Developers' Corner

MVTec experts regularly contribute tips and tricks for solving different vision tasks with MVTec HALCON and MERLIC. Feel free to ask questions or suggest an interesting topic yourself.

| Developers' Corner

Speed up your Image Classification

Classification is a very important method, often used in image processing. It can be utilized for directly segmenting an image into known classes, i.e., pixels are classified and grouped into regions, which can then be processed further. Important…

| Developers' Corner

Inspection of variables

Everyone knows the issue, when you have numeric tuples with many elements, and you are interested in a quick overview of their content. Since HALCON 12, a new feature has been available to visualize numeric tuples graphically. In the Variable View,

| Developers' Corner

How to use the Feature Histogram

One of the most powerful tools in HDevelop is the Feature Histogram. The Feature Histogram is a very useful tool to get a feeling for the features of regions or contours. In many applications, it is necessary to select regions or contours depending…

| Developers' Corner

Best Practice for Classification and OCR

A recommended practice for setting up classification tasks and OCR: Regularly review your growing set of training data with the HDevelop OCR Training File Browser – while developing the segmentation part, but also at further development steps. It is…

| Developers' Corner

How To Use Rejection Classes in MVTec HALCON

In the Developers' Corner article "Using regularization in MLP classification", we already described the use of regularization during the training of a multilayer perceptron (MLP) to enhance its capabilities of generalization to unknown data. In some…

| Developers' Corner

Using Regularization in MLP classification

When training any classifier, the goal is to train it so that it generalizes well for unknown data. However, in a real application, overfitting is often a problem, i.e., the classifier adapts too well to the training data and is not able to classify…