JPH04307357A - Apparatus for detecting bruise of fruit and vegetable - Google Patents

Abstract

PURPOSE:To evaluate only fruit or vegetable whose bruise can be certainly judged regardless of the feed posture of the fruit or vegetable by removing the element indefinite in the evaluation of the bruise from the image of the fruit or vegetable and to also eliminate trouble such that the total area of a bruise is not calculated in such a case that the fruit or vegetable is fed in such a state that the calyx thereof is turned down. CONSTITUTION:A color camera 4 takes the image of the fruit or vegetable with a calyx fed by a feeder 1. When the taken image is inputted, the saturation of said image is calculated and the fruit or vegetable being an object is extracted from the image of the calculated saturation. The part corresponding to the calyx and the peripheral part thereof are removed from the image of the fruit or vegetable to extract the residual part. The bruise of the fruit or vegetable is detected from the extracted image.

Description

[Detailed description of the invention]

0001

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a fruit and vegetable flaw detection apparatus for detecting flaws in fruits and vegetables with stems, such as persimmons, mandarin oranges, tomatoes, and eggplants.

0002

[Prior Art] Conventionally, methods for detecting this type of flaw include:
The fruits and vegetables being conveyed by the conveyance device are photographed using a color sensor, the total area of scratches is calculated from this image, the area corresponding to the dead body is uniformly subtracted from the total sum, and the result of the subtraction is calculated as the area of scratches on the fruits and vegetables. The total area is known.

0003

By the way, fruits and vegetables transported by a transport device are transported with their stems facing upward or downward, and the state of the transport varies. Therefore, in the case of fruits and vegetables that are transported with their stems facing upward, the total area of scratches detected as described above is accurate.

However, in the case of fruits and vegetables that are transported with the stem facing downward, the total area of the detected scratches is not only inaccurate, but also when the total area of the scratches is less than the area corresponding to the stem, the total area of the scratches is not accurate. There is a disadvantage that the area cannot be detected, and a solution to this problem has been desired.

[0005] In view of these points, the present invention removes uncertain elements in the evaluation of flaws from images of fruits and vegetables, and evaluates only those that can be reliably determined to be flaws, regardless of the conveyance posture of the fruit or vegetables. The purpose is to

[0006]

[Means for Solving the Problems] In order to achieve the above object, the present invention is constructed as follows. That is, the present invention provides a light source that irradiates light toward fruits and vegetables with stems that are conveyed by a conveyance device, an imaging device that photographs the fruits and vegetables in color, and an image capturing device that captures images of fruits and vegetables photographed by the imaging device. The image forming apparatus includes an extracting means for extracting the remaining part by excluding the corresponding part, and a flaw detection means for detecting flaws in fruits and vegetables from the extracted image.

[0007]

[Operation] The imaging means photographs fruits and vegetables with stems being conveyed by the conveying device. The extracting means removes a portion corresponding to the stem from the image of the photographed fruit or vegetable and extracts the remaining portion. The flaw detection means detects flaws in fruits and vegetables from the extracted image. In this way, the fruit or vegetable image extracted by the extracting means is obtained by removing the portion corresponding to the stem, in other words, the element that is uncertain in determining the damage. Therefore,
With the present invention, it is possible to evaluate only those that can be reliably determined to be scratches, regardless of the conveyance posture of fruits and vegetables, and when the fruits and vegetables are conveyed with the stems facing downward, it is not possible to calculate the total area of scratches as in the conventional method. This inconvenience can be resolved.

[0008]

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

In FIG. 1, reference numeral 1 denotes a conveyance device for conveying fruits and vegetables 2 from the back of the paper toward the front. The fruits and vegetables 2 conveyed by this conveying device 1 are fruits and vegetables with stems, such as persimmons, mandarin oranges, tomatoes, and eggplants. Further, a pair of light sources 3, 3 are arranged on the left and right sides of the conveyance device 1, which illuminate the fruits and vegetables 2 being conveyed from the left and right directions. A color camera 4 such as a CCD camera is installed right above the conveying device 1 as an imaging means for photographing fruits and vegetables 2 illuminated by light sources 3, 3.

