Processing Tool Parameters

The Processing parameters control the way that images are processed by the tool. Changing these parameters does not require the tool to be retrained; the effect can be seen right away by reprocessing the database.

Note:

The Iterations, Simple Regions, Region Filter and Use Baseline parameters (used only with the Red Analyze Tool) are only available when Expert Mode is enabled. This is enabled via the Help menu.
The Feature Filter parameter is only available for the Blue Locate Tool and Blue Read Tool, when Expert Mode is enabled.

Parameter

Description

Sampling Density

Specifies the density of sampling points with respect to the tool's Feature Size (F_s) setting. The tool's processing time depends approximately quadratically to the Sampling Density (S_d) value. For example, a Sampling Density setting of 0.5 is four times faster than a setting of 1 [0(n²)].

Threshold

This parameter is used by all three tools.

For the Blue Locate Tool, the Threshold determines how closely the found feature must be to the desired feature in order for it to be considered detected. The found feature must exceed the setting.
For the Red Analyze Tool, there are two settings, T1 and T2 (expressed as [T1,T2]. They determine the threshold which determines whether or not regions are detected and marked as good or bad. Values below T1 will be classified as good, and values above T2 will be classified as bad. The T1 and T2 values can also be set interactively using the Scores graphic in the Database Overview.
For the Green Classify Tool, the Threshold parameter determines the minimum score of a view to be classified.

Precision*

The Blue Locate tool includes a unique parameter, Precision, which refines the position of a feature iteratively. With each iteration, a new feature position is computed. The Precision parameter controls when this refinement is terminated.

Feature position refinement is repeated until the difference between the current position and the new, refined position is less than the specified precision, multiplied by the Feature Size. For example, if you have a Feature Size of 40, and a Precision setting of 5%, the tool will stop searching for the position of the feature when the next jump would be less than 2 pixels (0.05 * 40 = 2 pixels).

If Precision is equal to 400%, the Blue Locate tool will stop at D₀.

200% = D₁

100% = Matches with precision

Stop criteria:

Feature Filter*

Specifies a filter for the Blue Locate and Blue Read tools, based on feature id, x, y, size and orientation, which is used as criteria for found features. By specifying a filter for features, features that do not match the filter will be removed from the results. If the parameter is left blank, all features will be returned. Since this filtering is done after the tool has processed the images, the features are not removed, simply hidden from the results. Features that are not present due to the filter will reappear, without reprocessing the image, by removing the filter criteria.

Note: The syntax for filters is the same as that used for Display Filters. For more information about constructing the syntax for a filter, see the Custom Display Filters.

For example, if the Feature Filter parameter was set to the following:

Feature Filter	Description
x in [0,width] and y in [0,height]	With this filter, only features whose center is within the ROI will be returned.
(id = '0' and x < 200) or (x='1' and x > 200)	With this filter, assuming a View that has a width of 400, features that have an ID of 0 and are on the left, and features that have an ID of 1 and are on the right, will be returned.

Iterations*

Specifies the number of times the Red Analyze tool will search locally to find stronger anomalies. In contrast to the Sampling Density parameter, processing time only depends linearly on the number of iterations.

Simple Regions*

Specifies that the Red Analyze tool should only extract only "simple regions", i.e. polygons without holes.

Region Filter*

Specifies a filter for the Red Analyze tool to be used as criteria for found regions. By specifying a filter, regions that do not match the filter will be removed from the results. If the parameter is left blank, all regions will be returned.

Note: The syntax for filters is the same as that used for Display Filters. For more information about constructing the syntax for a filter, see the Custom Display Filters.

The available region properties are:

score
area
perimeter
compactness
x
y

Use Baseline*

Specifies whether or not the Red Analyze tool should use a weight on the scoring on the different regions of the image, depending on the variation over this region, measured in all images. This parameter will lower the response with the average noise level. This is useful when the view contains multiple distinctive structured areas.

	High Noise Areas
	Low Noise Areas

This allows us to use a single Threshold for both areas.