Efficient image synthesis

US10878609B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-10878609-B2
Application numberUS-202016749060-A
CountryUS
Kind codeB2
Filing dateJan 22, 2020
Priority dateMar 30, 2015
Publication dateDec 29, 2020
Grant dateDec 29, 2020

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

A method for synthesizing images includes selecting a background image from a plurality of source images and selecting one or more foreground elements from a plurality of source files. The foreground elements include at least one of a foreground image or a foreground text. The method further includes dividing at least a portion of the selected background image to one or more sub-regions for displaying the one or more selected foreground elements, each sub-region is used for displaying at least one foreground element. The method further includes determining a display format and a display location for each of the one or more foreground elements and synthesizing the one or more foreground elements to the corresponding one or more sub-regions of the background image based on the display format and the display location.

First claim

Opening claim text (preview).

What is claimed is: 1. A computer-implemented method for providing multiple distinct, synthesized images that each include a same background image and a same foreground element, the method comprising: selecting a background image and quantity n foreground elements that are both to be used to generate each of multiple, distinct synthesized images; selecting a sub-region of the background image in which the foreground element is to be synthesized in each of the multiple, distinct synthesized images; for each of the multiple, distinct synthesized images that are to be generated: selecting a parameter that is unique to the synthesized image that is to be generated, selecting, from among multiple pre-determined curve functions that are each associated with displaying foreground elements in synthesized images, a particular curve function based at least on the parameter that is unique to the synthesized image that is to be generated, generating a curve based on the selected, particular curve function, dividing the curve into n line segments, for each of the foreground elements, aligning the foreground element with a starting point of a different line segment, and generating a distinct, synthesized image that comprises the background image overlaid within the sub-region by the foreground elements that are each aligned with a starting point of a different line segment; and providing one or more of the multiple, distinct synthesized images in response to a request for a synthesized image. 2. The method of claim 1 , wherein each foreground element comprises text. 3. The method of claim 1 , wherein each foreground element comprises a foreground image. 4. The method of claim 1 , comprising dividing the background image into sub-regions based on configuration information associated with the foreground elements. 5. The method of claim 1 , comprising processing the foreground elements to be unrecognizable by an automated optical character recognition (OCR) process. 6. The method of claim 1 , wherein aligning the foreground element comprises determining a display shape associated with the foreground element. 7. A non-transitory computer-readable medium storing one or more instructions executable by a computer system to perform operations for providing multiple distinct, synthesized images that each include a same background image and a same foreground element, the operations comprising: selecting a background image and quantity n foreground elements that are both to be used to generate each of multiple, distinct synthesized images; selecting a sub-region of the background image in which the foreground element is to be synthesized in each of the multiple, distinct synthesized images; for each of the multiple, distinct synthesized images that are to be generated: selecting a parameter that is unique to the synthesized image that is to be generated, selecting, from among multiple pre-determined curve functions that are each associated with displaying foreground elements in synthesized images, a particular curve function based at least on the parameter that is unique to the synthesized image that is to be generated, generating a curve based on the selected, particular curve function, dividing the curve into n line segments, for each of the foreground elements, aligning the foreground element with a starting point of a different line segment, and generating a distinct, synthesized image that comprises the background image overlaid within the sub-region by the foreground elements that are each aligned with a starting point of a different line segment; and providing one or more of the multiple, distinct synthesized images in response to a request for a synthesized image. 8. The non-transitory computer-readable medium of claim 7 , wherein each foreground element comprises text. 9. The non-transitory computer-readable medium of claim 7 , wherein each foreground element comprises a foreground image. 10. The non-transitory computer-readable medium of claim 7 , wherein the operations comprise dividing the background image into sub-regions based on configuration information associated with the foreground elements. 11. The non-transitory computer-readable medium of claim 7 , wherein the operations comprise processing the foreground elements to be unrecognizable by an automated optical character recognition (OCR) process. 12. The non-transitory computer-readable medium of claim 7 , wherein aligning the foreground element comprises determining a display shape associated with the foreground element. 13. A system comprising: one or more computers; and one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing instructions, that when executed by the one or more computers, perform operations for providing multiple distinct, synthesized images that each include a same background image and a same foreground element, the operations comprising: selecting a background image and quantity n foreground elements that are both to be used to generate each of multiple, distinct synthesized images; selecting a sub-region of the background image in which the foreground element is to be synthesized in each of the multiple, distinct synthesized images; for each of the multiple, distinct synthesized images that are to be generated: selecting a parameter that is unique to the synthesized image that is to be generated, selecting, from among multiple pre-determined curve functions that are each associated with displaying foreground elements in synthesized images, a particular curve function based at least on the parameter that is unique to the synthesized image that is to be generated, generating a curve based on the selected, particular curve function, dividing the curve into n line segments, for each of the foreground elements, aligning the foreground element with a starting point of a different line segment, and generating a distinct, synthesized image that comprises the background image overlaid within the sub-region by the foreground elements that are each aligned with a starting point of a different line segment; and providing one or more of the multiple, distinct synthesized images in response to a request for a synthesized image. 14. The system of claim 13 , wherein each foreground element comprises text. 15. The system of claim 13 , wherein each foreground element comprises a foreground image. 16. The system of claim 13 , wherein the operations comprise dividing the background image into sub-regions based on configuration information associated with the foreground elements. 17. The system of claim 13 , wherein the operations comprise processing the foreground elements to be unrecognizable by an automated optical character recognition (OCR) process.

Assignees

Inventors

Classifications

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

  • G06T11/60Primary

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

  • Drawing from basic elements · CPC title

  • involving foreground-background segmentation · CPC title

  • Scaling of whole images or parts thereof, e.g. expanding or contracting · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US10878609B2 cover?
A method for synthesizing images includes selecting a background image from a plurality of source images and selecting one or more foreground elements from a plurality of source files. The foreground elements include at least one of a foreground image or a foreground text. The method further includes dividing at least a portion of the selected background image to one or more sub-regions for dis…
Who is the assignee on this patent?
Advanced New Technologies Co Ltd
What technology area does this patent fall under?
Primary CPC classification G06T11/60. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Dec 29 2020 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 3 related publications on this page (citations in our corpus or others sharing the same primary CPC).