Image processing device, image processing program, and image processing method

Abstract

To favorably assist work of appropriately cutting an element which is required to be cut from a food product having variation.SOLUTION: An image processing apparatus comprises: an image acquisition unit that acquires an image in which a subject including an element required to be cut is drawn; a position identification unit that superimposes a predetermined diagram which is different from the subject on the image and identifies a position of the element in the subject using the predetermined diagram; a boundary identification unit that identifies a boundary between the element and a part other than the element on the image by performing image processing of the image; and a trajectory determination unit that determines a trajectory of a blade in cutting the element from the subject on the basis of the boundary.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to an image processing device, an image processing program, and an image processing method. [Background technology]

[0002] Foods handled in factories and the like may contain unnecessary elements. For example, if the food is chicken thighs, the unnecessary elements include skin, fat, tendons, etc. Currently, the entire process of removing skin, fat, tendons, etc. from chicken thighs and shaping the chicken thighs is performed manually. However, this work is dangerous because it requires the use of blades. In addition, this work must be performed at low temperatures, which places a heavy burden on workers. Furthermore, the problem of labor shortages has become apparent in recent years. For example, a device has been developed to solve these problems, such as the one disclosed in Non-Patent Document 1. This device uses a water jet to cut food. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] "YouTube (registered trademark) JBT - Protein - Europe, Middle East and Africa DSI 800s-PL," [Retrieved June 24, 2020], Internet<URL:https: / / www.youtube.com / watch?v=kGfcRU7QpQw> Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned device may not be able to suitably perform the task of cutting out elements that need to be cut out from food products that have variations in shape, color, etc., such as chicken thighs.

[0005] The present invention has been made in consideration of the above-mentioned circumstances, and aims to provide an image processing device, an image processing program, and an image processing method that can effectively assist in the task of appropriately cutting out elements that need to be cut out from food that has variations. [Means for solving the problem]

[0006] One aspect of the present invention is to provide an image acquisition unit that acquires an image depicting a subject including an element that needs to be cut out, and an image acquisition unit that acquires an image depicting a subject including an element that needs to be cut out and an image capture unit that captures an image depicting a subject that needs to be cut out. A figure whose sides circumscribe an area depicting a second element that is a part of the subject other than the element. The image processing device includes a position identification unit that superimposes a predetermined figure and identifies the position of the element on the subject using the predetermined figure, a boundary identification unit that identifies the boundary between the element and a portion other than the element on the image by performing image processing on the image, and a trajectory determination unit that determines the trajectory of a blade when cutting the element from the subject based on the boundary.

[0008] In one aspect of the present invention, in the image processing device described above, the predetermined graphic is a combination of a plurality of graphics that are identical to one another.

[0009] One aspect of the present invention is the above-mentioned image processing device, which acquires an image depicting the subject including at least two of the elements, and the position identification unit identifies the position of the element in the subject using the relative positional relationship between the at least two of the elements.

[0010] In one aspect of the present invention, in the image processing device described above, the trajectory determination unit sets the trajectory a predetermined distance away from the boundary.

[0011] One aspect of the present invention is to provide an image capturing function for capturing an image depicting a subject including an element that needs to be cropped, and a method for capturing an image depicting a subject that needs to be cropped, the image capturing function including an element that needs to be cropped, the image depicting a subject that needs to be cropped, and a method for capturing an image depicting a subject that needs to be cropped. A figure whose sides circumscribe an area depicting a second element that is a part of the subject other than the element.This is an image processing program that causes a computer to realize a position identification function that superimposes a predetermined figure and uses the predetermined figure to identify the position of the element on the subject, a boundary identification function that identifies the boundary between the element and parts other than the element on the image by applying image processing to the image, and a trajectory determination function that determines the trajectory of a blade when cutting the element from the subject based on the boundary.

