KR101858829B1 - Segregation analysis apparatus and method - Google Patents

Abstract

According to one technical aspect of the present invention, there is provided a segregation analysis apparatus comprising: an image acquisition unit for acquiring an image of an image of a mold specimen including a plurality of specimens; a plurality of specimen images for the plurality of specimens And a segregation information generation unit for detecting segregation regions in each of the specimen image extraction unit and the plurality of specimen images, and generating segregation analysis information by digitizing the segregation region.

Description

[0001] SEPARATION ANALYSIS APPARATUS AND METHOD [0002]

The present invention relates to an apparatus and a method for analyzing segregation capable of automatically determining a center segregation grade of a wire rod product using an image.

The wire rod is a linear steel and can be used in various fields such as tire cord and construction. These wire rods are generally required to have higher strength than ordinary steels, and accordingly there is a high demand for quality control.

If there is a center segregation in the inside of such a wire, there is a high possibility that disconnection will be caused. Therefore, various techniques for detecting segregation of such wire are being developed.

Conventional wire segregation detection technologies determine whether segregation exists in the center of a wire rod based on an image of a wire rod section. On the other hand, in the case of such a conventional technique, there is a problem in that the accuracy of detection of segregation is lowered when a change in an image of an image is caused by illumination, camera performance, or the like.

Such prior art can be easily understood with reference to Korean Laid-Open Patent Publication No. 2009-0046920, Korean Laid-Open Patent Publication No. 2010-0078590, and Korean Laid-Open Patent Publication No. 2012-0068635.

Korean Patent Publication No. 2009-0046920 Korean Patent Publication No. 2010-0078590 Korean Patent Publication No. 2012-0068635

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems of the prior art, and it is an object of the present invention to automate inspection and quality control of a specimen by detecting segregation and providing segregation analysis information for each of a plurality of specimens. And provides a precise analysis with a seismic analysis apparatus and method.

A technical aspect of the present invention proposes a segregation analysis apparatus. The segregation analyzing apparatus includes an image obtaining unit for obtaining an image of a mold specimen including a plurality of specimens, a specimen image extracting unit for extracting a plurality of specimen images for the plurality of specimens from the captured image, And a segregation information generation unit for detecting the segregation area in each of the sample images and generating the segregation analysis information by digitizing the segregation area.

In one embodiment, the image acquiring unit may include a ring illumination having a hollow corresponding to the shape of the camera and the lens of the camera.

In one embodiment, the specimen image extracting unit includes a matching unit that performs correlation coefficient matching between the template image and the sensed image, a binarizer that performs binarization on the output of the matching unit, and a binarizer that binarizes the output of the binarizer based on the output of the binarizer. And an image extractor for extracting the plurality of specimen images from the plurality of specimen images.

In one embodiment, the segregation information generating unit may include a variable binarizer for setting a peripheral region of the central region as a reference region in the specimen image, and variably binarizing the center region using the average brightness of the reference region, As the segregation area, an area in which the histogram of the pixel value of the reference area, which is variable-binarized, is equal to or less than a preset threshold value at the output of the seismic area determining unit.

In one embodiment, the segregation information generation unit may further include an information generator that calculates at least one of the size, length, brightness information, angle, segregation amount, and segregation ratio of the segregation region to generate the segregation analysis information .

Another technical aspect of the present invention proposes a segregation analysis method. Wherein the segregation analysis method comprises the steps of: obtaining a captured image for a mold specimen comprising a plurality of specimens; extracting a plurality of specimen images for each of the plurality of specimens in the captured image, Detecting the area, and generating the segregation analysis information by digitizing the segregation area.

In one embodiment, acquiring the sensed image can include irradiating light to the plurality of specimens using ring illumination with a hollow corresponding to the shape of the camera lens.

In one embodiment, the extracting of the plurality of specimen images may include correlating coefficient matching of the template image and the sensed image, performing binarization on the correlation coefficient matched result, And extracting the plurality of specimen images from the captured image.

In one embodiment, generating the segregation analysis information comprises: setting a peripheral region of the central region as a reference region in the specimen image; variable binarizing the center region using the average brightness of the reference region; Determining an area having the histogram of the pixel value of the reference area that is variable-binarized to be less than a predetermined threshold value as the segregation area with respect to the result of binarization.

