In our previous Support item we described the preliminary steps for training a deep learning (DL) classifier in HALCON. In…
A Closer Look at the HDevelop Example for the GigEVision2 interface
Setting up a GigE Vision image acquisition device with HALCON is easy. Just connect the camera and grab images… But…
Preparing To Train a Deep Learning Classifier in HALCON
The deep learning (DL) functionalities of HALCON 17.12 enable users to train a DL classifier for their specific application without…
Increasing Speed in Deflectometry Set-Ups
Deflectometry is useful for inspecting reflective (specular) surfaces. These surfaces are tricky to inspect with other methods, due to a…
Single Image Calibration for 2D Measurements with HALCON
Fig 1: Calibration and measurement planes with emphasised differences (misalignments and offsets). Many HALCON users are dealing with…
Speeding up Shape Based Matching with ‘Greediness’
The parameter “Greediness” defines a tradeoff between speed and completeness. On the one hand, the search speed can be increased…
Deep Learning with HALCON 17.12 – Training a CNN
Gain ‘Deep Learning’ out of the Box with HALCON 17.12. Users will be able to train their own classifier using…
How to Simplify your HDevelop Debugging Process
Let’s have a look at some helpful tools that are provided to simplify the debugging process in HDevelop. Beside some…
How to get the best from Classification and OCR tools in HALCON
A recommended practice for setting up classification tasks and OCR: Regularly review your growing set of training data with the HDevelop…
How To Use Rejection Classes in MVTec HALCON
In a previous support article we described the use of regularisation during the training of a multilayer perceptron (MLP) to…
Using regularisation in MLP classification with HALCON
When training any classifier, the goal is to train it so that it generalises well for unknown data. However, in…
HALCON Hand-Eye Calibration with a 3D Sensor
HALCON’s surface-based matching is a powerful, field-proven technique to locate individual objects within point-clouds. Translating the found poses into robot…