Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Semantic representation of the content of an image

An image content and image technology, which is applied in still image data retrieval, vector format still image data, special data processing applications, etc. performance degradation, etc.

Inactive Publication Date: 2017-12-01
COMMISSARIAT A LENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Nevertheless, the method of defining "metaclasses" does not ensure a diverse representation of image content
In addition, quantization also leads to performance degradation
[0011] Current state-of-the-art rarely addresses aspects related to the diversity of image searches

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
  • Semantic representation of the content of an image
  • Semantic representation of the content of an image
  • Semantic representation of the content of an image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] figure 1 Illustrates the classification or annotation of the document. In the example considered, the file is an image 100 . The label 130 of the document indicates its degree of membership in each category 110 considered. For example, by considering four categories (here "wood", "metal", "soil" and "cement"), the label 120 of the annotation file 100 is a four-dimensional vector 140, each component of which is a probability (if the file does not corresponds to a category, equals 0, and equals 1 if the file corresponds to a category in a certain way).

[0030] figure 2 An example of supervised classification is shown. The method comprises in particular two steps: a first so-called training step 200 and a second so-called testing step 210 . The training step 200 is usually performed "off-line" (that is to say, on a previous basis or in advance). The second step 210 is usually performed "on-line", ie in real time during the actual searching and / or sorting steps.

...

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 discloses a method implemented by computer for semantically describing the content of an image comprising the steps consisting of receiving a signature associated with said image; receiving a plurality of groups of initial visual concepts; the method being characterised by the steps consisting of expressing the signature of the image in the form of a vector comprising components referring to the groups of initial visual concepts; and modifying said signature by applying a filtering rule that is applied to the components of said vector. Developments describe, in particular, filtering rules that involve filtering by thresholds and / or by intra-group or inter-group order statistics, partitioning techniques including the visual similarity of the images and / or the semantic similarity of the concepts, and the optional addition of manual annotations to the semantic description of the image. The advantages of the method in terms of sparse and diversified semantic representation are presented.

Description

technical field [0001] The present invention relates generally to the technical field of data mining, and in particular to the technical field of automatic annotation of image content. Background technique [0002] A "multimedia" document includes a variety of information by etymology, usually related to different sensory or cognitive abilities (for example, related to vision or hearing). A multimedia file can be, for example, an image accompanied by a "markup", that is to say by annotations, or correspond to a web page comprising images and text. [0003] Digital files can typically be divided into several "channels" of information, which can include, for example, textual information (eg, derived from OCR character recognition) and visual information (eg, illustrations and / or photographs identified in the file). A video can also be divided into several such channels: a visual channel (e.g., the frames of a video), an audio channel (e.g., an audio channel), a textual channe...

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): G06F17/30G06K9/62G06N20/00G06V10/70
CPCG06F16/5838G06F16/56G06N20/00G06V10/70G06V30/413G06V30/274
Inventor A·波佩斯库N·巴拉A·L·金斯卡H·勒博涅
Owner COMMISSARIAT A LENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com