[0012] In one aspect of the present invention, an image depicting a subject including an element that needs to be cut out is acquired by an image acquisition unit or an image acquisition function, and an image different from the subject is added to the image. A figure whose sides circumscribe an area depicting a second element that is a part of the subject other than the element. This is an image processing method that superimposes a predetermined figure, identifies the position of the element on the subject using the predetermined figure, performs image processing on the image to identify the boundary between the element and parts other than the element on the image using a boundary identification unit or boundary identification function, and determines the trajectory of a blade when cutting the element from the subject based on the boundary using a trajectory determination unit or trajectory determination function. [Effects of the Invention]

[0013] According to the present invention, it is possible to favorably assist the task of favorably cutting out elements that need to be cut out from food products that have variations. [Brief explanation of the drawings]

[0014] [Figure 1] FIG. 1 is a diagram illustrating an example of a hardware configuration of an image processing apparatus according to an embodiment. [Figure 2] 1 is a diagram illustrating an example of an image processing device, an imaging device, lighting, and a food processing line according to an embodiment. [Figure 3] FIG. 3 is a diagram showing an example of the chicken thigh and its surroundings shown in FIG. 2 as viewed from above. [Figure 4] FIG. 2 is a diagram illustrating an example of a software configuration of the image processing apparatus according to the embodiment. [Figure 5] 10A and 10B are diagrams illustrating an example of boundaries between the first skin, the second skin, the third skin, or the muscle and the lean meat identified by the image processing device according to the embodiment. [Figure 6] FIG. 10 is a diagram showing an example of a first skin of a chicken thigh identified by the image processing device according to the embodiment. [Figure 7] FIG. 10 is a diagram showing an example of twelve rectangles superimposed on an image depicting a chicken thigh according to an embodiment. [Figure 8] 10A and 10B are diagrams showing examples of the boundary between the first skin and the lean meat, the boundary between the second skin and the lean meat, and the boundary between the muscle and the lean meat identified by the image processing device according to the embodiment; [Figure 9] 10A and 10B are diagrams showing examples of the blade trajectory when cutting the first skin from the chicken thigh, the blade trajectory when cutting the second skin from the chicken thigh, and the blade trajectory when cutting the tendon from the chicken thigh, determined by the image processing device according to the embodiment. [Figure 10] 10 is a flowchart illustrating an example of processing executed by the image processing apparatus according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0015] [Embodiment] An image processing device, an image processing program, and an image processing method according to an embodiment will be described with reference to Figures 1 to 10. First, the hardware constituting the image processing device according to an embodiment and the hardware attached to the image processing device will be described with reference to Figures 1 to 3.

[0016] 1 is a diagram illustrating an example of the hardware configuration of an image processing device according to an embodiment. As shown in FIG. 1, the image processing device 10 includes a processor 11, a main memory device 12, a communication interface 13, an auxiliary memory device 14, an input / output device 15, and a bus 16.

[0017] The processor 11 is, for example, a CPU (Central Processing Unit), and reads and executes an image processing program to realize the functions shown in Fig. 4. The processor 11 may also read and execute a program other than the image processing program to realize functions necessary for realizing each function of the image processing device 10.

[0018] The main storage device 12 is, for example, a RAM (Random Access Memory), and stores in advance an image processing program and other programs that are read and executed by the processor 11.

[0019] The communication interface 13 is an interface circuit for communicating with the image capturing device 154, the control device 200, and other devices via a network. The communication interface 13 is connected to, for example, the image capturing device 154 and the control device 200 shown in Figures 1 and 2. The network referred to here is, for example, a WAN (Wide Area Network), a LAN (Local Area Network), the Internet, or an intranet.

[0020] The auxiliary storage device 14 is, for example, a hard disk drive (HDD), a solid state drive (SSD), a flash memory, or a read only memory (ROM).

