JP2018059775A - Fruit and vegetable inspection device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a fruit and vegetable inspection device that precisely detects abnormality such as a putrid part derived from a change in water content existing on the surface of a skin of fruit and vegetables or inside the skin, and can detect even a minute water rot.SOLUTION: A fruit and vegetable inspection device includes: near infrared light projecting means for emitting near infrared light to fruit and a vegetable; ultraviolet light projecting means for emitting ultraviolet light to the fruit and vegetable; near infrared image imaging means for taking a near infrared image of the fruit and vegetable by the near infrared light; fluorescent image imaging means for taking a fluorescent image of the fruit and vegetable by visible fluorescent light excited by the ultraviolet light; and analysis means for finding whether there is abnormality in the fruit and vegetable on the basis of the near infrared image and the fluorescent image. The near infrared light projecting means can emit light including an inspection wavelength of 1450±50 nm. The analysis means finds whether there is abnormality in the fruit and vegetable using the near infrared image and the fluorescent image on the basis of light of the inspection wavelength.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a fruit and vegetable inspection apparatus for inspecting the presence or absence of an abnormality in the fruit and fruit skin, such as water rot that appears on the surface of a citrus fruit skin.

  In citrus fruits, when the skin is damaged, if bacteria enter the wound and are stored in a hot and humid state, a symptom called water rot may appear.

  The reason for the scratches on the pericarp is roughly that rainwater enters from the small cracks formed in the pores and expands, so that the cracks spread while being submerged. Injuries, such as trauma, insect bites, and bruises.

When fungi such as mold enter from wounds caused by natural occurrence, the fungus such as fungus propagates and destroys oil vesicles as symptoms progress.
When the symptom further progresses, the water disappears from the place where the rot occurs, and a state called dry rot occurs.

  In this way, when citrus fruits with water rot are mixed and packed with normal products, there is a risk of rot to normal products, so in order to ensure product quality, It is desired to eliminate it at the selection stage.

  By the way, there is a flavonoid-based substance that emits fluorescence in the visible region in the oil vesicles of the pericarp, and when the oil vesicle is destroyed, it becomes possible to detect the flavonoid-based substance that emits fluorescence in the visible region. In Patent Documents 1 to 4, image inspection is performed by detecting a specific fluorescence wavelength derived from a flavonoid-based substance that emits fluorescence in the visible region by ultraviolet irradiation.

  In addition, as a method for inspecting the presence or absence of water rot, mold and dry rot, for example, as disclosed in Patent Document 5, light is emitted from an illumination lamp such as a halogen lamp to fruits and vegetables. There is known a method for detecting the presence or absence of a discolored or corrupt portion of fruit and vegetables by imaging reflected light with an imaging camera.

  Further, Patent Document 6 irradiates fruits and vegetables from visible light to near-infrared light, and captures changes in surface layer components such as moisture and oil at wavelengths in the near-infrared region, thereby enabling multivariate analysis. Determining a change in moisture status is disclosed.

Japanese Patent Laid-Open No. 2003-14650 JP 2011-33612 A JP 2013-231668 PR JP2015-184071 PR Japanese Patent Laid-Open No. 9-24343 Japanese Patent Laying-Open No. 2005-201636

  However, substances that fluoresce when irradiated with ultraviolet light are in a detectable state when citrus oil vesicles are destroyed. Can not be detected unless the oil is propagated and even the oil vesicles are destroyed.

  In other words, natural water rot caused by rainwater entering from the small cracks formed in the pores to expand and become water-immersed, especially minute water rot of about 10 mm in diameter as required in the market in recent years. Cannot be reliably detected by the inspection disclosed in these patent documents.

  In addition, as disclosed in Patent Document 6, in a calibration curve using multivariate analysis using visible light and near infrared light, technical knowledge is required to create a calibration curve, and complicated work is required. Therefore, not everyone can use it easily.

Furthermore, the sensitivity of the Si photodiode in the near-infrared region is low, and there is a possibility that the initial detection of water rot is insufficient and cannot be detected.
On the other hand, even in a rot state where water rot has progressed, there is also a problem that it is difficult to detect dry rot, raw wounds, and the like with near-infrared light.

  In the present invention, in view of the current situation, fruits and vegetables that can accurately detect abnormalities such as rot and scratches existing on the surface and inside of the skin of fruits and vegetables, and can detect even minute water rot. An object is to provide an inspection device.

The present invention was invented in order to solve the problems in the prior art as described above.
A fruit and vegetable inspection apparatus for determining the presence or absence of abnormality of fruit and vegetables,
Near-infrared light projecting means for irradiating the fruit and vegetables with near-infrared light;
Ultraviolet light projecting means for irradiating the fruits and vegetables with ultraviolet light;
A near-infrared image capturing means for capturing a near-infrared image of the fruit and vegetables with the near-infrared light;
Fluorescence image capturing means for capturing a fluorescent image of the fruits and vegetables by visible fluorescence excited by the ultraviolet light;
Analyzing means for detecting the presence or absence of abnormality of the fruits and vegetables based on the near-infrared image and the fluorescent image;
The near infrared light projecting means can irradiate light including an inspection wavelength of 1450 ± 50 nm,
The analyzing means is configured to detect the presence or absence of abnormality of the fruits and vegetables using the near infrared image based on the light of the inspection wavelength and the fluorescence image.

In this case, further comprising a transport means for transporting the fruits and vegetables in a predetermined direction,
It can also be configured to perform the fruit and vegetable inspection in-line.
Furthermore, further comprising a reflecting mirror on both sides of the transport device,
By projecting the side part of the fruit and vegetables on the reflecting mirror, the whole fruit and vegetables can be imaged by the near-infrared image capturing unit and the fluorescent image capturing unit.

Moreover, the said conveyance means can also be provided with the fruit and vegetables rotation mechanism which rotates the said fruit and vegetables in a desired direction.
The near-infrared image capturing means and the fluorescent image capturing means are disposed above the fruits and vegetables,
The near-infrared image capturing unit and the fluorescent image capturing unit may be further disposed below the fruits and vegetables.
Further, the near-infrared image capturing unit and the fluorescent image capturing unit may be disposed above the fruits and vegetables.
Moreover, the said near-infrared image imaging means and the said fluorescence image imaging means may be arrange | positioned under the said fruits and vegetables.

  According to the present invention, among the absorption wavelengths of water, by using near-infrared light including an inspection wavelength of 1450 ± 50 nm, a change in moisture state can be accurately captured, and flavonoids can be obtained using ultraviolet light. By detecting the fluorescence reaction of the system substances, it is possible to simultaneously examine the damage of the pericarp that causes water rot such as damage of oil vesicles. For this reason, it is possible to detect water rot of fruits and vegetables with high accuracy, and it is possible to reliably eliminate abnormal fruits and vegetables at the fruit selection stage.

FIG. 1 is a schematic configuration diagram for explaining the configuration of an embodiment of the fruit and vegetable inspection apparatus of the present invention. FIG. 2 is a schematic configuration diagram for explaining a configuration in another embodiment of the fruit and vegetable inspection apparatus of the present invention. FIG. 3 is a plan view of FIG. FIG. 4 is a schematic configuration diagram for explaining a modification of the fruit and vegetable inspection apparatus in FIG. 2. FIG. 5 is a plan view of FIG. FIG. 6 is a schematic configuration diagram for explaining another modified example of the fruit and vegetable inspection apparatus in FIG. 2. FIG. 7 is a plan view of FIG. FIG. 8 is a schematic configuration diagram for explaining a configuration in still another embodiment of the fruit and vegetable inspection apparatus of the present invention. FIG. 9 is a schematic configuration diagram for explaining a modification of the fruit and vegetable inspection apparatus in FIG. 8. FIG. 10 is a schematic configuration diagram for explaining another modified example of the fruit and vegetable inspection apparatus in FIG. 8. FIG. 11 is a schematic configuration diagram for explaining a configuration in still another embodiment of the fruit and vegetable inspection apparatus of the present invention. FIG. 12 is a schematic configuration diagram for explaining a configuration in still another embodiment of the fruit and vegetable inspection apparatus of the present invention. FIG. 13 is an example when the mandarin orange in which initial water rot has occurred is examined as the fruits and vegetables S. FIG. 13A is an appearance image by visible light, and FIG. 13B is a gray scale image of a fluorescent image. 13 (c) is an analysis image of FIG. 13 (b), FIG. 13 (d) is a gray scale image of a near-infrared image, and FIG. 13 (e) is an image of FIG. 13 (d). It is an analysis image. FIG. 14 shows an example of a test for mandarin orange that has undergone water rot, which is relatively advanced as fruits and vegetables S. FIG. 14A shows an appearance image by visible light, and FIG. 14B shows a gray fluorescent image. Scaled image, FIG. 14C is an analysis image of FIG. 14B, FIG. 14D is a gray scale image of a near-infrared image, and FIG. 14E is FIG. ) Analysis image. FIG. 15 shows an example of a test for mandarin orange with white mold and water rot as fruits and vegetables S. FIG. 15 (a) is an appearance image by visible light, and FIG. 15 (b) is a gray scale fluorescence image. 15 (c) is an analysis image of FIG. 15 (b), FIG. 15 (d) is a gray scale image of a near-infrared image, and FIG. 15 (e) is FIG. 15 (d). This is an analysis image. FIG. 16 is an example of a case where mandarin oranges with green mold and white mold are inspected as fruits and vegetables S. FIG. 16 (a) is an appearance image by visible light, and FIG. 16 (b) is a gray scale fluorescence image. 16 (c) is an analysis image of FIG. 16 (b), FIG. 16 (d) is a gray scale image of a near infrared image, and FIG. 16 (e) is FIG. 16 (d). FIG. 16F shows an analysis image obtained by analyzing the image of FIG. 16D with the contrast of light and dark reversed. FIG. 17 is an example when green fruit, white mold, and mandarin orange with water rot are inspected as fruits and vegetables S. FIG. 17 (a) is an appearance image by visible light, and FIG. 17 (b) is a fluorescence image. 17 (c) is an analysis image of FIG. 17 (b), FIG. 17 (d) is a gray scale image of a near-infrared image, and FIG. 17 (e) is FIG. It is an analysis image of (d). FIG. 18 shows an example of a test for mandarin orange that has been dried and rotted as fruits and vegetables S. FIG. 18A is an appearance image by visible light, and FIG. 18B is a gray scale image of a fluorescent image. 18 (c) is an analysis image of FIG. 18 (b), FIG. 18 (d) is a gray scale image of a near-infrared image, and FIG. 18 (e) is an analysis image of FIG. 18 (d). It is.

