Deflectometric techniques provide abundant information useful for aesthetic defect inspection in specular and glossy/shinny surfaces. A series of light patterns is observed indirectly through their reflection on the surface under inspection, and different geometrical or texture information about the surface can be extracted.

A typical deflectometric system consists of a camera, or sever al cameras, focused on the surface under inspection and an LCD screen displaying a series of spatially coded patterns placed nearby, such that the camera observes such reference structure from its reflection on the surface.

This technique has been applied in different industrial scenarios, obtaining qualitative results for different type defect detection, or quantitative results with absolute measurements.

This technology can also serve to perform a surface inspection in big size parts, within a robotic cell.

Defect/Anomaly detection based on deep learning can also be included in order to accelerate the inspection time and robustness.

 

 

 

This technology will be available in the project, taking into account that it will have to be adapted to address correctly the particular needs of each use-case or challenge. Acquisition set-up optimization must be realized depending on part geometry variability (light patterns, part orientations, capture time, etc.)

For more information, please contact: