This module serves to detect a specific surface and it can also classify the types of surface, which are to be detected, into different classes like the Classifier.
Surfaces are marked by brush painting in the image. Each surface type has one color assigned. For quick brush switching, you can press a numeric key indicating the number of the class that is given in square brackets. To change the brush size or switch between brush and eraser, you can either use the sliders at the top, or you can use shortcuts, which can be found in the Help section under the ‘?’ symbol.
If you paint in the searched-for areas by the brush, the image is automatically included in training. If none of the searched-for surfaces are present in the image, you can manually add it to the training by ticking the Include option. In that case, it is assumed that the searched-for surface is not in it, thereby improving the training.
Surfaces marked with ‘Ignore’ class are excluded from the training. Whereas, parts of the image which are left unannotated, are part of the training, but are considered an ‘OK’ class, which is not displayed when detected.
Types of surface detector
Two types of surface detector are available, each based on a different kind of neural network. We recommend to try Type 1 first and if you're not getting good results, then try using Type 2.
The training works slightly differently for each type. For Type 1 you just start the training and then stop it at the right time based on the graph, like you would do e.g. with the Detector module. You can also choose network sizes based on whether you aim for performance or accuracy. For Type 2 you choose the number of epochs beforehand.
Size of the viewfinder 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 than what would work with Type 2.
Further information about the training options can be found in the section training.
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.