In one embodiment, the generating of the segregation analysis information includes generating at least one of the size, length, brightness information, angle, segregation amount, and segregation ratio of the segregation region to generate the segregation analysis information .

The solution of the above-mentioned problems does not list all the features of the present invention. Various means for solving the problems of the present invention can be understood in detail with reference to specific embodiments of the following detailed description.

According to one embodiment of the present invention, segregation is detected for each of a plurality of specimens and segregation analysis information is provided for each of the plurality of specimens, thereby providing an effect of automating inspection and quality control of a specimen and providing accurate analysis .

According to an embodiment of the present invention, segregation is determined based on variable binarization using an average value of brightness, thereby providing an effect of accurately determining a segregation even in a change in illumination or the like.

1 is a block diagram illustrating a segregation analysis apparatus according to an embodiment of the present invention.
2 is a reference diagram illustrating an embodiment of the image acquisition unit shown in FIG.
3 is a block diagram for explaining an embodiment of the specimen image extracting unit shown in FIG.
FIG. 4 is a reference view for explaining that a specimen image is extracted by the specimen image extracting unit shown in FIG.
5 is a reference diagram for explaining that correction of an image is performed by the specimen image extracting unit shown in FIG.
FIG. 6 is a block diagram illustrating an embodiment of the segregation information generating unit shown in FIG. 1. FIG.
7 is a reference diagram for explaining that segregation information is extracted by the segregation information generation unit shown in Fig.
8 is a graph for explaining segregation determination performed in the segregation information generation unit shown in Fig.
FIG. 9 is a reference graph for explaining variable binarization by the variable binarizer shown in FIG.
10 is a reference diagram showing a result of fixed value binarization for a sample image having different brightnesses.
11 is a reference diagram showing a result of performing variable binarization on a specimen image having different brightnesses.
12 is a flowchart illustrating a method of analyzing segregation according to an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings.

However, the embodiments of the present invention can be modified into various other forms, and the scope of the present invention is not limited to the embodiments described below. Further, the embodiments of the present invention are provided to more fully explain the present invention to those skilled in the art.

1 is a block diagram illustrating a segregation analysis apparatus according to an embodiment of the present invention.

Referring to FIG. 1, the segregation analysis apparatus 100 may include an image acquisition unit 110, a specimen image extraction unit 120, and a segregation information generation unit 130.

The image acquiring unit 110 may acquire a sensed image of a mold specimen including a plurality of specimens.

The specimen image extracting unit 120 can extract a plurality of specimen images for a plurality of specimens from the captured image, respectively.

The specimen image extracting unit 120 may number and sort the plurality of extracted specimen images.

The specimen image extracting unit 120 may sense the sensed image and rotate it in the forward direction if the sensed image is rotated.

The segregation information generation unit 130 can detect the segregation area in each of the plurality of specimen images and generate the segregation analysis information by digitizing the segregation area.

The segregation information generation unit 130 may detect a segregation area in the central region of the specimen image. For example, the segregation information generation unit 130 may perform variable binarization using the average brightness of the peripheral region of the central region to detect the segregation region in the central region of the specimen image.

Hereinafter, various embodiments of the segregation analysis apparatus 100 will be described in more detail with reference to Figs. 2 to 11. Fig.

2 is a reference diagram illustrating an embodiment of the image acquisition unit shown in FIG.

Referring to FIG. 2, the image acquisition unit 110 may include a camera 210 and a lighting device 220 including a plurality of light source devices. In the illustrated example, the illumination device 220 is shown as a ring illumination device, but this is exemplary. Therefore, various embodiments of the lighting apparatus including a plurality of light source elements may be modified according to the embodiment.

The camera 210 includes a lens 211 and is capable of photographing the mold specimen 10 including a plurality of specimens to generate a sensed image.

In one embodiment, the camera 210 may comprise a telecentric lens. Therefore, it is possible to exclude segregation size distortion caused by photographing of a general camera.

