A pattern recognition method and device

A pattern recognition and pattern matching technology, applied in the field of pattern recognition, can solve the problems of poor convergence effect and low recognition accuracy, and achieve the effect of improving clustering performance

Active Publication Date: 2020-11-13
GEER TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a method and device for pattern recognition to solve the problems of poor convergence effect and low recognition accuracy of kernel possibility fuzzy C-means clustering algorithm in the prior art

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 pattern recognition method and device
  • A pattern recognition method and device
  • A pattern recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The technical idea of ​​the present invention is to propose a solution to the problems existing in the improved VQ algorithm, such as the KPFCM (Kernel Possibility Fuzzy C-Means) clustering algorithm. The inventors of the present application found that: although KPFCM has made great progress compared with the traditional method, the parameters of the kernel function of the KPFCM clustering algorithm are fixed, which cannot accurately reflect the discreteness of the feature data itself, and the convergence result is easy to fall into a local optimum Excellent, which limits the performance of clustering.

[0019] For this reason, for the parameter setting of the kernel function of the KPFCM algorithm is fixed, the distribution characteristics of the feature data itself cannot be fully utilized, and the clustering result is difficult to achieve the optimal defect. This embodiment proposes an adaptive kernel possibility fuzzy C-means aggregation Class algorithm (Adaptive Ke...

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 pattern recognition method and device. The pattern recognition method includes: performing feature extraction on input training data, performing cluster analysis through an adaptive kernel possibility fuzzy C-means clustering algorithm, establishing a reference model and saving it to A reference model database; performing the same feature extraction on the input test data to obtain a test feature vector, performing pattern matching on the test feature vector and each reference model in the reference model database, and obtaining a pattern recognition result. The pattern recognition device includes: a training unit and a recognition unit. The scheme of this embodiment uses the adaptive kernel possibility fuzzy C-means clustering algorithm (AKPFCM) to establish a reference model after clustering analysis, and can adaptively adjust the parameters of the kernel function according to the distribution of the characteristic data, so as to achieve better performance for the characteristic data. The clustering can effectively improve the clustering performance.

Description

technical field [0001] The invention relates to the technical field of pattern recognition, in particular to a pattern recognition method and device. Background technique [0002] With the development of information technology, pattern recognition has more and more extensive demands. After extracting the features of the signal, it needs to be recognized reliably through a suitable pattern matching method. Commonly used pattern recognition methods mainly include: template matching, vector quantization (Vector Quantization, referred to as VQ), probability statistics model method, artificial neural network and support vector machine (Support Vector Machine, referred to as SVM). Among them, VQ forms a codebook that can characterize the pattern by performing cluster analysis on the feature vectors extracted from the signal to be identified. Cluster analysis is an important method in unsupervised pattern recognition, which has been widely used in data mining, image processing, a...

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
CPCG06F18/23213
Inventor 苏鹏程张一凡
Owner GEER TECH CO LTD
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