Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and device for extracting and classifying image features

An image feature extraction and feature extraction technology, which is applied in image analysis, image enhancement, image data processing and other directions, can solve the problems of small sample volume, stay, and difficulty in meeting the requirements of online detection, and achieves the goal of improving accuracy and efficiency. Effect

Active Publication Date: 2018-09-28
SUZHOU XIAOCREATE OPTOELECTRONICS TECH
View PDF13 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the algorithm research is still in the laboratory stage, the sample size is small, and there is a lack of verification of a large number of online products.
In addition, some methods use a long algorithm calculation time, which is difficult to meet the requirements of online detection.

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 and device for extracting and classifying image features
  • Method and device for extracting and classifying image features
  • Method and device for extracting and classifying image features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0050] The embodiment of the present invention provides image feature extraction and classification. The image feature extraction and classification method extracts the features from the acquired grayscale images of the warp knitted fabrics, and classifies them according to the extracted features. Through the method of image feature extraction and classification, fast and effective feature extraction of warp-knitted fabric image flaws and classification and identification of warp-knitted fabric flaws, the efficiency and accuracy of recognition are improved.

[0051] see figure 1 , by carrying out the method for feature extraction to the gray-scale image of the warp-knitted fabric that obtains, comprise the following steps:

[0052] S110: Acquiring a grayscale image of the warp-knitted fabric;

[0053] Specifically, the grayscale image of the warp-knitted fabric is obtained, and the grayscale image is divided into images with a size of 64*64 pixels.

[0054] S120: Perform me...

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 and device for extracting and classifying image features. The method for extracting and classifying the image features comprises the steps of carrying out feature extraction on obtained gray images of warp knitted fabrics and classifying the warp knitted fabrics according to the extracted features. The method for extracting and classifying the image features has the beneficial effects that defect feature extraction and defect classification recognition are quickly and effectively carried out on the images of the warp knitted fabrics; the efficiency is improved; and the recognition accuracy is increased.

Description

technical field [0001] The invention relates to the fields of image processing, analysis and machine vision, in particular to a method and device for image feature extraction and classification. Background technique [0002] Current textiles have become an indispensable item in people's daily life, and most of them are produced automatically by warp knitting machines. Defects in warp knitted fabrics refer to production defects such as warp breaks, weft breaks, holes, and skipped stitches that occur during the production process of warp knitting machines. Such defects will affect the appearance of the finished product and cause economic losses. In order to improve consumer experience and reduce losses, it is necessary to monitor the above-mentioned defects in real time during the production process of warp knitting machines. Maintenance provides data support. The traditional detection method adopts the method of manual line inspection to observe whether the warp knitted fab...

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): G06K9/62G06K9/46G06T7/00G06T7/136
CPCG06T7/0008G06T7/136G06T2207/20032G06T2207/30124G06V10/40G06F18/241
Inventor 李鹏飞殷晓平邵健李哲诚
Owner SUZHOU XIAOCREATE OPTOELECTRONICS TECH