Unlock instant, AI-driven research and patent intelligence for your innovation.

Image patch matching using probabilistic sampling based on oracle

A patch and image technology, applied in image enhancement, image data processing, 2D image generation, etc., to achieve the effect of improving the convergence speed

Active Publication Date: 2018-05-11
ADOBE SYST INC
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] One or more embodiments described herein provide advantages and solve one or more of the foregoing or other problems in the art with systems and methods that provide image patch matching at higher speeds

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image patch matching using probabilistic sampling based on oracle
  • Image patch matching using probabilistic sampling based on oracle
  • Image patch matching using probabilistic sampling based on oracle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] One or more embodiments described herein provide advantages and address one or more of the foregoing or other problems in the art with a patch matching system that provides an image patch matching search that converges to a match more quickly. The patch matching system described herein improves the convergence rate for finding patch matches by using oracles to bias sampling towards those parts of the search space that are more likely to contain matches. Specifically, the patch matching system uses oracles to probabilistically identify image patches that have a high likelihood of matching a target image patch. The patch matching system performs a deeper analysis of the identified image patches to determine whether any of the probabilistically identified image patches actually match the target image patch.

[0018] As described above, patch matching systems randomly analyze digital images using oracles to search for image patches of the digital image that match a target i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention discloses a system and method for image patch matching. In particular, the system and method perform sampling of image patches to identify those image patches that match a target image patch. The system and the method probabilistically accept image patch proposals as potential matches based on an oracle. The oracle is computationally inexpensive to evaluate but more approximate than similarity heuristics. The system and the method use the oracle to quickly guide the search to areas of the search space more likely to have a match. Once areas are identified that likely include a match, the system and the method use a more accurate similarity function to identify patch matches.

Description

Background technique [0001] Many software applications exist to help users create and edit images and videos using various editing tools. The capabilities of these tools range from preliminary resizing and cropping to more complex lighting adjustments and object manipulation. Patch matching is a process often used in image editing software. Patch matching searches for parts of images that share one or more attributes. Patch matching techniques allow removing unwanted objects from images, drawing new objects to match images, stereo matching, texture synthesis, and altering digital images in various ways. [0002] Patch matching searches for similar image patches based on spatial coherence. Specifically, conventional patch matching is based on using random sampling to find a good match and using the natural consistency in the image to quickly propagate this match to surrounding regions. Conventional patch matching scans over corresponding image patches of a digital image and...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T11/00G06K9/62G06V20/00G06V10/764
CPCG06T11/00G06F18/22G06V20/00G06V10/761G06V10/764G06T5/005G06T11/60G06T11/001G06F18/2415
Inventor N·卡尔K·桑卡瓦利M·卢卡克E·舍施特曼
Owner ADOBE SYST INC
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com