Method for eliminating interference of forging images under high temperature environment

Abstract

The present invention discloses a method for eliminating interference of forging images in a high temperature environment, which specifically comprises the following steps: step 1, using a forging image and preprocessing the collected image; step 2, eliminating infrared interference from the image processed by step 1; step 3, performing median filtering on the image obtained in step 2 to obtain a filtered matrix, which is recorded as #imgabs0#; step 4, performing histogram equalization processing on the matrix #imgabs1# obtained in step 3 to obtain a matrix #imgabs2#; step 5, obtaining an output matrix AO according to the result obtained in step 4 m×n The present invention can eliminate the interference of high temperature and high noise environment on the image without losing the image quality as much as possible.

Description

Technical Field

[0001] The invention belongs to the technical field of machine vision in industrial sites under complex environments, and relates to a method for eliminating interference of forging images under high-temperature environments. Background Art

[0002] At present, due to the rapid development of the electronics industry and the materials industry, infrared thermal imagers, CCD cameras and other imaging instruments are becoming cheaper and cheaper and are being used more and more widely. However, these instruments have some fatal shortcomings. Because the working environment is extremely changeable and unstable, the instruments must be kept extremely stable at all times when in use in order to obtain clear images with the lowest loss, highest authenticity and highest restoration.

[0003] In the field of thermal processing, many factors in the industrial field will interfere with the collected image information. In particular, high temperature environment will cause thermal noise to appear in the collected image information, and the image quality will decrease exponentially with the increase of temperature, and cause high-brightness reflection phenomenon.

[0004] In previous papers, researchers usually use highlight area recognition, texture restoration and traditional filtering methods to deal with the above problems. However, these methods almost do not really solve the problems involved. Therefore, how to better eliminate the impact of high temperature environment on the target image without losing the target image becomes very urgent. Summary of the invention

[0005] The purpose of the present invention is to provide a method for eliminating interference in forging images in a high-temperature environment, by which the interference caused by the high-temperature and high-noise environment to the image is eliminated without losing the image quality as much as possible.

[0006] The technical solution adopted by the present invention is a method for eliminating interference of forging images in a high temperature environment, which specifically comprises the following steps:

[0007] Step 1, using a forging image and preprocessing the collected image;

[0008] Step 2, eliminating infrared interference from the image processed in step 1;

[0009] Step 3: Perform median filtering on the image obtained in step 2 to obtain the filtered matrix, which is recorded as ;

[0010] Step 4: For the matrix obtained in step 3 Perform histogram equalization to obtain the matrix ;

[0011] Step 5: Get the output matrix based on the result of step 4 .

[0012] The present invention is also characterized in that:

[0013] The specific process of step 1 is: collect the forging image through the camera, and let the collected forging image be , the image According to the principle of three primary colors R, G, and B, it is divided into three layers; they are respectively recorded as: , , ,in Representing images The number of pixels in the horizontal direction, Representing images The number of pixels in the vertical direction.

[0014] The specific process of step 2 is: obtain , , The value of the pixel point with the same coordinate value in is recorded as , , ,in:, The value range is 1~ , The value range is 1~ When the following formula (1) is satisfied, , , are all recorded as 0, otherwise, , , The value of does not change, so the corrected , , :

[0015] (1);

[0016] in, , , is the proportional coefficient, and its value range is 1~10.

[0017] The specific process of step 5 is to statistically matrix The frequencies of all pixels in the image are arranged from high to low to obtain Gray values ​​are recorded as follows: ,right All pixels in the The pixel points at different coordinates are recorded as , and record the processed single pixel value as , all pixel values ​​form an output matrix, recorded as .

[0018] In step 5, the following formula (2) is used to calculate the value of a single pixel: :

[0019] (2);

[0020] in: for The number of horizontal pixels, for The number of vertical pixels, The value range is 1~ , The value range is 1~ .

