JP2017111085A - Food product inspection system and food product inspection method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a food product inspection system and a food product inspection method capable of more correctly detecting a hair in a food product.SOLUTION: An imaging part 13 images an image of a food product. A contrast calculation part 112 calculates a contrast of an attention area in the image which is imaged by the imaging part 13 and a peripheral area with respect to the attention area. A hair detection part 114 detects an image of a hair included in the image which is imaged by the imaging part 13 based on the contrast calculated by the contrast calculation part 112. Therefore, since it is possible to detect an image of the hair using not an absolute value but a relative value, so that the hair in the food product can be detected more correctly.SELECTED DRAWING: Figure 2

Description

  The present invention relates to a food inspection system and a food inspection method for detecting hair in food.

  In the manufacturing process and packing process of food, the operator's hair (head hair, eyebrows, eyelashes, etc.) may adhere to the food. Thus, it is not preferable from the viewpoint of hygiene management that the food is shipped with the hair attached thereto. Thus, various foreign object detection devices for detecting foreign substances mixed in food have been proposed (for example, see Patent Document 1 below).

  Many foreign object detection devices exemplified in Patent Document 1 take a food image, binarize the image, and then perform a process for detecting the foreign object included in the image. That is, by binarizing the image and distinguishing between a region close to white and a region close to black in the image, foreign matter close to black is easily detected.

Special table 2008-541007 gazette

  However, it is particularly difficult to detect hair among foreign substances, and it has been difficult to reliably prevent cases where the hair is shipped with food attached to the food. Even if it is easy for humans to identify food with the naked eye, it may not be possible to reliably detect hair using conventional image processing as described above. It was.

  The reason may be that information from the human eye does not always match what is actually seen (information recognized by the brain). In other words, the process of binarizing the image is a process that is far from the method that humans recognize with the brain, so even though it can distinguish between areas close to white and areas close to black, it is hair. It is difficult to accurately detect whether or not it is hair, and it is considered that it is difficult to determine whether or not it is hair by performing binarization processing.

  The present invention has been made in view of the above circumstances, and an object thereof is to provide a food inspection system and a food inspection method capable of more accurately detecting hair in food.

  The food inspection system according to the present invention is a food inspection system for detecting hair in food, and includes a photographing unit, a contrast calculation unit, and a hair detection unit. The imaging unit captures an image of food. The contrast calculation unit calculates a contrast between a region of interest in the image photographed by the photographing unit and a peripheral region with respect to the region of interest. The hair detection unit detects an image of hair included in the image photographed by the photographing unit based on the contrast calculated by the contrast calculation unit.

  According to such a configuration, the binarization process is not performed on the image photographed by the photographing unit, but the contrast (difference) between the attention area in the image and the peripheral area with respect to the attention area is calculated. By doing so, the image of the hair contained in the photographed image is detected based on the contrast. Thereby, since the image of hair can be detected using a relative value rather than an absolute value, hair in food can be detected more accurately.

  The contrast calculation unit includes a region of interest and a region of interest for at least one element among red (R), green (G), blue (B), hue (H), saturation (S), and brightness (V). Contrast with the surrounding area may be calculated.

  According to such a configuration, the contrast between the attention area in the image and the peripheral area with respect to the attention area is calculated for at least one element included in RGB and HSV. Since these elements are important elements when humans process information from the eyes, it is possible to more accurately detect hair in food by using the elements.

  The food inspection system may further include a food type input receiving unit that receives an input of a type of food to be inspected. In this case, the contrast calculation unit calculates the contrast between the attention area and the surrounding area with respect to the attention area for the at least one element selected according to the type of food received by the food type input reception section. It may be calculated.

  According to such a configuration, at least one element included in RGB and HSV is appropriately selected according to the type of the food to be inspected whose input is received by the food type input receiving unit, and the element is used. Thus, the hair in the food can be detected more accurately. For example, when the type of food is red meat, the hair in the food can be detected more accurately by using the blue (B) element.

  The food inspection system may further include a contour region extraction unit that extracts a region of interest whose contrast calculated by the contrast calculation unit is equal to or greater than a threshold value as a contour region. In this case, the hair detection unit may detect a hair image included in the image photographed by the photographing unit based on the contour region extracted by the contour region extraction unit.