The color camera 4 is connected to the input side of an image processing computer 6 via an A/D conversion circuit 5. The image processing computer 6 processes the images of fruits and vegetables 2 taken by the color camera 4 as described below. An image output device 7 consisting of a display device, a printer, etc. is connected to the output side of the image processing computer 6.

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

Now, when fruits and vegetables 2 with stems are conveyed by the conveying device 1, the fruits and vegetables 2 are photographed by a color camera 4, and R, G, and B signals are outputted from the color camera 4. These R, G, and B signals are converted into A/D converter circuit 5.
/D conversion and then input to the image processing computer 6 (S1). The image processing computer 6 calculates the saturation of the image by a predetermined calculation based on the R, G, and B signals (S2), and stores the calculated saturation distribution in the memory, as shown in FIG. Images with high and low saturation are obtained in memory. Thereafter, the target fruit or vegetable is extracted from the image (S3).

Next, from the extracted fruits and vegetables images,
The portion corresponding to the stem is removed (S4). If the fruit or vegetable has a flattened center such as persimmons or mandarin oranges, find the center of the fruit or vegetable from the image, define a circle whose radius is a certain distance from the found center as the center part A, and define this center part A. Remove the part corresponding to the stem (see Figure 4). continuation,
In order to prevent false detection due to blurring or uneven illumination around the image, the periphery of the fruit or vegetable image is removed (S5). In this process, a certain distance from the outline of the fruit or vegetable image is defined as the peripheral part B of the image, and this is removed (see FIG. 4).

[0014] In the fruit and vegetable images extracted in this way, only the parts for which damage determination is certain are extracted, and the parts corresponding to the stems, which are uncertain elements for damage determination, and the parts of the image are extracted. All peripheral parts are in a state where they have been removed. Next, the saturation of each point of the extracted fruit or vegetable image is compared with a predetermined reference value, and points lower than the reference value are determined to be flaws. Then, the total sum of the scratches determined in this way is determined (S6).

[0015] As described above, in the embodiment of the present invention, the part corresponding to the rotten part and the peripheral part of the image are removed from the image of fruits and vegetables, so that uncertain elements in the determination of flaws are removed. . Therefore, regardless of the transportation posture of fruits and vegetables, only those that can be reliably determined to be scratches can be evaluated, and even if the fruits and vegetables are transported with the stems facing downward, it is not possible to calculate the total area of scratches as in the past. This inconvenience can be resolved.

[0016]

[Effects of the Invention] As described above, in the present invention, the remaining portion is extracted from an image of fruits and vegetables photographed by an imaging means, excluding the portion corresponding to the stem, and scratches on the fruits and vegetables are detected from the extracted image. I did it like that. Therefore, in the present invention, since elements that are uncertain in determining flaws are removed from images of fruits and vegetables,
Regardless of the transportation posture of fruits and vegetables, it is possible to evaluate only those that can be reliably determined to be scratches, and it also eliminates the inconvenience of not being able to calculate the total area of scratches when the fruits and vegetables are transported with the stems facing downward. can.

[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 according to an embodiment of the present invention.

FIG. 3 is a diagram showing an example of storage in an image memory.

FIG. 4 is an explanatory diagram for removing parts corresponding to stems from images of fruits and vegetables.

[Explanation of symbols]

1 Conveyance device 2 Fruits and vegetables 3 Light source 4 Color camera 6 Image processing computer 7 Image output device

Claims (1)

[Claims] 1. A light source that irradiates light toward fruits and vegetables with a stem that are conveyed by a conveying device, an imaging device that photographs the fruits and vegetables in color, and a device that extracts an image of the fruits and vegetables taken by the imaging device. A flaw detection device for fruits and vegetables, comprising: an extractor for extracting a remaining portion by excluding a portion corresponding to the image; and a flaw detecting means for detecting flaws in the fruit or vegetables from the extracted image.