The illumination device 220 may be a ring-shaped illumination device including a plurality of light source elements, and may have a hollow corresponding to the shape of the lens 211 of the camera. Therefore, when the illumination device is located, as in the example shown in the drawing, since a plurality of light source elements are disposed in the periphery of the camera, light can be uniformly irradiated to the mold specimen. It is possible to minimize the occurrence of noise due to the unevenness of the surface of the test piece.

In one embodiment, the light irradiated on the mold specimen 10 by the illumination device 220 has a light uniformity of the horizontal axis and a light uniformity of the vertical axis of 96% or more, and the light uniformity of the horizontal axis The difference in the light uniformity of the vertical axis may be within 2%. Table 1 below shows the uniformity of this embodiment.

Distance (mm) Transverse optical uniformity Vertical axis light uniformity 110 98% 98% 140 98% 97% 170 98% 98% 200 96% 96% 230 98% 96% 250 98% 97% 260 98% 97% 270 99% 98% 280 99% 97% 290 98% 97% 300 98% 97%

Referring to Table 1, the light irradiated by the illumination device 220 has a light uniformity of the horizontal axis of not less than 96% and a light uniformity of the vertical axis of not less than 2% at a distance of 110 mm to 300 mm from the mold specimen. %. ≪ / RTI >

That is, when the optical uniformity of each of the transverse axis and the longitudinal axis is 96% or more, and the mutual light uniformity difference between the two axes is 2% or less, distortion of the segregation image is not caused by the difference in the light uniformity, It can be canceled by the operation of the segregation information generation unit 130 described below.

FIG. 3 is a block diagram for explaining an embodiment of the specimen image extracting unit shown in FIG. 1, and FIG. 4 is a reference view for explaining that a specimen image is extracted by the specimen image extracting unit shown in FIG.

3, the specimen image extracting unit 120 may include a matching unit 310, a binarizer 320, and an image extracting unit 330.

The matching unit 310 may correlate and match the template image and the sensed image.

The binarizer 320 may perform binarization on the output of the matching unit 310.

The image extractor 330 may extract a plurality of sample images from the captured image based on the output of the binarizer 320. [

The image extractor 330 may extract a plurality of specimen images and perform numbering for each specimen image.

Referring to Fig. 4, FIG. 5 (a) shows a captured image of the mold specimen, and FIG. 5 (b) shows a template image.

FIG. 3C shows an example of a result of correlation coefficient matching between the template image and the sensed image by the matching unit 310. It can be seen that a point having the closest shape to the template image in the captured image is detected by the correlation coefficient matching of the matching unit 310.

Figure (d) shows an example of the binarized result for the figure (c) by the binarizer 320.

(E) shows an example in which a plurality of sample images are extracted from the captured image based on the image (d) by the image extracting unit 330. FIG.

5 is a reference diagram for explaining that correction of an image is performed by the specimen image extracting unit shown in FIG.

When the mold specimen is mounted on the segregation analyzer by the operator, the recognition rate may be lowered when the mold is rotated. Therefore, when the mold is rotated and fixed, it is possible to correct the rotation of the captured image without requiring the operator to re-mount the mold.

That is, the specimen image extracting unit 110 may detect the center point of a plurality of specimen images and form array lines 510 using at least a part of a plurality of points belonging to the uppermost line among the plurality of center points.

The specimen image extracting unit 120 may rotate the sensed image corresponding to the angular difference between the preset reference line 520 and the arrangement line 510 in the horizontal direction.

FIG. 6 is a block diagram illustrating an embodiment of the segregation information generating unit shown in FIG. 1. FIG.

6, the segregation information generation unit 130 may include a variable binarizer 510 and a segregation region decider 520. [ According to an embodiment, the segregation information generation unit 130 may further include an information generator 530. [

The variable binarizer 510 may set the peripheral region of the center region as a reference region in the specimen image, and may variably binarize the center region using the average brightness of the reference region.

The segregation area determiner 520 can determine, as the segregation area, an area in which the histogram of the pixel value of the variable area binarized in the output of the variable binarizer 510 is equal to or less than a predetermined threshold value.

The information generator 530 may generate the segregation analysis information by calculating at least one of the size, length, brightness information, angle, segregation amount, and segregation ratio of the segregation area detected by the segregation area determiner 520.