  According to such a configuration, the contour region can be satisfactorily extracted using a relative value instead of an absolute value, and thus hair in food can be detected more accurately based on the extracted contour region. it can.

  The food inspection system may further include a sample image storage unit that stores a sample image of hair. In this case, the hair detection unit compares the image of the contour region extracted by the contour region extraction unit with the sample image stored in the sample image storage unit, thereby capturing an image photographed by the photographing unit. You may detect the image of the hair contained in.

  According to such a configuration, the image of the hair included in the photographed image is detected by comparing the image of the contour region with the sample image of the hair. Since humans recognize hair by contrast with their own memory, according to the present invention, hair in food can be detected more accurately by using a process similar to the human recognition method.

  The hair detection unit may detect an image of hair included in the image photographed by the photographing unit based on the linearity of the contour region image extracted by the contour region extraction unit.

  According to such a configuration, an image of hair included in the photographed image is detected based on whether or not the image of the contour region is close to a straight line. Since humans tend to recognize that hair is more likely to be hair when the contour region is close to a straight line, according to the present invention, hair in food is more accurately detected using a process similar to the human recognition method. Can be detected.

  The hair detection unit detects a hair image included in the image photographed by the photographing unit based on the number of pixels of the contour region image extracted by the contour region extraction unit and the number of pixels inside the contour region. May be.

  According to such a configuration, by counting the number of pixels (peripheral length L) of the image of the contour region and the sum (area S) of the number of pixels of the contour region and the number of pixels inside the contour region, the image A hair image included in the photographed image is detected based on whether the ratio (L / S) between the perimeter length L and the area S is large. Since humans tend to recognize that hair is likely to be hair when the value of L / S is large, according to the present invention, the hair in food is more easily treated using the same process as the human recognition method. It can be detected accurately.

  The food inspection method according to the present invention is a food inspection method for detecting hair in food, and includes a photographing step, a contrast calculation step, and a hair detection step. In the photographing step, a food image is photographed. In the contrast calculation step, a contrast between the attention area in the image photographed in the photographing step and a peripheral area with respect to the attention area is calculated. In the hair detection step, an image of hair included in the image photographed in the photographing step is detected based on the contrast calculated in the contrast calculation step.

It is the schematic which showed the structural example of the food inspection system which concerns on one Embodiment of this invention. It is the block diagram which showed an example of the electric constitution of a mobile terminal. It is an example of the image image | photographed by the imaging | photography part. FIG. 3B is an example of an image obtained by the contour region extraction unit extracting a contour region from the image of FIG. 3A. FIG. It is an example of the image which the hair detection part performed the process for detecting the image of hair based on the image of FIG. 3B. It is another example of the image image | photographed by the imaging | photography part. 4B is an example of an image obtained by the contour region extraction unit extracting a contour region from the image of FIG. 4A. It is an example of the image which the hair detection part performed the process for detecting the image of hair based on the image of FIG. 4B. It is another example of the image image | photographed by the imaging | photography part. 5B is an example of an image obtained by the contour region extraction unit extracting a contour region from the image of FIG. 5A. It is an example of the image which the hair detection part performed the process for detecting the image of hair based on the image of FIG. 5B. It is the flowchart which showed the flow of the process by a control part. It is the flowchart which showed the 1st modification of the process by a control part. It is the flowchart which showed the 2nd modification of the process by a control part.

  FIG. 1 is a schematic diagram illustrating a configuration example of a food inspection system according to an embodiment of the present invention. This food inspection system is a system for detecting hair (head hair, eyebrows, eyelashes, etc.) adhering to the surface of the food F, and in the process of transporting the food F on the conveyor 1, the food F The inspection is performed. For example, the food F is transported on the conveyor 1 in a state of being placed on the tray T, and after being inspected, packed by the wrap W and then shipped.

  In this food inspection system, for example, the food F is inspected using the mobile terminal 10. Specifically, the food F on the conveyor 1 is photographed using the mobile terminal 10, and the food F is inspected by performing calculations in the mobile terminal 10 based on the photographed image. The mobile terminal 10 is a concept including a small notebook personal computer, a smartphone, a tablet terminal, or the like.

