Method for detecting surface defects of mechanical parts based on image texture and fractal dimension

A technology of fractal dimension and mechanical parts, applied in image analysis, image data processing, measuring devices, etc., can solve problems that do not conform to the actual observation of the human eye, and achieve simple and easy actual observation of the human eye and meet the actual observation of the human eye Effect

CN101710081AInactive Publication Date: 2010-05-19HANGZHOU DIANZI UNIV
0 Cites 12 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2010-05-19
Estimated Expiration
Not applicable · inactive patent

Smart Images

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

Abstract

The invention relates to a method for detecting surface defects of mechanical parts based on image texture and fractal dimension. Traditional methods for detecting surface defects of mechanical parts have the disadvantages of low efficiency and low detecting accuracy. The method comprises the following steps of: firstly preprocessing mechanical parts to be detected, placing the preprocessed mechanical parts on a conveyor belt, acquiring an image of a part surface to be detected with a CCD image acquisition system to obtain a texture image of the part surface; then calculating the fractal dimension and the voidage of the texture image; and finally matching and comparing the calculated fractal dimension and the calculated voidage of the texture image with those of a standard part in a mechanical part database. The invention can realize the evaluation of the machine visual quality by calculating the fractal dimension and the voidage features representing subjective perceptions based on the external features of the surface defect texture of mechanical parts.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of machine vision, and in particular relates to a method for detecting surface defects of mechanical parts based on image texture and fractal dimension. Background technique

[0002] At present, mechanical parts are widely used in the automobile industry, aviation industry, medical industry, etc., and the automatic and precise detection of surface defects of mechanical parts is a very important link in the production process. The accuracy of the detection system directly affects the classification of products and the quality of products. One of the key technologies for improving the detection system to identify surface defects of mechanical parts is to select an appropriate quality evaluation method. At present, the detection systems used in the production process of mechanical parts in my country mostly use subjective evaluation. Therefore, the evaluation process is inefficient, and the evaluation results ...

Examples

Embodiment Construction

[0027] A method for detecting surface defects of mechanical parts based on image texture and fractal dimension comprises the following steps:

[0028] Step (1), pre-processing the mechanical parts to be tested, the specific method of pre-processing is to first apply black ink to the surface of the part to be tested, and after the ink fills the pores on the surface of the part to be tested, wipe the surface of the part with a dry cloth;

[0029] Step (2), placing the pre-processed mechanical parts on the conveyor belt, using a CCD image acquisition system to collect images of the surface of the part to be tested, to obtain a texture image of the surface of the part;

[0030] Step (3), calculate the fractal dimension and the porosity of the texture image;

[0031] The method to calculate the fractal dimension of the texture image is:

[0032] The surface image of the mechanical part is extended to several zero rows or several zero columns at the corresponding boundaries so that...