Interactive image tagging

• US 20080229192A1
• Filed: 03/15/2007
• Published: 09/18/2008
• Est. Priority Date: 03/15/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: George, Sam J., Gear, Gavin M., Spencer, Richard L.
• Granted Patent: US 8,347,206 B2
• Time in Patent Office: Days
• US Class Current: 715/268
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06V 30/1423 the instrument generating sequences of position coordinates corresponding to handwriting preprocessing or recognising digital ink G06V30/32

Abstract

Techniques are described for performing automatic generation of one or more tags associated with an image file. One or more ink annotations for a displayed image are received. Handwriting recognition processing of the one or more ink annotations is performed. A string is generated and the string includes one or more recognized words used to form the one or more tags associated with the image file. The handwriting recognition processing and generating the string are performed in response to receiving the ink annotations.

Claims

1. A method for performing automatic generation of one or more tags associated with an image file comprising:

receiving one or more ink annotations for a displayed image;

performing handwriting recognition processing of the one or more ink annotations; and

generating a string including one or more recognized words used in forming the one or more tags associated with the image file, said performing and said generating being performed in response to said receiving.

2. The method of claim 1, further comprising:

collecting one or more ink strokes;

analyzing the one or more ink strokes to form the one or more ink annotations; and

generating one or more lines of ink text in accordance with the one or more ink annotations, wherein the ink text is an ink representation of one or more lines of text.

3. The method of claim 1, wherein the one or more recognized words are used in forming one or more keyword tags.

4. The method of claim 3, further comprising:

storing the one or more keyword tags as part of the image file.

5. The method of claim 4, wherein the keyword tags are stored as metadata of the image file.

6. The method of claim 1, further comprising:

indicating an implicit tagging mode; and

when in the implicit tagging mode, storing the one or more tags and the one more ink annotations as part of the image file.

7. The method of claim 1, further comprising:

indicating an explicit tagging mode; and

when in the explicit tagging mode, storing the one or more tags as part of the image file without storing the ink annotations as part of the image file.

8. The method of claim 1, further comprising:

providing one or more portions of a display area, each of the one or more portions having a corresponding type of tag;

receiving an ink annotation entered onto a first portion of the display area having a corresponding first type of tag; and

creating a tag of the first type in accordance with the ink annotation of the first portion.

9. The method of claim 1, wherein the one or more ink annotations are entered on any arbitrary location of a display area including the displayed image.

10. The method of claim 1, wherein the steps of receiving, performing, and generating are performed using at least one of a touch-screen, digitizing tablet, or other two-dimensional input device.

11. The method of claim 1, further comprising:

loading, by an image application, the image file;

forwarding, by the image application, one or more ink strokes to an ink analysis component;

generating, by the ink analysis component, one or more lines of ink text in accordance with the one or more ink strokes; and

generating, by a recognition engine, the string in accordance with the one or more lines of ink text.

12. The method of claim 3, further comprising:

indexing the one or more keywords associated with the image file;

using a search engine to perform a search operation in accordance with specified search criteria and said one or more keywords; and

generating search results including said image file if the one or more keywords match the specified search criteria.

13. A method for generating and storing one or more keyword tags associated with an image file comprising:

displaying an image in accordance with image data from the image file;

receiving one or more ink annotations for the image, the ink annotations being interactively input, and in response, automatically;

generating a string including one or more words by performing handwriting recognition processing of the one or more ink annotations; and

forming one or more keyword tags using the one or more words of the string; and

storing the one or more keyword tags in the image file.

14. The method of claim 13, wherein said storing is performed automatically in response to said receiving.

15. The method of claim 13, wherein the keyword tags are stored as metadata included in the image file.

16. The method of claim 13, further comprising:

indicating an implicit tagging mode; and

when in the implicit tagging mode, storing the one or more keyword tags and the one more ink annotations as part of the image file.

17. The method of claim 13, further comprising:

indicating an explicit tagging mode; and

when in the explicit tagging mode, storing the one or more keyword tags as part of the image file without storing the ink annotations as part of the image file.

18. The method of claim 13, further comprising:

providing one or more portions of a display area, each of the one or more portions having a corresponding type of tag;

receiving an ink annotation entered onto a first portion of the display area having a corresponding first type of tag; and

creating a tag of the first type in accordance with the ink annotation of the first portion.

19. The method of claim 13, further comprising:

receiving one or more additional ink annotations used in connection with forming one or more of a subject tag, a user comment tag, and a title tag associated with the image file by performing said handwriting recognition processing and said forming in accordance with the one or more additional ink annotations.

20. A computer readable medium comprising instructions stored thereon for performing automatic generation of one or more tags associated with an image file, the computer readable medium comprising instructions stored thereon for:

displaying an image in accordance with image data from the image file;

interactively inputting ink annotations in the form of digital handwriting over the image as displayed so that the ink annotations are displayed as inputted at arbitrary locations over the image;

in response to interactively inputting the ink annotations, automatically;

performing handwriting recognition processing of the one or more ink annotations, generating a string including one or more words recognized by the handwriting recognition processing, and storing the one or more words as metadata in an image file that includes the image data unaltered by the ink annotations.