  The mobile terminals 10 are arranged above the conveyor 1 with a gap. The periphery of the mobile terminal 10 is surrounded by the housing 2, and the illumination 3 and the like are arranged in the housing 2 in addition to the mobile terminal 10. During the inspection, photographing by the mobile terminal 10 is performed while illuminating the food F with the light from the illumination 3. However, the structure which illuminates the food F using the illumination (not shown) with which the mobile terminal 10 was equipped may be sufficient.

  FIG. 2 is a block diagram showing an example of the electrical configuration of the mobile terminal 10. The mobile terminal 10 includes, for example, a control unit 11, an operation unit 12, a photographing unit 13, a storage unit 14, an audio output unit 15, and the like. The control unit 11 includes, for example, a CPU (Central Processing Unit), and when the CPU executes a program, the food type input reception unit 111, the contrast calculation unit 112, the contour region extraction unit 113, the hair detection unit 114, and It functions as the detection result output unit 115 and the like.

  The operation unit 12 is configured by, for example, a touch panel provided on a display screen. However, the operation unit is not limited to the touch panel, and may be configured by operation buttons or the like. The imaging unit 13 is configured by, for example, a CMOS image sensor, but is not limited thereto. The storage unit 14 includes a RAM (Random Access Memory) and a ROM (Read Only Memory). The audio output unit 15 includes a speaker or an earphone jack.

  When the food F is inspected, an image of the food F on the conveyor 1 is taken by the photographing unit 13. The control unit 11 processes the image (moving image) obtained in this manner, whereby the hair in the food F is detected. Specifically, first, the contrast calculation unit 112 performs a process of calculating the contrast between each pixel included in the captured moving image and the neighboring pixels adjacent to each pixel.

  That is, each pixel in the captured image is sequentially selected as a target pixel (a pixel to be subjected to image processing), and the contrast between the target pixel and eight peripheral pixels surrounding the target pixel is calculated. . As the contrast, for example, a difference for at least one element of red (R), green (G), blue (B), hue (H), saturation (S), and lightness (V) is calculated. In this example, a configuration in which contrast is calculated using each pixel as a region of interest (a pixel of interest) and each pixel adjacent to the region of interest as a peripheral region (peripheral pixel) will be described. The contrast may be calculated using a plurality of pixels adjacent to the attention area as a peripheral area.

  The food type input receiving unit 111 receives an input of the type of food F to be inspected based on the operation of the operation unit 12 by the operator. For example, the worker can select a type corresponding to the inspection target from among a plurality of types of food F displayed on the display screen of the mobile terminal 10. The type of food F may be, for example, a type such as meat, fish, lunch, etc., a subdivided type such as chicken or pork among meats, or a fillet, chicken meat, chicken wings or chicken wings among chickens. The classification may be subdivided into parts such as the inside.

The contrast calculation unit 112 selects red (R), green (G), blue (B), hue (H), and saturation selected according to the type of the food F that has been received by the food type input reception unit 111. For at least one element of (S) and brightness (V), the contrast between each pixel of interest and the surrounding pixels with respect to the pixel of interest is calculated. For example, when the type of the food F is red meat, the contrast is calculated for the B (blue) element. Specifically, for example, the contrast can be calculated in the following manner.
(1) Contrast is calculated for blue (B) elements for pink colors such as chicken, pork, and salmon fillets, or brown such as fried food.
(2) For a blue color such as a fish with a blue back, the contrast is calculated for the red (R) element.
(3) Contrast is calculated for lightness (V) and blue (B) elements for green such as leaves.
(4) The bento is examined by classifying the element for calculating the contrast and the threshold value according to the food type such as the white portion of the rice and the portion of the side dish.
(5) Even when the salmon fillet (pink) and croquette (brown) are adjacent to each other, the contrast is calculated for the same element, so it is not necessary to check separately and can be examined at once.

