © NeuroCheck)
Example of another type
NeuroCheck Deep-Learning - Fittings Pollution (Image © NeuroCheck)
Recognition of screw despite soiling
NeuroCheck Deep-Learning - Fittings Visibility (Image © NeuroCheck)
Screw not completely visible
NeuroCheck Deep-Learning - Fittings Variance (Image © NeuroCheck)
Screws of varying number and size
Traditional industrial vision processes require the creation and adjustment of special inspection programs for each assembly type. The high number of variants made this approach very time-consuming and entailed maintenance difficulties.

By using a neural network, the entire task was solved with a single program. In addition, robustness of recognition under changing environmental conditions was greatly improved compared with the traditional process.

A NeuroCheck 6.2 KI-Xtension sample project (CPU, GPU) can be found in our download area.

Note: To use the full functionality, you need an additional license.

Contact NeuroCheck (Image © designed by Pressfoto -

As your competent partner, we look forward to be of assistance

Our work in this area is based on deep learning and machine learning algorithms and ranges from basic research to industrial knowledge transfer to the implementation of deep-learning systems.

If you have any questions or require further information on the subject of “Deep Learning in industrial image processing”, please contact us using our contact form or by e-mail. Our experienced experts will advise you competently and comprehensively.

Copyright notice for the photos used on this page:

Images Header, Deep Learning © NeuroCheck
Image Contact © designed by Pressfoto –