Hereinafter, embodiments (examples) of the present invention will be described in more detail with reference to the drawings.
FIG. 1 is a schematic configuration diagram for explaining the configuration of an embodiment of the fruit and vegetable inspection apparatus of the present invention.

As shown in FIG. 1, the fruit and vegetable inspection apparatus 10 according to the present embodiment includes a near-infrared light projecting unit 12 that irradiates near-infrared light from above the fruit and vegetables S onto the fruit and vegetable S to be measured. The near-infrared image which picks up the near-infrared image of fruits and vegetables S from the upper part of fruits and vegetables S by the ultraviolet light projection means 13 which irradiates ultraviolet light from above S, and the near-infrared light (reflected light) reflected on the fruits and vegetables S Image capturing means 14, fluorescence image capturing means 15 for capturing a fluorescent image of the fruits and vegetables S by visible fluorescence excited by ultraviolet light irradiated to the fruits and vegetables S from above the fruits and vegetables S, a near-infrared image and fluorescence And an analysis means 16 for detecting a rot portion of the fruit and vegetables S based on the image.
Here, “above” the fruits and vegetables S is above the surface on which the fruits and vegetables S are placed, and includes the vertical direction and the oblique direction of the fruits and vegetables S.

In the present embodiment, the fruits and vegetables S are not particularly limited, but can be, for example, citrus fruits such as mandarin oranges and citrus fruits, pears, peaches, loquats, plums, and apples.
Further, in the case of such a fruit and vegetable S, in the fruit and vegetable inspection apparatus 10 of the present embodiment, for example, water rot found in citrus fruits, water fruit found in pears, peach, loquat, plums, apples and the like. It can be inspected for scars and the like.

Here, “water rot” means that when the skin is damaged, as described above, bacteria enter the wound, and the surface of the skin is wet for a long time due to rain or dew. It is a symptom that appears as if the pericarp swells, appearing under temperature conditions.
In addition, “water fruit” is a symptom in which the pulp is immersed in water. When the degree becomes severe, the pulp becomes brownish.
In addition, “pressing marks” are the result of local pressure being applied to the surface of fruits and vegetables by contact between the fruits and vegetables, destroying the flesh tissue of the fruits and vegetables, and moisture exuded from the flesh tissue between the peel and the flesh. This is a symptom in which a state to perform (in other words, a state of internal bleeding in the human body) appears.

  The fruit and vegetable inspection apparatus 10 according to the present embodiment is not limited to the inspection of such a failure, but, for example, is a general failure related to the increase or decrease of water that appears in the skin surface and / or under the skin when the pulp cell is destroyed. It is possible to check for.

  Furthermore, if the flavonoid substances are secreted by damaging the skin, such as citrus fruits and vegetables S, it is possible to detect the presence or absence of a skin wound causing water rot by capturing fluorescence. it can.

  The near-infrared light projecting means 12 is not particularly limited as long as it can irradiate near-infrared light including an inspection wavelength of 1450 ± 50 nm. For example, a halogen lamp or an LED light source is used. Can do. The LED light source may be one that emits white light, but may be one that emits only light of a specific wavelength.

  The ultraviolet light projecting means 13 is not particularly limited as long as it can irradiate ultraviolet light including light having a wavelength of 320 nm to 420 nm as ultraviolet light in which a flavonoid substance is excited to generate fluorescence. For example, an LED light source or a deuterium lamp can be used.

  The near-infrared image capturing unit 14 is not particularly limited as long as it can capture a near-infrared image based on near-infrared light having a wavelength irradiated by the near-infrared light projecting unit 12. An area camera, a line camera, an imaging spectrometer, a multiband camera, or the like can be used.

  The present invention is characterized in that an InGaAs photodiode is used as the imaging element of such a near-infrared image capturing means 14. As described above, by using the InGaAs photodiode, even inspection light having a wavelength of 1450 ± 50 nm can be detected with high sensitivity and low noise.

  The fluorescence image capturing means 15 is not particularly limited as long as it can capture a fluorescence image based on fluorescence generated by excitation of a flavonoid substance, and is an area camera, a line camera, an imaging spectrometer, a multiband camera. Etc. can be used.

  In this embodiment, the near-infrared image capturing unit 14 and the fluorescence image capturing unit 15 are illustrated as separate cameras, but a near-infrared image and a fluorescent image can be captured simultaneously, such as a multiband camera. A camera can also be used.

  Further, a near-infrared imaging filter 18 that transmits only light having a predetermined wavelength is provided between the fruits and vegetables S and the near-infrared image capturing unit 14. Fluorescent imaging filters 19 that transmit only light can also be provided.

  By configuring in this way, the near-infrared image capturing unit 14 and the fluorescence image capturing unit 15 can receive only light having a necessary wavelength, respectively, and do not receive light having a wavelength unnecessary for image analysis. Noise can be reduced.

  As shown in FIG. 1, the fluorescence imaging filter 19 is a filter that transmits fluorescence and blocks ultraviolet light when provided between the fruits and vegetables S and the fluorescence image capturing means 15. Can do.

  On the other hand, the fluorescence imaging filter 19 can be provided between the ultraviolet light projecting means 13 and the fruits and vegetables S. In this case, a filter that transmits only ultraviolet light can be obtained.

  The analysis means 16 is not particularly limited as long as it can determine the presence / absence of a spoiled part based on the captured inspection image by image analysis as will be described later. For example, the image analysis program Can be a computer in which is embedded.

  In the fruit and vegetable inspection apparatus 10 of the present embodiment, the near-infrared light projecting means 12 irradiates the fruit and vegetables S with near-infrared light, and the near-infrared image capturing means 14 uses the reflected light from the fruits and vegetables S. The fruit and vegetables S are imaged and a near-infrared image is acquired.

  Further, the fruits and vegetables S are irradiated with ultraviolet light from the ultraviolet light projecting means 13, and the fluorescence images are captured by the fluorescence image capturing means 15 using the fluorescence from the fruits and vegetables S to obtain a fluorescence image. In addition, since the fluorescence by a flavonoid type substance is visible fluorescence, you may make it acquire the image based on visible light as a fluorescence image.

  Each pixel value of the near-infrared image can be determined based on the light amount L of the near-infrared light received by the near-infrared image capturing means 14, but in this embodiment, it is expressed by the following formula (1). In addition, the reflection ratio of the fruits and vegetables S calculated as a ratio between the reflected light Rs from the fruits and vegetables S and the reflected light Rr from a standard body (for example, a gray chart) obtained by irradiating incident light acquired in advance. Each pixel value of the near-infrared image is determined based on R. In addition, as represented by the following formula (2), the pixel value may be determined based on the apparent absorbance A from the calculated reflection ratio R.

  In this way, by using the reflected light Rr from the standard as a reference, even when, for example, the near-infrared light projecting means 12 deteriorates over time, the reflection ratio R hardly changes. Since it can be measured, a long-term stable inspection can be performed.

The determination of each pixel value of the near-infrared image based on the reflection ratio R and the apparent absorbance A can be performed as follows, for example.
For example, in the case of an 8-bit image, the pixel value is a value from 0 to 255. Therefore, the assumed minimum value of the reflection ratio R (which is appropriately set based on the performance of the near-infrared image capturing unit 14) is “0”. The reflection ratio R of each pixel may be converted so that 1 which is the maximum value of the reflection ratio R is “255”.

Then, by analyzing the inspection image with the analysis means 16, the rot portion of the fruit and vegetables S can be detected.
The image analysis in the analysis means 16 is, for example, detecting a change in contrast in the inspection image, or performing a pre-processing such as expansion, contraction, blurring, and edge extraction, which are known techniques, as image processing, to change the contrast. After making the image stand out, a binarization process can be performed to detect a corrupt portion in the inspection image.

  In the near-infrared image, the spoiled part of the fruits and vegetables S has a larger amount of water than the normal part. Therefore, the light having the absorption wavelength of water is absorbed by the spoiled part and imaged by the near-infrared image capturing means 14. In this case, the decayed part can be detected based on the fact that the amount of light at the decayed part is lower than that of the normal part.

  On the other hand, in the fluorescence image, flavonoid substances secreted by citrus and other skin peels are excited by ultraviolet light to generate fluorescence. Based on the fact that the amount of light is higher than that of the part, it is possible to detect the decayed part.

  In the present embodiment, it is preferable that the irradiation time of the near-infrared light from the near-infrared light projecting means 12 to the fruits and vegetables S is kept to the minimum necessary for capturing the near-infrared image. This is to prevent the fruits and vegetables S from being heated by near infrared rays.

  On the other hand, the irradiation time of the ultraviolet rays from the ultraviolet light projecting means 13 to the fruits and vegetables S may be at least a time necessary for capturing a fluorescent image, but the irradiation may be continued for a longer time. This is because a bactericidal effect by ultraviolet rays can be expected.

  In the present embodiment, the analysis unit 16 performs image analysis on both the near-infrared image and the fluorescence image. However, when either the near-infrared image or the fluorescence image is image-analyzed, the fruits and vegetables S If an abnormality is detected, it is possible to determine that there is an abnormality in the fruits and vegetables S without performing image analysis on the remaining one of the images.

FIG. 2 is a schematic configuration diagram for explaining a configuration in another embodiment of the fruit and vegetable inspection apparatus of the present invention, and FIG. 3 is a plan view of FIG.
The fruit and vegetable inspection apparatus 10 shown in FIGS. 2 and 3 has basically the same configuration as the fruit and vegetable inspection apparatus 10 shown in FIG. 1, and the same components are denoted by the same reference numerals and detailed description thereof is omitted. To do. Further, in order to simplify the description, a part of the configuration is omitted.

  In the fruit and vegetable inspection apparatus 10 shown in FIG. 1, the near-infrared light projecting means 12 irradiates near-infrared light to the stationary fruit and vegetables S, and a near-infrared image based on the near-infrared light is converted into a near-infrared image. In addition to imaging by the imaging unit 14, the fluorescent image imaging unit 15 captures a fluorescence image based on fluorescence generated from the flavonoid-based material that is irradiated with ultraviolet light from the ultraviolet light projecting unit 13 and excited by the ultraviolet light. ing.

  On the other hand, in the fruit and vegetable inspection apparatus 10 according to the embodiment shown in FIGS. 2 and 3, near-infrared light and ultraviolet light are applied to the fruits and vegetables S conveyed in one direction by the conveying means 20 from above the conveying means 20. Each is irradiated, and a near infrared image and a fluorescence image are respectively captured by the near infrared image capturing unit 14 and the fluorescence image capturing unit 15.

Here, “upward” of the conveying means 20 is above the conveying means 20 on which the fruits and vegetables S are placed, and includes the vertical direction and the oblique direction of the fruits and vegetables S.
In this embodiment, a multiband camera 23 in which the near-infrared image capturing unit 14 and the fluorescence image capturing unit 15 are integrated is used.

In this way, a large amount of fruits and vegetables can be efficiently inspected by configuring so as to inspect the fruits and vegetables in-line.
When the inspection is performed while the fruits and vegetables S are transported by the transport means 20, as shown in FIG. 3, the reflecting mirrors 22 are provided on both sides in the transport direction, so that the side surfaces of the fruits and vegetables S are reflected on the reflecting mirrors. Therefore, it is preferable that the entire fruit and vegetables S be imaged by the multiband camera 23.

  2 and 3, the near-infrared image capturing unit 14 and the fluorescent image capturing unit 15 are provided one by one. However, the near-infrared image capturing unit 14 and the fluorescent image capturing unit 15 are installed. The number is not limited, and can be appropriately changed according to the shape and size of the fruits and vegetables S.

  For example, as shown in FIGS. 4 and 5, two near-infrared image capturing means 14 and one fluorescent image capturing means 15 may be provided, or as shown in FIGS. Two external image capturing means 14 and two fluorescent image capturing means 15 may be provided. 4 to 7 are partially omitted in order to simplify the description.

Moreover, in the fruit and vegetable inspection apparatus 10 shown in FIGS. 1-7, although the near-infrared image imaging means 14 and the fluorescence image imaging means 15 are arrange | positioned above the fruits and vegetables S, the conveyance means 20 is like a roller conveyor, for example. When there is a gap, when there is a gap in the joint between the conveyors, or when the belt part of the belt conveyor has translucency, as shown in FIG. The image capturing unit 14 and the fluorescence image capturing unit 15 may be arranged.
Here, “downward” of the conveying means 20 is below the conveying means 20 on which the fruits and vegetables S are placed, and includes the vertical direction and the oblique direction of the fruits and vegetables S.

In addition, when imaging from the gap of a roller conveyor, it is preferable to use a line camera as the near-infrared image capturing unit 14 and the fluorescence image capturing unit 15.
Further, by using the beam splitter 24, as shown in FIG. 9, the near-infrared image capturing unit 14 and the fluorescence image capturing unit 15 can be arranged. Of course, the near-infrared image capturing unit 14 and the fluorescent image capturing unit 15 can be arranged. When using the multiband camera 23 in which the image pickup means 15 is integrated, it is also possible to pick up an image from directly under the fruits and vegetables S as shown in FIG.

  In addition, as shown in FIG. 11, the near-infrared image and the fluorescence image are captured from above the fruits and vegetables S, and the near-infrared image and the fluorescence image are also captured from below the fruits and vegetables S. The entire circumference of S can be inspected without any problem.

  In addition, when it cannot image from the downward direction of the fruits and vegetables S, as shown in FIG. 12, the fruits and vegetables rotation mechanism 26 which rotates the fruits and vegetables S to a desired direction is provided in the conveyance means 20, and the fruits and vegetables S are rotated and moved. Thus, the fruits and vegetables S may be imaged not only from one direction but also from a plurality of directions. By transporting the fruits and vegetables S by the transport means 20 provided with the fruits and vegetables rotating mechanism 26, the entire circumference of the fruits and vegetables S can be sequentially inspected.

  As the fruit and vegetables rotating mechanism 26, a rotating mechanism that rotates the fruit and vegetables S placed on the conveying means 20 in a desired direction such as a horizontal direction or a vertical direction can be used, and is not particularly limited. For example, it is possible to use a mechanism for reversing the top of the fruit and vegetables S as disclosed in JP-A-10-53213, JP-A-2000-153912, JP-A-2014-97455, and the like.

Note that the drawings shown in FIGS. 9 to 12 are partially omitted in order to simplify the description.
Moreover, the near-infrared image imaging means 14 and the fluorescence image imaging means 15 shown in FIGS. 1-12 are arrange | positioned in the vertical direction upper direction or the vertical direction lower direction of the fruits and vegetables S, and the angle above or below the fruits and vegetables S There are things that are attached, etc., but the direction is not particularly limited, and it can be changed appropriately according to the device configuration, such as attaching an angle or changing the angle between the upper and lower sides It is.

  FIGS. 13 to 18 are examples of a near-infrared image and a fluorescence image when the fruits and vegetables S are inspected using the fruits and vegetables inspection apparatus 10 shown in FIG. In addition, the external appearance image by visible light of the fruit and vegetables S shown as reference is image | photographed with the common digital camera.

  FIG. 13 is an example when the mandarin orange in which initial water rot has occurred is examined as the fruits and vegetables S. FIG. 13A is an appearance image by visible light, and FIG. 13B is a gray scale image of a fluorescent image. 13 (c) is an analysis image of FIG. 13 (b), FIG. 13 (d) is a gray scale image of a near-infrared image, and FIG. 13 (e) is an image of FIG. 13 (d). It is an analysis image.

FIG. 14 shows an example of a test for mandarin orange that has undergone water rot, which is relatively advanced as fruits and vegetables S. FIG. 14A shows an appearance image by visible light, and FIG. 14B shows a gray fluorescent image. Scaled image, FIG. 14C is an analysis image of FIG. 14B, FIG. 14D is a gray scale image of a near-infrared image, and FIG. 14E is FIG. ) Analysis image.
In the fluorescence images obtained as shown in FIGS. 13 (b) and 14 (b), the rotting site is determined by the analysis means 16 as described above, as shown in FIGS. 13 (c) and 14 (c). A simple analysis image is generated.

  In the image analysis, since a certain amount of error is expected, it is preferable to determine a portion where a continuous predetermined range is filled as a corrupt portion. That is, in FIG. 14C, the part surrounded by the white line at the upper left of the image is determined as the corruption part.

  On the other hand, in FIG. 13 (c), there was no continuous predetermined range (filled location), and it was not possible to determine the decay location from the fluorescent image.

  Similarly, the near-infrared images obtained as shown in FIGS. 13D and 14D are similarly determined by the analysis means 16 as described above, and the rotting site is determined, as shown in FIGS. An analysis image as shown in e) is generated.

In FIG. 13 (e) and FIG. 14 (e), a part surrounded by a white line is a part determined to be a corrupt part.
As described above, it is possible to accurately determine the rotting site in the near-infrared image in FIG. 13 and in both the near-infrared image and the fluorescence image in FIG. 14 without overlooking. Therefore, it is possible to prevent the distribution of fruits and vegetables with initial water rot, which has been overlooked only by the fluorescent image, to the market.

FIG. 15 is an example of a test for mandarin orange with white mold and water rot as the fruits and vegetables S. FIG. 15A shows an appearance image by visible light, and FIG. 15B shows a fluorescence image. FIG. 15C is an analysis image of FIG. 15B, FIG. 15D is a gray scale image of a near infrared image, and FIG. 15E is FIG. It is an analysis image of d).

  Furthermore, FIG. 16 is an example when inspecting the mandarin orange in which green mold and white mold occurred as the fruits and vegetables S, FIG. 16 (a) is an appearance image by visible light, and FIG. 16 (b) is a fluorescence image. FIG. 16C is an analysis image of FIG. 16B, FIG. 16D is a gray scale image of a near-infrared image, and FIG. 16E is FIG. FIG. 16F shows an analysis image obtained by reversing the brightness and darkness of the image shown in FIG. 16D.

  Moreover, FIG. 17 is an example at the time of test | inspecting about the mandarin orange in which green mold, white mold, and water rot occurred as fruit and vegetables S, FIG.17 (a) is an external appearance image by visible light, FIG.17 (b), FIG. 17C is an analysis image of FIG. 17B, FIG. 17D is a gray scale image of a near-infrared image, and FIG. It is an analysis image of Drawing 17 (d).

  Further, FIG. 18 is an example when the mandarin orange having dried rot as the fruits and vegetables S is inspected. FIG. 18 (a) is an appearance image by visible light, and FIG. 18 (b) is a gray scale image of a fluorescent image. 18 (c) is an analysis image of FIG. 18 (b), FIG. 18 (d) is a gray scale image of a near-infrared image, and FIG. 18 (e) is an image of FIG. 18 (d). It is an analysis image.

15 and 17, both the fluorescence image and the near-infrared image, as shown in the portions surrounded by white lines (FIGS. 15C, 17C, 15E, and 17E). Thus, it is possible to accurately determine the rotting site of the fruits and vegetables S. In addition, it is possible to accurately determine the rot portion of the fruits and vegetables using the near-infrared image in FIG. 16 and the fluorescence image in FIG.
That is, if both the fluorescent image and the near-infrared image are obtained in the fruits and vegetables S, it is possible to accurately determine a rot portion that may be overlooked by only one of them without being overlooked.
In the case of a mandarin orange with green mold and white mold as shown in FIG. 16, even if a fluorescent image or a near-infrared image is subjected to image analysis as it is, it is not possible to determine a decayed portion.

  In such a case, as shown in FIG. 16F, the near-infrared image is obtained by inverting the brightness of the image in FIG. Based on the above, it is possible to determine the corruption site.

  The preferred embodiment of the present invention has been described above, but the present invention is not limited to this, and various modifications can be made without departing from the object of the present invention.

DESCRIPTION OF SYMBOLS 10 Fruit and vegetable inspection apparatus 12 Near-infrared light projection means 13 Ultraviolet-light projection means 14 Near-infrared image imaging means 15 Fluorescence image imaging means 16 Analysis means 18 Near-infrared filter 19 Ultraviolet-fluorescence filter 20 Conveyance means 22 Reflector 23 Multiband camera 24 Beam splitter 26 Fruits and vegetables rotation mechanism S Fruits and vegetables

The present invention was invented in order to solve the problems in the prior art as described above.
A fruit and vegetable inspection apparatus for determining the presence or absence of abnormality of fruit and vegetables,
Near-infrared light projecting means for irradiating the fruit and vegetables with near-infrared light;
Ultraviolet light projecting means for irradiating the fruits and vegetables with ultraviolet light;
A near-infrared image capturing means for capturing a near-infrared image of the fruit and vegetables with the near-infrared light;
Fluorescence image capturing means for capturing a fluorescent image of the fruits and vegetables by visible fluorescence excited by the ultraviolet light;
Based on the near-infrared image and the fluorescent image, analysis means for detecting the presence or absence of abnormality of the fruits and vegetables,
A transport means for transporting the fruits and vegetables in a predetermined direction ,
The near infrared light projecting means can irradiate light including an inspection wavelength of 1450 ± 50 nm,
The analysis means uses the near-infrared image based on the light of the inspection wavelength and the fluorescence image, and binarizes the near-infrared image and the fluorescence image after highlighting a change in contrast. By the above, it is configured to detect in- line the presence or absence of abnormality including at least water rot of the fruits and vegetables.

Moreover, the said conveyance means can also be provided with the fruit and vegetables rotation mechanism which rotates the said fruit and vegetables in a desired direction.
The near-infrared image capturing means and the fluorescent image capturing means are disposed above the fruits and vegetables,
The near-infrared image capturing unit and the fluorescent image capturing unit may be further disposed below the fruits and vegetables.
Further, the near-infrared image capturing unit and the fluorescent image capturing unit may be disposed above the fruits and vegetables.
Moreover, the said near-infrared image imaging means and the said fluorescence image imaging means may be arrange | positioned under the said fruits and vegetables.
In addition, each pixel value of the near-infrared image is calculated as a ratio of the reflected light Rs from the fruits and vegetables and the reflected light Rr from the standard obtained by irradiating the incident light acquired in advance. The reflection ratio R can be determined based on the following formula (1).
Further, each pixel value of the inspection image can be determined based on the apparent absorbance A, that is, the following equation (2).

The present invention was invented in order to solve the problems in the prior art as described above.
A fruit and vegetable inspection apparatus for determining the presence or absence of abnormality of fruit and vegetables,
Near-infrared light projecting means for irradiating the fruit and vegetables with near-infrared light;
Ultraviolet light projecting means for irradiating the fruits and vegetables with ultraviolet light;
A near-infrared image capturing means for capturing a near-infrared image of the fruit and vegetables with the near-infrared light;
Fluorescence image capturing means for capturing a fluorescent image of the fruits and vegetables by visible fluorescence excited by the ultraviolet light;
Based on the near-infrared image and the fluorescent image, analysis means for detecting the presence or absence of abnormality of the fruits and vegetables,
A transport means for transporting the fruits and vegetables in a predetermined direction,
The near infrared light projecting means can irradiate light including an inspection wavelength of 1450 ± 50 nm,
The analysis means uses the near-infrared image based on the light of the inspection wavelength and the fluorescence image, and binarizes the near-infrared image and the fluorescence image after highlighting a change in contrast. Is configured to detect in-line presence or absence of abnormality including at least water rot of the fruits and vegetables ,
Each pixel value of the near-infrared image is a reflection ratio of the fruits and vegetables calculated as a ratio of the reflected light Rs from the fruits and vegetables and the reflected light Rr from the standard obtained by irradiating the incident light acquired in advance. R is determined based on the following formula (1) .

Moreover, the said conveyance means can also be provided with the fruit and vegetables rotation mechanism which rotates the said fruit and vegetables in a desired direction.
The near-infrared image capturing means and the fluorescent image capturing means are disposed above the fruits and vegetables,
The near-infrared image capturing unit and the fluorescent image capturing unit may be further disposed below the fruits and vegetables.
Further, the near-infrared image capturing unit and the fluorescent image capturing unit may be disposed above the fruits and vegetables.
Moreover, the said near-infrared image imaging means and the said fluorescence image imaging means may be arrange | positioned under the said fruits and vegetables .
Also, each pixel value of the inspection image, absorbance A of the apparent, i.e., can be determined on the basis of the following formula (2).

Claims (7)

A fruit and vegetable inspection apparatus for determining the presence or absence of abnormality of fruit and vegetables,
Near-infrared light projecting means for irradiating the fruit and vegetables with near-infrared light;
Ultraviolet light projecting means for irradiating the fruits and vegetables with ultraviolet light;
A near-infrared image capturing means for capturing a near-infrared image of the fruit and vegetables with the near-infrared light;
Fluorescence image capturing means for capturing a fluorescent image of the fruits and vegetables by visible fluorescence excited by the ultraviolet light;
Analyzing means for detecting the presence or absence of abnormality of the fruits and vegetables based on the near-infrared image and the fluorescent image;
The near infrared light projecting means can irradiate light including an inspection wavelength of 1450 ± 50 nm,
The fruit and vegetable inspection apparatus, wherein the analysis means is configured to detect the presence or absence of abnormality of the fruit and vegetables using the near-infrared image based on the light of the inspection wavelength and the fluorescence image. It further comprises transport means for transporting the fruits and vegetables in a predetermined direction,
The fruit and vegetable inspection apparatus according to claim 1, wherein the fruit and vegetable inspection is configured to be performed inline. Further comprising reflecting mirrors on both sides of the conveying device;
The whole fruit and vegetables can be imaged by the near-infrared image imaging means and the fluorescent image imaging means by projecting the side surface of the fruit and vegetables on the reflecting mirror. Fruit and vegetable inspection device.   The fruit and vegetable inspection apparatus according to claim 2 or 3, wherein the transport means includes a fruit and vegetable rotation mechanism that rotates the fruit and vegetables in a desired direction. The near-infrared image capturing means and the fluorescent image capturing means are disposed above the fruits and vegetables,
5. The fruit and vegetable inspection apparatus according to claim 1, wherein the near-infrared image capturing unit and the fluorescence image capturing unit are further disposed below the fruit and vegetable.   The fruit and vegetable inspection apparatus according to claim 1, wherein the near-infrared image capturing unit and the fluorescence image capturing unit are disposed above the fruit and vegetable.   5. The fruit and vegetable inspection apparatus according to claim 1, wherein the near-infrared image capturing unit and the fluorescence image capturing unit are disposed below the fruit and vegetable.