Method for detecting optical defects within windshield
A method for detecting optical defects within a windshield. The method takes, as input, a digital image map of the intensity of optical power of a windshield, and provides, as output, a digital image map of optical defects. The method includes (a) an image processing of the digital image map of optical powers for detecting and delimiting regions that differs in intensity of optical power; (b) computing, for each detected regions, a representative geometric distance and a representative value of the optical power; (c) computing an image map of the detected regions for which the product between the representative geometric distance and the representative value of the optical power is equal or superior to 2.9·10 −4 .
1 . A computer implemented method for detecting optical defects within a windshield, wherein said method takes, as input, a digital image map of an intensity of optical power of a windshield, and provides, as output, a digital image map of optical defects, wherein said method comprises the following steps:
(a) performing an image processing of said digital image map of optical powers for detecting and delimiting regions that differ in intensity of optical power;
(b) computing, for each of the detected regions, a representative geometric dimension and a representative value of the optical power;
(c) computing a digital image map of the detected regions for which the product between the representative geometric dimension and the representative value of the optical power falls within a range, the range including values equal or superior to 2.9·10 −4 , and
(d) based on the digital image map of detected regions from step (c), automatically identifying the windshield as defective.
2 . The computer implemented method according to claim 1 , wherein the range in step (c) is between 5·10 −4 and 2·10 −3 .
3 . The computer implemented method according to claim 2 , wherein the range in step (c) is between 7·10 −4 and 1.5·10 −3 .
4 . The computer implemented method according to claim 1 , wherein the image processing of step (a) is a blob detection through the computing of the Laplacian of the Gaussian of the digital image map of optical powers, of the difference of the Gaussian of the digital image map of optical powers or of the determinant of the Hessian of the digital image map of optical powers.
5 . The computer implemented method according to claim 1 , wherein the detected regions at step (a) are delimited with ellipses and wherein the representative geometric dimensions of the detected regions computed at step (b) are the minor axis of said ellipses.
6 . The computer implemented method according to claim 1 , wherein the representative value of the optical power of each detected regions is the average optical power, the median optical power, the maximum optical power or a difference between the maximum optical power and a minimum optical power in said detected region.
7 . A data processing system comprising means for carrying out the method according to claim 1 .
8 . A non-transitory computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to claim 1 .
9 . A process comprising performing a method according to claim 1 in a manufacturing process of a windshield.
10 . A computer implemented method for detecting optical defects within a windshield, wherein said method takes, as input, a digital image map of an intensity of optical power of a windshield, and provides, as output, a digital image map of optical defects, wherein said method comprises the following steps:
(a) performing an image processing of said digital image map of optical powers for detecting and delimiting regions that differ in intensity of optical power;
(b) computing, for each detected regions which are such that their apparent size in the scale of visual decimal acuity falls within a first range between 0.5 and 3, a representative geometric dimension and a representative value of the optical power;
(c) computing a digital image map of the detected regions for which the product between the representative geometric dimension and the representative value of the optical power falls within a second range, the second range including values equal or superior to 2.9·10 −4 , and
(d) based on the digital image map of detected regions from step (c), automatically identifying the windshield as defective.
11 . The computer implemented method according to claim 10 , wherein the first range of the apparent size in the scale of visual decimal acuity is between 0.67 and 1.25.
12 . The computer implemented method according to claim 10 , wherein the second range in step (c) is between 5·10 −4 and 2·10 −3 .
13 . The computer implemented method according to claim 12 , wherein the second range in step (c) is between 7·10 −4 and 1.5·10 −3 .
14 . A process for detecting optical defects within a windshield, the process comprising:
(a) acquiring a digital image map of an intensity of optical power of a windshield;
(b) processing, with a computing system, said digital image map for detecting and delimiting regions that differ in intensity of optical power;
(c) computing, with the computing system, a digital image map of the detected regions for which the product between a representative geometric dimension and a representative value of the optical power falls within a range, the range including values equal or superior to 2.9·10 −4 , and
(d) based on the digital image map of detected regions from step (c), automatically identifying the windshield as defective.
15 . The process according to claim 14 , wherein the range in step (c) is between 5·10 −4 and 2·10 −3 .
16 . The process according to claim 15 , wherein the range in step (c) is between 7·10 −4 and 1.5·10 −3 .