Systems and methods for automatic formatting of images for media assets based on prevalence
Control circuitry may identify an image corresponding to a media asset, where the image comprises a plurality of portions, and where each portion of the plurality of portions comprises a respective entity. The image identified by control circuitry may include several portions, where each portion includes a respective entity. Control circuitry may determine an identity of each respective entity in each respective portion of the plurality of portions. Control circuitry may then access a database to determine a level of prevalence of each identity in the media asset. Based on these identifications, control circuitry may determine which respective entity corresponds to a highest level of prevalence (e.g., with respect to the other entities), and may generate for display a respective portion comprising the respective entity that corresponds to the highest level of prevalence.
1. A method for selectively generating for display portions of an image, the method comprising:
identifying an image corresponding to a media asset, wherein the image comprises a plurality of portions, and wherein each portion of the plurality of portions comprises a respective entity;
determining an identity of each respective entity in each respective portion of the plurality of portions by;
performing a facial recognition on each respective entity of the image; and
comparing a result of the facial recognition with data of a knowledge graph;
accessing a database to determine a level of prevalence of each identity in the media asset;
determining which respective entity corresponds to a highest level of prevalence; and
generating for display a respective portion comprising the respective entity that corresponds to the highest level of prevalence.
2. The method of claim 1 , further comprising:
accessing a user profile from a database;
comparing metadata of the user profile with each identity of each respective entity;
ranking each respective entity based on the comparing;
weighting each respective entity based on a respective level of prevalence corresponding to the respective entity;
heuristically combining the rank and weight of each respective entity to determine a combined rank of each respective entity; and
generating for display a respective portion comprising the respective entity that corresponds to the highest combined rank.
3. The method of claim 1 , wherein generating for display the respective portion comprises cropping the image to include less than the entire image and to include the preferred entity.
4. The method of claim 1 , further comprising:
identifying a plurality of prevalent entities by determining two or more entities with the highest prevalence levels, relative to each other entity; and
generating for display a sufficient amount of the plurality of portions comprising entities of the plurality of preferred entities to satisfy a specified aspect ratio requirement.
5. The method of claim 1 , further comprising:
receiving a selection by a user of the respective portion; and
generating for display the image in response to receiving the selection.
6. The method of claim 1 , further comprising:
recognizing textual content in the image; and
generating for simultaneous display the textual content with the respective portion comprising the preferred entity.
7. The method of claim 1 , further comprising:
determining characteristics of the entity that corresponds to the highest level of prevalence;
determining optimal characteristics for features surrounding the entity in the respective portion corresponding to the entity that corresponds to the highest level of prevalence; and
altering characteristics of the features surrounding the entity to reflect the optimal characteristics.
8. The method of claim 1 , wherein the level of prevalence is determined based on at least one of screen time, amount of time in close-up footage, amount of time in wide shot footage, and amount of time of being the sole character in a frame in the media asset.
9. A system for selectively generating for display portions of an image, the system comprising:
communications circuitry; and
control circuitry configured to:
identify an image corresponding to a media asset, wherein the image comprises a plurality of portions, and wherein each portion of the plurality of portions comprises a respective entity;
determine an identity of each respective entity in each respective portion of the plurality of portions by;
performing facial recognition on each respective entity of the image; and
comparing a result of the facial recognition with data of a knowledge graph;
access, using the communications circuitry, a database to determine a level of prevalence of each identity in the media asset;
determine which respective entity corresponds to a highest level of prevalence; and
generate for display a respective portion comprising the respective entity that corresponds to the highest level of prevalence.
10. The system of claim 9 , wherein the control circuitry is further configured to:
access a user profile from a database;
compare metadata of the user profile with each identity of each respective entity;
rank each respective entity based on the comparing;
weight each respective entity based on a respective level of prevalence corresponding to the respective entity;
heuristically combine the rank and weight of each respective entity to determine a combined rank of each respective entity; and
generate for display a respective portion comprising the respective entity that corresponds to the highest combined rank.
11. The system of claim 9 , wherein the control circuitry is further configured, when generating for display the respective portion, to crop the image to include less than the entire image and to include the preferred entity.
12. The system of claim 9 , wherein the control circuitry is further configured to:
identify a plurality of prevalent entities by determining two or more entities with the highest prevalence levels, relative to each other entity; and
generate for display a sufficient amount of the plurality of portions comprising entities of the plurality of preferred entities to satisfy a specified aspect ratio requirement.
13. The system of claim 9 , wherein the control circuitry is further configured to:
receive a selection by a user of the respective portion; and
generate for display the image in response to receiving the selection.
14. The system of claim 9 , wherein the control circuitry is further configured to:
recognize textual content in the image; and
generate for simultaneous display the textual content with the respective portion comprising the preferred entity.
15. The system of claim 9 , wherein the control circuitry is further configured to:
determine characteristics of the entity that corresponds to the highest level of prevalence;
determine optimal characteristics for features surrounding the entity in the respective portion corresponding to the entity that corresponds to the highest level of prevalence; and
alter characteristics of the features surrounding the entity to reflect the optimal characteristics.
16. The system of claim 9 , wherein the level of prevalence is determined based on at least one of screen time, amount of time in close-up footage, amount of time in wide shot footage, and amount of time of being the sole character in a frame in the media asset.