...
Three types of surface detector are available, each based on a different kind of neural network.
Type 1 – Fast:
Detects a wide range of defects, however can suffer from a higher amount of false positives (good parts evaluated as bad by the software).
...
Training time is reduced, with bigger & less options of view-finder sizes.
This type does not require large datasets, however, performance on highly variable patterns may be suitable for the Precise option.
Type 2 – Experimental:
This type
...
may work well for
...
smaller defects, however, it usually requires
...
a lot more training data and it is our Experimental type, meaning that may not perform well in some applications.
Training time is usually longer.
Smaller & more precise view-finder sizes.
Type 3 – Precise: Very precise heatmaps, does not generate many false positives, it is ideal when searching for objects. (no view-finder
This type works well with smaller defects such as scratches and others, however, it usually requires more training data to perform well.
Training time is usually longer.
View-finder size not available & ignore function not included
...
.
View-finder
Size of the view-finder determines how much the inspection will be focused. The size is selected depending on how detailed inspection model is desired. If you choose a size which is too small, you lose the knowledge of the surroundings and therefore can miss some defects; on the other hand, if chosen size is too large, details can be overlooked.
Just as when a human eye focuses on detecting errors. Some errors are seen from a larger distance, and others can only be seen through a magnifying glass.
Along with the size, the recognition speed also varies. There is no general rule on how to set the right size, you need to try out a number of sizes and learn how to estimate the best size at the first try. The size of the defects you are searching for might be of help.
Surface detector of Type 1 usually works better using bigger size of viewfinder view-finder than what would work with Type 2. The Type 3 surface detector doesn't use this parameter.
...
The detection result is a set of heatmaps (one for each class). When validating, heatmaps are plotted in the image for better illustration. In the heatmaps, the searched-for areas surrounded by rectangles are added to the context to ‘detectedRectangles’. Each rectangle has a class assigned, depending on which heatmap it was found in.
Evaluation
We can set the rules for all classes or individually. There are three options for the evaluation rules:
Count - number of defects (rectangles)
Edge length - length of the edge of individual rectangle
Area - sum of pixels (of given class if it’s selected) in the whole heatmap