Page Comparison

...

Surfaces can be marked in two ways - by brush painting in the image or by making polygons, those ways can also be combined. Each surface class has one color assigned. For quick color switching, you can press a numeric key indicating the number of the class that is given in square brackets.

...

Brush painting

Basic painting into the image by a brush of selected size. To change the brush size or switch between paint- and erase mode, 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. Currently, you can press or hold the 'kK' and 'lL' keys to decrease resp. increase the brush size, and holding 'eE' temporarily switches the paintbrush to the eraser.

...

It can be used when a defect-free/OK

Status
colour Green title ok

image has some noise or it’s slightly scratched for instance, or it has some very variable background and we get false defects detected on it. It can help achieve higher accuracy.

Ignore

Info
Available only in Lightweight training

Surfaces marked with ‘Ignore’ Ignore class are excluded from the training. Whereas, parts Parts of the image which are left unannotated , are part of the training, but are considered an ‘OK’ as an

Status
colour Green title ok

class, which is not displayed when detected.

Can be used e.g. in case in cases when we are unsure whether a specific part of an image is OK or NG

Status
colour Green title ok

or

Status
colour Red title ng

or if there’s some distortion and we don’t want to put that part into training. The standardtype of surface detector doesn't use Ignore class.

Settings

Types of Surface Detection

...

• Detects a wide range of defects, however, can suffer from a higher amount of false positives (good parts evaluated as bad by the software), adjusting the Confidence threshold after training can help reduce this.

• Faster inference and training.

• Multiple options for view-finder size.

• The model can optionally be optimized using Tensor RT for the specific GPU used when you check the TRT switch in the model list. The optimization improves inference times when processing images using this model.

Info
The model is optimized for specific GPU, so if you transfer the project to a PC with a different type of GPU, the optimization needs to be done again for the new graphics card.

Note
The TRT optimization is available only for models with one class at the moment.

• This type does not require large datasets, however, performance on highly variable patterns may be more suitable for the Standard option.

...

• This type produces very precise heatmaps and usually doesn’t have too many false positives. It's ideal for searching for objects/defects with closed shapes. It also takes into account the surroundings, not just the surface itself.

• Training time is usually longer.

• View-finder size is not used in this type & ignore Ignore function is not included.

View-finder

...

Feature size

Read more about Feature Size (TODO)

Feature size determines the size of the surface defects the model is able to reliably find. Tweak the feature size by using the grid that appears and fit it according to the size of the image defects.

Info
With small sizes the model loses the knowledge of the surroundings and

...

can miss some defects

...

. With bigger sizes the model has the “bigger picture” and some 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 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 on the first try. The size of the defects you are searching for might be of help.

Note
When using smaller or narrow images, be careful that the viewfinder size must be smaller than the smallest image dimension. When rotation is on, there is also additional padding, so even if the viewfinder is slightly smaller than the image, it may not fit - in that case, use smaller viewfinder, upscale image in Preprocess, or turn off the rotation.

The Standardtype of Surface Detection doesn't use this parameter.

Detection

The detection result is a set of heatmaps (one for each class). When validating, heatmaps are plotted in the image for better illustration. Heatmaps for the whole image are added to 'heatmaps' in Context, and all the rectangles surrounding the searched-for areas are added to ‘detectedRectangles’ detectedRectangles. Each rectangle has a class assigned, depending on which heatmap it was found in.

Notice the grid specifying the feature size and the resulting heatmap. The detection sizes correspond to the feature size grid - the holes are filled using a higher feature size than optimal resulting in a worse heatmap accuracy.

...