Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image classification method based on sparse nonlinear subspace migration

A classification method and subspace technology, which is applied in the directions of instruments, computing, character and pattern recognition, etc., can solve the problem of low accuracy of the subspace migration method, and achieve the effect of improving accuracy

Inactive Publication Date: 2017-01-11
CHONGQING UNIV
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In fact, subspace independence and sufficient data are difficult to satisfy, so the accuracy of the subspace transfer method based on low-rank representation is low

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 sparse nonlinear subspace migration
  • Image classification method based on sparse nonlinear subspace migration
  • Image classification method based on sparse nonlinear subspace migration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] Below in conjunction with accompanying drawing and embodiment the present invention will be further described:

[0049] The present invention first maps data from the original space to the regenerated Kernel Hilbert space (RKHS) through the kernel method, and then through such as figure 2 The transformation shown, in the kernel Hilbert space, consists of a pre-defined basis transformation P that transforms the target domain training data X T The target data PX is obtained by mapping the basic transformation P to the preset subspace T , the source domain training data X S Get PX by mapping the basic transformation P to the preset subspace S , due to the present invention through the source domain and target domain data P[X S ,X T ] to reconstruct the target data, so P[X S ,X T ] is also collectively referred to as source domain data, and then use source domain data P[X S ,X T ] Transformed by the sparse matrix Z, and PX T Share distributions within preset subsp...

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 sparse nonlinear subspace migration. The method comprises the steps of mapping data from an original space to a regenerated kernel Hilbert space via a kernel method, mapping target domain training data XT to a preset subspace via predefined fundamental transformation P in the kernel Hilbert space to obtain target data PXT, mapping source domain training data XS to the preset subspace via the fundamental transformation P to obtain P[XS, XT], transforming the source domain data P[XS, XT] via a spare matrix Z, and distributing the P[XS, XT] and the PXT in the preset subspace in a sharing mode. The method has the advantages of improving the migration accuracy of image data in the preset subspace and being applicable to transformation of nonlinear data.

Description

technical field [0001] The invention belongs to an image classification method, in particular to an image classification method based on sparse nonlinear subspace transfer. Background technique [0002] Generally speaking, the data collected when the sensor does not drift is called the source domain, and the data obtained after the sensor drifts after a period of use is called the target domain. In the image field, any posture of an object can be called the source domain, and another posture obtained by changing external conditions (such as angle, light intensity, background color change, etc.) is called the target domain. The basics of image classification The task is to be able to find these similar objects in different states. [0003] For simplicity of description, the present invention stipulates: [0004] "S" represents the source domain, "T" represents the target domain; the source domain training data is denoted as The target domain training data is denoted as ...

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): G06K9/62G06K9/00
CPCG06V20/64G06V40/172G06F18/24G06F18/214
Inventor 张磊邓平聆段青言
Owner CHONGQING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com