Automatic media naming using facial recognization and/or voice based identification of people within the named media content

• US 9,535,921 B2
• Filed: 07/03/2015
• Issued: 01/03/2017
• Est. Priority Date: 03/14/2013
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bubash, Tanya E., Fitzpatrick, Gregory P., Flores, Romelia H., Santana, Endemecio, Supakkul, Tassanee K., Vora, Janki Y.
• Primary Examiner(s): Uddin, M D. I
• Application Number:
  US14/791,300
• Publication Number:
  US 20150310028A1
• Time in Patent Office: 550 Days
• Field of Search: 707/737, 707/745, 707/748, 707/822, 707/823
• US Class Current: 1/1
• CPC Class Codes: G06F 16/166 File name conversion

Abstract

A computing device identifies a plurality of media files within a data store, each of the media files lacking user established file names. The computing device analyzing the plurality of media files to recognize humans in the media files based on facial recognition and/or voice recognition programs. Using results of the analyzing to generate a plurality of content identification keywords, which are scored and ranked. Establishing a filename prefix for the media files using scored and ranked content identification keywords. Automatically generating a unique file name for each of the media files, wherein each unique file name includes the established filename prefix.

Claims

1. A method for intelligent media naming comprising:

a computing device, comprising hardware and software that the hardware executes, identifying a plurality of media files within a data store, each of the media files lacking user established file names;

the computing device analyzing the plurality of media files for images to automatically recognize faces within image content of the media files using a facial recognition program;

the computing device analyzing the plurality of media files for audio to automatically recognize voices within audio content of the media files using a speaker identification recognition or speaker identify verification program;

the computing device based upon the recognized faces and voices generating a plurality of different content identification keywords for naming the media files, wherein the content identification keywords vary based on identities of humans with the recognized faces and voices;

the computing device establishing a filename prefix for the media files using scored and ranked content identification keywords;

for at least a subset of the media files with a common filename prefix, automatically determining a filename suffix for the subset of media files and automatically concatenating the filename prefix and a filename suffix to create a unique file name for each of the subset of the media files;

automatically generating a unique file name for each of the media files using semantic metadata, wherein each unique file name includes the established filename prefix, and wherein for the subset of media files the unique file names includes the concatenation of the established filename prefix and the unique filename suffix.

2. The method of claim 1, further comprising:

the computing device computing frequency or predominance of appearance in the media files of humans using the recognized faces and voices, computing relationships between humans having recognized faces and voices, and utilizing results of the computing to score and rank the content identification keywords in order of significance.

3. The method of claim 1, wherein each of the media files is a user taken video, wherein the computing device is a digital camera, a video recorder, or mobile phone, said computing device comprising a camera and a memory, wherein the camera captures environmental input used to create the media files, and wherein the memory stores the media files.

4. The method of claim 1, wherein the computing device is a set of one or more servers linked to a network, wherein the one or more servers permit users to upload and view the media files, wherein the set of one or more servers provide an option for automatically renaming uploaded media files per the method.

5. A method for intelligent media naming comprising:

a computing device, comprising hardware and software that the hardware executes, identifying a plurality of media files within a data store, each of the media files lacking user established file names;

the computing device analyzing the plurality of media files to automatically recognize faces and voices within content of the media files;

the computing device based upon the recognized faces generating a plurality of different content identification keywords for naming the media files, wherein the content identification keywords vary based on identifies of humans with the recognized faces;

the computing device establishing a filename prefix for the media files using scored and ranked content identification keywords;

for at least a subset of the media files with a common filename prefix, automatically determining a filename suffix for the subset of media files and automatically concatenating the filename prefix and a filename suffix to create a unique file name for each of the subset of the media files; and

automatically generating a unique file name for each of the media files using semantic metadata, wherein each unique file name includes the established filename prefix, and wherein for the subset of media files the unique file names includes the concatenation of the established filename prefix and the unique filename suffix.

6. The method of claim 5, further comprising:

the computing device computing frequency or predominance of appearance in the media files of the recognized faces, relationships between the recognized faces, and identity based prioritization values based on the recognized facts to score and rank the content identification keywords in order of significance.

7. The method of claim 5, wherein each of the media files is a user taken photograph or user taken video, wherein the computing device is a digital camera, a video recorder, or mobile phone, said computing device comprising a camera and a memory, wherein the camera captures environmental input used to create the media files, and wherein the memory stores the media files.

8. The method of claim 5, wherein the computing device is a set of one or more servers linked to a network, wherein the one or more servers permit users to upload and view the media files, wherein the set of one or more servers provide an option for automatically renaming uploaded media files utilizing semantic metadata.

9. The method of claim 5, further comprising;

automatically generating an icon for each of the media files, wherein the icons generated for the media files vary from each other depending on the automatically recognized faces contained within.

10. The method of claim 5, wherein the media files are digital images.

11. The method of claim 5, wherein the media files are digital home videos.

12. The method of claim 5, wherein the plurality of media files comprise one or more file types from a group of file types comprising an image file type, a video file type, an audio file type, and a document file.

13. The method of claim 5, wherein the analyzing determines an identity of a human facially recognized in the corresponding one of the subset of media files, wherein a file name that includes a name of the identified human is generated for the corresponding media file.

14. The method of claim 5, further comprising:

the computing device analyzing the plurality of media files for audio to automatically recognize voices within audio content of the media files using a speaker identification recognition or speaker identity verification program, wherein the scoring of the content identification keywords is adjusted based on identifies of recognized voices in corresponding ones of the media files.

15. A method for intelligent media naming comprising:

a computing device, comprising hardware and software that the hardware executes, identifying a plurality of media files within a data store, each of the media files lacking user established file names;

the computing device analyzing the plurality of media files for audio to automatically recognize voices within audio content of the media files using a speaker recognition or speaker identity verification program;

the computing device based upon the recognized voices generating a plurality of different content identification keywords for naming the media files, wherein the content identification keywords vary based on identities of humans with the recognized voices;

the computing device establishing a filename prefix for the media files using scored and ranked content identification keywords;

for at least a subset of the media files with a common filename prefix, automatically determining a filename suffix for the subset of media files and automatically concatenating the filename prefix and a filename suffix to create a unique file name for each of the subset of the media files; and

automatically generating a unique file name for each of the media files using semantic metadata, wherein each unique file name includes the established filename prefix, and wherein for the subset of media files the unique file names includes the concatenation of the established filename prefix and the unique filename suffix.

16. The method of claim 15, further comprising:

the computing device computing frequency or predominance of appearance in the media files of humans based on the recognized voices, computing relationships between humans having the recognized voices, and utilizing results of the computing to score and rank the content identification keywords in order of significance.

17. The method of claim 15, wherein each of the media files is a user taken video or user taken audio recording, wherein the computing device is a digital camera, a video recorder, or mobile phone, said computing device comprising a camera and a memory, wherein the camera captures environmental input used to create the media files, and wherein the memory stores the media files.

18. The method of claim 15, wherein the computing device is a set of one or more servers linked to a network, wherein the one or more servers permit users to upload and view the media files, wherein the set of one or more servers provide an option for automatically renaming uploaded media files per the method.

19. The method of claim 15, wherein the plurality of media files comprise one or more file types from a group of file types comprising an image file type, a video file type, an audio file type, and a document file.

20. The method of claim 15, wherein the analyzing determines an identity of a human facially recognized in the corresponding one of the subset of media files, wherein a file name that includes a name of the identified human is generated for the corresponding media file.