That is, the information generator 530 can generate quantitative numerical information with a simple degree of segregation degree. For example, the information generator 530 can determine the seismic size, length, brightness information, segregation amount, and the like by using an image processing technique for the segregation area and quantify the segregation area as quantitative data.

FIG. 7 is a reference view for explaining that the segregation information is extracted by the segregation information generation unit shown in FIG. 6. Referring to FIG. 7, FIG. 7 (a) shows an example of a specimen image.

Referring to FIG. 5B, the variable binarizer 510 sets the peripheral region 720 of the central region 710 as a reference region in the specimen image, (710) can be variable-binarized.

The result of the variable binarization is the same as shown in Fig. (C), and the segregation region decider 520 can determine the region 731 having an area of a certain area or more as a segregation region. That is, the segregation area determiner 520 can remove the noise by deleting the binarized value 732 having a size smaller than a predetermined value in the variable binarized result.

8 is a graph for explaining segregation determination performed in the segregation information generation unit shown in Fig.

As described above, the segregation region determiner 520 can determine, as the segregation region, an area in which the pixel value histogram of the variable-binarized reference region is equal to or less than a preset threshold value.

The graph of FIG. 8 shows the relationship between the pixel value (Gray level) of the variable binarized reference area and the histogram (histogram).

In the illustrated example, the lower 2% is set as the threshold value, and the region corresponding to the lower 2% threshold value of the pixel value histogram is determined as the segregation region. However, according to the embodiment, the lower% value as the threshold value may be changed and set.

It can be seen that in an embodiment of the present invention that illuminates uniform light, gray levels appear with relatively even distribution similar to the example shown in the histogram for the image. Therefore, the area corresponding to the dark area of the lower 2% or less corresponds to the area having a high dark value as compared with the average of the surrounding area, which corresponds to the segregation area.

FIG. 9 is a reference graph for explaining variable binarization by the variable binarizer shown in FIG. 6. Referring to FIG. 9, the variable binarization will be described. In the variable binarization, the average brightness value of the reference area 720 varies This means that the standard of binarization is variable.

That is, in the conventional fixed value binarization, binarization is performed by applying the image brightness of the center region on the basis of a predetermined reference value, but the variable binarizer 510 performs binarization on the center region with reference to the average brightness value of the reference region, The binarization can be accurately performed even if the specimen image has different overall brightness according to the specimen image.

FIG. 10 shows a result of fixed value binarization for a specimen image of different brightness, and FIG. 11 shows a result of a variable binarization according to the present invention for a specimen image of the same specimen having different brightness. And is a reference diagram showing one result.

Since the fixed value binarization is used in FIG. 10, the region other than the segregation is also detected as the segregation in FIG. (A), and the segregation is not detected in the region (b).

In FIG. 11 according to the present invention, since the variable binarization is used, it can be seen that the segregation is detected in the same manner even when the brightness of FIGS. (A) and (b) is different.

Various embodiments of the segregation analysis apparatus have been described above with reference to Figs. 1 to 11. Fig.

Hereinafter, various embodiments of the segregation analysis method will be described with reference to FIG. However, the segregation analysis method described below can be more easily understood with reference to the description of the segregation analysis apparatus described with reference to Figs. 1 to 11. [

12 is a flowchart illustrating a method of analyzing segregation according to an embodiment of the present invention.

Referring to FIG. 12, the segregation analysis apparatus can acquire a sensed image of a mold specimen including a plurality of specimens (S1210).

The segregation analysis apparatus can extract a plurality of specimen images for the plurality of specimens from the sensed image (S1220).

The segregation analysis apparatus detects segregation areas in each of the plurality of specimen images (S1230), and generates segregation analysis information by digitizing the segregation areas (S1240).

In one embodiment of the step S1210, the segregation analysis apparatus can irradiate the plurality of specimens with light using a ring illumination having a hollow corresponding to the shape of the camera lens.

In one embodiment of step S1220, the segregation analysis apparatus may correlate-match the template image and the sensed image, and perform a binarization on the correlation-matched result. Thereafter, the plurality of specimen images may be extracted from the sensed image based on the binarized result.