  The contour region extraction unit 113 extracts a target pixel whose contrast calculated by the contrast calculation unit 112 is equal to or greater than a threshold value as a contour pixel. However, in a configuration in which contrast is calculated using a plurality of pixels as a region of interest and a plurality of pixels adjacent to the region of interest as a peripheral region, the region of interest (a plurality of pixels) having a contrast equal to or greater than a threshold is outlined. It may be extracted as a region. When the hair is contained in the food F by the processing of the contour region extraction unit 113, the contour region of the hair is extracted. However, a contour region other than the hair may be extracted. .

Therefore, the hair detection unit 114 detects the hair in the food F after performing processing for removing pixels corresponding to the contour region other than the hair on the contour region extracted by the contour region extraction unit 113. To do. Examples of the process for removing pixels other than hair include the following (1) to (3).
(1) Since the hair is slender and does not have a large area, pixels in the area where the area surrounded by the outline area has a large area are removed. (2) With white portions such as tray T and meat fat The pixels at the boundary are removed because the difference in saturation is large.
(3) The floating pixels are removed because they do not constitute hair.

  After removing pixels other than the hair in this way, the hair detection unit 114 performs a smoothing process on the obtained image, and is imaged by the imaging unit 13 based on the contour region included in the image. An image of hair contained in the image is detected. In the present embodiment, a plurality of sample images having various lengths and various shapes are stored in advance in the storage unit 14 as hair sample images, and the hair detection unit 114 has the contour extracted by the contour region extraction unit 113. By comparing the image of the region with the sample image stored in the storage unit 14, an image having a matching degree equal to or higher than a threshold value is detected as a hair image.

  The detection result by the hair detection unit 114 is output by the detection result output unit 115. Specifically, when hair is detected by the hair detection unit 114, the detection result output unit 115 outputs a warning sound via the audio output unit 15. However, not only the warning sound but also a configuration in which the conveyor 1 is stopped or a lamp (not shown) is lit or blinked based on a signal output from the detection result output unit 115 may be used. .

  The detection result by the hair detection unit 114 may be transmitted to a server (not shown). In the server, not only the detection result but also the obtained image may be stored and accumulated as a production history. Data transmission from the mobile terminal 10 to the server can be performed using a wireless communication function provided in the mobile terminal 10.

  FIG. 3A is an example of an image photographed by the photographing unit 13. FIG. 3B is an example of an image obtained by the contour region extraction unit 113 extracting a contour region from the image of FIG. 3A. FIG. 3C is an example of an image obtained by performing processing for detecting the hair image by the hair detection unit 114 based on the image of FIG. 3B. FIG. 4A is another example of an image photographed by the photographing unit 13. FIG. 4B is an example of an image obtained by the contour region extraction unit 113 extracting a contour region from the image of FIG. 4A. FIG. 4C is an example of an image obtained by performing processing for detecting the hair image by the hair detection unit 114 based on the image of FIG. 4B. FIG. 5A is still another example of an image photographed by the photographing unit 13. FIG. 5B is an example of an image obtained by the contour region extraction unit 113 extracting a contour region from the image of FIG. 5A. FIG. 5C is an example of an image obtained by performing processing for detecting the hair image by the hair detection unit 114 based on the image of FIG. 5B.

  As shown in FIGS. 3B, 4B, and 5B, when the contour region is extracted by the contour region extraction unit 113, the contour region of the hair can be extracted, but the contour region other than the hair is also extracted. The hair detection unit 114 performs a process of removing pixels other than the hair on such an image, so that the hair image can be easily identified as shown in FIGS. 3C, 4C, and 5C. And an image of the hair is detected.

  As described above, in this embodiment, the binarization process is not performed on the image captured by the imaging unit 13, but the contrast (difference) between the attention area in the image and the surrounding area with respect to the attention area. ) Is calculated, the hair image included in the photographed image is detected based on the contrast. Thereby, since the image of hair can be detected using a relative value rather than an absolute value, the hair in the food F can be detected more accurately.

  In particular, in the present embodiment, for at least one element included in RGB and HSV, the contrast between the attention area in the image and the peripheral area with respect to the attention area is calculated. Since these elements are important elements when humans process information from the eyes, the hair in the food F can be detected more accurately by using the elements.

