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

Feature fusion identification method and device based on D-S evidence theory

A technology of evidence theory and feature fusion, applied in character and pattern recognition, instruments, computer components, etc.

Active Publication Date: 2018-11-06
GUANGDONG UNIV OF TECH
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] A feature fusion recognition method based on D-S evidence theory provided by the present invention solves the problem that existing methods are mainly based on template matching, feature point and edge detection, etc.

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
  • Feature fusion identification method and device based on D-S evidence theory
  • Feature fusion identification method and device based on D-S evidence theory
  • Feature fusion identification method and device based on D-S evidence theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] In order to make the purpose, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the following The described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0065] figure 1 It is a flowchart of an embodiment of a feature fusion recognition method based on D-S evidence theory in the present invention. A feature fusion recognition method based on D-S evidence theory provided by an embodiment of the present invention may include:

[0066] 100: Perform geometric normalization on the training sam...

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 a feature fusion identification method and device based on the D-S evidence theory. Through combining rotation, scaling and translation invariance of the invariant moment and HOG features and utilizing incomplete and uncertain combination advantages of the D_S evidence theory, final identification is obtained according to decision rules, identification accuracy of low quality images is effectively improved, and better robustness is realized compared with single feature identification.

Description

technical field [0001] The present invention relates to the field of image detection, in particular to a target detection method, equipment and computer-readable storage medium. Background technique [0002] For vehicle logo recognition, existing methods are mainly based on template matching, feature points and edge detection. Template matching is a relatively traditional image classification method. Wang et al. proposed a method for vehicle logo classification using template matching and edge direction histograms. However, this method usually requires the collection of a large number of template samples, which is time-consuming. Psyllos et al. proposed a SIFT-based enhanced matching algorithm to improve the recognition accuracy, but the algorithm based on feature points has a relatively high accuracy for the original image. Resolution, for low-resolution image recognition effect is relatively poor. With the development of deep learning, a new method is provided for extrac...

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
CPCG06V2201/08G06F18/25G06F18/257G06F18/253
Inventor 程良伦陈仿雄
Owner GUANGDONG UNIV OF TECH