Efficient local feature descriptor filtering

a local feature and filtering technology, applied in still image data indexing, instruments, computing, etc., can solve the problems of high computational load, time-consuming manual image annotation, high computational complexity to compare all features descriptors from one image, etc., to achieve fast and accurate image retrieval, fast and computational efficient

Active Publication Date: 2016-08-11
SONY CORP
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

[0012]The present invention is based on the realization that by utilizing clusters, where similar images are already grouped together, an efficient feature vector or feature descriptor filtering can be achieved by guiding the filtering algorithm toward the relevant features (SIFT, SURF or other feature descriptors). This will in the end make a very fast and also accurate image retrieval system, where similar objects, faces, buildings etc. can be found.
[00

Problems solved by technology

Manual image annotation is time-consuming, laborious and expensive.
One problem that often occurs in such CBIR system is the sheer computational complexity to compare all features descriptors from one image, with all the featu

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
  • Efficient local feature descriptor filtering
  • Efficient local feature descriptor filtering
  • Efficient local feature descriptor filtering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025]FIG. 1 describe by way of example a way of clustering similar images in order to guide a filtering algorithm for feature vectors towards relevant feature vectors. As described above, such an approach may efficiently remove pointless feature vectors, e.g. on grass, water and other moving textures, which do not describe valuable features of the images in the cluster. By employing such filtering, efficient searching for a similar image among a plurality of stored images may be facilitated. The first step of the method is to, for each stored image, calculating S102 only one feature vector representing the content of the stored image. The feature vector may be a global feature vector, which describe the entire content of the stored image in a good way. There are many suitable available algorithms for calculating such global feature vector. For example, a color histogram of the image can be calculated. Further examples of a global feature vector are a vector describing a mini-thumbn...

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 disclosure generally relates to methods and computer program products for searching for a similar image among a plurality of stored images, and in particular to a method and computer program product used in a content based image retrieval system where roughly similar images are clustered and feature vectors for the clustered images are filtered based on a matching frequency for the feature vectors among the images in the cluster.

Description

TECHNICAL FIELD[0001]The present disclosure generally relates to methods and computer program products for searching for a similar image among a plurality of stored images, and in particular to a method and computer program product used in a content based image retrieval system where roughly similar images are clustered and feature vectors for the clustered images are filtered based on a matching frequency for the feature vectors among the images in the cluster.TECHNICAL BACKGROUND[0002]Searching for images similar to a certain image among a plurality of images is a well-used feature in today's image retrieval system. Most traditional and common methods of image retrieval utilize some method of manual image annotation which rely on that a person manually adds metadata such as keywords to the images so that retrieval can be performed over the metadata words. Manual image annotation is time-consuming, laborious and expensive.[0003]Instead, Content-based image retrieval (CBIR) system m...

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
IPC IPC(8): G06K9/62G06F17/30G06K9/52
CPCG06K9/6215G06K9/52G06F17/3028G06F17/30256G06K9/6218G06F16/5838G06F18/23G06F16/51G06F18/22
Inventor ENGSTRÖM, JIMMY
Owner SONY CORP
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