JPH04238252A - Quality checking device for vegetable and fruit - Google Patents

Abstract

PURPOSE:To correctly grasp the colored state and check a vegetable or a fruit with high precision regardless of its shape or colored state by comparing the color value of each unit picture element of a photographed color image with the reference color value of the corresponding picture element. CONSTITUTION:A vegetable or a fruit 2 radiated by a light source 1 is photographed by a color camera 3, and an image processing computer 4 processes the image and outputs it to an image output device 5. The reference color value of each unit picture element of the standard color distribution pattern corresponding to the vegetable or the fruit 2 is stored in an image memory 6 in advance. The computer 4 compares the color value of each unit picture element of the photographed color image with the corresponding reference color value and judges the quality of the vegetable or the fruit 2 based on the result. The colored state can be correctly grasped, and the quality can be judged with high precision even if the shape and colored state of the vegetable or the fruit 2 are complex.

Description

[Detailed description of the invention]

0001

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an improvement in a fruit and vegetable quality testing apparatus for testing the quality of fruits and vegetables such as apples, pears, tomatoes, persimmons, and mandarin oranges.

0002

[Prior Art] Conventionally, as an example of this type of apparatus, there has been a device that photographs fruits and vegetables with a color camera, determines the shape and coloring state of the fruits and vegetables based on the color image obtained by the photographing, and tests the quality of the fruits and vegetables. It is being

0003

[Problem to be Solved by the Invention] However, since fruits and vegetables generally have complex shapes and coloring, conventional devices cannot accurately determine the coloring of fruits and vegetables, and as a result, highly accurate quality inspection cannot be performed. There was a drawback.

[0004] Accordingly, an object of the present invention is to provide an apparatus that can perform quality inspection of fruits and vegetables with high precision.

[0005]

[Means for Solving the Problems] In order to achieve the above object, the present invention provides an imaging means for photographing fruits and vegetables in color;
an image storage means that stores in advance a reference color value of each unit pixel of a standard color distribution pattern corresponding to the fruits and vegetables to be photographed; and a color value of each unit pixel of the color image photographed by the imaging means is stored in the image storage means. and a quality determining means for determining the quality of fruits and vegetables according to the comparison results.

[0006]

[Operation] The image storage means stores in advance the reference color value of each unit pixel of the standard color distribution pattern corresponding to fruits and vegetables photographed by the imaging means. The determining means compares the color value of each unit pixel of the color image photographed by the imaging means with the reference color value of the corresponding unit pixel stored in the image storage means. The quality determining means determines the quality of the fruits and vegetables according to the comparison results. Therefore, in the present invention, even if the shape and coloring state of fruits and vegetables are complex, the coloring state can be accurately grasped, and the quality of the fruits and vegetables can be verified with high accuracy.

[0007]

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

[0008] In FIG. 1, reference numeral 1 denotes a light source placed above the left and right sides of fruits and vegetables 2 to illuminate the fruits and vegetables 2. As shown in FIG. A color camera 3 such as a color television camera or a CCD camera is arranged above the fruits and vegetables 2 as an imaging means for photographing the fruits and vegetables 2 in color.

The color camera 3 is connected to the input side of an image processing computer 4. The image processing computer 4 processes images of fruits and vegetables 2 captured by the color camera 3 as described later. An image output device 5 consisting of a display device, a printer, etc. is connected to the output side of the image processing computer 4. Further, the image processing computer 4 is connected to an image memory 6 in which reference color values of each unit pixel of a standard color distribution pattern corresponding to fruits and vegetables such as apples photographed by the color camera 3 are stored in advance.

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

First, a standard color distribution pattern 7 of a fruit or vegetable 2 (for example, an apple) to be photographed with a color camera 3 and subjected to image processing is created as shown in FIG. The permissible range of the reference color value in each unit pixel 8 is determined, and the data is stored in the image memory 6 (
Step S1). An example of the allowable range of the reference color value in the unit pixel 8 is expressed as follows when expressed using the L*a*b* color system.

[0012]a1≦L*<a2 a3≦a*　<a4 a5≦b*　<a6 Here, in the above formula, a1 to a6 are predetermined numerical values.

Next, fruits and vegetables 2 photographed with a color camera 3
A color image of is input (step S2). Then, the center of gravity of the input color image is calculated, and the calculated center of gravity is aligned with the center of gravity of the standard color distribution pattern 7 shown in FIG. 3 (step S3). Thereafter, pattern matching is performed by image manipulation such as image reduction, enlargement, and rotation (step S4).

Subsequently, the color of each unit pixel of the input color image is digitized, and each color value belongs to the allowable range of the reference color value in the corresponding unit pixel 8 of the standard color distribution pattern 7 stored in the image memory 6. It is determined whether or not the color value is within the allowable range of the reference color value, and unit pixels belonging to the allowable range of the reference color value are extracted from the input color image (steps S5 and S6). Then, this number of extracted pixels is compared with the total number of pixels constituting the standard color distribution pattern 7, and the fruits and vegetables 2 are graded as "excellent", "excellent", and "substandard" (step S7).

[0015] Through the above-described image processing, even if the shape and coloring of fruits and vegetables are complex, the coloring state can be accurately grasped, thereby making it possible to grade fruits and vegetables with high accuracy.

By the way, in the above-mentioned geometric conversion in step S4, the data conversion of the image memory is carried out separately into the contour part (outer part) and the central part excluding the contour part, which is the grade test for fruits and vegetables. This is preferable in order to improve the accuracy. In other words, during geometric transformations such as reduction, enlargement, and rotation, input pixel data is distributed according to the distance to the four output pixel positions surrounding the data, and this distribution is performed in the central part of the image memory. The process is performed only on the data of the contour part, and not on the data of the contour part. Specifically, when setting the image memory, a command to prohibit distribution of the contour data is stored in the memory of the contour data, or after setting the image memory, filter processing and contour extraction are performed to prevent distribution. This can be realized by storing the command in the outline data memory.

[0017]

As explained above, in the present invention, the reference color value of each unit pixel of the standard color distribution pattern corresponding to the fruits and vegetables to be photographed is stored in advance in the image storage means,
The color value of each unit pixel of the color image taken by the imaging means is
The color value of the corresponding pixel stored in the image storage means is compared with the reference color value, and the quality of the fruits and vegetables is determined according to the comparison result. Therefore, in the present invention, even if the shape and coloring state of fruits and vegetables are complex, the coloring state can be accurately grasped, and the quality of fruits and vegetables can be verified with high accuracy.

[Brief explanation of the drawing]

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 according to an embodiment of the present invention.

FIG. 3 is a diagram schematically showing the relationship between a standard color distribution pattern and a unit pixel.

[Explanation of symbols]

1 Light source 2 Fruits and vegetables 3 Color camera 4 Image processing computer 5 Image output device 6 Image memory

Claims (1)

[Claims] 1. An imaging means for photographing fruits and vegetables in color; an image storage means for storing in advance a reference color value of each unit pixel of a standard color distribution pattern corresponding to the fruits and vegetables to be photographed; Comparing means for comparing the color value of each unit pixel of the image with a reference color value of each corresponding unit pixel stored in the image storage means, and quality determining means for determining the quality of the fruits and vegetables according to the comparison result. A quality inspection device for fruits and vegetables.