CPC G06T 7/001 (2013.01) [G01N 21/95 (2013.01); G01N 35/00584 (2013.01); G06N 20/00 (2019.01); G06T 11/00 (2013.01); G06V 10/764 (2022.01); G06T 2207/10152 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30141 (2013.01); G06V 2201/06 (2022.01)] | 19 Claims |
1. A method for manufacturing and/or for checking and/or for testing a component carrier, the method comprising:
(a) supplying a semifinished component carrier or a component carrier to an automatic or semi-automatic optical inspection device;
(b) performing an automatic or a semi-automatic optical inspection of the semifinished component carrier or the component carrier by means of the automatic or the semi-automatic optical inspection device, wherein performing the automatic or the semi-automatic optical inspection comprises the following steps:
capturing a first image of the semifinished component carrier or the component carrier with a first illumination;
capturing a second image of the semifinished component carrier or the component carrier with a second illumination, the first illumination having a first spectral composition being different to a second spectral composition of the second illumination;
comparing an actual data set being indicative of at least one of the first image and the second image with a reference data set being indicative of a reference image for the semifinished component carrier or the component carrier; and
identifying potential defects of the semifinished component carrier or the component carrier based on the result of comparing the actual data set with the reference data set;
(c) carrying out a quality classification of the semifinished component carrier or the component carrier, wherein carrying out the quality classification comprises the following steps:
generating, based on at least one of the first image and the second image, a virtual third image of the semifinished component carrier or the component carrier, wherein the third image is indicative of the semifinished component carrier or the component carrier under a virtual third illumination having a third spectral composition being different both to the first spectral composition and to the second spectral composition;
processing the first image, the second image, and the third image by applying artificial intelligence; and
classifying the identified potential defects based on the artificial intelligence processing; and
(d) taking an action based on the carried out quality classification.
|