US 12,229,930 B2
Distortion-based filtering for image classification
Utsav Drolia, Milipitas, CA (US); Srimat Chakradhar, Manalapan, NJ (US); and Sibendu Paul, West Lafayette, IN (US)
Assigned to NEC Corporation, Tokyo (JP)
Filed by NEC Laboratories America, Inc., Princeton, NJ (US)
Filed on Oct. 7, 2021, as Appl. No. 17/496,246.
Claims priority of provisional application 63/089,681, filed on Oct. 9, 2020.
Claims priority of provisional application 63/089,570, filed on Oct. 9, 2020.
Prior Publication US 2022/0114717 A1, Apr. 14, 2022
Int. Cl. G06N 3/04 (2023.01); G06T 7/00 (2017.01); H04N 23/60 (2023.01)
CPC G06T 7/0002 (2013.01) [G06N 3/04 (2013.01); H04N 23/64 (2023.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30168 (2013.01); G06T 2207/30232 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method for image filtering, comprising:
detecting a distortion level of input images, using a distortion detection model that is trained using confidence values generated by a pre-trained image classifier with a set of distorted training images;
performing analysis on input images having a detected distortion level that is lower than a threshold, with input images having an above-threshold detected distortion level being filtered out; and
adjusting an image capture setting responsive to a determination that the input image has an above-threshold distortion level.