A Yao nationality pattern symbol recognition method based on target detection

A target detection and pattern technology, applied in character and pattern recognition, neural learning methods, instruments, etc., can solve problems such as slow detection speed, achieve the effect of improving efficiency, flexible and convenient expansion and update, and reducing feature loss

Active Publication Date: 2022-04-26
GUILIN UNIV OF ELECTRONIC TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

One of the two-stage target detection algorithms represented by R-cnn and Faster-cnn can roughly determine the area of ​​​​the object to be detected, saving processing time for the subsequent classification and regression stages, but the detection speed slower

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 Yao nationality pattern symbol recognition method based on target detection
  • A Yao nationality pattern symbol recognition method based on target detection
  • A Yao nationality pattern symbol recognition method based on target detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0025] refer to figure 1 , a target detection-based positioning and recognition method for Yao pattern symbols, comprising the following steps:

[0026] 1) Input the pictures of Yao patterns and symbols: Take multiple pictures of Yao patterns and symbols with a mobile phone, mark the pictures with the types of Yao patterns and symbols, divide the marked pictures into a training set and a test set, the training set is used for model training, and the test set is used for model training. model predictions;

[0027] 2) Data enhancement: Data enhancement can increase the diversity of data, enhance the robustness of simulation, reduce the sensitivity of the model to parameters, improve the generalization ability of the model, and flip and zoom the pictures on the marked training set , rotation, brightness, and shift changes are the same, using data enhancement to make limited data equivalent to more data;

[0028] 3) Model training: Input the training set pictures after data enha...

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 target detection-based positioning and recognition method for the pattern symbols of the Yao nationality, which is characterized in that it comprises the following steps: 1) inputting a picture of the pattern symbols of the Yao nationality; 2) data enhancement; 3) model training; for positioning and forecasting. This method uses feature fusion to reduce the problem of feature loss in the convolution process, enhance the detection of small targets of Yao pattern symbols, and improve detection accuracy and speed.

Description

technical field [0001] The invention relates to image classification technology, in particular to a method for recognizing patterns and symbols of the Yao nationality based on target detection. Background technique [0002] Modernization is a worldwide historical process, and national symbols, as the representation of a nation, inherit the spirit of a nation and are an important element for the continuation of a nation. Ethnic minorities embody their religious culture and totem culture in the patterns of clothing and architectural decoration, which not only beautifies themselves, but also convey special meaning. However, due to the complex and changeable features such as the shape, structure, and color of the Yao pattern symbols, the detection rate is not high. [0003] In existing technologies, conventional algorithms such as SIFT, HOG, and Haar-like, etc., have a huge amount of calculation, and also generate redundant windows, and because of the diversity of illumination ...

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): G06V10/44G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V10/449G06N3/048G06N3/045G06F18/241
Inventor 王鑫颜靖柯覃琴
Owner GUILIN UNIV OF ELECTRONIC 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