Building fireproof wood defect detection method based on Gaussian filtering

Abstract

The invention relates to a building fireproof wood defect detection method based on Gaussian filtering, and the method comprises the steps: obtaining a gray level image of wood, determining the three-dimensional vector of each pixel point in the gray level image, and enabling the three-dimensional vector to comprise the horizontal coordinate value, the vertical coordinate value and the gray level value of the pixel point; constructing a circular window in the grayscale image, and determining an offset according to a three-dimensional vector of a central point of the circular window and three-dimensional vectors of other pixel points in the circular window; according to the offset, performing clustering according to a mean shift algorithm to obtain a to-be-determined defect area, and expanding the to-be-determined defect area to obtain an expanded area; fitting the expansion area by adopting a preset Gaussian mixture model to obtain the defect degree of the expansion area, and determining the defect edge of the wood according to the defect area; according to the invention, the defect detection precision of the fireproof wood can be improved, and the defect can be completely cut when the wood is subjected to defect cutting.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for detecting fire-resistant timber defects in buildings based on Gaussian filtering. Background technique [0002] Fire-resistant wood is a new type of material commonly used in building construction. Fire-resistant wood can improve the fire resistance of buildings after construction. However, the wood will have dead branches during the growth process, and the connection between the dead branches and the branches will form dead knots when making square wood. Due to the necrosis of the dead knot, it is likely to have been separated from the surrounding wood tissue, so the dead knot is easy to form a cavity, which affects the quality of the wood. Once the wood is broken, it will cause a more serious accident. [0003] Therefore, before fire-resistant wood is used, the dead joints of the wood need to be tested. In the prior art, a threshold segmentation method ...

AI Technical Summary

Problems solved by technology

[0004] The invention provides a Gaussian filter-based detection method for building fireproof wood defects, which aims to solve the problem that only part of the defects are cut when cutting wood defects, resulting in still quality problems in the wood

Images