US 12,482,232 B2
Image crop
Shaoyuan Xu, West Lafayette, IN (US); Yang Cheng, West Lafayette, IN (US); Jan Allebach, West Lafayette, IN (US); and Qian Lin, Palo Alto, CA (US)
Assigned to Purdue Research Foundation, West Lafayette, IN (US); and Hewlett-Packard Development Company, L.P., Spring, TX (US)
Appl. No. 18/253,264
Filed by Hewlett-Packard Development Company, L.P., Spring, TX (US); and Purdue Research Foundation, West Lafayette, IN (US)
PCT Filed Nov. 23, 2020, PCT No. PCT/US2020/061745
§ 371(c)(1), (2) Date May 17, 2023,
PCT Pub. No. WO2022/108601, PCT Pub. Date May 27, 2022.
Prior Publication US 2024/0020952 A1, Jan. 18, 2024
Int. Cl. G06V 10/82 (2022.01); G06V 10/46 (2022.01); G06V 10/75 (2022.01); G06V 10/77 (2022.01); G06V 10/771 (2022.01); G06V 10/80 (2022.01); G06V 20/40 (2022.01); G06V 20/58 (2022.01)
CPC G06V 10/771 (2022.01) [G06V 10/462 (2022.01); G06V 10/7715 (2022.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01)] 19 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable data storage medium storing program code executable by a processor to perform processing comprising:
generating a saliency map of an image;
identifying a plurality of saliency regions of the saliency map;
merging the saliency regions into a combined saliency region;
generating a plurality of candidate image crops of the image based on the combined saliency region; and
selecting an image crop of the image from the candidate image crops using a machine learning model, wherein the machine learning model is a neural network trained as a twin neural network based on reference images and image crops of the reference images using a ranking loss objective in which the image crops are negative samples and the reference images are positive samples.