spacer

CPI Feature extract

solino® CPI

(Computation of particular Images)


CPI is a software solution to compute one (particular) image from one image set, taking into account the consistency and calibration of the image input.

The acquisition consistency drives to BRDF information and CPI permits to decompose this information in sub-layers, with an image as sub-layer.

Each (particular) image is a result of multiple operations – processing from pixel values distribution.

To improve Quality Control processes CPI provides an image gallery to explore surface anomalies as a first step towards an automated inspection, driven by humans and powered by AI.


Representation of product features as image information

When identifying and determining surface defects, it is essential to be able to recognise the defect in the image at all or to be able to find it again and again, regardless of the environmental conditions. The same applies to similar anomalies, which must also be recognised and displayed accordingly.

solinoT® was developed for this purpose. Non-relevant image information is deliberately suppressed and anomalies are highlighted.

The image is cleaned of unimportant factors, resulting in a repeatable and reliable image analysis.

solinoViewer user interface

The solinoViewer supplied with our IM-solino 10x12 enables a live image display as well as a preview of four processed CPI anomaly images.

A total of more than 200 algorithms are available for the analysis and evaluation of the 64 individual images, according to which the result images are displayed. The selection is made via a drop-down menu (see image on the right).

The solinoViewer offers:

  • an intuitive user interface for identifying product defects or anomalies
  • a slider image manager with one widget per image
  • the solino Image Editor for batch processing of stereo-photometric images
  • a selective list of image processing processes to be output
  • the selection of the colour channel to be processed

Member of
To give you the best possible experience, this site uses cookies. Click on 'More Information' if you want to learn more about cookies or change your cookie settings. More Information
Please subscribe to our newsletter

With your click on submit, you accept our privacy policy.