Generating a Pose

When used to generate a pose, you create a Model, which is used to output a transform that can be applied to any Views that are referencing that Model. A Model can be created of a single feature or a combination of multiple features.

If necessary, adjust the ROI of the tool.
Within the ROI, while hovering over the image, the mouse-cursor will have a cross-hairs icon which is used to place the feature label of the Blue tool. Click on a feature to label it.
The feature label will have a default character of 0. Enter in a meaningful character (A-Z, 0-9) to identify the feature. For identical features, you can use the same identifier.
In the bottom-left corner of the display, there is a circle graphic that graphically illustrates the size of the Feature Size parameter setting.
1. This circle graphic can be moved into the ROI and placed over the largest feature. Then, using the drag handle, you can adjust the Feature Size so that it approximately covers the feature.
If there is more than one feature that you want to find in the image, identify and label each feature.
Create a Model out of the labeled features:
1. Select the features that will comprise the Nodes of the Model. Hold down the Shift key to select multiple features.
2. Right-click and select Create Model.
3. This will launch the Model Editor dialog.
  1. The Model has its own properties relating to the number of Nodes that can be found, as well as the minimum distances and angle range that the model can exist in.
    Note: Models can also be created and detected post training.
  2. Each node also has some of its own information, such as angle, position in the model, and what the valid features are for that slot.
Go through several of the images in your training database and add the feature marker(s) to each image.
1. If you have created a Model, after you have labeled the first feature, the tool will automatically start applying the model to the features.
2. You will need to enter the correct identifier for each Node of the Model.
Once you have applied the Model to several of the images, press the Brain icon to train the tool.
After training, review the results:

Go through all of the images and determine whether or not the tool correctly marked the features in the image.
1. If the tool has correctly marked the features, right-click the image and select Accept View.
2. If the tool has incorrectly marked the features, or failed to identify a present feature:
  1. Right-click the image and select Accept View.
  2. Right-click the image again and select Clear Markings and Labels.
  3. Manually label the features in the image.
If you encountered the scenario in (a.), you are ready to use the tool. If you encountered the scenario in (b.), you will need to retrain the tool and repeat steps 7 and 8.