Computer Vision, User Segment, and Missing Item Determination

Abstract

Techniques and systems are described that leverage computer vision as part of search to expand functionality of a computing device available to a user and increase operational computational efficiency as well as efficiency in user interaction. In a first example, user interaction with items of digital content is monitored. Computer vision techniques are used to identify digital images in the digital content, objects within the digital images, and characteristics of those objects. This information is used to assign a user to a user segment of a user population which is then used to control output of subsequent digital content to the user, e.g., recommendations, digital marketing content, and so forth.

What is claimed is: 
     
         1 . A method comprising:
 training, by at least one computing device, a machine-learning model using a plurality of digital images depicting persons wearing outfits that include at least one clothing item;   receiving, by the at least one computing device, an additional digital image subsequent to training the machine-learning model, the additional digital image being included in a live feed of digital images capturing an outfit of a person;   determining, by the at least one computing device, that at least one common clothing item in the digital images of similar outfits to the outfit is missing from the outfit of the person based on the additional digital image and the trained machine-learning model;   locating, by the at least one computing device, augmented reality digital content that corresponds to a missing clothing item of the outfit of the person; and   outputting, by the at least one computing device, the located augmented reality digital content as part of the live feed of digital images.   
     
     
         2 . The method of  claim 1 , wherein the outfit and the similar outfits include a similar top. 
     
     
         3 . The method of  claim 1 , wherein the outfit and the similar outfits include similar bottoms. 
     
     
         4 . The method of  claim 1 , further comprising:
 determining that at least one common fashion accessory in the digital images of similar outfits to the outfit is missing from the outfit of the person based on the additional digital image and the trained machine-learning model;   locating additional augmented reality digital content that corresponds to a missing fashion accessory for the outfit of the person; and   outputting the additional augmented reality digital content as part of the live feed of digital images.   
     
     
         5 . The method of  claim 1 , further comprising locating the augmented reality digital content that corresponds to a missing clothing item based on a style of the outfit of the person. 
     
     
         6 . The method of  claim 1 , further comprising locating the augmented reality digital content that corresponds to a missing clothing item based on a similar style to the outfit of the person. 
     
     
         7 . The method of  claim 1 , wherein the located augmented reality digital content is selectable to purchase the missing item. 
     
     
         8 . The method of  claim 1 , wherein the located augmented reality digital content is a listing for the missing item. 
     
     
         9 . The method of  claim 1 , wherein the plurality of digital images are training digital images. 
     
     
         10 . A system comprising:
 one or more processors; and   memory storing instructions that, responsive to execution by the one or more processors, cause the one or more processors to perform operations including:
 training a machine-learning model using a plurality of digital images depicting persons wearing outfits that include at least one clothing item; 
 receiving an additional digital image subsequent to training the machine-learning model, the additional digital image being included in a live feed of digital images capturing an outfit of a person; 
 determining that at least one common clothing item in the digital images of similar outfits to the outfit is missing from the outfit of the person based on the additional digital image and the trained machine-learning model; 
 locating augmented reality digital content that corresponds to a missing clothing item of the outfit of the person; and 
 outputting the located augmented reality digital content as part of the live feed of digital images. 
   
     
     
         11 . The system of  claim 10 , wherein the outfit and the similar outfits include a similar top. 
     
     
         12 . The system of  claim 10 , wherein the outfit and the similar outfits include similar bottoms. 
     
     
         13 . The system of  claim 10 , wherein the operations further include:
 determining that at least one common fashion accessory in the digital images of similar outfits to the outfit is missing from the outfit of the person based on the additional digital image and the trained machine-learning model;   locating additional augmented reality digital content that corresponds to a missing fashion accessory for the outfit of the person; and   outputting the additional augmented reality digital content as part of the live feed of digital images.   
     
     
         14 . The system of  claim 10 , wherein the operations further include locating the augmented reality digital content that corresponds to a missing clothing item based on a style of the outfit of the person. 
     
     
         15 . The system of  claim 10 , wherein the operations further include locating the augmented reality digital content that corresponds to a missing clothing item based on a similar style to the outfit of the person. 
     
     
         16 . The system of  claim 10 , wherein the located augmented reality digital content is selectable to purchase the missing item. 
     
     
         17 . One or more computer-readable storage media storing instructions that are executable by a computing device to perform operations including:
 training a machine-learning model using a plurality of digital images depicting persons wearing outfits that include at least one clothing item;   receiving an additional digital image subsequent to training the machine-learning model, the additional digital image being included in a live feed of digital images capturing an outfit of a person;   determining that at least one common clothing item in the digital images of similar outfits to the outfit is missing from the outfit of the person based on the additional digital image and the trained machine-learning model;   locating augmented reality digital content that corresponds to a missing clothing item of the outfit of the person; and   outputting the located augmented reality digital content as part of the live feed of digital images.   
     
     
         18 . The one or more computer-readable storage media of  claim 17 , wherein the outfit and the similar outfits include a similar top. 
     
     
         19 . The one or more computer-readable storage media of  claim 17 , wherein the outfit and the similar outfits include similar bottoms. 
     
     
         20 . The one or more computer-readable storage media of  claim 17 , wherein the operations further include:
 determining that at least one common fashion accessory in the digital images of similar outfits to the outfit is missing from the outfit of the person based on the additional digital image and the trained machine-learning model;   locating additional augmented reality digital content that corresponds to a missing fashion accessory for the outfit of the person; and   outputting the additional augmented reality digital content as part of the live feed of digital images.