A pca-based optimal classification and recognition method for svm cloud particles

A technology of classification, recognition and particle, applied in character and pattern recognition, instruments, computing, etc., can solve the problems of less application of CPI cloud particle classification, lack of targeted preprocessing of CPI cloud particle raw data, large noise of raw data, etc. , to achieve the effect of improving the efficiency of classification and recognition

Active Publication Date: 2021-06-15
CHENGDU UNIV OF INFORMATION TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Among image classification and recognition technologies, decision tree methods, random forest integration methods, support vector machine methods, neural network-based methods, etc., are widely used in the detection of parts precision instruments, face, license plate recognition, tumor detection and other fields. However, there are few applications in the classification of CPI cloud particles
Moreover, all kinds of methods are basically based on the original data of CPI cloud particles for training and learning, and these original data generally have relatively large noise, and the lack of targeted preprocessing of the original data of CPI cloud particles in existing methods is also a major problem
In addition, there is no related method for multi-classification of cloud particle morphology and identification of pictures of broken ice crystal particles, and this problem needs to be solved urgently

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 pca-based optimal classification and recognition method for svm cloud particles
  • A pca-based optimal classification and recognition method for svm cloud particles
  • A pca-based optimal classification and recognition method for svm cloud particles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] 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. The method includes the following steps:

[0036] Step 1: Carry out cloud particle segmentation on the CPI image, including:

[0037] Step 1.1: Carry out grayscale processing to CPI image, concrete method is to convert RGB three-channel CPI image into single-channel grayscale image;

[0038] Step 1.2: Binarize the CPI grayscale image, first extract 10 cloud particle images I in the CPI grayscale image p , for 10 frame I p The pixel values ​​in the image are sorted from large to small according to the gray value, and the 5% pixels with the largest gray value are selected to calculate the average gray value avg(I p ), and then with the background image gray value mean avg(I bg ) to compare and calculate a fixed threshold Th, where the background image I bg for the s...

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 relates to a PCA-based SVM cloud particle optimization classification and recognition method, which mainly includes firstly segmenting the cloud particle image on a CPI image, then delabeling the segmented cloud particle image, and then classifying the SVM cloud particle image based on PCA dimensionality reduction Identification. Due to the lack of targeted preprocessing of the raw data of CPI cloud particles in the existing methods, this method can effectively classify cloud particles and identify pictures of broken ice crystal particles.

Description

technical field [0001] The invention belongs to the field of shape classification of cloud particles, in particular to fast and efficient ice crystal shape recognition and classification based on artificial intelligence algorithms for ice crystal particle images detected by airborne CPI. Background technique [0002] Image classification and recognition technology is an important field of artificial intelligence. It refers to the object classification of images to identify various patterns of targets and objects. The development of image classification and recognition technology has mainly gone through three stages: the stage of digital text recognition (started in 1950), the stage of digital image processing and recognition (started in the late 1960s), and the stage of natural image recognition (started in 1970). ), in general, image recognition technology has been developed for more than half a century, and it is widely used in military, medical, meteorological, transport...

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): G06K9/62G06K9/34G06K9/38
CPCG06V10/26G06V10/28G06F18/2411
Inventor 刘说赵德龙吴泽培杨玲何晖黄梦宇周嵬丁德平陈青青
Owner CHENGDU UNIV OF INFORMATION TECH
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