Image annotation method and electronic device

An image annotation and image technology, applied in character and pattern recognition, instruments, computing, etc., can solve problems such as difficult image description, and achieve the effect of improving user experience

Active Publication Date: 2019-03-08
LENOVO (BEIJING) LTD +1
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when it comes to the annotation of image abstract concepts (such as eating, business trip, group photo, etc.), based on a small amount of information such as vision and camera parameters, it is difficult to make an accurate and comprehensive description of the image

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
  • Image annotation method and electronic device
  • Image annotation method and electronic device
  • Image annotation method and electronic device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0088] Such as figure 1 As shown, the image labeling method according to the embodiment of the present invention includes:

[0089] Step S101: Acquiring the first image to be labeled;

[0090] Step S102: Obtain multiple different types of information related to the first image, each of the multiple different types of information is used to mark one or more abstract concept types involved in the first image;

[0091] Step S103: Perform probability inference on the abstract concept types of the first image according to the acquired information of various types, so as to obtain the probability distribution of each abstract concept type in the first image;

[0092] Step S104: Determine the correlation between each abstract concept type;

[0093] Step S105: According to the determined correlation, the joint probability of each abstract concept type is maximized, so as to determine the labeling result of the first image.

[0094] Specifically, in step S101, the user may take a ph...

no. 2 example

[0149] The following will refer to Figure 5 An electronic device according to an embodiment of the present invention is described. Such an electronic device may be any electronic device, such as a smart phone, a tablet computer, a Pad computer, etc., as long as the electronic device has computing capability.

[0150] Such as Figure 5 As shown, the electronic device 500 according to the embodiment of the present invention includes:

[0151] An electronic device 500 according to an embodiment of the present invention includes:

[0152] An image acquisition unit 501 configured to acquire a first image to be marked;

[0153] The relevant information acquiring unit 502 is configured to acquire multiple different types of information related to the first image, each of the multiple different types of information is used to mark one or more abstractions involved in the first image concept type;

[0154] The probability determination unit 503 is configured to perform probabilit...

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 an image labeling method and electronic equipment. The method includes: acquiring a first image to be labeled; acquiring multiple different types of information related to the first image, each of the multiple different types of information is used to label the first image related to one or more abstract concept types; perform probability inference on the abstract concept types of the first image according to the acquired information of the plurality of types, so as to obtain a probability distribution of each abstract concept type of the first image; determine The correlation between each abstract concept type; and according to the determined correlation, maximizing the joint probability of each abstract concept type, so as to determine the labeling result of the first image.

Description

technical field [0001] The present application relates to an image labeling method and an electronic device. Background technique [0002] At present, with the popularization of portable devices (such as smart phones, tablet computers, etc.) with camera functions, the number of digital images is increasing rapidly. The richness and accuracy of labeling these images is related to the efficiency of users in various operations such as image retrieval, sorting and classification. [0003] The traditional image annotation technology mainly focuses on annotating the image by using the visual information of the image or some parameters when the camera takes pictures. However, when it comes to labeling abstract concepts of images (such as meals, business trips, group photos, etc.), based on a small amount of information such as vision and camera parameters, it is difficult to make an accurate and comprehensive description of the image. [0004] For this reason, it is desirable to ...

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): G06K9/62G06K9/00
CPCG06V20/20G06F18/2415
Inventor 蒋树强徐瑞邯闵巍庆贺志强
Owner LENOVO (BEIJING) 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