Sketch-based image search

An image and sketch technology, applied in the field of image search, can solve problems such as inability to implement scalable index solutions, unmanageable size or complexity, comparison, etc.

Active Publication Date: 2012-02-01
MICROSOFT TECH LICENSING LLC
View PDF2 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, some proposed techniques lack efficient edge representations and cannot quickly and accurately compare input sketches with indexed images
Other proposed techniques do not enable scalable indexing solutions, resulting in indexes with unmanageable size or complexity when applied to millions of images

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
  • Sketch-based image search
  • Sketch-based image search
  • Sketch-based image search

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Sketch Based Search

[0027] The techniques described herein are generally directed to techniques for sketch-based image search. Some implementations employ salient curve discovery schemes to detect dominant or salient curves in natural images to allow efficient indexing and representation of images. Furthermore, some implementations apply primitive curve-based procedures to compute the similarity between the query sketch input and the curves generated for natural images. Additionally, a user interface may be provided to allow the user to flexibly formulate queries using any combination of sketch input, text input, and color selection input.

[0028] To index millions of images and to enable real-time response to sketch-based queries, some implementations utilize a position-sensitive curvilinear indexing framework designed to consider storage cost, image retrieval accuracy, and computational efficiency. The indexing techniques disclosed herein can be used to create ma...

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

Sketch-based image search may include receiving a query curve as a sketch query input and identifying a first plurality of oriented points based on the query curve. The first plurality of oriented points may be used to locate at least one image having a curve that includes a second plurality of oriented points that match at least some of the first plurality of oriented points. Implementations also include indexing a plurality of images by identifying at least one curve in each image and generating an index comprising a plurality of oriented points as index entries. The index entries are associated with the plurality of images based on corresponding oriented points in the identified curves in the images.

Description

technical field [0001] The present invention relates to image search, and more particularly to sketch-based image search. Background technique [0002] With the increasing popularity of electronic imaging devices and the Internet, billions of digital images have become publicly available and searchable online. Indexing such a huge amount of data to enable users to find desired images quickly is a huge and difficult task. For example, many images are posted without accurate descriptions or labels, making it difficult to index these images using typical keyword techniques. Therefore, when a user wishes to locate a complex image with specific characteristics, conventional text-based search engines that rely on short text queries are often unable to locate the desired image in a timely and efficient manner. [0003] Additionally, although sketch-based search of image databases has been intensively studied, little progress has been made in developing practical large-scale sketc...

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): G06F17/30
CPCG06F17/30259G06F17/30277G06F16/5854G06F16/532G06V30/32
Inventor 王长虎李志伟张磊
Owner MICROSOFT TECH LICENSING LLC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap