JPH08166380A - Automatic bruise detector for vegitable and fruit - Google Patents

Abstract

PURPOSE: To judge the presence or absence and the size of the bruise on the surfaces of vegitables and fruits automatically and mechanically by comparing the saturation of each pixel, which is deteced based on the signals of red, green and blue with the partical average value of the saturations of the individual pixels corresponding to the above described saturation. CONSTITUTION: The signals of the red R, the green G and the blue B of each pixel picked up with an imaging device (R.G.B camera) 4 undergoe A/D conversion 20. The signals are inputted into a color converter 21 of an imaging computer, and lightness Y, hue H and the saturation C are computed for every pixel. When the presence or absence of a part corresponding to a bruise is judged, the partial average value Cn of the saturation corresponding to the saturation C of the certain pixel is obtained by averaging (average moving method) the saturations C of the pixels at a plurality of points, which are separated by the specified number of the pixels in orthogonally intersecting two directions with the specified pixel as the center, for every pixel in a partial-average-value computer 22. When the difference ΔCn between the average value Cn and the saturation C of each pixel exceeds the specified threshold value Ck set by a bruise-detecting-sensitivity setting means 24, the bruise part is judged and outputted.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to the determination of appearance quality of fruits and vegetables, which has been conventionally performed by a skilled inspection worker.
Typically, the presence / absence of injury, size, etc. are automatically judged.
The present invention relates to a mechanical injury automatic detection device for fruits and vegetables.

[0002]

Background of the Invention and Prior Art The appearance quality, which is one of the judgment factors when selecting or evaluating fruits and vegetables, is based on the surface condition such as color and presence of injury in addition to the classification according to the shape and dimensions. It is also important for grading, and it occupies a large weight that cannot be ignored as a selection factor for fruits and vegetables in the selection field of production areas.

Among such factors such as classification, relatively simple factors such as the shape and size of fruits and vegetables can be evaluated relatively easily based on the imaging information of a monochrome camera, and many proposals have been made. It is actually widely used for automatic sorting as well as sorting elements such as weighed weight.

However, it is difficult to secure a skilled worker for grade determination based on factors such as the presence or absence of injury or color of fruits and vegetables, and there is a demand for cost reduction through automation and mechanization of work. However, the performance of the conventionally proposed automation method and device is significantly inferior to the judgment level by the skilled worker, and there are many problems, so that the actual solution is not yet provided. .

As a conventional proposal for a method of automatically determining the presence or absence of an injury, for example, a method of detecting an injury of "fat and attached fruits and vegetables" or a method of detecting a white injury of citrus fruits (Japanese Patent Laid-Open No. HEI 2) No. 218944) is known.

In the former method of detecting scratches on "vegetable fruits and vegetables", saturation is calculated from R, G, B signals obtained by picking up a plane image of fruits and vegetables with a color camera, and the plane image is kept constant. The inside of the circle of diameter is removed as the central part where there is a stain, and further the peripheral part is removed to prevent erroneous detection due to blurring around the image and uneven lighting, and then the saturation of the remaining part is set to a constant reference value. The point lower than the reference value is judged as a scratch in comparison with the above.

In the latter method of detecting citrus whites, the citrus epidermis surface is photographed by a camera having a sensitivity in a wavelength band excluding orange, which is the citrus epidermis color, and wavelengths in the vicinity thereof, and a video signal thereof is obtained. Is binarized at a first binarization level that is higher than the luminance level of the skin color of citrus and lower than the luminance level of white injury, and based on the binarized signal (white scratches + stains) The first number of pixels of the image signal is obtained, and the binarization processing is performed at a second binarization level that is higher than the luminance level of the white damage of the video signal and lower than the luminance level of the foot portion, and the binarization is performed. 2nd only based on the signal
And subtracting the second number of pixels from the first number of pixels to obtain the number of pixels with only white injury.
The detection is performed by using the light of a specific wavelength band and utilizing the difference between the lightness and darkness of the white flaw and the hem.

[0008]

However, in the former method for detecting an injury of "fat and fruit and vegetables", since the settled portion is uniformly set as the central portion of a circle having a constant diameter, Since the position of the scabbard of the fruit is not always constant, the diameter of the circle to be excluded must be set relatively large, and the peripheral part is also removed from uneven lighting etc., so the injury is to be detected. The region is extremely narrow and limited, and the injury detection is extremely insufficient as compared with the judgment level by a skilled worker, and the practical use cannot be satisfied at all.

Further, the latter method of detecting white blemishes on citrus fruits is to detect white blemishes by brightness / darkness treatment with brightness using illumination light in a specific wavelength range. Cannot be detected. Therefore, it is necessary to develop further other injury detection means in order to automate the grade determination including those other than white scratches.

By the way, the detection of injury in fruits and vegetables is
As described above, not only is it necessary to combine the optical technology of illumination and imaging with the signal processing technology obtained thereby, but the fruits and vegetables to be detected may have different colors depending on the type, or may cause injury. It is hard to say that the types and colors are constant, and there is the presence or absence of stains due to fruits and vegetables.
It is difficult to consider a versatile injury detection method that can be applied to various fruits and vegetables because it is extremely diverse and the hues of fruits and vegetables of the same variety may differ depending on the season. Even if a dedicated machine for a single product is provided, it is not easy to solve the problem.

For example, considering only the point of obtaining an image pickup signal for signal processing, it is not enough to image only the upper surface of the fruit and vegetables in order to detect scratches on the surface of the fruit and vegetables as wide as possible. Although it is possible to use a camera to shoot a wide range, the conventional method of detecting injuries by comparing with a certain reference value may cause false detection of injuries if the sensitivity adjustment between multiple cameras used is not sufficient. Unavoidable. Further, in the above-described conventional method for detecting a white flaw by the brightness / darkness processing with brightness, the problem of erroneous detection due to the temporal variation of the light amount of the light source and the uneven illumination cannot be ignored.

As described above, the conventional method and apparatus for automating and mechanizing the judgment of injury cannot be practically applied on an industrial level, or even if possible, in an extremely limited narrow range and limited items. Although it is the actual situation that it can be judged only at a level that is not very accurate as compared with the judgment of appearance quality such as the presence or absence of injury by a skilled worker, the present invention detects the injury of such fruits and vegetables automatically and mechanically. And it was made in order to provide the apparatus which can perform judgment correctly and stably.

That is, an object of the present invention is to provide an automatic injury detecting device for fruits and vegetables capable of stably and highly accurately detecting an injury over a wide range of the epidermis of fruits and vegetables.

Another object of the present invention is to reduce erroneous detection of an injury due to the influence of the light amount variation of the light source with time and the unevenness of illumination of the illumination system as much as possible, and to approach the judgment level of a skilled worker. An object is to provide an automatic injury detection device for fruits and vegetables that can perform high-level automation and mechanized determination.

Still another object of the present invention is a versatility that can be modified so that specific damage detection can be performed on fruits and vegetables of different varieties and can be widely used for damage detection on many kinds of fruits and vegetables. It is in the position of providing an automatic injury detection device for fruits and vegetables.

[0016]

One of the features of the automatic fruit and vegetable injury detecting apparatus according to the present invention that achieves the above object is to provide a light source for applying illumination light to a plurality of fruits and vegetables which are conveyed apart from each other. Means, a light receiving means for picking up the illuminated fruits and vegetables to extract red, green and blue signals for each pixel, and the saturation (C) of each pixel based on the red, green and blue signals In addition, the presence or absence of the injury-corresponding part is compared by comparing the saturation of each pixel with the partial average value corresponding to the calculation means for obtaining the partial average value of the saturation of each pixel by the moving average method. And a determining means for determining.

In determining the presence or absence of an injury, it is preferable to provide an image of the fruit surface of the target fruits and vegetables over as wide an area as possible. For this purpose, a method of imaging three surfaces with a single camera ( Japanese Examined Patent Publication No. 5-60544), a method of picking up images of 5 surfaces with a single camera (Japanese Patent Laid-Open No. 63-611).
No. 05) and the like, and the device of the present invention is
Even when these methods are adopted, the presence or absence of injury can be accurately determined.

That is, in the case of picking up a fruit table of fruits and vegetables over a wide range as described above, it is not easy to uniformly illuminate the whole fruit table to be photographed, so that the light amount in the peripheral portion is often low. . However, in the device of the present invention, since the partial average value of the saturation of the peripheral pixels obtained by the moving average method is compared with the saturation of the pixel, it is not easy to uniformize the illumination of the entire result table. This is because the effect is greatly reduced. Such a specific means for minimizing the influence of fluctuations in light quantity, shading, etc. by comparing the central pixel and the peripheral area when determining whether or not a certain point is a scratch is limited. Although not limited, for example, ± x in the X direction from a certain point C _n
4 points separated by ₁ , ± x ₂ (x ₂ > x ₁ ) dots, or a point separated by ± x dots in the X direction from the point C _n (C _nx
), (C _{n + x} ), and two points (C _ny ) and (C _{n + y} ), which are ± y dots apart in the Y direction, a total of 4 points, and the average value of the saturation is calculated. The system can be exemplified.

