Egg surface inspection device

Abstract

To provide an egg surface inspection device that can evaluate concavity and convexity of a shell from image data having an egg photographed.SOLUTION: An egg surface inspection device of the present invention comprises: a conveyer that conveys eggs in a state where two rollers support the egg; image capture means that is installed above an LED light source irradiating the egg on the conveyer with white light and the conveyer, and includes a color camera image-capturing the egg during conveyance; and image determination means that determines a square-sized inspection image relative to an image of the image-captured egg, after a full color image of the inspection image is converted to a gray scale image, calculates an approximate curve relative to an inspection line in the gray scale image with a gray scale value of each pixel regarded as concavity and convexity of a shell surface, calculates a standard deviation (m) of roughness from a top and bottom relative to the approximate curve, and determines the pass / fail of the shell on the basis of the standard deviation (m).SELECTED DRAWING: Figure 8

Description

[Technical field]

[0001] The present invention relates to an egg surface inspection device capable of evaluating the unevenness of the egg shell. [Background technology]

[0002] Small clumps of bumps sometimes appear on the surface of chicken eggs. This does not affect the contents of the egg, but it is considered desirable to separate the eggs as they look unattractive. Patent Document 1 shows a dirty egg inspection device that inspects eggshells for dirt, and is equipped with a color CCD camera, a lighting unit, a transport roller, an image processing device, and an image judgment unit. However, the unevenness of the eggshell is the same white color as the rest of the egg and is fine, so there is a problem that it is difficult to judge from the image. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2008-309678 A Summary of the Invention [Problem to be solved by the invention]

[0004] The present invention provides an egg surface inspection device capable of evaluating the unevenness of an egg shell from image data obtained by capturing an image of the egg surface. [Means for solving the problem]

[0005] The egg surface inspection device according to the present invention is characterized in comprising: a conveyor that transports eggs supported by two rollers; imaging means having an LED light source that irradiates white light onto the eggs on the conveyor and a color camera that is installed above the conveyor and images the eggs as they are transported; and image judgment means that determines a rectangular inspection image for the captured egg image, converts the full-color image of the inspection image into a grayscale image, and then calculates an approximation curve for an inspection line in the grayscale image by regarding the grayscale value of each pixel as the unevenness of the shell surface, calculates the standard deviation (m) of roughness from the peaks and valleys of the approximation curve, and judges the pass / fail of the shells based on the standard deviation (m).

[0006] The shell is judged to be acceptable or not according to whether the value (m / σ) obtained by dividing the standard deviation (m) by the standard deviation (σ) of normal eggs that has been determined in advance is greater or smaller than a predetermined threshold value (T).

[0007] The approximation curve is characterized in that it is approximated by a fourth-order function with x as a variable. Effect of the Invention

[0008] According to the egg surface inspection device of the present invention, a full-color image of an egg is converted into a grayscale image, and the grayscale value of each pixel for the inspection line in the grayscale image is regarded as the unevenness of the shell surface, and the standard deviation of the roughness is calculated, so that a judgment can be made using a numerical value based on the standard deviation, which is more accurate than judging whether there is a shadow on the egg surface.

[0009] The standard deviation (m) is divided by the previously determined standard deviation (σ) of normal eggs to calculate a judgment value (m / σ), and the pass / fail judgment of the shell is made based on whether the judgment value is greater or smaller than a predetermined threshold value (T), allowing for a more accurate and stable pass / fail judgment.

[0010] The approximation curve is a quartic function with x as a variable, so it can approximate the shape of the egg's surface curve. It can calculate the standard deviation more accurately than linear approximation. [Brief description of the drawings]

[0011] [Figure 1] FIG. 2 is a plan view of an egg surface inspection device for inspecting eggs. [Diagram 2] FIG. 2 is a detailed configuration diagram of the imaging means in FIG. [Diagram 3] FIG. 13 is an explanatory diagram of an inspection image of an egg. [Figure 4] FIG. 1 shows a full-color inspection image. [Diagram 5] FIG. 2 illustrates an example of conversion from color pixels to grayscale pixels. [Figure 6] FIG. 13 shows an inspection image converted to grayscale. [Figure 7] FIG. 13 is a graph showing an inspection line. [Figure 8] This is a graph in which the deviation from the approximation curve in FIG. 7 is normalized. [Figure 9] 4 is a process flowchart of the egg surface inspection device. [Figure 10] This is an example of visualizing a grayscale image in pseudocolor. [Figure 11] 1 is an example of an inspection image visualized in pseudocolor. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an egg surface inspection device according to the present invention will be described in detail with reference to the drawings. EXAMPLES

[0013] FIG. 1 is a plan view of an egg surface inspection device 100 that inspects eggs. The egg surface inspection device 100 includes a conveyor 7, an imaging means 20 installed on the conveyor 7, and an image determination means 30. The image determination means 30 can use a computer equipped with a processor, memory, and a magnetic disk. The conveyor 7 has one lane, and conveys eggs 1 supported by two rollers 8 at a predetermined speed in the conveying direction. In this embodiment, the eggs 1 are raw chicken eggs. In the case of chicken eggs, the shell has a thickness of about 0.3 mm. The unevenness of the shell is about 0.1 to 0.3 mm.

[0014] FIG. 2 is a detailed diagram of the imaging means 20 in FIG. 1. The imaging means 20 includes an LED light source 4 that irradiates the egg 1 with white light, and a color camera 5 that images the egg 1 during transportation. A line scan camera is better than an area camera for the color camera 5, since it can detect fine irregularities. A color camera is used because it is expected that the egg's color will be determined for the egg surface inspection, and it can be applied to other purposes. As shown in FIG. 2, the light 14 emitted from the LED light source 4 is reflected by a half mirror 10 to become the light 15 irradiated onto the egg 1. The light 16 reflected from the egg 1 passes through the half mirror 10 to become the light 17 incident on the camera 5. In the case of a line sensor camera, the egg 1 moves in the transportation direction by the conveyor 7, and is imaged line by line. The light 15 irradiated onto the egg 1 and the light 17 incident on the camera 5 are configured to be on the same axis. In this case, the side located on the outside (outer circumference) of the egg 1 is imaged slightly darker than the upper surface, since the reflected light does not go directly upward.

[0015] FIG. 3 is an explanatory diagram of an inspection image 11 of an egg 1. Color camera 5 captures an image so that the entire egg 1 is within imaging range 19. The grey part is the background 21. The side of egg 1 located on the outer periphery appears slightly dark, so a bright rectangular-sized part at the top of the egg is used as inspection image 11. The shell of egg 1 shows similar unevenness everywhere, so there is no need to check the entire circumference of egg 1. It is sufficient to inspect inspection image 11 of the top surface of egg 1, and the overall condition of the shell can be determined.

[0016] FIG. 4 is a diagram showing a full-color inspection image 11. Assume that the inspection image 11 is a full-color image and is composed of n×m pixels. If n and m are 1000 pixels and a length of 20 mm is captured with 1000 pixels, the size of one pixel is approximately 0.02 mm. A color pixel 2 is composed of three bytes of R, G, and B, and R, G, and B can each express a tone of 0 to 255. Here, the tone is a numerical value indicating the color density or brightness.

[0017] FIG. 5 is a diagram showing an example of conversion from a color pixel 2 to a grayscale pixel 3. FIG. 5 shows five typical examples of color conversion. When the color pixel 2 (R, G, B) = (255, 255, 255) is white and converted to a grayscale pixel 3, the white pixel has a Gs of 255. When the color pixel 2 is (R, G, B) = (255, 255, 0) indicating yellow, the gray pixel has a Gs of 170. When the color pixel 2 is (R, G, B) = (255, 0, 0) indicating red, the gray pixel has a Gs of 85. When the color pixel 2 is (R, G, B) = (0, 0, 0) indicating blue, the gray pixel has a Gs of 85. When the color pixel 2 is (R, G, B) = (0, 0, 0) indicating black, the grayscale pixel has a Gs of 0. The conversion formula (R + G + B) / 3 is used for conversion from the color pixel 2 to the grayscale pixel 3 as described above. The present invention is not limited to this, and a weighted conversion formula may be used.

[0018] FIG. 6 is a diagram showing an inspection image 11 converted into a grayscale image. A grayscale pixel 3 can be expressed by a gradation of 0 to 255. An inspection line 6 is defined at a position (indicated by AA) of an X coordinate k in the inspection image 11. The pixels of the inspection line 6 are designated p1 to p n In this example, n is set to 1000.

[0019] 7 is a diagram showing a graph of the inspection line 6. Each of the pixels p1 to p 1000 When plotted, a zigzag waveform is obtained, as shown by the wavy line as an example. The downward slope to the right indicates that the brightness of the lower part of the inspection image 11 is reduced because the inspection image 11 is set slightly below the center of the egg 1, as shown in FIG. 3. The numerical values ​​of the grayscale pixels are brightnesses that reflect the unevenness of the shell surface. Pixels p1 to p 1000 The approximate curve for each value can be obtained as shown by the thick line. The approximate curve is y=a1X 4 +a2X 3 +a3X 2 +a1X 1 +a5. The coefficients a1 to a5 are calculated based on the values ​​of each pixel, and a1 is 1.303e -9 , a2 is -1.127e -6, a3 is 0.000211, a4 is -0.0505, and a5 is 204.8. When X is 0, Y is 204.8, so these values ​​are slightly lower than pure white (255).

