Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A window counting method and device based on multi-category incremental learning

A technology of incremental learning and counting method, applied in the field of image processing and machine learning, which can solve the problems of being easily affected by human factors, unevenness, errors, etc. Effect

Active Publication Date: 2022-03-15
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The weighing method requires that the weight of the weighing object is basically the same and meets the minimum unit of measurement, but the felt pad is small in size and light in weight, and uneven density and thickness are likely to cause large errors
The manual counting method is relatively slow, inefficient, and easily affected by human factors, occupying and wasting human resources
[0004] How to improve the efficiency and accuracy of counting regular objects with light weight, small volume and uneven density similar to industrial sealing felt pads is an urgent problem to be solved

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 window counting method and device based on multi-category incremental learning
  • A window counting method and device based on multi-category incremental learning
  • A window counting method and device based on multi-category incremental learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] For the convenience of describing the content of the present invention, some terms are firstly explained here:

[0031] Support Vector Machine SVM. SVM is a supervised learning model, usually used for pattern recognition, classification, and regression analysis. SVM analyzes the case of linear separability. For the case of linear inseparability, the nonlinear mapping algorithm is used to transform the linearly inseparable samples of the low-dimensional input space into a high-dimensional feature space to make it linearly separable, so that the high-dimensional feature space adopts linear The algorithm makes it possible to perform linear analysis on the nonlinear characteristics of samples.

[0032] AdaBoost algorithm. The AdaBoost algorithm is a boosting algorithm. In classification problems, it can learn multiple classifiers by changing the weight of training samples, and linearly combine these classifiers to improve the performance of the classifier. The algorithm ...

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 provides a window-based counting method and device based on multi-category incremental learning, which makes full use of the characteristics of regular target shapes, establishes a direct relationship between pixels and numbers, reduces cumulative errors, and realizes fast counting, while allowing objects Sticking, ignoring non-uniform density and mass factors. In order to avoid the limitation of the shooting angle when collecting images, there will be errors in the pixels of each area of ​​the target image, the detection range is divided into partitions by windows, and each window is counted separately to reduce the error. The device uses a dark box to avoid the interference of external light sources, and has very low requirements on the external environment; the multi-window template partitions the counting area to avoid the rolling of target objects and the adhesion between adjacent windows. The invention realizes high-accuracy fast counting of regular objects with light weight, small volume and uneven density similar to industrial sealing felt pads.

Description

technical field [0001] The invention relates to image processing and machine learning technology, in particular to fast counting of regular objects with light weight, small volume and uneven density. Background technique [0002] Industrial sealing felt pad is a sealing gasket made by punching, which has the functions of sealing, heat insulation, sound insulation, shockproof, filtering, etc. It is widely used in various industrial fields such as home appliances, musical instruments, sports equipment, automobiles, and cultural products. , Accurately calculating the number of felt pads is very important to ensure the economic benefits of the manufacturer. [0003] The basic characteristics of felt pads are small size, light weight, and regular shape. Since the processed raw materials contain different types of wool, the final finished product will have uneven density and thickness due to the length and thickness of the wool, resulting in errors. The traditional methods are ge...

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): G06V10/30G06V10/774G06V10/764G06K9/62G06T7/136
CPCG06T7/136G06V10/30G06F18/2411G06F18/214
Inventor 解梅秦国义公衍翔卢欣辰
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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
Eureka Blog
Learn More
PatSnap group products