JP3097153B2 - Grade testing equipment for fruits and vegetables - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION The present invention is applicable to a grade test for fruits and vegetables having stripes on the surface, such as whether the melon is easy to be used, and a test for both different properties such as meat and fat of loin. The present invention relates to a widely applicable testing device for fruits and vegetables.

[0002]

2. Description of the Related Art Hitherto, for example, the evaluation of the grade of a striped melon has been carried out visually by a human.

[0003]

However, the conventional visual rating test has the drawbacks that the work efficiency is poor, and that the dispersion is low and the reliability is low.

[0004] Therefore, an object of the present invention is to improve the work efficiency of the grading test for fruits and vegetables, improve the reliability thereof, and automate the same.

[0005]

In order to achieve the above object, according to the present invention, there is provided an image pickup means for photographing an object such as fruits and vegetables in color, and a surface portion of the object from the photographed color image. Color data calculating means for determining the color data of the stripe portion and the color data group of the surface portion and the color data group of the stripe portion. From the balance of
And a grade test means for evaluating the grade of the object based on a preset value. Also,
The invention according to claim 2 is an imaging means for photographing fruits and vegetables in color, a color data calculating means for respectively obtaining color data of a surface portion and a stripe portion of the fruits and vegetables from the photographed color image, and A center of gravity in color coordinates of the color data group, and a center of gravity calculating means for respectively obtaining the center of gravity in the color coordinates of the color data group of the obtained stripe portion, and a slope calculating means for calculating the slope of a line connecting the obtained both centers of gravity. And a grade test means for testing the grade of fruits and vegetables based on the obtained inclination.

[0006]

According to the first aspect of the present invention, the color data calculation means obtains color data of the surface portion and the stripe portion of the object from the color image taken by the imaging means. The grading test means obtains a representative value on the color coordinate from each color data group of the surface part and the stripe part of the object, and obtains the object based on a preset value from the mutual color balance based on the representative value. Assess the grade of an object. According to the second aspect of the invention, the color data calculation means obtains color data of the surface portion and the stripe portion of the fruits and vegetables from the color image taken by the imaging means. The center-of-gravity calculating means calculates the center of gravity in the color coordinates of the color data group of the obtained surface portion and the center of gravity in the color coordinates of the color data group of the obtained stripe portion. Each of the obtained centroids can be said to represent color information in the surface portion and the stripe portion, respectively. The grade tester tests the grade of a fruit or vegetable based on the slope of the line connecting the centers of gravity obtained by the slope calculator. The slope of this line segment varies depending on the grade of the fruits and vegetables, and can be said to accurately reflect that grade.

Therefore, according to the present invention, it is possible to improve the work efficiency, the reliability, and the automation of the grade test for fruits and vegetables having stripes such as melon.

[0008]

Embodiments of the present invention will be described below with reference to the drawings.

In FIG. 1, reference numeral 1 denotes a light source arranged above and below the fruits and vegetables 2 to irradiate the fruits and vegetables 2. Above the fruits and vegetables 2, a color camera 3 such as a color television camera or a CCD camera is arranged as an image pickup means for taking a color image of the fruits and vegetables 2.

The color camera 3 is connected to an input side of an image processing computer 4. Image processing computer 4
Processes an image of the fruits and vegetables 2 captured by the color camera 3 as described later. An output side of the image processing computer 4 is connected to an image output device 5 such as a display device or a printer.

Next, an example of image processing of the embodiment configured as described above will be described with reference to the flowchart of FIG.

First, a color image of a fruit or vegetable 2 such as a melon with stripes photographed by the color camera 3 is input (step S1). And in the captured color image,
As shown in FIG. 3, color measurement of the stripe portion and the surface portion is performed from the predetermined portion Z or the whole of the fruit and vegetable 2 (steps S2 and S3). Now, the color of the color image is, for example, L
When the data is classified and represented by the * a * b * color system, the color data of the stripe portion and the surface portion of the color image are L *, a *, b
Calculated as * respectively.

Next, a plurality of color data of the striped portion and the surface portion measured in this manner are converted into, for example, an L * -a * coordinate system, a *
The positions are displayed on the -b * coordinate system and the L * -b * coordinate system, and the respective positions of the center of gravity of the color data group of the surface portion and the center of gravity of the color data group of the stripe portion are obtained (step S4). Now, examples in which a plurality of calculated color data of the stripe portion and the surface portion are displayed on the L * -b * coordinate system are shown in FIGS. 4 and 5, respectively. A in the figure
Indicates the center of gravity of the color data group of the stripe portion, and B in the figure indicates the center of gravity of the color data group of the surface portion. 4 and 5 show the case of the mask melon, FIG. 4 shows the case where the grade is “medium”, and FIG. 5 shows the case where the grade is “special”.