[0020] FIG. 8 is a graph in which the deviation from the approximation curve 9 in FIG. 7 is converted into a horizontal straight line. 1000 The deviation of each value from the approximation curve 9 is plotted. Approximation curve 9 is assumed to be horizontal. This graph is the same as for evaluating the surface roughness of metal, and the standard deviation (m) can be calculated from the values ​​of the peaks and valleys that represent the unevenness. In addition, the standard deviation (σ) of normal eggs is determined in advance, and a judgment value (m / σ) is calculated. Depending on whether the judgment value (m / σ) is larger or smaller than the threshold value (T), a pass / fail judgment is made regarding the unevenness of the eggshell.

[0021] The standard deviation (m) can be calculated using the following formula 1. m is calculated by squaring the height of the i-th peak (or the depth of the valley), adding up the total number of these squared, dividing by n, and taking the root. Note that the number of inspection lines 6 is not limited to one, and pass / fail may be determined using multiple inspection lines 6.

[0022] [Formula 1] TIFF2024171251000002.tif20128

[0023] FIG. 9 is a process flow chart of the egg surface inspection device 100. S1 is a step of capturing an image of the surface of an egg being transported with a camera to obtain a full-color image. S2 is a step of cutting out an inspection image from the captured image. The size of the inspection image is m×n (m pixels horizontally and n pixels vertically). S3 is a step of gray-scaling each pixel (RGB) of the inspection image to create a gray-scale inspection image. S4 is a step of determining an inspection line within the inspection image. S5 is a step of calculating an approximation curve for the value of each pixel of the inspection line. S6 is a step of normalizing the deviation from the approximation curve to create a graph of the height of the peaks and the depth of the valleys. S7 is a step of calculating the standard deviation (m). S8 is a step of dividing the standard deviation (m) by the standard deviation (σ) of normal egg shells to obtain a judgment value (m / σ), and judging whether the judgment value (m / σ) is larger or smaller than a threshold value (T) to judge whether the shell passes or fails. Eggs whose judgment value (m / σ) is greater than a threshold value (T) can be picked up by a clamp installed above the conveyor and passed onto another conveyor.

[0024] Figure 10 is an example of visualizing a grayscale image with pseudocolor. It is difficult to tell the difference in gray even if the density changes. Therefore, the 255 gradation values ​​are divided into seven levels, and seven pseudocolors are assigned: red, orange, yellow, green, blue, indigo, and purple. For example, red is assigned to 217 to 255 on the grayscale, so the convex parts of the shell that reflect white are displayed in red, making it easy for the worker to check by displaying the inspection image on a monitor. The concave parts of the shell that are dark gray are displayed in blue to indigo, making it easy for the worker to check.

[0025] Figure 11 is an example of an inspection image 11 visualized in pseudocolor according to Figure 10. The grayscale image of Figure 8 was used for inspection image 11. As shown in (a), in the case of an NG egg, it can be seen that there are red lumps on the surface of the shell. On the other hand, as shown in (b), in the case of an OK egg, there are no red areas and there are mostly yellow areas.

[0026] The grayscale image is pseudocolorized and the number of red, orange, yellow, green, blue, indigo, and purple pixels in the inspection image 11 is counted. If there are a lot of red pixels or a lot of indigo pixels, this indicates that the shell is uneven, and can be used to distinguish between OK eggs and NG eggs. [Industrial Applicability]

[0027] The egg surface inspection device of the present invention can be applied to egg conveyor lines and is suitable as an egg surface inspection device for evaluating the unevenness of egg shells. [Explanation of symbols]

[0028] 1 egg 2 pixels (color) 3 pixels (grayscale) 4 LED light source 5 Color Camera 6 Inspection Line 7 Conveyor 8. Lola 9 Approximate curve 10 Half Mirror 11 Inspection images 12 Standard deviations 13 Roughness (unevenness) 14 Light emitted from LED 15 Light irradiation on eggs 16 Reflected light from eggs 17 Incident light to the camera 19 Imaging range 20 Imaging means 30 Image Judgment Method 100 Egg surface inspection device

Claims

1. A conveyor that transports eggs while being supported by two rollers; an imaging means including an LED light source that irradiates white light onto the eggs on the conveyor and a color camera that is installed above the conveyor and captures images of the eggs being transported; an image assessment means for determining a rectangular inspection image for a captured egg image, converting the full-color image of the inspection image into a grayscale image, calculating an approximation curve for an inspection line in the grayscale image by regarding the grayscale values ​​of each pixel as the unevenness of the shell surface, calculating a standard deviation (m) of roughness from the peaks and valleys of the approximation curve, and assessing the pass / fail of the shell based on the standard deviation (m).

2. 2. The egg surface inspection device according to claim 1, wherein the pass / fail of the shells is determined based on whether the value (m / σ) obtained by dividing the standard deviation (m) by a previously determined standard deviation (σ) of normal eggs is larger or smaller than a predetermined threshold value (T).

3. 2. The egg surface inspection device according to claim 1, wherein the approximation curve is approximated by a fourth-order function with x as a variable.

Images