Calibrate Functions

Calibration is the process of converting pixel measurements into meaningful, real-world values. In this process, a two-dimensional (2D) transformation mathematically maps points from an image's pixel coordinates to real-world coordinates. Once an image has been calibrated, other vision tools can then reference the calibration as an input, and report the results in the calibrated (real-world) units.

In-Sight Explorer provides four separate calibration methods; a means to associate a calibration to an image; and eight transform functions to convert between image and world coordinates:

• Calibrate: Utilizing four, user-specified points, creates a 2D transformation to convert between pixel and real-world coordinate systems. Accounts for linear and non-linear distortion.

• CalibrateAdvanced: Utilizing one to thirty-two user-specified points, creates a 2D transformation to convert between pixel and real-world coordinate systems. Accounts for linear and non-linear distortion; higher degree of accuracy than Calibrate (for 5 or more points).

• CalibrateGrid: Utilizing a user-configurable calibration grid pattern, creates a 2D transformation to convert between pixel and real-world coordinate systems. Accounts for linear, non-linear and lens distortion; highest degree of accuracy.

  Note:

  • When using a Calibrate, CalibrateAdvanced or CalibrateGrid function, the physical and optical set-up (the lens, sensor and the physical relationship between the sensor and the scene being acquired) must be the same for both the calibration and run-time operation. If any of these items is altered, the system must be re-calibrated. Therefore, it is recommended that the same sensor and lens be used to both calibrate and process the run-time images. The sensor and lens must also retain their original set-up and calibration settings. For example, changing the acquisition format (by altering the resolution) or moving the sensor will invalidate the computed 2D transformation that maps pixel to real-world coordinates.
  • The In-Sight 5604 line scan vision system only operates in pixel coordinates. While the Calibrate Functions may be added to a job running on an In-Sight 5604, they will produce inaccurate results.
• CalibrateImage: Associates a Calib structure with an Image structure, which can then be referenced by other vision tools.
• ExtractCalibration: Creates a 2D transformation, in real-world coordinates, based on the Image structure returned by TransformImage.
• TransBlobsToWorld: Converts a Blobs structure's pixel coordinates to real-world coordinates.
• TransEdgesToWorld: Converts an Edges structure's pixel coordinates to real-world coordinates.
• TransFixtureToWorld: Converts a fixture from pixel coordinates to real-world coordinates.
• TransformImage: Generates an Image structure that accounts for the distortion present in a CalibrateGrid function.
• TransInspEdgeDefectToWorld: Converts an InspectEdgeForDefect Inspect data structure's pixel coordinates to real-world coordinates.
• TransInspEdgeWidthToWorld: Converts an InspectEdgeWidth Inspect data structure's pixel coordinates to real-world coordinates.
• TransOCRMaxToWorld: Converts an OCRMax data structure's pixel coordinates to real-world coordinates.
• TransPatternsToWorld: Converts a Patterns structure's pixel coordinates to real-world coordinates.
• TransPixelToWorld: Converts a point from pixel coordinates to real-world coordinates.
• TransSurfaceFlawToWorld: Converts a   SurfaceFlaw structure's pixel coordinates to real-world coordinates.

• TransWorldToPixel: Converts real-world coordinates to pixel coordinates.

  Note: The output of any vision tool that reports in real-world coordinates cannot be used as a fixture or region input to another vision tool.