Setting Up the Surface Flaw Defect Detection Tool

Setting up this tool involves establishing the thresholds that will be used to determine whether or not flaws are present. Before beginning, a database of images of the part to be inspected (in both its passing and failing states) should be loaded, by loading images from a PC.

To begin, load an image of the part in its error-free state. Next, add the Surface Flaw tool.
Configure the region in the image. From the Region Type drop-down menu, select the type of region: Rectangle (default), Circle, Annulus or Polygon. Position and configure the region within the image where you expect the flaw(s) to appear; make sure that the boundaries of the region cover the flaw(s) and their possible locations.
Note:
- To help the performance of the tool, try to create smaller regions; larger regions require longer to inspect. If you’re not using a fixture, ensure that the flaw(s) are present in roughly the same location in every image, or the region is large enough to account for the expected movement of the features.
- After adding the tool, you can change the type of region by right-clicking the region in the image and selecting the desired shape from the Change Region to option.

Press the OK button to confirm the region (press the Cancel button to not add the tool to the job).
With the part in its error-free state, adjust the tool's parameters to ensure that the tool does not identify any flaws. Use the Display Image parameter in the Flaw Candidates tab to display visual feedback on how parameter adjustments affect the tool's results. Set the Display Image parameter to Flaw Candidates to begin, so that any detected flaws are enclosed within a red bounding box.

Note: Optionally, a mask may be created to highlight areas of the image for inspection, while excluding other areas. Masks are very helpful when configuring an inspection that involves text, labels or other features that should be ignored.
When adjusting the parameters, start with the tool's region to ensure that the ROI is properly enclosing the area to be inspected: it does not contain extraneous features, such as labels, the edges of characters or logos, for example. If the inspection will include an edge of a part, the region must be positioned parallel to the edge (the same applies to circular-shaped Regions, with the circular region arc being parallel to the edge of the part).
Next, try adjusting the Sampling Factor and Smoothing Factor parameters. Increase the Sampling parameter when trying to detect low gradient flaws, or large flaws with low contrast. Increase the Smoothing Factor parameter to help get rid of small, false defects.
After adjusting those parameters, use the different options of the Detection Type, Detection Size and Detection Axis parameters. For most applications, the Detection Type parameter may be set to Fast, with a Detection Size of 1. For applications that require Light Flaws, Dark Flaws or Light and Dark Flaws, the Detection Size parameter must be set to a size that is greater than the radius of the flaw to be detected. If the Region was configured to be parallel to an edge, the Detection Axis must be set to run parallel to the Region.
Then adjust the Minimum Flaw Area, Maximum Flaw Area and Minimum Contrast parameters.
Once the tool is correctly inspecting the part in its error-free state, load an image of the part containing a flaw. Again, go through the process of adjusting the parameters until the tool correctly identifies the desired flaws. Load more images of the part with flaws, and adjust parameters as necessary to identify the additional flaws.
After the flaws have been identified, re-load the images of the part in its error-free state and ensure it is still being correctly inspected as not containing flaws. The tool will be ready for run-time inspections once it is properly configured.
Finally, if desired, use the tool's Input/Output properties to share tool data between other tools and/or other external devices.