  Further, in the present embodiment, at least one element included in RGB and HSV is appropriately selected according to the type of food to be inspected whose input is received by the food type input receiving unit 111, and the element is used. Thus, the hair in the food F can be detected more accurately. For example, when the type of the food F is red meat, the hair in the food F can be detected more accurately by using the blue (B) element.

  Furthermore, in this embodiment, the image of the hair included in the photographed image is detected by comparing the image of the contour region with the sample image of the hair. Since humans recognize hair by contrast with their own memory, according to the present embodiment, it is possible to more accurately detect hair in food F using the same process as the human recognition method.

  FIG. 6 is a flowchart showing the flow of processing by the control unit 11. When detecting hair in the food F, first, an image of the food F is photographed by the photographing unit 13 (step S101: photographing step). Then, the contrast between the attention area in the photographed image and the surrounding area with respect to the attention area is calculated (step S102: contrast calculation step), and the attention area whose calculated contrast is equal to or greater than the threshold is extracted as a contour area ( Step S103: contour region extraction step).

  Thereafter, the pixels corresponding to the contour region other than the hair in the extracted contour region are removed (step S104), and the obtained image is subjected to smoothing processing (step S105). Thereby, it becomes easy to discriminate | determine the image of hair, and the image of the hair contained in the image image | photographed by the imaging | photography part 13 is detected by the comparison with the sample image memorize | stored in the memory | storage part 14 (step S106).

  The process of said step S104-S106 comprises the hair detection step. The detection result of this hair detection step is output via the audio output unit 15 or the like (step S107), and if the food F contains hair, the operator is notified of that fact. Thus, it is possible to prevent the food F from being shipped as it is.

  FIG. 7 is a flowchart showing a first modification of the processing by the control unit 11. Since the process from step S201 to S204 in this example is the same as the process from step S101 to S104 in FIG. 6, detailed description thereof is omitted.

  In this example, after the pixels corresponding to the contour region other than the hair are removed from the extracted contour region (step S204), based on the linearity of the image of the contour region in the obtained image, the photographing unit 13 An image of hair included in the photographed image is detected (step S205). The linearity means whether or not it is close to a straight line, and a straight line or a smooth curved line segment has high linearity (close to a straight line). For example, if the radius of curvature of the contour region image having the smallest curvature radius is equal to or greater than a predetermined threshold value, the contour region image is close to a straight line (high linearity). That is, the straightness of the contour region is calculated, and the straightness is compared with a threshold value, so that if the image of the contour region is close to a straight line, it is determined as hair, and if it is not close to a straight line, it is determined as an image other than hair. . However, the present invention is not limited to this method. For example, a plurality of images with high linearity are stored, and the image of the hair is detected by comparing these images with the image of the obtained contour region (pattern matching). Also good.

  The processes in steps S204 and S205 constitute a hair detection step. The detection result of this hair detection step is output via the audio output unit 15 or the like (step S206), and when the food F contains hair, the operator is notified of that fact. Thus, it is possible to prevent the food F from being shipped as it is.

  In this example, an image of hair included in the captured image is detected based on whether or not the image of the contour region is close to a straight line. Since humans tend to recognize that there is a high possibility of being hair when the contour region is close to a straight line, according to this embodiment, hair in food is more processed using a process similar to the human recognition method. It can be detected accurately.

  FIG. 8 is a flowchart showing a second modification of the process by the control unit 11. Since the process from step S301 to S304 in this example is the same as the process from step S101 to S104 in FIG. 6, detailed description thereof is omitted.

  In this example, after the pixels corresponding to the contour region other than the hair are removed from the extracted contour region (step S304), the number of pixels in the contour region in the obtained image is counted (step S305). . The number of pixels of the contour region image thus counted corresponds to the peripheral length L of the image. Then, the number of pixels inside the contour region is counted (step S306). The sum of the number of pixels in the contour area counted in step S305 and the number of pixels inside the contour area counted in step S306 corresponds to the area S of the image. Thereafter, the ratio (L / S) of the peripheral length L to the area S of the image is compared with the threshold value, thereby detecting the hair image included in the image photographed by the photographing unit 13 (step S307). That is, if the value of L / S is equal to or greater than the threshold value, it is determined as hair, and if it is less than the threshold value, it is determined as an image other than hair.

