US 12,314,311 B2
Image-based popularity prediction
Anjan Goswami, Sunnyvale, CA (US); and Sung Hwan Chung, Fremont, CA (US)
Assigned to eBay Inc., San Jose, CA (US)
Filed by eBay Inc., San Jose, CA (US)
Filed on Mar. 20, 2023, as Appl. No. 18/123,846.
Application 18/123,846 is a continuation of application No. 16/200,881, filed on Nov. 27, 2018, granted, now 11,636,364.
Application 16/200,881 is a continuation of application No. 14/621,296, filed on Feb. 12, 2015, granted, now 10,176,429, issued on Jan. 8, 2019.
Application 14/621,296 is a continuation of application No. 13/462,179, filed on May 2, 2012, granted, now 8,977,629, issued on Mar. 10, 2015.
Claims priority of provisional application 61/489,669, filed on May 24, 2011.
Prior Publication US 2023/0229692 A1, Jul. 20, 2023
Int. Cl. G06F 16/00 (2019.01); G06F 16/24 (2019.01); G06F 16/242 (2019.01); G06F 16/2457 (2019.01); G06F 16/2458 (2019.01); G06F 16/248 (2019.01); G06F 16/332 (2019.01); G06F 16/338 (2019.01); G06F 16/34 (2019.01); G06F 16/58 (2019.01); G06F 16/583 (2019.01); G06F 16/587 (2019.01); G06F 16/951 (2019.01); G06F 17/00 (2019.01); G06F 18/2115 (2023.01); G06F 18/22 (2023.01); G06N 5/048 (2023.01); G06N 20/00 (2019.01); G06Q 30/02 (2023.01); G06V 10/10 (2022.01); G06V 10/40 (2022.01); G06V 10/50 (2022.01); G06V 10/75 (2022.01); G06V 10/771 (2022.01); G06V 20/69 (2022.01)
CPC G06F 16/583 (2019.01) [G06F 16/00 (2019.01); G06F 16/24 (2019.01); G06F 16/242 (2019.01); G06F 16/24578 (2019.01); G06F 16/2462 (2019.01); G06F 16/2465 (2019.01); G06F 16/2471 (2019.01); G06F 16/248 (2019.01); G06F 16/332 (2019.01); G06F 16/338 (2019.01); G06F 16/345 (2019.01); G06F 16/5838 (2019.01); G06F 16/5866 (2019.01); G06F 16/587 (2019.01); G06F 16/951 (2019.01); G06F 17/00 (2013.01); G06F 18/2115 (2023.01); G06F 18/22 (2023.01); G06N 5/048 (2013.01); G06N 20/00 (2019.01); G06Q 30/02 (2013.01); G06V 10/10 (2022.01); G06V 10/40 (2022.01); G06V 10/507 (2022.01); G06V 10/75 (2022.01); G06V 10/771 (2022.01); G06V 20/695 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
a memory storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
receiving training images depicting training items, each respective training image having an image quality label indicating a human perceived quality of the respective training image;
extracting photographic features from the training images, in part, by extracting image color values and image intensity values from the training images;
training a machine learning model to learn a relationship between the photographic features and image quality based on the photographic features and the image quality labels;
determining, using the machine learning model, a plurality of image quality scores for a plurality of images of items listed via an online marketplace based, in part, on a standard deviation of the image intensity values depicted in backgrounds of the plurality of images;
receiving, from a user device, a search request associated with at least one item of the items; and
transmitting, to the user device and in response to the search request, one or more search results that reference or include one or more images of the plurality of images selected based on one or more image quality scores associated with the one or more images.