In one embodiment of the step S1230, the segregation analysis apparatus may set the peripheral region of the central region as a reference region in the specimen image, and variably binarize the central region using the average brightness of the reference region. Thereafter, an area in which the histogram of the pixel value of the reference area that is variable-binarized with respect to the variable binarized result value is equal to or less than a predetermined threshold value can be determined as the segregation area.

In one embodiment of the step S1240, the segregation analysis apparatus may generate the segregation analysis information by calculating at least one of the size, length, brightness information, angle, segregation amount, and segregation ratio of the segregation region.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are not intended to limit the invention to the particular forms disclosed. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

100: Segregation analyzer
110: image acquiring unit 120: specimen image extracting unit
130: Segregation information generating section
210: camera 211: lens
220: Lighting device
310: matching machine 320: binarizer
330: image extractor
510: variable binarizer 520: segregation region determiner
530: Information generator

Claims (10)

An image acquiring unit acquiring a sensed image of a mold specimen including a plurality of specimens;
A plurality of specimen images for each of the plurality of specimens are extracted from the captured image, a center point is detected for the plurality of specimen images, an array line is formed using center points belonging to the highest level line, A specimen image extracting unit for rotating the sensed image; And
The method comprising: setting a peripheral region of a center region as a reference region in each of a plurality of specimen images; performing variable binarization using the average brightness of the reference region to detect a segregation region; A segregation information generating unit for generating information;
And a seismic analysis device.
The apparatus of claim 1, wherein the image obtaining unit
camera; And
An illumination device including a plurality of light source elements and having a cavity corresponding to a shape of a lens of the camera;
And a seismic analysis device.
The apparatus of claim 1, wherein the specimen image extracting unit
A matching unit for performing correlation coefficient matching between the template image and the sensed image;
A binarizer for binarizing the output of the matching unit; And
An image extractor for extracting the plurality of specimen images from the captured image based on an output of the binarizer;
And a seismic analysis device.
The apparatus according to claim 1, wherein the segregation information generating unit
A variable binarizer for setting a peripheral region of a center region as a reference region in the specimen image and variably binarizing the center region using an average brightness of the reference region; And
A segregation area determiner for determining, as the segregation area, an area whose histogram of the pixel value of the reference area is variable and binarized to be less than a preset threshold value;
And a seismic analysis device.
The apparatus according to claim 1, wherein the segregation information generating unit
An information generator for calculating at least one of size, length, brightness information, angle, segregation amount, and segregation ratio of the segregation region to generate the segregation analysis information;
Further comprising:
Obtaining an image of an image of a mold specimen including a plurality of specimens;
A plurality of specimen images for each of the plurality of specimens are extracted from the captured image, a center point is detected for the plurality of specimen images, an array line is formed using center points belonging to the highest level line, Rotating the captured image; And
The method comprising: setting a peripheral region of a center region as a reference region in each of a plurality of specimen images; performing variable binarization using the average brightness of the reference region to detect a segregation region; Generating information;
≪ / RTI >
7. The method of claim 6, wherein obtaining the captured image comprises:
Irradiating light having a light uniformity of the horizontal axis and a light uniformity of the vertical axis of 96% or more and a difference between the light uniformity of the horizontal axis and the light uniformity of the vertical axis within 2%;
≪ / RTI >
7. The method of claim 6, wherein extracting the plurality of specimen images comprises:
Correlating the template image with the sensed image;
Performing a binarization on the correlation coefficient matched result; And
Extracting the plurality of sample images from the captured image based on the binarized result;
≪ / RTI >
7. The method of claim 6, wherein generating the segregation analysis information comprises:
Setting a peripheral region of the center region as a reference region in the specimen image;
Variable-binarizing the center region using an average brightness of the reference region; And
Determining, as the segregation area, an area in which the histogram of the pixel value of the reference area, which is variable-binarized, is less than or equal to a predetermined threshold value with respect to the result of the variable binarization;
≪ / RTI >
7. The method of claim 6, wherein generating the segregation analysis information comprises:
Calculating at least one of the size, length, brightness information, angle, segregation amount, and segregation ratio of the segregation region to generate the segregation analysis information;
≪ / RTI >

Images