[0021] The input / output device 15 is, for example, an input / output port. For example, the mouse 151, keyboard 152, and display 153 shown in FIG. 1 are connected to the input / output device 15. FIG. 2 is a diagram showing an example of an image processing device, a photographing device, lighting, and a food processing line according to an embodiment. FIG. 3 is a diagram showing an example of a top view of the chicken thigh and its surroundings shown in FIG. 2. Furthermore, lighting 155, lighting 156, lighting 157, and lighting 158 are connected to the control device 200, and the control device 200 controls these four lightings.

[0022] The mouse 151 and keyboard 152 are used, for example, to input data required to operate the image processing device 10.

[0023] The display 153 is, for example, a liquid crystal display, and displays, for example, a graphical user interface (GUI) of the image processing device 10.

[0024] The photographing device 154 is a camera that photographs a subject in color. The subject is, for example, chicken thigh meat M shown in FIG. 2. The chicken thigh meat M is transported by a belt conveyor 201 that constitutes food processing line 20, and is successively detected by photoelectric sensors 202, 203, and 204. The belt conveyor 201, photoelectric sensors 202, 203, and 204 are controlled by a control device 200. For example, as shown in FIG. 2, the photographing device 154 is installed in a position where it can photograph the chicken thigh meat M from above when the chicken thigh meat M is transported between photoelectric sensors 203 and 204 by the belt conveyor 201.

[0025] Lighting 155, lighting 156, lighting 157, and lighting 158 are devices that irradiate a subject with light such as white light, and include, for example, LEDs (light emitting diodes). As shown in FIG. 2, lighting 155 is installed above belt conveyor 201 and irradiates light onto chicken thigh meat M from the upstream side of belt conveyor 201 relative to camera 154. As shown in FIG. 2, lighting 156 is installed above belt conveyor 201 and irradiates light onto chicken thigh meat M from the downstream side of belt conveyor 201 relative to camera 154. As shown in FIG. 3, lighting 157 and lighting 158 are installed to the side of the path along which chicken thigh meat M is transported by belt conveyor 201 and irradiate light from the side onto chicken thigh meat M that has been transported by belt conveyor 201 to a position where it can be photographed by camera 154.

[0026] The bus 16 connects the processor 11, the main memory device 12, the communication interface 13, the auxiliary memory device 14, and the input / output device 15 so that data can be transmitted and received among them.

[0027] Next, processing executed by the image processing device according to the embodiment will be described with reference to Fig. 4 to Fig. 9. Fig. 4 is a diagram showing an example of the software configuration of the image processing device according to the embodiment. As shown in Fig. 4, the image processing device 10 includes an image acquisition unit 101, a boundary identification unit 102, a position identification unit 103, and a trajectory determination unit 104.

[0028] The image acquisition unit 101 acquires an image depicting a subject including an element that needs to be cut out. For example, the image acquisition unit 101 acquires an image depicting a subject including at least two elements. The image is, for example, a color image captured by the image capture device 154 and depicting a chicken thigh M. Furthermore, if the subject is a chicken thigh M, the elements are, for example, a tendon, a first skin, a second skin, and a third skin.

[0029] The tendon is a white string-like substance that is attached to the meat near the tip of the leg when an incision is made along the bone from the tip of the leg to the thigh and the meat is opened.

[0030] The first skin is the skin located first when the chicken thigh meat M is meat from the left leg of the chicken and the circumference of the chicken thigh meat M, viewed from the side where the bone was attached, is traced clockwise from the tendon. Alternatively, the first skin is the skin located third when the chicken thigh meat M is meat from the right leg of the chicken and the circumference of the chicken thigh meat M, viewed from the side where the bone was attached, is traced clockwise from the tendon. In other words, the position of the first skin relative to the tendon is uniquely determined whether the chicken thigh meat M is meat from the left leg of the chicken or the right leg of the chicken. Also, the first skin is the skin of the chicken's buttocks.

[0031] The second skin is the skin located second when the chicken thigh meat M is meat from the left leg of the chicken and the circumference of the chicken thigh meat M, viewed from the side where the bone was attached, is traced clockwise from the tendon. Alternatively, the second skin is the skin located second when the chicken thigh meat M is meat from the right leg of the chicken and the circumference of the chicken thigh meat M, viewed from the side where the bone was attached, is traced clockwise from the tendon. In other words, the position of the second skin relative to the tendon is uniquely determined whether the chicken thigh meat M is meat from the left leg of the chicken or the chicken thigh meat M is meat from the right leg of the chicken. Also, the second skin is the skin from the back of the chicken.

[0032] The third skin is the skin located third when the chicken thigh meat M is meat from the left leg of the chicken and the circumference of the chicken thigh meat M, viewed from the side where the bone was attached, is traced clockwise from the tendon. Alternatively, the third skin is the skin located first when the chicken thigh meat M is meat from the right leg of the chicken and the circumference of the chicken thigh meat M, viewed from the side where the bone was attached, is traced clockwise from the tendon. In other words, the third skin has a unique position relative to the tendon, whether the chicken thigh meat M is meat from the left leg of the chicken or the right leg of the chicken. The third skin is also the skin from the chicken's buttocks or back.

[0033] The boundary identification unit 102 calculates the difference between the pixel value of each pixel in an image obtained by extracting only the red component from the color image acquired by the image acquisition unit 101 and the pixel value of each pixel in an image obtained by extracting only the green component from the color image, and generates a difference image in which the pixel value of each pixel is the difference.The boundary identification unit 102 then performs a binarization process on the image to separate areas depicting the muscles, first skin, second skin, or third skin from areas depicting other red meat, and identifies the boundaries between them.

[0034] FIG. 5 is a diagram showing an example of the boundary between the first skin, the second skin, the third skin, or the tendon and the lean meat identified by the image processing device according to the embodiment. The chicken thigh M shown in FIG. 5 is meat from the left leg of a chicken. The boundary identification unit 102, for example, generates the difference image shown in FIG. 5 and performs a binarization process on the difference image to identify the boundary shown by the dashed line in FIG. 5. The area inside the dashed line shown in FIG. 5 is the area where the lean meat of the chicken thigh M is depicted. On the other hand, the area outside the dashed line shown in FIG. 5 is the area where the tendon, the first skin, the second skin, or the third skin of the chicken thigh M is depicted.

[0035] The position identifying unit 103 identifies the position of the element that needs to be cut out based on the image acquired by the image acquiring unit 101. For example, the position identifying unit 103 identifies the area that has the largest area among the areas outside the boundary identified by the boundary identifying unit 102 and shown by the dashed line in Fig. 5 as the area depicting the first skin.

[0036] FIG. 6 is a diagram showing an example of the first skin of a chicken thigh identified by the image processing device according to the embodiment. The chicken thigh M shown in FIG. 6 is meat from the left leg of a chicken. The area inside the dashed line shown in FIG. 6 is an area in which the muscle, first skin, second skin, or third skin of the chicken thigh M is depicted. The position identifying unit 103 identifies, for example, the area with the largest area among the areas inside the dashed line shown in FIG. 6 as the area in which the first skin is depicted.

[0037] FIG. 6 is a diagram showing an example of a first skin of a chicken thigh identified by the image processing device according to the embodiment. The chicken thigh M shown in FIG. 6 is meat from the left leg of a chicken. The area inside the dashed line shown in FIG. 6 is an area in which the muscle, first skin, second skin, or third skin of the chicken thigh M is depicted. The length of the long side of each of the two rectangles shown in FIG. 6 is equal to the width of the area depicting the lean meat of the chicken thigh M in the direction parallel to the long side. Furthermore, as shown in FIG. 6, these two rectangles share one long side. For example, the position identification unit 103 compares the area in which one of the three skins is depicted for the two rectangles shown in FIG. 6. Then, the position identification unit 103 determines that the first skin is depicted inside the rectangle with the larger area in which one of the three skins is depicted.

