Red Analyze Tool – High Detail

Red Analyze High Detail completes the same task as Red Analyze Supervised but there are some differences in how it delivers the results. This means that Red Analyze High Detail also concentrates on teaching the network what defects look like as in Red Analyze Supervised.

High Detail mode uses an architecture which is different from that of Focused mode. Due to its architectural difference, it doesn't have Sampling Parameters in Tool Parameters pane as it samples from the entire view. Because of this, High Detail mode takes more time for Training/Processing than the Focused mode, but you can get more accurate or detailed results in pixel levels. The way you label images and create a model in High Detail mode is basically the same as Focused mode but there are some differences in tool parameters.

As well as Red Analyze Supervised, only the binary classes (Good/Bad) are supported in Red Analyze High Detail. It means that multiple classes are not supported.

When you label an image as Good in Red Analyze High Detail (for example an image that does not contain any defect regions), the tool will also use that image for training once it is added to the training set. In particular, the tool will attempt to train the network so that images labeled Good do not generate any defect responses. Adding labeled, defect-free Good images to your Training Image Set can help you validate the performance of the tool in classifying good and bad images.

 

The process for training High Detail mode is:

  1. Collect images that represent the full range of defects that you expect to encounter.

  2. Go through each image in your training image set and carefully label the defects. Drawing the region is important to make a better model.

    Defect Label

  3. Add a few good images and label them as Good.

  4. Edit tool parameters.

  5. Train the tool and check the result.

  6. Validate the tool by presenting images that were not used during training, which contain defects as well as good images that do not contain defects.

    Defect Marking