Image classification method

A classification method and image technology, which are applied in the fields of instrument, calculation, character and pattern recognition, etc., to achieve the effect of fast coding, shortening training time, and improving classification accuracy

Active Publication Date: 2015-07-15
厚普清洁能源(集团)股份有限公司
View PDF5 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But the vision of the robot is incompa

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
  • Image classification method
  • Image classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] In order to describe the content of the present invention conveniently, some terms are explained first.

[0025] Feature area: The feature area is a grid that is evenly divided on the image, and these grids contain the edge texture and direction information of the image. These information are very stable for a specific image, they represent the general outline of the image, and have good discrimination.

[0026] Feature descriptor: The feature descriptor (Descriptor) is a quantitative data description of the local features near the feature area. A good feature descriptor should be able to fully express the shape and texture structure of the local image of the feature point, with high robustness, uniqueness and distinction. In layman's terms, it is to use a vector to represent the characteristics of a local area.

[0027] Sparse coding: Due to the sparsity of natural image signals, the image signal I(x,y) can be decomposed into a linear combination of a set of bases. ...

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 classification method. An SPM framework is reserved, a covariance matrix feature extraction technology and an LLC (locality-constrained linear coding) technology are combined on the basis of an SIFT (scale invariant feature transform) feature extraction technology, and multiple covariance matrix features are fused and are not sensitive to the scale, rotation and illumination change. LLC is high in coding speed and high in efficiency and lays a foundation for linear classification. The training time is shortened due to usage of a linear classifier, and the system robustness is enhanced while the classification accuracy is increased.

Description

technical field [0001] The invention belongs to the technical field of digital image processing. Background technique [0002] Image understanding is a process of transforming "pixel value determination": it converts the image representation in the form of icons into another form of knowledge symbols, that is, what content is contained in each pixel block of the image. Among them, image classification is a branch of image understanding, which has a wide range of applications in content-based image retrieval, object classification and recognition, and scene classification. In computer vision, a fundamental problem is how to make computers "see" like humans. In practice, although we receive huge amounts of visual data every second, we hardly realize that we are processing them at a fairly rapid rate. It is very easy to classify objects, such as tables, ping pong balls, or a scene of mountains and flowing mountains. But the current vision of robots is incomparable with that ...

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
IPC IPC(8): G06K9/62
Inventor 解梅马争张达明于国辉
Owner 厚普清洁能源(集团)股份有限公司
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