Subsequently, the gradient of the line connecting them is calculated from both the centers of gravity obtained as described above (step S5), and the obtained gradient is compared with a predetermined reference value.
The grade of the fruits and vegetables is determined (step S6). The inclination of the line connecting the two centers of gravity differs depending on the grade in the case of a striped melon, for example, as shown in FIGS. 4 and 5, and can be said to accurately reflect the grade. Becomes possible.

In the above embodiment, the case of melon was described. However, the present invention is not limited to this case. For example, the case of testing the relationship between meat and fat having different properties such as fat and fat can be used. Of course, it can be widely applied.

Next, an example of image processing for discriminating a melon stripe from the surface using the apparatus shown in FIG. 1 will be described.

In this case, first, a color image of a striped melon taken by the color camera 3 is input. Next, from the input RGB image, a human selects stripes and a surface portion on the equatorial line of the melon, respectively.
A discriminant for discriminating between melon stripes and the surface using the image density values R, G, and B is obtained, for example, as in the following equation (1).

F = −20, 3893 + 0, 5568R−0, 2002G−0, 2598B (1) Next, using this discriminant, the stripes and the surface of each pixel on the equator of the melon of the input color image described above. Is determined. This makes it possible to evaluate the uniformity of the melon stripes.

[0019]

As described above, according to the present invention, the color data of the surface portion and the stripe portion of fruits and vegetables are obtained from the color image taken by the imaging means, and the color data group and the stripe portion of the obtained surface portion are obtained. , A representative value on each color coordinate is obtained from the color data group, and the class of the object is evaluated based on a preset value from the mutual color balance based on the representative value. Alternatively, the color data of the surface portion and the stripe portion of fruits and vegetables are obtained from the color image taken by the imaging means, the center of gravity of the obtained color data group of the surface portion in the color coordinates, and the obtained color data group of the stripe portion. , The center of gravity of each color coordinate is determined, the slope of a line connecting the determined centers of gravity is determined, and the grade of the fruit or vegetable is tested based on the result. Therefore, in the present invention, especially in the grade test of fruits and vegetables having stripes such as melon, the improvement of the work efficiency, the improvement of the reliability thereof, and the automation thereof can be realized.

[Brief description of the drawings]

FIG. 1 is a diagram showing an overall configuration of an embodiment of the present invention.

FIG. 2 is a flowchart illustrating an example of image processing according to an embodiment of the present invention.

FIG. 3 is a diagram illustrating color measurement of a predetermined portion of a color image.

FIG. 4 shows an example in which a plurality of color data of a stripe portion and a surface portion of a mask melon are displayed in an L * -b * coordinate system;
This is the case when the grade is “medium”.

FIG. 5 shows an example of displaying a plurality of color data of a stripe portion and a surface portion in a mask melon in an L * -b * coordinate system;
This is the case when the grade is “special”.

[Explanation of symbols]

 Reference Signs List 1 light source 2 fruits and vegetables 3 color camera 4 image processing computer 5 image output device

──────────────────────────────────────────────────続 き Continued on the front page (58) Field surveyed (Int.Cl. ⁷ , DB name) G06T 1/00 G01N 21/85 G01N 21/88-21/958

Claims (2)

(57) [Claims] An imaging means for photographing an object such as fruits and vegetables in color, a color data calculating means for respectively obtaining color data of a surface portion and a stripe portion of the object from the photographed color image, A representative value on each color coordinate is obtained from the color data group of the surface part and the color data group of the stripe part, and the class of the object is evaluated based on a preset value from the mutual color balance based on the representative value. And a grade testing device for fruits and vegetables, comprising: 2. An imaging means for photographing fruits and vegetables in color, a color data calculating means for respectively obtaining color data of a surface part and a stripe part of fruits and vegetables from the photographed color image, and a color data of the surface part thus found. Centroid in the color coordinates of the group,
And a center of gravity calculating means for calculating the center of gravity of the color data group of the obtained stripe data in color coordinates, a slope calculating means for calculating a slope of a line connecting the obtained centers of gravity, and a fruit or vegetable based on the obtained slope And a grade testing means for testing the grades of fruits and vegetables.