Further, a plurality of points separated from the center point in a matrix form, for example, the above-mentioned two points (C _nx ), (C _{n + x} ), and ± y dots from each of these points in the Y direction. Points (C _n-xy1 ), (C _n-xy2 ), (C _{n + xy1} ), (C
It is also possible to use a method of calculating an average value of saturation of 6 points in total of 4 points ( _{n + xy2} ). In order to reliably detect a linear scratch, a method of obtaining the average of a plurality of points in the X and Y2 directions from the center point is preferable. Note that the degree of separation of the peripheral pixels selected for obtaining these partial average values from the central pixel may be appropriately determined within a range of several pixels to several tens of pixels.

As the judging means, the partial average value [ C _n ] of the saturation corresponding to each pixel obtained as described above is used.
And the difference ΔC _n between the original signal C _n and ΔC _n = [C _n ]
-C _n , and this ΔC _n and a predetermined threshold value C _K
It can be provided so as to judge that a site exceeding C _K is an injury by comparing with.

By doing so, the flaw can be detected from the information of the peripheral range in which the illumination conditions are substantially uniform, and the influence of variations in the illumination optical system in the entire apparatus can be reduced.

As the automatic injury detection device of the present invention, a luminance (Y) signal can be used in place of the above-described method of using the signal of the saturation (C) in order to detect the black injury. That is, a light source unit that applies illumination light to a plurality of fruits and vegetables conveyed apart from each other, a light receiving unit that picks up an image of the illuminated fruits and vegetables and extracts a luminance signal for each pixel, and a moving average method for each pixel. It is possible to provide an apparatus having a calculating means for obtaining a partial average value of peripheral brightness and a determining means for comparing the brightness of each pixel with the partial average value corresponding thereto and for determining the presence or absence of the injury-corresponding part.

In this configuration, similarly to the case of using the saturation signal, the partial average value [ Y _n ] of the luminance around each pixel is obtained by the moving average method, and the difference obtained from this and the original signal Y _n is obtained. By comparing ΔY _n with a predetermined threshold value Y _K , it is possible to detect a black line flaw in which the luminance is low.

Further, in the automatic damage detection device for fruits and vegetables of the present invention, detection exclusion color information setting means for setting detection exclusion color information for colors not detected as scratches, and red for each pixel taken out by the light receiving means, The color information calculation means for obtaining color information corresponding to the detection exclusion color information from the green and blue signals, and the color information of each pixel obtained by this color information calculation means are compared with the set detection exclusion color information. It is also preferable to include a detection exclusion determination unit that determines whether or not the detection as a scratch is necessary or unnecessary.

For example, when the fruits and vegetables have stains, the detection exclusion color information setting means and the red color for each pixel taken out by the light receiving means are used as means for preventing the false detection of the stain portion as a scratch. It is possible to provide color information calculation means for obtaining color information corresponding to the detection exclusion color information from the green, green, and blue signals, and detection exclusion determination means for determining the necessity / unnecessity of detection as a flaw.

That is, in order to prevent erroneous detection of the stain portion as a scratch, the average color of the stain given by the type of fruits and vegetables is lightness (Y) 20, hue (H) 160, and saturation (C). In the case of 30, Y = 0 to 40 and H = 1 for each of these three elements with ± 20 as an allowable range.
40-180, C = 10-50 are set as color information,
As for a pixel satisfying these three conditions, it is possible to exemplify a pixel which has a configuration in which it is determined that this portion is a stain and is not a flaw (detection is excluded).

Further, in the case of fruits and vegetables in which the color of the fruit surface is a mixture of green and yellow, for example, uncolored / semi-ripe mandarin orange, the saturation of the green portion is likely to be low, which may cause false detection as a scratch. There is Therefore, it is preferable to provide a means for preventing the erroneous detection of the green area in the same manner as the case of the above-mentioned problem.