[0038] Next, the position identifying unit 103 superimposes a predetermined graphic on the image and identifies the positions of the elements in the subject using the predetermined graphic. Furthermore, the position identifying unit 103 identifies the positions of these four elements in the chicken thigh M using the relative positional relationships among the tendon, the first skin, the second skin, and the third skin. For example, the position identifying unit 103 superimposes a plurality of rectangles on the color image acquired by the image acquiring unit 101 and identifies the positions of the tendon, the first skin, the second skin, and the third skin in the chicken thigh M using the plurality of rectangles.

[0039] FIG. 7 is a diagram illustrating an example of twelve rectangles superimposed on an image depicting chicken thigh meat according to an embodiment. The chicken thigh meat M shown in FIG. 7 is meat from the left leg of a chicken. FIG. 7 illustrates rectangles P1, P2, P3, P4, P5, P6, P7, P8, P9, P10, P11, and P12. The long sides of these twelve rectangles are all inclined at 40 degrees with respect to the top and bottom sides of the image shown in FIG. 7 and the top and bottom sides of the plate-like member on which the chicken thigh meat M is placed. Furthermore, the rectangles P4, P5, P8, and P9 circumscribe the area depicting the lean meat of the chicken thigh meat M identified using the difference image shown in FIG. 5.

[0040] When the position identifying unit 103 determines that the chicken thigh M is meat from the left leg of a chicken as shown in FIG. 7 and that the first skin is depicted inside the lower rectangle of the two rectangles shown in FIG. 6, it identifies the portion of the chicken thigh M where the rectangle P3 is superimposed as the region where the first skin is depicted. Next, when the position identifying unit 103 determines that the chicken thigh M is meat from the left leg of a chicken as shown in FIG. 7 and that the first skin is depicted inside the lower rectangle of the two rectangles shown in FIG. 6, it identifies the portion of the chicken thigh M where the rectangle P1 or the rectangle P2 is superimposed as the region where the second skin is depicted. Next, when the position identifying unit 103 determines that the chicken thigh M is meat from the left leg of a chicken as shown in FIG. 7 and that the first skin is depicted inside the lower rectangle of the two rectangles shown in FIG. 6, it identifies the portion of the chicken thigh M where the rectangle P9 is superimposed as the region where the third skin is depicted. Then, when the position identification unit 103 determines that the chicken thigh meat M is meat from the left leg of a chicken as shown in Figure 7 and that the first skin is depicted inside the lower rectangle of the two rectangles shown in Figure 6, it identifies the part of the chicken thigh meat M where the rectangle P8 is superimposed as the area where the muscle is depicted.

[0041] When the position identifying unit 103 determines that the chicken thigh M is meat from the left leg of a chicken and that the first skin is depicted inside the upper rectangle of the two rectangles shown in FIG. 6, it identifies the portion of the chicken thigh M where the rectangle P10 is superimposed as the region where the first skin is depicted. Next, when the position identifying unit 103 determines that the chicken thigh M is meat from the left leg of a chicken and that the first skin is depicted inside the upper rectangle of the two rectangles shown in FIG. 6, it identifies the portion of the chicken thigh M where the rectangle P11 or the rectangle P12 is superimposed as the region where the second skin is depicted. Next, when the position identifying unit 103 determines that the chicken thigh M is meat from the left leg of a chicken and that the first skin is depicted inside the upper rectangle of the two rectangles shown in FIG. 6, it identifies the portion of the chicken thigh M where the rectangle P4 is superimposed as the region where the third skin is depicted. If the chicken thigh M is meat from the right leg of a chicken, the position specifying unit 103 specifies the portion of the chicken thigh M where the rectangle P5 is superimposed as the region where the muscle is depicted.

