JPH06249634A - Device for evaluating stripe of netted melon - Google Patents

Abstract

PURPOSE:To improve the melon stripe evaluating accuracy and reliability and, at the same time, to save the manpower of stripe evaluating work by automation. CONSTITUTION:The image of a netted melon is inputted (S1) and the area of the melon are measured (S2). The skin section (from which stripes are removed) of the melon extracted from the image of the melon (S3). The longitudinal and transversal lengths of each extracted skin are found and the aspect ratio of each extracted skin is found from the longitudinal and transversal lengths (S4). The means value and standard deviation of the found aspect ratios are calculated (S5). Then the uniformity of net pattern of the melon is evaluated by comparing the means value and standard deviation of the found aspect ratios with reference values prefixed in corresponding to the measured area of melon measured in the step S2.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a net-type melon fringe evaluation device for evaluating fringes (net) of a net-type melon.

[0002]

2. Description of the Related Art Conventionally, since melon stripes are an important factor in appearance quality, it is common for an inspector to visually evaluate them.

[0003]

As described above, since the inspector has conventionally evaluated by visual inspection, there is a problem that the evaluation varies and the evaluation standard changes due to fatigue of the inspector. is there. Therefore, the conventional evaluation has a problem in that it is inferior in accuracy and reliability.

Therefore, an object of the present invention is to improve the precision of melon fringe evaluation and its reliability, and to realize labor saving of the evaluation work by its automation.

[0005]

In order to achieve the above object, the present invention has the following constitution. That is, the present invention is directed to an image pickup means for photographing a net-type melon, an epidermis extraction means for extracting a portion of the melon's epidermis from the photographed image, and a vertical and horizontal length ratio for calculating a vertical-horizontal length ratio of each extracted epidermis. The apparatus is provided with a ratio calculation means and a fringe evaluation means for evaluating melon stripes based on the calculated aspect ratio of each epidermis.

[0006]

The present invention is based on the finding that the fringes of net melon can be evaluated based on the skin of the melon. That is, the magnitude of the average value of the aspect ratio of many epidermis extracted from the melon, the magnitude of the standard deviation of the aspect ratio, etc. reflect the quality of the alignment of the fringes (net) of the net melon, It is based on the finding that it can be used as an index for judging the quality.

Therefore, in the present invention, the epidermis extracting means extracts the portion of the melon epidermis from the image taken by the imaging means. The aspect ratio calculating means calculates the ratio of the length and width of each extracted epidermis. The fringe evaluation means evaluates the melon stripes based on the calculated aspect ratio of each epidermis.

As described above, according to the present invention, the epidermis portion is extracted from the image of the net-type melon, the aspect ratio of each extracted epidermis is calculated, and based on the calculated aspect ratio of each epidermis. Since the fringes of the net-type melons are evaluated, the accuracy and reliability of the fringes of the net-type melons can be improved, and the automation can save labor in the evaluation work.

[0009]

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

In FIG. 1, reference numeral 1 is an image input device for photographing a net melon which is a subject of photographing evaluation. The image input device 1 is connected to the image processing device 3 via the camera controller 2. The image processing device 3 includes a CPU, a memory, and the like, and performs predetermined image processing as described later. Further, the display device 4 and the system controller 5 are connected to the image processing device 3.

Next, an example of image processing of the embodiment thus constructed will be described with reference to the flowchart of FIG.

First, an image of a net melon taken by the image input device 1 is input (S1), and the area of the melon is measured (S2). Next, when the part of the epidermis of the net melon (the part excluding the stripes) is extracted from the image (S3), many epidermis are extracted.

Subsequently, the vertical and horizontal lengths of the extracted skins, for example, the Feret diameters in the vertical and horizontal directions are obtained, and the aspect ratio is obtained from the obtained vertical and horizontal lengths (S4). Next, the average value of the obtained aspect ratio of the skin and the standard deviation of the aspect ratio are calculated (S5).

As described above, the average value of the aspect ratio of the epidermis and the standard deviation thereof are obtained by comparing the average value of the aspect ratios of many epidermis extracted from the net melon and the standard deviation of the aspect ratio. This is based on the knowledge that the quality of the fringes of the net melon can be reflected and can be used as an index for determining the quality. For example, as shown in FIG. 3, the average size of the aspect ratio of the epidermis is the quality of the fringes of the net melon (the alignment of the fringes), that is, the grade of the melon is “excellent”, “excellent”,
Corresponds to "good".

