Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A Method of Automatic Image Annotation Based on Semantic Scene Classification

An image automatic labeling and semantic scene technology, which is applied in the field of image automatic labeling algorithm based on semantic scene classification, can solve the problem of label hard classification without considering the mapping relationship between labels and semantic scenes, so as to improve the efficiency of the algorithm, improve the effect of labeling, The effect of reducing noise disturbance

Active Publication Date: 2020-05-19
DALIAN UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Aiming at the problem of not considering the mapping relationship between tags and semantic scenes and the existing hard classification of tags in the image tagging problem, the present invention proposes an automatic image tagging method based on semantic scene classification

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
  • A Method of Automatic Image Annotation Based on Semantic Scene Classification
  • A Method of Automatic Image Annotation Based on Semantic Scene Classification
  • A Method of Automatic Image Annotation Based on Semantic Scene Classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The specific embodiments discussed are merely illustrative of implementations of the invention, and do not limit the scope of the invention. Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0056] The embodiment of the present invention in benchmark instance Iaprtc12 is as follows:

[0057] Symbolic representation: training set {X, Y}, test set {X′}, X represents the sample feature matrix, Y represents the label information of the training set, and X′ represents the test set feature matrix.

[0058] (1) Feature extraction

[0059] The five features of Gist (512D), DenseHue (100D), HarrisHue (100D), DenseSift (1000D) and HarrisSift (1000D) existing in the reference instance Iaprtc12 are used as the feature {X} of this embodiment.

[0060] (2) Scene detection example

[0061] According to the formula (1) and the label matrix Y to construct the label relationship graph C, according to the formula (2)...

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 belongs to the field of computer application and computational vision, and relates to an image automatic tagging algorithm based on semantic scene classification. This method uses the method based on non-negative matrix decomposition to detect the semantic scene information of the label, maps the training set samples to the corresponding scenes in a probabilistic manner, and uses the scene information of the samples to train the scene classifier based on the extreme learning machine and the differential evolution algorithm. Finally, the scene classifier is used to quickly map the samples to be labeled to a sample subset related to its scene, and the KNN-based algorithm is used to complete the labeling in this sample subset. The invention not only narrows the scope of searching for the nearest neighbor samples and improves the efficiency of the algorithm, but also enables the KNN algorithm to label semantically related sample sets, thereby reducing noise interference and improving the labeling effect. The number of scenes in this method is far less than the number of labels, so it solves the problem that the method based on model learning is not suitable for data sets with a large number of labels.

Description

technical field [0001] The invention relates to the fields of computer application and computer vision, and relates to an automatic image labeling algorithm based on semantic scene classification. Background technique [0002] It is a common and relatively simple and effective way to manage and retrieve images through image tags, but there are still a large number of unlabeled or incompletely labeled images on the Internet, so designing an effective automatic image labeling and classification algorithm is a solution to this problem. The key technology of the problem. In recent years, there has been a lot of research work on the problem of automatic image annotation. The main research methods can be divided into two categories: methods based on model learning and methods based on searching databases. [0003] The method based on searching the database directly provides label candidate sequences according to the labels of the marked images in the database, which is simple an...

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
CPCG06F18/241G06F18/214
Inventor 葛宏伟王志强孙玮婷孙亮
Owner DALIAN UNIV OF TECH
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
Eureka Blog
Learn More
PatSnap group products