[0042] Furthermore, when the position identification unit 103 determines that the chicken thigh M is meat from the right leg of a chicken and that the first skin is depicted inside the lower rectangle of the two rectangles shown in Figure 6, it identifies the part of the chicken thigh M where the rectangle P7 is superimposed as the area where the first skin is depicted. Next, when the position identifying unit 103 determines that the chicken thigh M is meat from the right leg of a chicken and that the first skin is depicted inside the lower rectangle of the two rectangles shown in FIG. 6, it identifies the portion of the chicken thigh M where the rectangle P11 or the rectangle P12 is superimposed as the region where the second skin is depicted. Next, when the position identifying unit 103 determines that the chicken thigh M is meat from the right leg of a chicken and that the first skin is depicted inside the lower rectangle of the two rectangles shown in FIG. 6, it identifies the portion of the chicken thigh M where the rectangle P5 is superimposed as the region where the third skin is depicted. Then, when the position identifying unit 103 determines that the chicken thigh M is meat from the right leg of a chicken and that the first skin is depicted inside the lower rectangle of the two rectangles shown in FIG. 6, it identifies the portion of the chicken thigh M where the rectangle P4 is superimposed as the region where the muscle is depicted.

[0043] Furthermore, when the position identification unit 103 determines that the chicken thigh meat M is meat from the right leg of a chicken and that the first skin is depicted inside the upper rectangle of the two rectangles shown in Figure 6, it identifies the part of the chicken thigh meat M where the rectangle P6 is superimposed as the area where the first skin is depicted. Next, when the position identification unit 103 determines that the chicken thigh M is meat from the right leg of a chicken and that the first skin is depicted inside the upper rectangle of the two rectangles shown in FIG. 6, it identifies the portion of the chicken thigh M where the rectangle P1 or the rectangle P2 is superimposed as the region where the second skin is depicted. Next, when the position identification unit 103 determines that the chicken thigh M is meat from the right leg of a chicken and that the first skin is depicted inside the upper rectangle of the two rectangles shown in FIG. 6, it identifies the portion of the chicken thigh M where the rectangle P8 is superimposed as the region where the third skin is depicted. Then, when the position identification unit 103 determines that the chicken thigh M is meat from the right leg of a chicken and that the first skin is depicted inside the upper rectangle of the two rectangles shown in FIG. 6, it identifies the portion of the chicken thigh M where the rectangle P9 is superimposed as the region where the muscle is depicted.

[0044] The boundary identifying unit 102 identifies the boundary between an element and a portion other than the element on the image by performing image processing on the image. For example, the boundary identifying unit 102 determines a closed curve circumscribing a region depicting the lean meat of the chicken thigh M in the color image acquired by the image acquiring unit 101, and identifies a portion of the closed curve passing through a region depicting the tendon, first skin, second skin, or third skin in the color image as the boundary between the tendon, first skin, second skin, or third skin and the lean meat of the chicken thigh M.

[0045] 8 is a diagram showing an example of the boundary between the first skin and the lean meat, the boundary between the second skin and the lean meat, and the boundary between the tendon and the lean meat identified by the image processing device according to the embodiment. The chicken thigh M shown in FIG. 8 is meat from the right leg of a chicken. The boundary identification unit 102 determines a closed curve C that circumscribes the area depicting the lean meat of the chicken thigh M shown in FIG. 8. Then, the boundary identification unit 102 identifies a line L91 of the closed curve C as the boundary between the first skin and the lean meat of the chicken thigh M. Furthermore, the boundary identifying unit 102 identifies a line L92 of the closed curve C as the boundary between the second skin and the lean meat of the chicken thigh M. Furthermore, the boundary identifying unit 102 identifies a line L94 of the closed curve C as the boundary between the muscle and the lean meat of the chicken thigh M.

[0046] The trajectory determination unit 104 determines the trajectory of the blade when cutting out the element from the subject based on the boundary. For example, the trajectory determination unit 104 determines a line segment passing through the boundary identified by the boundary identification unit 102 as the trajectory of the blade.

