Recall

The Recall is the percentage of labeled features or classes that the tool correctly identified.

Recall represents how well a model A specific spatial arrangement of a set of features (Blue Locate and Blue Read tools only.) During a post-processing step, the Blue Locate and Blue Read tools can fit all of the features detected in an image to the models defined for the tool. The overall pose and identity of the model is then returned. can identify actual positive cases. Recall is calculated as the number of true positive predictions divided by the number of actual positive instances (true positives + false negatives). It measures the ability of the tool to capture all positive instances.

• A tool with a low Recall score typically fails to identify all of the features that should have been detected from the test data, and so it returns many false negative results.
• A tool with a high Recall score typically succeeds to identify all of the features from the test data, but if combined with low Precision, there can be many false positive results.

The ideal statistical results for typical inspection cases (there could be exceptional cases) includes high Precision and high Recall.

Recall Calculation of Blue Read

For the Blue Read tool, Recall is the percentage of labeled features that are not in the training Training is the process that your tool, which is a neural network, is learning about the features (pixels) based on the labels you made. For example, a tool will learn the defect/normal pixels in each image based on the defect/normal labels you drew. The goal of the tool Training is learning enough to give the correct inspection results of whether an unseen image is defective or not. The key to training is to ensure that you include all possible variations within your training set, and that your images are accurately labeled. Training times vary by the application, tool setup and the GPU in the PC being used to train the network. set and that are correctly identified by the tool. For example, a Recall score of 90% for character “A” means that the neural network catches 90% of all appearances of " an “A" among the test data.

Labeled Image	Recall Results

Recall Calculation of Green Classify

For the Green Classify tool, the Recall is a percentage of the labeled classes that are correctly identified by the tool.

The tool calculates Recall by the fraction of classified views labeled as class i that are correctly classified as class i:

For example, a Recall of 90% for the class i means that the neural network will correctly classify an image of class i 9 out of 10 times.