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

Method and device for identifying content attribute of image

A content attribute, image technology, applied in the field of image processing

Active Publication Date: 2013-10-30
FUJITSU LTD
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, how to quickly and accurately retrieve these images and videos has become a key issue restricting content sharing

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
  • Method and device for identifying content attribute of image
  • Method and device for identifying content attribute of image
  • Method and device for identifying content attribute of image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Embodiments of the present invention will be described below with reference to the drawings. It should be noted that representation and description of components and processes that are not related to the present invention and known to those of ordinary skill in the art are omitted from the drawings and descriptions for the purpose of clarity.

[0027] figure 2 is a flowchart illustrating a method of identifying content attributes of an image according to an embodiment of the present invention. In step S210, the top K training images most similar to the image to be labeled are searched from the training image database as adjacent images of the image to be labeled, where K>1; in step S220, the weights of the adjacent images are determined in the following manner: adjacent The weighted average of the image features of the image based on these weights is closest to the image features of the image to be labeled; in step S230, at least one content attributes as identified ...

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 invention provides a method and device for identifying a content attribute of images. The method comprises the steps that front K training images which are most similar to images to be marked are searched from a training image base to be used as adjacent images of the images to be marked, wherein K is larger than 1; weights of the adjacent images are determined through the following method; a result which is averagely obtained by conducting weighting on the image features of the adjacent images based on the weights is most close to the image features of the images to be marked; according to a weight sum which is obtained in the mode that the determined weights are used for conducting weighting on the content attributes of the adjacent images, at least one content attribute is determined and then used as an identified content attribute.

Description

technical field [0001] The present invention relates generally to image processing, and more particularly to methods and apparatus for identifying content attributes of images. Background technique [0002] With the rapid development and popularization of digital camera equipment, especially smart phones with camera functions, hundreds of millions of digital images and videos are generated every day in various application fields and occasions. In addition, the development of social networks such as Weibo and flickr has greatly promoted the sharing of images and videos, and people have become accustomed to uploading images and videos taken by themselves to the Internet for others to browse. Hence, a large amount of images and videos are accumulated on these social networking sites. However, how to quickly and accurately retrieve these images and videos has become a key issue restricting content sharing. [0003] Image content attribute recognition (image annotation) is an e...

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): G06K9/66
Inventor 刘汝杰于浩
Owner FUJITSU LTD