[0047] 9 is a diagram showing an example of a blade trajectory when cutting the first skin from the chicken thigh, a blade trajectory when cutting the second skin from the chicken thigh, and a blade trajectory when cutting the tendon from the chicken thigh, determined by the image processing device according to the embodiment. FIG. 9 shows a line segment L101 connecting points P11 and P12, a line segment L102 connecting points P21 and P22, and a line segment L104 connecting points P41 and P42. The horizontal direction of the image shown in FIG. 9 is the X direction. The vertical direction of the image shown in FIG. 9 is the Y direction.

[0048] Point P11 represents the starting point of the blade when cutting the first skin from the chicken thigh M. The X coordinate of point P11 is "242.4," as shown at the top of the image in FIG. 9. The Y coordinate of point P11 is "0," as shown at the top of the image in FIG. 9. Point P12 represents the ending point of the blade when cutting the first skin from the chicken thigh M. The X coordinate of point P12 is "10," as shown at the top of the image in FIG. 9. The Y coordinate of point P12 is "-239.8," as shown at the top of the image in FIG. 9. Line segment L101 represents the trajectory of the blade when cutting the first skin from the chicken thigh M. Note that "T:-0.969," shown below the coordinate of point P11 at the top of the image in FIG. 9, represents the speed of the blade when cutting the first skin from the chicken thigh M. Moreover, "θ:-44.09" shown below the coordinates of point P12 shown at the top of the image shown in FIG. 9 indicates the inclination of line segment L101.

[0049] Point P21 represents the starting point of the blade when cutting the second skin from the chicken thigh M. The X coordinate of point P21 is "65.2," as shown at the top of the image in FIG. 9. The Y coordinate of point P21 is "0," as shown at the top of the image in FIG. 9. Point P22 represents the ending point of the blade when cutting the second skin from the chicken thigh M. The X coordinate of point P22 is "292.3," as shown at the top of the image in FIG. 9. The Y coordinate of point P22 is "-151.8," as shown at the top of the image in FIG. 9. Line segment L102 represents the trajectory of the blade when cutting the second skin from the chicken thigh M. Note that "T: 1.404," shown below the coordinate of point P21 at the top of the image in FIG. 9, represents the speed of the blade when cutting the second skin from the chicken thigh M. Moreover, "θ:34.54" shown below the coordinates of point P22 shown at the top of the image shown in FIG. 9 indicates the inclination of line segment L102.

[0050] Point P41 represents the starting point of the blade when cutting the tendon from the chicken thigh M. The X coordinate of point P41 is "70.8," as shown at the top of the image in FIG. 9. The Y coordinate of point P41 is "0," as shown at the top of the image in FIG. 9. Point P42 represents the ending point of the blade when cutting the tendon from the chicken thigh M. The X coordinate of point P42 is "90.1," as shown at the top of the image in FIG. 9. The Y coordinate of point P42 is "-370.9," as shown at the top of the image in FIG. 9. Line segment L102 represents the trajectory of the blade when cutting the tendon from the chicken thigh M. Note that "T: 0.036," shown below the coordinate of point P41 at the top of the image in FIG. 9, represents the speed of the blade when cutting the tendon from the chicken thigh M. Moreover, "θ:2.06" shown below the coordinates of point P42 shown at the top of the image shown in FIG. 9 indicates the inclination of line segment L102.

[0051] The trajectory determination unit 104 determines the trajectory of the blade when cutting the first skin from the chicken thigh M to be line segment L101 shown in Fig. 9 based on line L91 shown in Fig. 8. Furthermore, the trajectory determination unit 104 determines the trajectory of the blade when cutting the second skin from the chicken thigh M to be line segment L102 shown in Fig. 9 based on line L92 shown in Fig. 8. Furthermore, the trajectory determination unit 104 determines the trajectory of the blade when cutting the tendon from the chicken thigh M to be line segment L104 shown in Fig. 9 based on line L94 shown in Fig. 8.

