Automatically organizing images
Abstract
Assigning a title to a digital image group is disclosed. A method includes receiving, by a computing device, a plurality of digital images associated with a user; extracting, by the computing device, time information from the plurality of digital images; clustering, by the computing device, the digital images into digital image groups based on the time information, where the digital image groups include the digital image group, and the digital image group corresponds to a first time information; identifying, by the computing device, a calendar entry in calendar data of the user, where the calendar entry having a second time information that is a common time period with the first time information; adding, by the computing device, a descriptor of the common time period in the title; and assigning, by the computing device, the title to the digital image group.
Claims
exact text as granted — not AI-modifiedWhat is claimed is:
1 . A method for assigning a title to a digital image group, the method comprising:
receiving, by a computing device, a plurality of digital images associated with a user; extracting, by the computing device, time information from the plurality of digital images; clustering, by the computing device, the digital images into digital image groups based on the time information, wherein
the digital image groups include the digital image group, and
the digital image group corresponds to a first time information;
identifying, by the computing device, a calendar entry in calendar data of the user, wherein the calendar entry having a second time information that is a common time period with the first time information; adding, by the computing device, a descriptor of the common time period in the title; and assigning, by the computing device, the title to the digital image group.
2 . The method of claim 1 , further comprising:
extracting, from the digital image group, visible image features; and identifying a concept based on a semantic relatedness of the visible image features; and wherein assigning the title to the digital image group further comprises: adding the concept to the title of the digital image group.
3 . The method of claim 1 , further comprising:
identifying, using facial recognition, a person in the digital image group; and wherein assigning the title to the digital image group further comprises: adding a name of the person in the title of the digital image group.
4 . The method of claim 3 , further comprising:
identifying the person as a social networking contact of the user; and retrieving the name of the person from the social networking contact.
5 . The method of claim 3 , further comprising:
identifying the person in another image, wherein the name of the person is associated with the another image; and retrieving the name of the person from the another image.
6 . The method of claim 1 , wherein identifying the calendar entry in calendar data of the user comprises:
receiving permission from the user to access the calendar data of the user.
7 . The method of claim 1 , wherein the title further includes a subject of the calendar entry.
8 . A non-transitory computer-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations for assigning a title to a digital image group, comprising:
receiving a plurality of digital images associated with a user; extracting time information from the plurality of digital images; clustering the digital images into digital image groups based on the time information, wherein
the digital image groups include the digital image group, and
the digital image group corresponds to a first time information;
identifying a calendar entry in calendar data of the user, wherein the calendar entry having a second time information that is a common time period with the first time information; adding a descriptor of the common time period in the title; and assigning the title to the digital image group.
9 . The non-transitory computer-readable storage medium of claim 8 ,
wherein the operations further comprise:
extracting, from the digital image group, visible image features; and
identifying a concept based on a semantic relatedness of the visible image features; and
wherein assigning the title to the digital image group further comprises:
adding the concept to the title of the digital image group.
10 . The non-transitory computer-readable storage medium of claim 8 ,
wherein the operations further comprise:
identifying, using facial recognition, a person in the digital image group; and
wherein assigning the title to the digital image group further comprises:
adding a name of the person in the title of the digital image group.
11 . The non-transitory computer-readable storage medium of claim 10 , wherein the operations further comprise:
identifying the person as a social networking contact of the user; and retrieving the name of the person from the social networking contact.
12 . The non-transitory computer-readable storage medium of claim 10 , wherein the operations further comprise:
identifying the person in another image, wherein the name of the person is associated with the another image; and retrieving the name of the person from the another image.
13 . The non-transitory computer-readable storage medium of claim 8 , wherein identifying the calendar entry in calendar data of the user comprises:
receiving permission from the user to access the calendar data of the user.
14 . The non-transitory computer-readable storage medium of claim 8 , wherein the title further includes a subject of the calendar entry.
15 . A system, comprising:
a processor; and a memory that stores executable instructions, that, when executed by the processor, facilitate performance of operations for assigning a title to a digital image group, comprising:
receiving a plurality of digital images associated with a user;
extracting time information from the plurality of digital images;
clustering the digital images into digital image groups based on the time information, wherein
the digital image groups include the digital image group, and
the digital image group corresponds to a first time information;
identifying a calendar entry in calendar data of the user, wherein the calendar entry having a second time information that is a common time period with the first time information;
adding a descriptor of the common time period in the title; and
assigning the title to the digital image group.
16 . The system of claim 15 ,
wherein the operations further comprise: extracting, from the digital image group, visible image features; and identifying a concept based on a semantic relatedness of the visible image features; and
wherein assigning the title to the digital image group further comprises:
adding the concept to the title of the digital image group.
17 . The system of claim 15 ,
wherein the operations further comprise:
identifying, using facial recognition, a person in the digital image group; and
wherein assigning the title to the digital image group further comprises:
adding a name of the person in the title of the digital image group.
18 . The system of claim 17 , wherein the operations further comprise:
identifying the person as a social networking contact of the user; and retrieving the name of the person from the social networking contact.
19 . The system of claim 17 , wherein the operations further comprise:
identifying the person in another image, wherein the name of the person is associated with the another image; and retrieving the name of the person from the another image.
20 . The system of claim 15 , wherein identifying the calendar entry in calendar data of the user comprises:
receiving permission from the user to access the calendar data of the user.Join the waitlist — get patent alerts
Track US2018365489A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.