As means for preventing such erroneous detection of the green area, the condition of the three elements Y, H, C of the color to be treated as the green area is used as color information, as in the erroneous detection means for the green portion. For the pixels that are set and satisfy this condition,
It is possible to exemplify a configuration in which this portion is a green region and is determined not to be a flaw (detection is excluded).

Furthermore, when the false detection prevention of the unclean portion or the false detection of the green area is performed for each of the plurality of image pickup screens (for example, 3 screens, 5 screens, etc.) described above, The condition of the injury detection exclusion color information can be separately set, and by doing so, the influence of the shading of the optical system different for each screen can be further reduced.

The apparatus of the present invention also sets the detection exclusion color information as described above to prevent erroneous detection of a portion such as a stain as a flaw. (For example, brown scratches appearing on the fruit surface in citrus fruits) are set as specific scratch color information by setting the conditions of Y, H, and C as described above, and the red, green, and blue of each pixel extracted by the light receiving unit are set. The color information corresponding to the specific flaw color information is obtained from the signal by the color information calculating means, and the presence or absence of the specific color flaw corresponding portion is determined by comparing the set specific flaw color information with the calculated color information. Means can also be provided.

The fruits and vegetables which can automatically detect an injury using the device of the present invention are not limited to specific ones, but representative ones include oysters, mandarin oranges, tomatoes, apples and pears. Can be mentioned.

The method of using the partial average value by the moving average method based on the signal of the saturation (or luminance) of the present invention for detecting the injury is configured as a device to which this method is applied to the whole surface of the fruit and vegetables imaged. However, the area where the injury can be detected at a higher judgment level by the conventional method (such as the central area of the upper surface of fruits and vegetables) because the illumination is likely to be performed uniformly, like the central area of the upper surface of the fruits and vegetables, is the predetermined saturation (or It is also possible to adopt a method of directly comparing the threshold value of luminance) with the detected saturation signal (or luminance signal), and employ a injury detection method using a partial average value by the moving average method only for the peripheral area.

In order to divide the area into the central area and the peripheral area, the total brightness is obtained from the red, green and blue signals or the brightness is obtained from any one of the red, green and blue signals for each pixel. Calculated and compared with a preset threshold value of luminance (inspection area setting value), an area larger than the threshold value is set as the central area,
It is preferable to partition a region smaller than the threshold value as a peripheral region, but in addition to this, a predetermined unit length (or range) of the imaged pixel group is set as a reference within this length (or range). The inspection area can be partitioned and set by comparing the magnitude of the luminance change amount with a predetermined threshold value and partitioning the area into a large luminance change area and a small luminance change area.

[0034]

DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be further described below based on the embodiments shown in the drawings.

Embodiment 1 FIG. 1 shows an illumination optical system and an image pickup means for picking up images of fruits and vegetables to be conveyed. In this figure, reference numeral 1 is a conveyor, and fruits and vegetables 2 are arranged from the back side to the front side of the figure. It is provided to be transported to. A pair of light sources 3, 3 for irradiating the illumination light from diagonally above and to the left are arranged in the middle of the conveying path of the conveyor 1, and a CCD color camera or the like for imaging the fruits and vegetables 2 illuminated by the light sources. An imaging device (R, G, B camera) 4 is arranged directly above the conveyor 1.

FIG. 2 shows an illumination optical system and an image pickup means configured to pick up images of both sides and the upper surface of fruits and vegetables by a single color camera. In FIG. 1, the fruits and vegetables 2, the light source 3, and the imaging device 4 are shown in FIG.
Is similar to. The feature of this example is that boxes 12 and 13 are arranged on the left and right of the fruits and vegetables 2 to be conveyed, and the reflected light from the fruits and vegetables is reflected by the mirrors 6 and 7 through the slits 16 provided in the diffusion plates 10 and 11, and Top plate 14
The image pickup device 4 is made to enter the image pickup device 4 through the slit 15 of the
The three surfaces of both side surfaces and the upper surface are imaged.

In the image pickup (three sides of the both sides and the upper surface of the fruit and vegetables) obtained by such an illumination optical system and the image pickup device, the images overlap each other. For example, the image pickup information is stored in a memory (not shown). Then, when reading this, by selecting and reading the central portion of each image, it is possible to obtain imaging information of a continuous surface with less shading.

