Method and device for automatic semantic annotation of image, and computer equipment

A semantic annotation and image technology, applied in the field of image processing, can solve the problems of limited feasibility, large human resources, consumption, etc., and achieve the effect of eliminating manual operations and having a wide range of uses

Active Publication Date: 2016-09-07
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF5 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the huge number of images in the image database, manually determining the salient region for each image will obviously consume a lot of human resources, which limits the feasibility of this solution

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 automatic semantic annotation of image, and computer equipment
  • Method and device for automatic semantic annotation of image, and computer equipment
  • Method and device for automatic semantic annotation of image, and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0047] First look at a typical application environment of the present invention, such as figure 1 shown. It shows two computer devices 1 and 2, and a network 3, the computer devices 1 and 2 are interconnected through the network 3, and the network 3 is also connected to other network elements or devices not shown in the figure. In this example, computer device 1 is a server of a search engine operator, and the operator maintains image data through the server. These image data are generally marked with image semantics, so that end users can use computer device 2 (such as a personal computer or other smart device) during image search. For example, if a user searches for the keyword "Tesla" through the computer device 2, images matching the semantics will be displayed on the computer device 2 as search results.

[0048] In order to continuously update ...

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 embodiment of the invention provides a method for training an image semantic annotation device, and the method comprises the steps: a, providing a plurality of training images, wherein the semantic and visual attribute description of each training image is known; b, enabling at least a part of the training images to be inputted to a positioner of the image semantic annotation device; c, enabling the positioner to determine at least one local area of each inputted training image, and inputting the determined local regions into an attribute predictor of the image semantic annotation device; d, obtaining the visual attribute prediction result of each inputted local region through the attribute predictor; e, training the positioner and the attribute predictor according to an obtained visual attribute prediction result of each local region and the known visual attribute description of the corresponding training images.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method and device for automatic semantic labeling of images and computer equipment including the device. Background technique [0002] In the past ten years, with the rapid development of computer network technology, popularization and application, and the sharp decline in the cost of data storage, the use of multimedia databases has become more and more common. Multimedia information presented in the form of images, music, and video plays an increasingly important role in both business and entertainment. How to effectively manage and organize such a large amount of data, and search out the information that users need has become a very important issue. There has been a long history of research on browsing, searching and indexing technologies for multimedia data, especially image data. Today, the topic of image databases and visual information search has become the most active ...

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): G06K9/32G06K9/62G06F17/30
CPCG06F16/532G06F16/951G06V10/25G06F18/2411G06V20/10G06V20/70G06F40/169G06F18/241
Inventor 刘霄王江文石磊丁二锐
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
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