Image classification method based on tree structure and system using same

A classification method and classification system technology, applied in the field of computer vision, can solve problems such as classification problems that cannot effectively deal with massive categories, and achieve the effect of reducing computational complexity and improving classification performance.

Active Publication Date: 2013-09-25
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a tree structure-based image classification method and its system, which are used to overcome the classification problem that the existing codebook (feature) learning cannot effectively deal with massive categories

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 classification method based on tree structure and system using same
  • Image classification method based on tree structure and system using same
  • Image classification method based on tree structure and system using same

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The technical solution of the present invention will be further described in more detail below in conjunction with the drawings and specific embodiments.

[0038] Such as figure 1 Shown is a flowchart of the image classification method based on a tree structure of the present invention. The method includes the following steps:

[0039] Step 101: Provide a sample set with label information and a semantic tree structure constructed according to the semantic relevance of the label information;

[0040] Step 102: Obtain a set of supervised codebook and classifier models through model training according to the sample set and the semantic tree structure;

[0041] Step 103: For the test image, use the supervised codebook group obtained by training to generate an intermediate layer feature representation, and use the classifier model to predict the category label of the test image based on the intermediate layer feature representation.

[0042] Such as figure 2 Shown is the structure d...

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 discloses an image classification method based on a tree structure and system using the method. The method includes the first step of providing a sample set with label information and building a semantic tree structure according to semantic correlation of the label information; the second step of obtaining a set of supervised codebooks and classifier models through model training according to the sample set and the semantic tree structure; the third step of generating multiple middle layer feature representations of an image to be tested through the supervised codebooks obtained from the model training, and predicting a classification label of the image to be tested by means of the classifier models according to the middle layer feature representations. The image classification method solves the classification problem that existing codebook (feature) learning can not effectively respond to massive classification.

Description

Technical field [0001] The present invention relates to image classification and recognition technology in the field of computer vision, in particular to an image classification method and system based on a tree structure. Background technique [0002] Image classification is an important research topic in the field of computer vision and machine learning. For classification tasks, features play a vital role. The visual bag-of-words feature based on local features (Mid-level feature) is a commonly used feature for image classification problems. Existing work uses codebook-based unsupervised sparse coding to generate intermediate layer features for classification tasks, and achieves better results. However, traditional image classification algorithms often target fewer categories, and use unsupervised sparse coding to generate intermediate layer features combined with a simple binary classifier model to achieve better results. However, there are many categories in the real worl...

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): G06K9/66
Inventor 王树徽申丽黄庆明蒋树强
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI
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