Height histogram segmentation-based method for identifying depth defect of refractory brick
A technology of height histogram and identification method, which is applied in the field of identification of deep defects of refractory bricks, can solve the problems of affecting the service life of refractory bricks, prone to misjudgment, and large subjective influence, so as to avoid osmotic corrosion, prolong service life, and achieve good results. The effect of execution efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0054] The identification method of depth defect of refractory brick based on height histogram segmentation comprises the following steps:
[0055] Step 1. Filter and denoise the original color image of refractory bricks collected by the sensor to obtain the denoised image; in the denoised image, segment the refractory brick area to obtain the grayscale image of the refractory brick, such as figure 1 shown;
[0056] Step 2. Use the least squares method to perform plane fitting on the point cloud of the refractory brick image to obtain the zero plane, and obtain the size parameters (height and width) of the original refractory brick image, and generate a corresponding The reference plane image of ;
[0057] Step 3. Make a difference between the original refractory brick image and the reference plane image to obtain the tilt-corrected point cloud data map, as shown in figure 2 shown;
[0058]Step 4. Filter and segment the height histogram of the tilt-corrected point cloud to...
Embodiment 2
[0088] In this embodiment, the geometric dimension of the refractory brick is measured on the basis of the threshold segmentation of the refractory brick image, and the methods for obtaining the refractory brick image, filtering and denoising processing and segmenting the refractory brick area are the same as in Embodiment 1.
[0089] A method for measuring the geometric dimensions of refractory bricks, comprising the following steps:
[0090] Step 1: Filter and denoise the original refractory brick color image to obtain the denoised image;
[0091] Step 2: In the denoised image, segment the refractory brick area to obtain the refractory brick image, such as figure 1 shown;
[0092] Step 3: Carry out morphological processing on the refractory brick image, make the edge of the refractory brick image transition smoothly, and remove the isolated point noise at the edge of the refractory brick image, and obtain the corrected refractory brick image;
[0093] Step 4: Use the Canny...
Embodiment 3
[0127] In this embodiment, on the basis of the threshold segmentation of the refractory brick image, the surface scratch recognition of the refractory brick is carried out. The acquisition of the refractory brick image, the filtering and noise reduction processing and the method of segmenting the refractory brick area are the same as in Embodiment 1.
[0128] A method for identifying scratches on the surface of refractory bricks based on frequency domain filtering enhancement, including the following steps:
[0129] Step 1: Filter and denoise the original color image of refractory bricks collected by the sensor to obtain a denoised image; in the denoised image, segment the area of refractory bricks to obtain a grayscale image of refractory bricks, such as figure 1 shown;
[0130] Step 2: convert the grayscale image of refractory bricks into a color image of refractory bricks, perform channel decomposition on the color image of refractory bricks, separate the images of R, G, ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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