Method for item identification and classification and defect detection based on machine vision

A technology for recognition classification and defect detection, which is applied in character and pattern recognition, instruments, computer parts, etc. It can solve the problems of not being able to detect defects of different types of items, not being able to use item classification and recognition, and detection objects limited to cloth, etc., to achieve detection Fast speed, high detection accuracy, and high detection accuracy

Active Publication Date: 2018-10-12
GUANGZHOU UNIVERSITY
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, the Chinese patent application with the publication number CN106872487A published on June 20, 2017 discloses "a method and device for detecting defects based on visual surfaces". Technical means, but the purpose is to classify the complex texture defects on the surface of the cloth, so that the surface defects of cloth with different textures can be detected, which can be applied to the detection of surface defects of various cloth; but the detection object of this document is still limited to the cloth Surface defect detection cannot be used for the classification and identification of items, nor can it be applied to the defect detection of different types of items, and the versatility is not strong

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
  • Method for item identification and classification and defect detection based on machine vision
  • Method for item identification and classification and defect detection based on machine vision
  • Method for item identification and classification and defect detection based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0034] Such as Figure 1-5 As shown, the machine vision-based item identification and classification and defect detection method of the present invention can be roughly divided into two steps: item type identification and classification and defect detection.

[0035] 1. The process of identifying and classifying items is based on the support vector machine, including the model training process and loading the model to realize the classification process; the training data is obtained through the positive and negative samples prepared in advance, the training is performed after configuring the parameters of the SVM trainer, and the trained model is saved; After opening the trained model, perform feature extraction on the detected pictures, compare the data obtained during training, extract matching labels, output the type of the label, and then perform classification.

[0036] 1. Model training process

[0037] First obtain the training pictures downloaded from the picture data...

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 method for item identification and classification and defect detection based on machine vision. The method includes an item category identification and classification process based on a support vector machine and a defect detection process based on a machine vision defect detection algorithm, wherein the item category identification and classification process includes amodel training process and a process of loading models to achieve classification; and the defect detection process based on the machine vision defect detection algorithm includes the following steps:performing a graph correction process, and calculating Hu invariant moments of graphs for similarity comparison; and judging whether pictures have defects according to a detection result. According tothe scheme of the invention, a support vector machine training template and a loading template are used for multi-classification, so that the categories of different objects can be identified, the detection of different objects can be realized, the universality of the algorithm can be improved, and the accuracy and detection speed of the defect detection can be improved.

Description

technical field [0001] The invention belongs to the field of machine vision detection, and in particular relates to a machine vision-based object recognition classification and defect detection method. Background technique [0002] In recent years, with the development of technology, automatic production of products is one of the main trends in the development of modern production. Automatic production is of great significance to accelerate the development of social productivity, improve enterprise production technology, and reduce labor force. [0003] Under the demand of high-end consumption and rapid growth of production capacity, enterprises want to improve their competitiveness, and product testing is becoming more and more important. Product surface defects can be divided into many types, such as: wrinkles, scratches, stains, etc. Therefore, the defect detection of machine vision is also essential. [0004] Traditional manual visual inspection is not only inefficient...

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 Applications(China)
IPC IPC(8): G06K9/62
CPCG06F18/2411G06F18/214
Inventor 吴羽陈泽嘉郑伟林黄文恺
Owner GUANGZHOU UNIVERSITY
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