Automatic measurement and classification method and system of steel dimple image depth uniformity

A technology for automatic measurement and image depth, used in instruments, character and pattern recognition, computer parts, etc., and can solve problems such as low accuracy and low efficiency

Inactive Publication Date: 2018-08-21
JIANGSU UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem of low efficiency and low precision of the current manual measurement and evaluation classification method, and propose a characteristic parameter of dimple depth uniformity based on dimple image grayscale extreme value and grayscale-depth mapping relationship Its measurement and classification method and its system, using computer to realize the automatic, accurate and efficient measurement and classification of the fracture dimple depth of iron and steel materials

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
  • Automatic measurement and classification method and system of steel dimple image depth uniformity
  • Automatic measurement and classification method and system of steel dimple image depth uniformity
  • Automatic measurement and classification method and system of steel dimple image depth uniformity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0107] Use the image acquisition device to obtain the original image of the steel dimple to be tested. The hardware of the image acquisition device is as follows: figure 2 Shown: a steel sample 1, a scanning electron microscope 2, a camera 3, a computer 4 and a printer 5, and the computer 4 is attached with an image acquisition card.

[0108] The specific steps of image acquisition are to use the scanning electron microscope 2 to adjust the image to a suitable focal length, and use the camera 3 to take pictures when the original image of the steel dimple to be tested is the clearest and store it in the image acquisition card in the computer 4 , the original image of the steel dimple to be tested in steel sample 1 is obtained (such as image 3 shown), followed by subsequent image preprocessing.

[0109] The process of image preprocessing includes: median filter denoising, binary segmentation and dimple defect boundary repair.

[0110] Median filter denoising: first use the m...

Embodiment 2

[0168] Figure 10 is the original image of the dimple to be tested in steel sample 2. The processing process of the present invention is as follows: first, the original image of the target dimple to be measured is subjected to median filtering and denoising, and the image after median filtering and denoising is as follows: Figure 11 As shown; the filtered image is processed by a local adaptive threshold segmentation algorithm, and the image after binary segmentation is as follows Figure 12 shown in Fig. 1; and then use the limit corrosion controlled by the quenching function method and the layer-by-layer expansion method to repair the missing boundary of the dimple. The image after the boundary repair is as follows Figure 13 Shown; area calibration is performed on the image to be tested, and the image after area calibration is traversed and scanned to extract the gray extreme value of each dimple area in the dimple image, and at the same time calculate the dimple equivalen...

Embodiment 3

[0170] Figure 15 is the original image of the dimple to be tested in steel sample 3. Now use the present invention to its processing process: first carry out median filtering denoising to target image, the image after median filtering denoising is as follows Figure 16 As shown; the filtered image is processed by a local adaptive threshold segmentation algorithm, and the image after binary segmentation is as follows Figure 17 shown in Fig. 1; and then use the limit corrosion controlled by the quenching function method and the layer-by-layer expansion method to repair the missing boundary of the dimple. The image after the boundary repair is as follows Figure 18 Shown; area calibration is performed on the image to be tested, and the image after area calibration is traversed and scanned to extract the gray extreme value of each dimple area in the dimple image, and at the same time calculate the dimple equivalent depth uniformity DDE (not specified by the user can provide th...

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

PropertyMeasurementUnit
Depthaaaaaaaaaa
Login to view more

Abstract

The invention belongs to an automatic measuring and classifying method and system for depth uniformity of a steel dimple image. The method comprises the steps of acquiring an original image of a steel dimple to be measured through an image acquiring device; processing the original image through an image pre-treating module by median filtering de-noising, binary segmenting, and dimple gap boundary repair; performing area calibration for the pre-treated image through an automatic measuring module to obtain the dimple image to be measured; extracting dimple gray parameters of the dimple image to be measured; obtaining the uniformity of the gray level of a core of the dimple to be measured according to the extreme dimple image gray value and the dimple depth uniformity feature parameters of the grey-depth mapping relationship and the calculation method; automatically classifying the dimple depth uniformity through an automatic classifying module according to the optimal threshold. According to the method and the system, the blank that the traditional manual mode cannot measure and classify the steel dimple depth uniformity measurement and classification is filled; the expression precision of the steel dimple image is up to + / -0.001 microns, which is the maximum expression precision in the current steel dimple analysis.

Description

technical field [0001] The invention relates to the field of fracture failure analysis of steel materials, in particular to an automatic measurement and classification method and system for the depth uniformity of steel dimple images. Background technique [0002] In the fracture failure analysis of various steel materials, the dimple image of the fracture is the most basic original morphology that reflects the fracture properties of the material, and is also the most essential basis for judging the fracture mechanism of the material. The depth of dimples, especially the uniformity of depth distribution, is closely related to the strength, plasticity, and formability of materials. Quantitative analysis and research on the depth uniformity of fracture dimples can provide an in-depth understanding of its fracture mechanism, crack formation reasons and the Essential influence on material properties. It can be seen that the quantitative analysis of dimple depth is an important ...

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): G06K9/00G06K9/62
Inventor 李新城唐永春朱伟兴刘杰王晓莉许金堡陈亮于慧慧
Owner JIANGSU UNIV
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