[0021] The beneficial effects of the present invention are as follows: the present invention can suppress interference signals including infrared thermal radiation without causing distortion of useful signals in an environment with high temperature and large noise interference, and acquire, amplify and classify target signals. This plays a positive role in subsequent target measurement and identification. At the same time, the present invention has low requirements on both the hardware system and the software system, and is convenient for practical large-scale application. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a hardware structure diagram of the method for eliminating interference of forging images in a high temperature environment of the present invention;

[0023] Figure 2 It is a flow chart of the method for eliminating interference of forging images in a high temperature environment of the present invention;

[0024] Figure 3 (a) to (c) are the results of histogram equalization and stratification of speckles using the forging image interference elimination method under high temperature environment of the present invention;

[0025] Figure 4 (a) to (c) are the result images after histogram equalization and stratification of the stripes using the forging image interference elimination method under high temperature environment of the present invention. DETAILED DESCRIPTION

[0026] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0027] The method for eliminating interference of forging images under high temperature environment of the present invention is as follows: Figure 1 As shown, the hardware of the present invention adopts green laser stripes or speckles to supplement the target object, which specifically includes the following steps: Figure 2 As shown:

[0028] Step 1, using a forging image and preprocessing the collected image;

[0029] The specific process of step 1 is: collect the forging image through the camera, and let the collected forging image be , the image According to the principle of three primary colors R, G, and B, it is divided into three layers; they are respectively recorded as: , , ,in Representing images The number of pixels in the horizontal direction, Representing images The number of pixels in the vertical direction.

[0030] Step 2, eliminating infrared interference from the image processed in step 1;

[0031] The specific process of step 2 is: obtain , , The value of the pixel point with the same coordinates is recorded as , , , when the following formula (1) is satisfied, , , are all recorded as 0, otherwise, , , The value of does not change, so the corrected , , :

[0032] (1);

[0033] in, , , is the proportional coefficient, and its value range is 1~10.

[0034] Step 3: Perform median filtering on the image obtained in step 2 to obtain the filtered matrix, which is recorded as ;

[0035] Step 4: Use formula (2) to obtain The "1 norm" of ,Will As a basis for judging Perform histogram equalization operation to obtain the matrix .

[0036] (2);

[0037] Step 5: Get the output matrix based on the result of step 4 .

[0038] Statistics Matrix The frequencies of all pixels in the image are arranged from high to low to obtain Gray values ​​are recorded as follows: ,right All pixels in the The pixel points at different coordinates are recorded as , and record the processed single pixel value as , all pixel values ​​form an output matrix, recorded as .

[0039] In step 5, the following formula (3) is used to calculate the value of a single pixel: :

[0040] (3);

[0041] in: for The number of horizontal pixels, for The number of vertical pixels, The value range is 1~ , The value range is 1~ .

[0042] like Figure 3 , Figure 4 The experimental steps of the present invention are shown in FIG. Figure 3 (a) and Figure 4 (a) shows the original image captured by the camera. The high-temperature and bright areas in the image introduce large errors to the speckle or line laser detection. Figure 3 (b) and Figure 4 (b) shows the experimental results after steps 1 to 3 are completed. It can be found that the influence of high-temperature highlight areas has been basically eliminated. Figure 3 (c) and Figure 4 (c) shows the final output result. The distribution boundaries of different distances in the figure are clearer, which facilitates the acquisition of subsequent distance values.

Claims

1. A method for eliminating interference of forging images in a high temperature environment, characterized by: The specific steps include: Step 1, using a forging image and preprocessing the collected image; The specific process of step 1 is: collect the forging image by camera, and make the collected forging image , the image According to the principle of three primary colors R, G, and B, it is divided into three layers; they are respectively recorded as: , , ,in Representing images The number of pixels in the horizontal direction, Representing images The number of pixels in the vertical direction; Step 2, eliminating infrared interference from the image processed in step 1; The specific process of step 2 is: obtain , , The value of the pixel point with the same coordinate value in is recorded as , , ,in: The value range is 1~ , The value range is 1~ ; When the following formula (1) is satisfied, , , are all recorded as 0, otherwise, , , The value of does not change, so the corrected , , : （1）； in, , , is the proportional coefficient, and its value range is 1~10; Step 3: Perform median filtering on the image obtained in step 2 to obtain the filtered matrix, which is recorded as ; Step 4: For the matrix obtained in step 3 Perform histogram equalization to obtain the matrix ; Step 5: Get the output matrix based on the result of step 4 .

2. The method for eliminating interference of forging images in a high temperature environment according to claim 1, characterized in that: The specific process of step 5 is: The frequencies of all pixels in the image are arranged from high to low to obtain Grayscale values ​​are recorded as follows: ,right All pixels in the The pixel points at different coordinates are recorded as , and record the processed single pixel value as , all pixel values ​​form an output matrix, recorded as .

3. The method for eliminating interference of forging images in a high temperature environment according to claim 2, characterized in that: In step 5, the following formula (2) is used to calculate the value of a single pixel: : （2）； in: for The number of horizontal pixels, for The number of vertical pixels, The value range is 1~ , The value range is 1~ .

Images