By using the illumination optical system and the image pickup apparatus as described above, the fruits and vegetables having (a) brown scratches, (b) white scratches, (c) brown scratches + white scratches, and (d) heat of FIG. The signal processing for detecting a flaw that is performed when an image is picked up will be described based on FIG. 4 showing the signal processing circuit. Note that FIG. 3 is illustrated as a case where fruits and vegetables are imaged from the side for convenience of description.

The image pickup device (R, G,
The red (R), green (G), and blue (B) signals of each pixel imaged by the B camera 4 are A / D converted by the A / D converter 20.
After conversion, the lightness (Y), the hue (H), and the saturation (C), which are the three elements of color, are input to the image processing computer and are set in the color converter 21 according to a known predetermined arithmetic expression. It is calculated for each pixel and stored in a memory (not shown).

Separately, the total brightness T is calculated in the T calculator 40 based on the R, G, B signals. The calculation of the total brightness T is for dividing the inspection area of the result table into the central area and the peripheral area, or the upper area and the lower area, and in this example, is given by the inspection area setting means 41 by the comparator 42. An area larger than the threshold value is detected as a central area or an upper area by comparison with the threshold value of the brightness obtained, and an area smaller than the threshold value is detected as a peripheral area or a lower area. Is output to.

The three color elements Y, H, and C are read out from a memory (not shown) in which they are stored, and in this example, three signal processes are performed in parallel.

The first of the parallel signal processes is the determination of the presence or absence of the injury-corresponding part, which is performed based on the saturation C.
That is, in the present example, the partial average value calculator 22 calculates the partial average value [ C _n ] of the saturation corresponding to a certain pixel C _n for each pixel by a predetermined number of pixels in two directions orthogonal to the pixel. The difference ΔC _n between the partial average value [ C _n ] obtained by the difference detector 23 and the saturation C _n of each pixel is obtained by averaging the saturations of the pixels at a plurality of points The comparator 25 is provided so as to judge and output as a scratched part when it exceeds a predetermined threshold value C _K set by the detection sensitivity setting means 24. In this example, the AND circuit 2
6, the logical product with the above-mentioned comparator 42 is taken, and thus, in the case of the region where the flaw detection by the saturation is performed (for example, only the peripheral area of the fruit table or the entire area of the fruit table), the flaw of the saturation difference is detected. I am trying to output as is.

The second of the parallel signal processing is the prevention of erroneous detection of the shaving portion. In this example, for this reason, the stagnation color information setting means 27 is used, for example, Y = 0 to 40 and H =
140-180 and C = 10-50 are set as the heat color information. And Y, H, C for each pixel corresponding to this
The set hetero color information is compared by the comparator 28, and pixels having the color of the hetero region are detected. The heather part detected in this manner is usually located near the center of the upper surface of the fruit and vegetables. Then, in this example, in order to prevent erroneous detection in the vicinity of the region detected as the heat region, the expansion calculator 29 sets an outer region for a certain number of pixels outside the group of pixel groups detected as the heat region. However, the inside of the outer region is determined to be the heather part. Then, for the pixel determined to be the heat region, the enlargement calculator 2 is used.
The output of 9 is inverted by the inverter 30, and the logical product (AND circuit 31) with the output from the AND circuit 36, which will be described later, is used. If it is a part, it is configured not to be detected as a scratch.

In order to detect a specific color flaw, in the third example of parallel signal processing, in the present example, the numerical range of Y, H and C corresponding to the color flaw is used as the specific flaw color information in advance. The comparator 33 compares the Y, H, and C signals for each pixel set in the color information setting means 32 and read from a memory (not shown) with the flaw color information set in the flaw color information setting means 32. Accordingly, it is determined that a pixel including any of them in the set numerical range of Y, H, and C has a specific color flaw, and the AND circuit 35 takes a logical product with the comparator 42. In the case where the scratch is detected (for example, only the central area of the fruit table, only the peripheral area of the fruit table, or the entire area of the fruit table), an output indicating that there is a color flaw is output.

In the circuit of this example, the OR circuit 36 outputs the logical sum of the outputs of the AND circuits 26 and 35 for each pixel, and when the output from the inverter 30 does not indicate the OR portion, the AND circuit 36 outputs. When 31 is satisfied, the flaw signal of the corresponding pixel is finally output.

FIGS. 5 to 8 show signal outputs of lightness (Y), hue (H), and saturation (C) obtained by the color converter 21 in the signal processing circuit described in FIG. 4 above. It is the figure which showed the state, and these figures are (a) -of FIG. 3 for convenience.
Y, H, and C detected as one linear pixel row in the left-right direction of the drawing so as to include a portion such as a scratch in each of (d).
Showed the change.

