Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Deep learning-based crack identification method

A crack identification and deep learning technology, applied in the field of crack identification based on deep learning, can solve problems such as inability to meet industrial inspection, high crack identification error rate, incomplete cracks, etc., to improve convergence and convergence efficiency, and avoid overfitting. The effect of combining and reducing workload

Active Publication Date: 2017-11-28
WUHAN UNIV
View PDF4 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the crack image contains strong noise, the crack target will show poor continuity and low contrast in the image, the cracks extracted by traditional crack identification methods are often incomplete, and the error rate of crack identification is high , can not meet the needs of industrial testing

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
  • Deep learning-based crack identification method
  • Deep learning-based crack identification method
  • Deep learning-based crack identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Below in conjunction with accompanying drawing and specific embodiment the present invention will be described in further detail:

[0032] A crack identification method based on deep learning, comprising the following steps:

[0033] Step 1: Construct the simulated crack dataset Dataset1, that is, use computer to generate 10 6 A blank image, using the line drawing algorithm to draw crack lines and noise on the blank image. Preferably, the line drawing adopts a spline curve drawing algorithm or a Bezier curve drawing algorithm, the drawn lines include continuous and discontinuous, the width of the line is a random value between 1 and 4, and the noise is drawn using random number generation Algorithm, determine a certain number of random point coordinates on each image, draw a short line segment with a length between 1 and 10 pixels on each random point, and the direction of the short line segment takes a random value between 0° and 180° , the width of the short line ta...

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 deep learning-based crack identification method. According to the method, correct identification of crack positions and crack attributes is realized at the same time by utilizing a deep convolutional neural network which comprises branches; on the trunk of the network, convolutional layers and de-convolutional layers are combined to realize end-to-end crack position prediction; and on the branches, attribute identification is realized. In order to overcome the difficulty that the labelling of crack samples wastes time and labor, a simulation crack drawing algorithm is designed to realize the automatic drawing and labeling of cracks, so that the workload of manual labeling is greatly lightened, training samples in large data volume are provided for deep learning, overfitting of deep network models is avoided, and the convergence and convergence efficiency during real crack training are improved; and according to the method, the identification correctness is greatly enhanced, the universality is stronger, the reliability is higher and demands of industrial detection can be satisfied.

Description

technical field [0001] The invention relates to the field of image linear target recognition, in particular to a crack recognition method based on deep learning. technical background [0002] Cracks are linear objects that often appear on highway pavements, building walls, tunnel tops, metal surfaces, etc. On the one hand, as cracks are an initial damage, timely repair or repair can not only reduce safety hazards, but also save maintenance costs; on the other hand, traditional manual identification methods are time-consuming and laborious to identify cracks, which cannot meet the needs of modern industries. Therefore, automatic identification and timely repair of cracks are of great economic significance. Optical images or distance images of cracks are usually acquired by means of optical photography or laser scanning, and then image processing algorithms are used to identify cracks in the images. However, when the crack image contains strong noise, the crack target will s...

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
IPC IPC(8): G06K9/62G06N3/04
CPCG06N3/045G06F18/217G06F18/214
Inventor 邹勤
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com