JPH04147042A - Device for checking class of vegetable and fruit - Google Patents

Abstract

PURPOSE:To achieve a highly accurate class checking by extracting an image with a same color which belongs to two preset extraction ranges from a shot color image and then checking class of vegetables and fruits from an area of the extracted image. CONSTITUTION:A color image of an apple 5 which is shot by a color camera 2 is input to a computer for image processing 3. In the computer 3, extraction color ranges (a) and (b) are set to enable a specific color to be extracted from the input color image. Then, comparison reference areas A and B under judgment conditions used for determining class are set. Then, an image with a same color as that belonging to a range a is extracted from an input color image and a total product image area x is obtained. In the similar manner, a total area y of an image which is the same color belonging to a range b is obtained. Then, the total area x and A and total area y and B are compared. When the total area x is smaller than A and the total area y is smaller than B, the class of the apple 5 is determined to be 'excellent'. It is determined to be 'good' in the other cases.

Description

DETAILED DESCRIPTION OF THE INVENTION (Field of Industrial Application) The present invention relates to an apparatus for determining the grade of fruits and vegetables such as apples, pears, tomatoes, persimmons, and mandarin oranges.

(Prior Art) Conventionally, as an example of this type of device, a color camera installed above the fruit and vegetables photographs the fruit and vegetables, and the color image obtained by the photographing is compared with a reference color to match the color of the reference. It is known that the total area of a color image is determined, and fruits and vegetables are graded based on the size of the determined total area.

(Problem to be solved by the invention) However, with the conventional apparatus, the ground color and the colored part of the fruit and vegetables are similar to each other, like the cup of an apple, and the colored part has a shading of color, and the shading affects the grading test. In such cases, a problem arises in that the accuracy of the grade test is low.

Therefore, in view of the above points, the present invention aims to solve the above problems.

(Means for Solving the Problems) In order to achieve the above object, the present invention was constructed as follows.

That is, the present invention provides a light source for illuminating fruits and vegetables, an imaging means for photographing the fruits and vegetables in color, and an extraction means for extracting images of the same color as those belonging to two extraction ranges set in advance from the photographed color images. , an image area calculating means for calculating the area of each extracted image, and a grading testing means for testing the grading of the fruits and vegetables based on the calculated area of each image.

(Function) In the present invention configured as described above, the extraction means extracts images of the same color as those belonging to two extraction ranges set in advance from the color images photographed by the imaging means.

The image area calculating means calculates the area of each of the extracted images. Then, the grade verification means performs a grade verification of the fruits and vegetables based on the calculated area of each image.

Therefore, in the present invention, when a fruit or vegetable has a ground color (uncolored part) and a colored part similar to each other, such as an apple cup, and the colored part has a shade of color, the shade affects the grade test. It is also possible to perform a grade test that takes into account the shade of the color, improving the accuracy of the grade test.

(Embodiments) Hereinafter, embodiments of the present invention will be described with reference to drawing numbers.

In FIG. 1, 1 is placed above the left and right of fruits and vegetables 5,
It is a light source that irradiates the fruits and vegetables 5. A color camera 2 such as a color television camera or a COD camera is arranged above the fruits and vegetables 5 as an imaging means for color photographing the fruits and vegetables 5.

The color camera 2 is connected to the input side of the image processing computer 3. The image processing computer 3 processes images of fruits and vegetables 5 captured by the color camera 2 as described later.

An image output device 4 consisting of a display device, a printer, etc. is connected to the output side of the image processing computer 3.

Next, an example of image processing in the embodiment configured as described above will be described with reference to FIG. 2 for the case where the fruit or vegetable 5 is a cup of apples.

First, a color image of an apple photographed by the color camera 2 is input (step SL).

Then, in order to extract a specific color from the manually created color image, the ranges a and b of the colors to be extracted are respectively set (step S2). As for this setting method, f,
When using the f-bi color system, for example, the extraction color range a is (1) on the coordinates a' and b as shown in Figures 3 and 4.
The equation and extraction color range are set as shown in equation (2).

0≦, f<5 (1) 5≦♂ (2) Here, the extraction color range is set only for gore and not for ridges, but this is acceptable in practice.

Next, as will be described later, comparison standard areas ASB related to the discrimination conditions used in grade discrimination are respectively set (step S3).

Next, from the input color image, extract an image with the same color as the color that belongs to the set extraction color range a, calculate the total area X of the extracted image, and similarly from the input color image, An image having the same color as the color is extracted and the total area y of the extracted image is determined (steps S4 and S5).

Then, the total area X obtained in this way is compared with the comparison reference area A set in step S3, and the total area y is similarly compared with the comparison reference area B (steps S6 and S7).

As a result of the comparison, if the total area X is smaller than the comparison standard area A and the total area y is smaller than the comparison standard area B, the grade of the apple is set as "extra large", and in other cases, the grade is set as " Hide”.

Now, select 10 detection points in the input color image, and calculate the value of each color of the red part and ground color (edge) in each part by 3 × 3.
When the average color of a total of 9 pixels is plotted on the coordinates d and vi, it becomes as shown in FIGS. 3 and 4.

Figure 3 shows the case where the grade of the apple cup is "extra large",
The red part is distributed in a narrow range where the detected value is from 0 to 5. Figure 4 shows the case where the grade of the apple cup is "excellent", and the red part is distributed in a wide range where the detected value is from 0 to 15. It can be seen that there is a distribution of

Therefore, when determining the grade of an apple cup, the color ranges a and b to be extracted are set on the coordinates d and bi as shown in equations (1) and (2), respectively, as described above. If image processing is performed using each of the steps described above, highly accurate grade verification becomes possible.

(Effects of the Invention) As described above, in the present invention, images of the same color as those belonging to two extraction ranges set in advance are extracted from a color image photographed by an imaging means, and the area of each extracted image is calculated. Since the fruit and vegetables are graded based on the area of each image, the ground color (uncolored part) and the colored part are similar, and the color of the colored part is similar to that of a fruit or vegetable, like a jade cup of an apple. Even in cases where there is a shading of color and the shading affects the grade test, the grading test can be performed taking into account the shading of the color, improving the accuracy of the grade test.

[Brief explanation of drawings]

Fig. 1 is a diagram showing the overall configuration of an embodiment of the present invention, Fig. 2 is a flowchart showing an example of image processing in the embodiment of the present invention, and Figs. , is a diagram plotted on the . 1 is a light source, 2 is a color camera, and 3 is an image processing computer.

Claims (1)

[Scope of Claims] A light source that illuminates fruits and vegetables, an imaging device that photographs the fruits and vegetables in color, and an extraction device that extracts images of the same color as those belonging to two preset extraction ranges from the photographed color images. A fruit and vegetable grading device comprising: an image area calculating means for calculating the area of each extracted image; and a grading testing device for performing a grading test of the fruits and vegetables based on the calculated area of each image.