  The processing of steps S304 to S307 constitutes a hair detection step. The detection result of this hair detection step is output via the audio output unit 15 or the like (step S308), and when the food F contains hair, the operator is notified of that fact. Thus, it is possible to prevent the food F from being shipped as it is.

  In this example, an image of hair included in the photographed image is detected based on whether or not the ratio (L / S) of the peripheral length L to the area S of the image is large. Since humans tend to recognize that there is a high possibility of being hair when the value of L / S is large, according to this embodiment, hair in food is treated using a process similar to the human recognition method. More accurate detection is possible.

  In the above embodiment, the configuration in which the hair in the food F is detected using the control unit 11 and the imaging unit 13 provided in the mobile terminal 10 has been described. However, the configuration is not limited to using the mobile terminal 10, and for example, a configuration in which the control unit 11 and the imaging unit 13 are individually provided may be used.

  Moreover, in the above embodiment, the structure which test | inspects with respect to the food F conveyed on the conveyor 1 was demonstrated. However, the configuration is not limited to using the conveyor 1, and may be a configuration in which an inspection is performed on the food F by, for example, an operator manually setting the food F at an inspection position.

  Further, in the above embodiment, the food inspection system in which the inspection for the food F is automatically performed has been described. However, the present invention can be applied to a configuration in which the operator manually inspects the food F. Is possible.

DESCRIPTION OF SYMBOLS 1 Conveyor 2 Housing 3 Illumination 10 Mobile terminal 11 Control part 12 Operation part 13 Image | photographing part 14 Memory | storage part 15 Audio | voice output part 111 Food type input reception part 112 Contrast calculation part 113 Contour area extraction part 114 Hair detection part 115 Detection result output part F Food T Tray W Wrap

Claims (8)

A food inspection system for detecting hair in food,
A shooting section for taking images of food;
A contrast calculation unit that calculates a contrast between a region of interest in the image captured by the imaging unit and a peripheral region with respect to the region of interest;
A food inspection system comprising: a hair detection unit that detects a hair image included in an image photographed by the photographing unit based on the contrast calculated by the contrast computing unit.   The contrast calculation unit includes a region of interest and a region of interest for at least one element among red (R), green (G), blue (B), hue (H), saturation (S), and brightness (V). The food inspection system according to claim 1, wherein a contrast with a peripheral region is calculated. A food type input receiving unit that receives an input of the type of food to be inspected;
The contrast calculation unit calculates a contrast between a region of interest and a surrounding region with respect to the region of interest for the at least one element selected according to the type of food received by the food type input receiving unit. The food inspection system according to claim 2. A contour region extraction unit that extracts a region of interest whose contrast calculated by the contrast calculation unit is a threshold value or more as a contour region;
The said hair detection part detects the image of the hair contained in the image image | photographed by the said imaging | photography part based on the outline area | region extracted by the said outline area | region extraction part. The food inspection system described in Crab. A sample image storage unit for storing a sample image of hair;
The hair detection unit is included in the image photographed by the photographing unit by comparing the image of the contour region extracted by the contour region extraction unit with the sample image stored in the sample image storage unit. The food inspection system according to claim 4, wherein an image of hair is detected.   The hair detection unit detects an image of hair included in an image photographed by the photographing unit based on linearity of an image of the contour region extracted by the contour region extraction unit. 4. The food inspection system according to 4.   The hair detection unit detects a hair image included in the image photographed by the photographing unit based on the number of pixels of the contour region image extracted by the contour region extraction unit and the number of pixels inside the contour region. The food inspection system according to claim 4. A food inspection method for detecting hair in food,
A shooting step for shooting food images;
A contrast calculation step for calculating a contrast between a region of interest in the image photographed by the photographing step and a peripheral region with respect to the region of interest;
A food inspection method comprising: a hair detection step of detecting an image of hair included in an image photographed by the photographing step based on the contrast calculated by the contrast calculating step.