Method and system for detecting optical defects within a glass windshield

1 . A computer implemented method for detecting optical defects within a glass windshield,

wherein said method takes as input a map of angular distances between primary and ghost images of a periodical pattern viewed through said glass windshield, an image of the periodical pattern viewed through said glass windshield, and at least one input shape parameter of the individual features of the periodical pattern;

wherein said method provides as output an image of optical defects,

wherein said method comprises the following steps:

(a) searching signal artefacts within said input map of angular distances;

(b) searching individual feature of the periodical pattern in zones of the input image of the periodical pattern, wherein said zones matched those of the signal artefacts searched at step (a);

(c) delineating by image processing the respective shape of the searched individual features;

(d) comparing the input shape parameter of the individual features of the periodical pattern to a corresponding shape parameter of the delineated shapes of step (c);

(e) generating an image from the input image of the periodical pattern, wherein the input shape parameter of the individual features of the periodical pattern does not match to the corresponding shape parameter of the delineated shapes, said generated image being the image of optical defects.

2 . The computer implemented method according to claim 1 , wherein the searched signal artefacts are a no signal detection or signal outliers for the ghost image of the map of angular distances.

3 . The computer implemented invention according to claim 1 , wherein the input shape parameter is selected from area, circularity, solidity, minor axis, major axis, perimeter, Feret diameter, or combination thereof.

4 . The computer implemented method according to claim 1 , wherein the periodical pattern is a dot matrix.

5 . The computer implemented method according to claim 4 , wherein dots of the dot matrix are point-like light sources.

6 . A data processing system comprising a computer configured to carry out a method according to claim 1 .

7 . An inspection system for detecting optical defects within glass windshield, wherein said inspection system comprises:

a periodical pattern, preferably a dot matrix of point like light sources;

an acquisition device configured to a map of angular distances between primary and ghost images of a periodical pattern viewed through said glass windshield and an image of the periodical pattern viewed through said glass windshield;

a data processing system according to claim 6 .

8 . The inspection system according to claim 7 , comprising a display module for displaying an image map of optical defects.

9 . The inspection system according to claim 7 , wherein the periodical pattern comprises a dot matrix of point-like light sources.

10 . A computer program comprising instructions which, when the program is executed by a computer, causes the computer to carry out a method according to claim 1 .

11 . A non-transitory computer-readable medium comprising instructions which, when said instructions are executed by a computer, causes the computer to carry out a method according to claim 1 .

12 . A process for detecting optical defects within a glass windshield, wherein said process comprises the following steps:

(a) providing a glass windshield;

(b) acquiring, with an inspection system, a map of angular distances between primary and ghost images of a periodical pattern viewed through said glass windshield and an image of the periodical pattern viewed through said glass windshield;

(c) defining at least one shape parameter of the individual features of the periodical pattern;

(d) carrying out a method according to claim 1 wherein said map of angular distances, said image of the periodical pattern and said at least one shape parameter are provided as input.