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

An Automatic Image Annotation Method Based on Attribute Discrimination

An automatic image and image technology, applied in character and pattern recognition, instruments, calculations, etc., can solve problems such as automatic image labeling

Active Publication Date: 2019-01-22
FUZHOU UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide an automatic image labeling method based on attribute discrimination to overcome the defects in the prior art and solve the problem of automatic image labeling for multiple objects and multiple labels

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
  • An Automatic Image Annotation Method Based on Attribute Discrimination
  • An Automatic Image Annotation Method Based on Attribute Discrimination
  • An Automatic Image Annotation Method Based on Attribute Discrimination

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The technical solution of the present invention will be specifically described below in conjunction with the accompanying drawings.

[0037] The present invention provides an automatic image labeling method based on attribute discrimination, such as figure 1 As shown, aiming at the unsatisfactory overall labeling effect due to unbalanced datasets, an image labeling method based on attribute discrimination is proposed, using the semantic concept of each keyword to construct a locally balanced dataset, and based on this dataset, a A semantic propagation algorithm (Semantic Propagation, SP) that effectively improves the accuracy of low-frequency tag labeling. Finally, combined with the Stacked Auto-Encoder (SAE) model, different annotation processes are selected by discriminating the high and low frequency attributes of the image, which improves the overall image annotation effect. Specific steps are as follows:

[0038] S1: According to each keyword, the training set is...

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 relates to an automatic image labeling method based on attribute discrimination: aiming at the problem that the overall labeling effect is unsatisfactory due to unbalanced data sets, an image labeling method based on attribute discrimination is proposed, and the semantic concept of each keyword is used to construct a local equilibrium Data set, and based on this data set, a semantic propagation algorithm is proposed to effectively improve the accuracy of low-frequency tag labeling. Finally, combined with the stacked autoencoder model, different annotation processes are selected by discriminating the high and low frequency attributes of the image, which improves the overall image annotation effect. This method uses the characteristics of the SAE model to better predict high-frequency tags and the SP algorithm to better predict low-frequency tags, and selects different labeling processes by distinguishing the high- and low-frequency attributes of unknown images, which improves the labeling effect of the entire model. This method is simple and flexible. , has strong practicability.

Description

technical field [0001] The invention relates to the fields of pattern recognition and computer vision, in particular to an automatic image labeling method based on attribute discrimination. Background technique [0002] With the rapid development of multimedia image technology, image information on the Internet is growing explosively. These digital images are widely used in business, news media, medicine, education and so on. Therefore, how to help users quickly and accurately find the desired image has become one of the hot topics in multimedia research in recent years. The most important technology to solve this problem is image retrieval and automatic image annotation technology. [0003] Automatic image annotation refers to automatically adding several keywords to the image to represent the semantic content of the image. Automatic image annotation can use the labeled image set to automatically learn the relationship model between semantic concept space and visual feat...

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): G06K9/62
CPCG06F18/214
Inventor 柯逍周铭柯杜明智
Owner FUZHOU UNIV