From these figures, the detected values of the Y, H, and C signals increase from the conveyor surface (left side of the horizontal axis in the figure) toward the upper surface of the fruit and vegetables (right side of the horizontal axis in the figure), In addition, the saturation signal C characteristically changes at the injured portion or the heather portion (see FIGS. 5 to 8), and the hue H signal characteristically increases at the heather portion (see FIG. 8).
I understand.

FIG. 9 shows the Y, H, and C signals collectively by changing the scale of the horizontal axis in FIGS. 5 to 8 described above. , FIG. 7 and FIG. 8 are shown respectively.

The comparator 2 of FIG. 4 corresponding to this FIG.
Fig. 1 shows the output signal of No. 5 (relative saturation change by the moving average method).
It was shown at 0. The partial average value in this example was obtained as a moving average of points separated by 3 pixels (dots) to the left and right of the central pixel.

As can be seen from this figure, the portions of the fruits and vegetables shown in FIG. 3 where the saturation is lower than the surrounding areas are shown in FIG.
It can be seen that it can be clearly detected at 0. In addition, in this example, in the case of FIG.
Although the output of 5 is detected as a flaw, the inverter 30 does not output the output of this region (the detected output is inverted), and therefore the AND circuit 31 does not output a flaw signal.

Example 2 This example shows an example in which a mandarin orange in which almost the entire fruit surface is yellow and a part of green is present is excluded from the detection of the green part as a scratch. ing.

That is, as shown in FIG. 11, fruits and vegetables 2
If almost all of the fruit surface is yellow and there is a green part in that part, the saturation of this green part is low and tends to be detected. Therefore, when the relative change in saturation is calculated by the moving average method of FIG.
The curve of the partial average value (indicated by the broken line) obtained by the moving average method shows a higher value than the curve of the original signal of saturation (indicated by the solid line) in the graph in the middle part of the figure, and in the lower part of the figure As shown, the output of the comparator 25 in FIG. 4 may be detected as a flaw.

Therefore, in this example, a signal processing circuit (not shown) for detecting and excluding the green portion is configured with the same configuration as that for detecting and excluding the heat portion in FIG. It should be noted that the detection exclusion color information for excluding the detection of green may be set by the method of setting the condition range of the Y, H, and C signals, similarly to the setting of the color information of the heather part, or by the set hue of green. Alternatively, a method may be used in which a green hue signal corresponding to the captured R, G, B signals is obtained and compared.

[0054]

According to the present invention, the accuracy of detection is greatly improved as compared with the conventional apparatus that mechanically detects an injury, and in particular, changes with time in the optical system for illumination and imaging,
Even if there is a change, it is possible to obtain the effect that the injury can be detected stably with almost no adverse effect on the detection accuracy.

Further, the influence of shading in the illumination of fruits and vegetables is reduced, and even when the light amount in the peripheral area is likely to be lower than that in the central area, each pixel is compared by the moving average method with the peripheral area as the background. An effect that high detection accuracy can be maintained is obtained.

Furthermore, the risk of erroneously detecting a green portion of a fruit or fruit or a mandarin orange as a scratch can be reliably prevented by performing signal processing that excludes this from being detected as a scratch if necessary. Therefore, there is an effect that the risk of erroneous detection is significantly reduced.

Furthermore, it may be required to detect a characteristic color damage injury depending on fruits and vegetables. In this case, the characteristic color damage injury can also be detected.
The effect of improving the accuracy of scratch detection can be obtained.

[Brief description of drawings]

FIG. 1 is a diagram showing an example of a positional relationship between an illumination optical system and an imaging device used for implementing the present invention,

FIG. 2 is a diagram showing another example of an arrangement relationship between an illumination optical system and an image pickup apparatus used for implementing the present invention,

FIG. 3 is a diagram showing an example of a scratch or the like of a fruit or vegetable targeted for scratch detection by the device of the present invention, where (a) is a fruit or vegetable with brown scratches, (b) is a fruit or vegetable with white scratches, (c). ) Indicates fruits and vegetables having both brown and white scars, and (d) indicates fruits and vegetables having a scab.