Then, the average value and the standard deviation of the calculated aspect ratio of the epidermis are compared with a comparison reference value which is determined in advance corresponding to the area of the melon measured in step S2, and the fringe pattern of the net melon is compared. The set is evaluated (S6).

In the above description, an example in which the fringes of the net-type melon are evaluated based on the average value of the aspect ratio of the epidermis and its standard deviation has been described. However, instead of this, after extracting the skin portion of the melon in the above step S3, the frequency distribution of the area of each extracted skin may be obtained and evaluated from the obtained frequency distribution.

Next, an example of evaluating the uniformity of the fringes of the net melon using the apparatus of FIG. 1 will be described with reference to the flowchart of FIG.

First, an image of a net-type melon imaged by the image input apparatus 1 is input (S11), and a fringe (net) portion of the melon is extracted from the brightness difference between the R image and the G image (S12). Next, the densities of stripes or epidermis in the division windows previously divided into a plurality of areas are calculated (S
13).

Here, for example, the stripe density K is calculated by K = area of the stripe in the window / area of the window.

As a result, for example, as shown in FIG. 5, the densities of stripes (or epidermis) in the areas A, B, C and D are obtained. Therefore, for example, the density of the stripes in the area A is used as a reference, and the ratio of this to the density of the stripes in the area B, C, or D is calculated (S14). Next, the uniformity of the fringes is evaluated based on the obtained variation in each density ratio. That is, for example, comparing each obtained density ratio with a preset value, when each density ratio is larger than the set value,
It is evaluated that "there is stripe unevenness" (S15).

In the evaluation example described above, local unevenness of net can be evaluated. Therefore, in the case of varieties with large net unevenness such as open-field melons, where cork quality is formed two-dimensionally on the surface, it is used for rough selection before highly accurate stripe uniformity evaluation. If this is done, it can be utilized for highly accurate stripe evaluation.

Next, a system in which an external input terminal is added to the image processing device capable of evaluating the appearance quality (structure of stripes, etc.) of the net-type melon and other processing functions are added in addition to the processing function of the appearance quality of the melon Will be described with reference to FIG.

In this system, the image processing apparatus 10 is provided with an external input terminal to which a personal computer 11, a video camera 12, etc. can be connected, and the personal computer 11, the video camera 12, etc. are connected to the external input terminal via a signal line. And each can be connected freely.

In a system having such a configuration, normally,
The melon is housed in the sample box 13, the melon is photographed by the image input device 14, and the appearance inspection is performed from the photographed melon image. Then, after the result of the appearance inspection is printed out on the paper by the printer 15, the worker sticks the printing paper on the melon. This allows the operator to easily align the melon balls.

On the other hand, for example, the melon growth situation in the field is photographed by the video camera 12, the photographed result is analyzed according to a predetermined procedure, and the melon cultivation is managed by using the analyzed result. As an example of this cultivation management, water management performed while confirming the occurrence state of melon stripes is suitable. The melons that manage water in this way are
This is because cracks occur on the surface and stripes are formed, but moisture is involved in the quality of the stripes.

[0026]

INDUSTRIAL APPLICABILITY As described above, according to the present invention, based on the knowledge that the fringes of the net-type melon can be evaluated based on the epidermis, the part of the epidermis is extracted from the image of the net-type melon and then extracted. The aspect ratio of each epidermis was calculated, and the stripes of the net melon were evaluated based on the calculated aspect ratio of each epidermis. Therefore, according to the present invention, the accuracy and reliability of the evaluation of the fringes of the net-type melon can be improved, and the automation thereof can realize the labor saving of the evaluation work.

[Brief description of drawings]

FIG. 1 is a block diagram of an embodiment of the present invention.

FIG. 2 is a flowchart showing an example of image processing of the present invention.

FIG. 3 is a diagram showing the relationship between each grade of melon and the average aspect ratio of the epidermis.

4 is a flow chart showing an example of evaluating the fringe uniformity of net melons using the apparatus of FIG.

FIG. 5 is a diagram showing an example in which a melon image is divided into a plurality of evaluation areas.

FIG. 6 is a diagram showing an example of the configuration of a system when another processing function is added to the image processing apparatus in addition to the visual inspection of melon.

[Explanation of symbols]

 1 image input device 3 image processing device 4 display device

Claims (1)

[Claims] 1. An image pickup means for photographing a net melon, an epidermis extraction means for extracting a portion of the melon's epidermis from the photographed image, and an aspect ratio for calculating a length-width ratio of each extracted epidermis. A net-type melon fringe evaluation device comprising: a calculation means; and a fringe evaluation means for evaluating melon stripes based on the calculated aspect ratio of each epidermis.