Computer-assisted text and visual styling for images

Patent metadata

Field	Value
Publication number	US-10049477-B1
Application number	US-201514752658-A
Country	US
Kind code	B1
Filing date	Jun 26, 2015
Priority date	Jun 27, 2014
Publication date	Aug 14, 2018
Grant date	Aug 14, 2018

Abstract

Implementations can relate to providing computer-assisted text and visual styling for images. In some implementations, a computer-implemented method includes determining a set of characteristics of an image, and applying one or more first visual modifications to the image based on one or more of the set of characteristics of the image. The method can include receiving user input defining user text, providing the user text in the image, and applying one or more second visual modifications to the image based on the user text and based on at least one of the set of characteristics of the image.

First claim

What is claimed is:

1. A computer-implemented method to provide visual modification to an image, the method comprising:
determining a set of characteristics of the image;
applying one or more first visual modifications to the image based on one or more characteristics of the set of characteristics of the image, wherein the applying comprises changing pixel values of a first plurality of pixels of the image;
receiving user input defining user text, wherein the user text has a semantic meaning that indicates image content that is not previously detected in the image;
adding the user text into the image as a second visual modification to the image, wherein adding the user text includes changing pixel values of a second plurality of pixels of the image; and
selecting and applying one or more third visual modifications to the image in response to receiving the user input defining the user text, wherein the one or more third visual modifications are selected based on a stored association with the image content indicated by the semantic meaning of the user text and based on a stored association with at least one characteristic of the set of characteristics of the image,
wherein the one or more third visual modifications include changing pixel values of one or more particular pixels of the image, wherein the one or more particular pixels include pixels different from the second plurality of pixels and pixels that are excluded from all text in the image after the one or more third visual modifications are applied,
wherein applying the one or more third visual modifications includes applying one or more edit operations to the image, wherein the one or more edit operations produce at least one of a vintage effect, a lens flare effect, a vignette effect, or a blur effect in the image.

2. The method of claim 1 wherein applying one or more first visual modifications includes:
detecting one or more content subjects depicted in the image; and
automatically generating generated text based on a semantic meaning of the one or more content subjects depicted in the image and adding the generated text to the image.

3. The method of claim 2 wherein generating the generated text includes transforming the generated text to appear three-dimensionally within a scene depicted in the image.

4. The method of claim 2 wherein automatically generating the generated text includes modifying a portion of the image on which the generated text is to be placed, wherein modifying a portion of the image includes blurring the portion of the image.

5. The method of claim 1 wherein the one or more first visual modifications and the one or more third visual modifications include one or more visual style modifications for the image, wherein the one or more first visual style modifications and the one or more third visual style modifications exclude adding new text to the image,
wherein applying the one or more third visual modifications includes applying the one or more third visual modifications to the user text added to the image.

6. The method of claim 5 wherein the one or more first visual style modifications apply at least one edit operation to the image to provide one or more visual effects in the image, wherein the one or more visual effects include at least one of: a vintage effect, a lens flare effect, a vignette effect, or a blur effect.

7. The method of claim 1 wherein determining the set of characteristics of the image includes identifying one or more image content characteristics that indicate one or more content subjects depicted in the image,
wherein the one or more content subjects include at least one of: one or more persons, one or more moods of persons as indicated by one or more facial features of the one or more persons, one or more objects, one or more landmarks, one or more landscape features, or one or more weather effects recognized and depicted in the image, and
wherein the one or more first visual modifications have a predefined association with the one or more characteristics of the set of characteristics,
wherein the one or more third visual modifications have a predefined association with the at least one characteristic of the set of characteristics, and wherein the one or more third visual modifications apply one or more edit operations to the image, wherein the one or more edit operations include at least one of: a sharpening operation, or a blur operation.

8. The method of claim 1 wherein determining the set of characteristics of the image includes identifying one or more condition characteristics that indicate one or more conditions associated with the image, wherein the condition characteristics are identified based on stored data associated with the image, and wherein the one or more condition characteristics include at least one of:
a time at which the image was captured,
a geographical location at which the image was captured indicated by location data, or
one or more camera parameters of a camera that captured the image,
wherein the one or more third visual modifications have a predefined association with the at least one characteristic of the set of characteristics, and wherein the one or more third visual modifications apply one or more edit operations to the image, wherein the one or more edit operations include at least one of: a sharpening operation, or a blur operation.

9. The method of claim 1 wherein applying one or more first visual modifications includes automatically generating generated text based on a plurality of characteristics of the set of characteristics and adding the generated text to the image,
wherein the plurality of characteristics include different types of characteristics including two or more of: a time of capture of the image, a location of capture of the image, a face content subject depicted in the image, or a landmark content subject depicted in the image, and
wherein automatically generating the generated text includes automatically selecting the generated text from a list of predetermined text items associated with a combination of multiple of the different types of the plurality of characteristics of the set of characteristics on which the generated text is based.

10. The method of claim 1 further comprising:
generating and causing display of a plurality of modified images based on the image, wherein each modified image includes a different modification for the one or more first third visual modifications based on a different characteristic of the set of characteristics of the image, such that a modification in a first modified image is based on image content, and a modification in a second modified image is based on one of a geographical location at which the image was captured indicated by location data, or a time of capture of the image, wherein each modified image includes the user text.

11. The method of claim 1 wherein the one or more third modifications modify an entirety of the image.

12. The method of claim 1 further comprising, before applying the one or more third modifications, presenting a menu of multiple different modification options based on the user text and based on at least one of the one or more characteristics, wherein each of the different modification options is associated with a different set of edit operations configured to change pixels of the image; and
receiving user input selecting a particular modification option of the multiple different modification options, wherein the one or more third modifications are applied to the image based on the particular modification option.

13. The method of claim 1 wherein the stored association between the one or more third visual modif

Assignees

• Google Inc
• Google Llc

Inventors

• Kokemohr Nils
• Krishnaswamy Aravind
• Wotzlaw Ronald Frank
• Schwarz Daniel Frederik

Classifications

• G06T11/10

  Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77) · CPC title

• G06T11/60 Primary

  Creating or editing images; Combining images with text · CPC title

• G09G5/30

  Control of display attribute · CPC title

• G09G5/36

  characterised by the display of a graphic pattern, e.g. using an all-points-addressable [APA] memory · CPC title

• G06T11/001

  Physics · mapped topic