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

Generation of annotation tags based on multimodal metadata and structured semantic descriptors

A metadata and annotation technology, applied in the field of annotation tags, can solve the problems of user privacy, potential data access/transmission delay, etc.

Active Publication Date: 2014-09-03
TELEFON AB LM ERICSSON (PUBL)
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Furthermore, known methods typically rely on network-provided metadata (e.g., aggregated databases of tag processing information) from the user community, which is disadvantageous in terms of user privacy as well as in terms of potential data access / delivery delays

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
  • Generation of annotation tags based on multimodal metadata and structured semantic descriptors
  • Generation of annotation tags based on multimodal metadata and structured semantic descriptors
  • Generation of annotation tags based on multimodal metadata and structured semantic descriptors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] figure 1 An electronic device 10 is illustrated. In an advantageous but non-limiting embodiment, device 10 comprises a camera phone or other mobile terminal with image capture capabilities. Although the specific architecture and functional units of device 10 may vary depending on the intended purpose, as contemplated herein, device 10 includes a processing device 12 for generating annotation labels for digital images. A "digital image" as used herein includes both individual still images and associated image sequences (eg, in MPEG movie files).

[0017] Processing device 12 includes embedded electronic circuitry such as microprocessors, digital signal processors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), programmable logic devices (PLDs), and the like. The processing device 12 includes or is associated with a memory 14 for maintaining a library 16 of human meaningful words or phrases organized as category entries accordi...

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

In one embodiment, a method for generating annotation labels (28) for digital images (22) includes maintaining a library (16) of human-meaningful words or phrases according to a plurality of definitions The image description categories (70) are organized into category entries (72); and contextual metadata (20) associated with the capture of a given digital image (22) is received. The method further includes selecting class-specific entries (72-1, 72-2) as lexical elements of the digital image (22) by mapping the contextual metadata (20) into the library (16). data (24); and generating annotation labels (28) for the digital image (22) by logically combining the lexical metadata (24) according to a defined set of derivation logic rules (30), the derivation Logical rules are based on said defined image description categories (70). In another embodiment, a processing device (12), such as a digital processor (18, 26) and supporting memory (14), etc., is configured to perform the method described above, or to perform a variation of the method described above.

Description

technical field [0001] The present invention relates to digital images and their capture, and in particular, to generating annotation tags for digital images. Background technique [0002] The development of digital photography and video over the past decade or so has brought many new and interesting challenges to how people organize, store and retrieve their multimedia libraries. Unlike textual data, automated methods for describing, indexing, and retrieving visual media such as image and video content have so far been limited. Existing multimedia search engines typically rely on manually generated text-based annotations (backed at best by EXIF ​​data) such as when the capture was made, camera model used, and so on. [0003] Photoblogging sites such as Flickr also take advantage of location tagging through support map tools, but still require authors to manually place user-generated content on a global map, which is a practically tedious task for users . Some professiona...

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 Patents(China)
IPC IPC(8): G06F17/24G06F17/30G06K9/00H04N1/32G06F16/51G06F16/58G06F18/00
CPCG06F17/3028G06F17/30265G06F16/51G06F16/58
Inventor 约金·索德博格安德雷斯·法斯本德尤纳斯·约克
Owner TELEFON AB LM ERICSSON (PUBL)