Infrared image defect edge detection method based on improved mathematical morphology

A mathematical morphology and edge detection technology, applied in image enhancement, image analysis, image data processing, etc., can solve problems such as failure of ferromagnetic material components, economic losses, etc., achieve noise suppression, good effect, and overcome poor anti-noise effect Effect
CN113012116APending Publication Date: 2021-06-22KUNMING UNIV OF SCI & TECH
3 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
KUNMING UNIV OF SCI & TECH
Publication Date
2021-06-22

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses an infrared image defect edge detection method based on improved mathematical morphology, which is characterized in that a pulsed eddy current nondestructive heating device is applied to ferromagnetic material damage detection; eddy current heating is performed on a test piece, and the damage characteristics of the test piece are represented in the form of a thermal image. The invention has the advantages that a detected object does not need to be contacted, the thermal imaging result is intuitive and clear, the detection efficiency is high, and a larger range can be detected in a shorter time; an infrared image of a ferromagnetic test piece is filtered and segmented by using a multi-scale and multi-direction mathematical morphology edge detection method, and the processing and experimental results show that the method has better image denoising and image segmentation effects than edge detection results of a Roberts operator and a Prewitt operator. The defect of poor anti-noise effect in edge detection is overcome, the noise in the image is effectively inhibited, the defect position in the image is accurately detected, and the edge information of the defect is reserved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to an infrared image defect edge detection method based on improved mathematical morphology, which belongs to the fields of non-destructive testing and image recognition. Background technique

[0002] Due to the continuous change and update of today's science and technology, the application of non-destructive testing technology in the field of modern industrial testing is becoming more and more common. Non-destructive testing technology is an indispensable technology in various fields. Non-destructive testing is the detection of the state of equipment test pieces, which can reduce accidents to a certain extent. Non-destructive testing technology can also effectively prevent various economic losses caused by equipment damage. It is of great significance to improve product quality and provide important guarantees for the safe operation of engineering equipment in actual production and life.

[0003] The actual engineering environm...

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