FIG. 4 is a block diagram showing a schematic configuration of a circuit that performs signal processing of the device of the present invention;

FIG. 5 is a diagram showing a change curve of Y, H, and C signals in a linear pixel row obtained for the fruits and vegetables shown in FIG.

FIG. 6 is a diagram showing a change curve of Y, H, and C signals in a straight line of pixels obtained for the fruits and vegetables shown in FIG.

FIG. 7 is a diagram showing a change curve of Y, H, and C signals of a linear pixel row obtained for the fruits and vegetables of FIG.

FIG. 8 is a diagram showing a change curve of Y, H, and C signals in a linear pixel row obtained for the fruits and vegetables shown in FIG.

9 is a diagram collectively showing the curves of FIGS. 5 to 8 with the horizontal scale being changed,

10 is a diagram showing a relative saturation change obtained by a moving average method based on the saturation signal of FIG. 9;

FIG. 11 is a diagram for explaining how to exclude detection of a green part in oranges.

[Explanation of symbols]

1 ... conveyor, 2 ... fruits and vegetables, 3 ... light source, 4
... Imaging device, 6,7 ... Mirror, 10,11 ...
・ Diffusion plate, 12, 13 ... Box, 14 ... Upper plate, 15, 16 ... Slit, 20 ... A / D converter, 21 ... Color converter, 22 ... Partial average value calculator, 23 ... difference detector, 24 ... flaw detection sensitivity setting means, 25 ... comparator, 26 ... AND circuit, 27
... Various color information setting means, 28 ... Comparator, 29.
..Enlargement calculator, 30 ... Inverter, 31 ... AND circuit, 32 ... Scratch color information setting means, 33 ... Comparator, 35 ... AND circuit, 36 ... OR circuit , 40
... T calculator, 41 ... inspection area setting means, 42 ...
..Comparators

Claims (7)

[Claims] 1. A light source means for applying illumination light to a plurality of fruits and vegetables conveyed at a distance, and a light receiving means for imaging the illuminated fruits and vegetables to extract red, green, and blue signals for each pixel, Calculating means for calculating the saturation (C) of each pixel on the basis of the red, green, and blue signals of each pixel, and calculating the partial average value of the saturation of each pixel by the moving average method; An automatic injury detection device for fruits and vegetables, comprising: a determining unit that determines the presence or absence of an injury-corresponding portion by comparing saturation and the partial average value corresponding thereto. 2. A light source means for applying illumination light to a large number of fruits and vegetables conveyed separately, a light receiving means for picking up an image of the illuminated fruits and vegetables to obtain a luminance signal for each pixel, and each pixel by a moving average method. And a determining unit that determines the presence or absence of an injury-corresponding site by comparing the brightness of each pixel with the partial average value corresponding to the brightness of each pixel. Automatic injury detection device for fruits and vegetables. 3. The partial average value obtained by the moving average method according to claim 1 or 2 is obtained as an average value of pixels at a plurality of points separated by a predetermined interval in two directions orthogonal to each pixel, or An automatic injury detection device for fruits and vegetables, characterized in that it is obtained as an average value of pixels at a plurality of points spaced in a matrix form centering on each pixel. 4. The automatic fruit and vegetable injury detection device according to claim 1, wherein detection exclusion color information setting means for setting detection exclusion color information for colors not detected as flaws, and red for each pixel taken out by the light receiving means, The color information calculation means for obtaining color information corresponding to the detection exclusion color information from the green and blue signals, and the color information of each pixel obtained by this color information calculation means are compared with the set detection exclusion color information. Of scratches,
An automatic detection device for a fruit or vegetable injury, which is provided with a detection exclusion determination means for determining unnecessaryness. 5. The automatic injury detection device for fruits and vegetables according to claim 4, wherein the detection exclusion color information that is set is the color information of the fruits and vegetables when the fruits and vegetables are attached. 6. The automatic injury detection device for fruits and vegetables according to claim 4, wherein the set detection exclusion color information is green when the fruits and vegetables are citrus fruits. 7. The automatic fruit and vegetable injury detection device according to claim 1, wherein flaw color information setting means for setting flaw color information on a specific color flaw, and red for each pixel taken out by the light receiving means,
Color information calculation means for obtaining color information corresponding to the flaw color information from green and blue signals, and color information of each pixel obtained by this color information computation means and specified flaw color information are specified. And a determination means for determining the presence or absence of the color scratch-corresponding part, and an automatic injury detection device for fruits and vegetables.