US 12,124,539 B2
Machine learning techniques for differentiability scoring of digital images
Arshiya Aggarwal, Delhi (IN); Sanjeev Tagra, Redmond, WA (US); Sachin Soni, Delhi (IN); Ryan Rozich, Austin, TX (US); Prasenjit Mondal, West Bengal (IN); Jonathan Roeder, Round Rock, TX (US); and Ajay Jain, Ghaziabad (IN)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Jun. 23, 2023, as Appl. No. 18/213,641.
Application 18/213,641 is a continuation of application No. 17/021,279, filed on Sep. 15, 2020, granted, now 11,748,451.
Prior Publication US 2023/0334121 A1, Oct. 19, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 18/22 (2023.01); G06F 18/2113 (2023.01); G06N 5/04 (2023.01); G06T 5/50 (2006.01); G06V 10/40 (2022.01)
CPC G06F 18/22 (2023.01) [G06F 18/2113 (2023.01); G06N 5/04 (2013.01); G06T 5/50 (2013.01); G06V 10/40 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for identifying a differentiated image for representing an electronic content item, the system comprising:
an image feature extraction module configured for generating an input feature vector of an input image;
a differentiability scoring module configured for:
determining a first distance between the input feature vector and a reference feature vector of a reference image, and
determining a differentiability score of the input image by applying, to the first distance, a weighting factor that indicates user interactions with the reference image, wherein the differentiability score indicates an estimated visual difference of the input image with respect to the reference image; and
an image modification module configured for:
determining a second distance between the reference feature vector and a combined feature vector,
generating, based on the second distance, image modification data that indicates a particular feature of the reference image,
determining that the image modification data increases the differentiability score of the input image, and
generating a recommended image by combining the image modification data with the input image, wherein a modified differentiability score for the recommended image indicates an improved estimated visual difference of the recommended image with respect to the input image.