US 11,816,946 B2
Image based novelty detection of material samples
Nicholas A. Asendorf, St. Paul, MN (US); Jennifer F. Schumacher, Woodbury, MN (US); Muhammad Jamal Afridi, Woodbury, MN (US); Himanshu Nayar, St. Paul, MN (US); and Golshan Golnari, Maple Grove, MN (US)
Assigned to 3M Innovative Properties Company, St. Paul, MN (US)
Appl. No. 17/247,773
Filed by 3M INNOVATIVE PROPERTIES COMPANY, St. Paul, MN (US)
PCT Filed Jun. 26, 2019, PCT No. PCT/IB2019/055385
§ 371(c)(1), (2) Date Dec. 22, 2020,
PCT Pub. No. WO2020/003150, PCT Pub. Date Jan. 2, 2020.
Claims priority of provisional application 62/691,330, filed on Jun. 28, 2018.
Prior Publication US 2021/0327041 A1, Oct. 21, 2021
Int. Cl. G07D 7/206 (2016.01); G06T 7/00 (2017.01); G06F 18/22 (2023.01); G06F 18/214 (2023.01); G06F 18/2135 (2023.01); G06F 18/2411 (2023.01); G06V 10/82 (2022.01)
CPC G07D 7/206 (2017.05) [G06F 18/214 (2023.01); G06F 18/2135 (2023.01); G06F 18/22 (2023.01); G06F 18/2411 (2023.01); G06T 7/0002 (2013.01); G06V 10/82 (2022.01); G06T 2200/24 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method of anomalous product identification, the method comprising:
providing, by a processor, a test image of a test sample as an input to a trained transformation function that is obtained by training a transformation function with training images of a batch of material samples;
executing, by the processor, the trained transformation function using the test image as the input, to obtain a transformed matrix;
comparing, by the processor, the transformed matrix to a reference matrix to compute a measure of similarity associated with the test image;
computing, by the processor, a threshold value from reconstruction errors of validation images by processing the validation images with the trained transformation function;
comparing the measure of similarity to the threshold value; and
based on the comparison of the measure of similarity to the threshold value, determining, by the processor, that the test sample is novel to the batch of material samples.