[0052] The trajectory determination unit 104 may set the trajectory at a predetermined distance from the boundary. For example, the trajectory determination unit 104 may determine the trajectory of the blade as a line obtained by moving the boundary a predetermined distance in a direction perpendicular to the boundary. Examples of such a trajectory include a line obtained by translating the line segment L101, line segment L102, or line segment L104 shown in FIG. 9 a predetermined distance. In this case, translation away from the lean meat of the chicken thigh M may be defined as translation in a positive direction, and translation toward the lean meat of the chicken thigh M may be defined as translation in a negative direction. Note that, even if the boundary is a broken line, a curve, or the like, the trajectory determination unit 104 may set the broken line, curve, or the like obtained by translating the boundary a predetermined distance as the trajectory of the blade.

[0053] Next, an example of processing executed by the image processing device according to the embodiment will be described with reference to Fig. 10. Fig. 10 is a flowchart showing an example of processing executed by the image processing device according to the embodiment.

[0054] In step S1, the image acquisition unit 101 acquires an image depicting a subject including an element that needs to be cut out.

[0055] In step S2, the boundary specifying unit 102 performs image processing on the image to specify the boundary between the element that needs to be cut out on the image and the portion other than the element.

[0056] In step S3, the position specifying unit 103 superimposes a predetermined graphic on the image and specifies the position of the element in the subject using the predetermined graphic.

[0057] In step S4, the boundary identifying unit 102 identifies the boundary between each element and the portion other than these elements, based on the position of each element identified in step S3.

[0058] In step S5, the trajectory determination unit 104 determines the trajectory of the blade when cutting the element from the subject based on the boundary identified in step S4.

[0059] The image processing device, image processing program, and image processing method according to the embodiments have been described above. The image processing device 10 includes an image acquisition unit 101, a boundary identification unit 102, and a trajectory determination unit 104. The image acquisition unit 101 acquires an image depicting a subject including an element that needs to be cut out. The boundary identification unit 102 performs image processing on the image to identify the boundary between the element and a portion other than the element on the image. The trajectory determination unit 104 determines the trajectory of a blade when cutting the element from the subject based on the boundary. This allows the image processing device 10 to optimally support the task of optimally cutting out elements that need to be cut out from food that has variations.

[0060] The image processing device 10 further includes a position specifying unit 103 that superimposes a predetermined graphic on the image and specifies the position of an element in the subject using the predetermined graphic. This allows the image processing device 10 to specify the element that needs to be cut out and to suitably determine the trajectory of the blade when cutting the element out of the subject.

[0061] Furthermore, the image processing device 10 acquires an image depicting a subject including at least two elements, and identifies the positions of the elements in the subject using the relative positional relationship between the at least two elements. As a result, even if the subject includes multiple elements that need to be cut out, the image processing device 10 can appropriately identify the position of each element and appropriately determine the trajectory of the blade when cutting the elements out of the subject.

[0062] In the above-described embodiment, the image processing device 10 shown in FIG. 1 is implemented by a processor 11 that reads and executes an image processing program. However, this is not limiting. At least a portion of the image processing device 10 shown in FIG. 1 may be implemented by hardware including circuitry such as a large-scale integration (LSI), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a graphics processing unit (GPU). Alternatively, at least a portion of the image processing device 10 shown in FIG. 1 may be implemented by a combination of software and hardware. Furthermore, these pieces of hardware may be integrated into one or may be separated into multiple pieces.

[0063] In addition, in the above-described embodiment, an example was given in which the subject is chicken thigh M and the elements that need to be cut out are the tendons, the first skin, the second skin, and the third skin, but this is not limited to this.

[0064] Although the embodiments of the present invention have been described above in detail with reference to the drawings, the specific configurations of the embodiments of the present invention are not limited to the above-described embodiments, and various combinations, modifications, substitutions, and / or design changes may be added to the above-described embodiments without departing from the spirit and scope of the present invention.

[0065] Furthermore, the effects of the present invention described in the above-described embodiments are merely examples, and therefore the present invention may also achieve other effects that a person skilled in the art can recognize from the description of the above-described embodiments. [Explanation of symbols]

[0066] 10...image processing device, 11...processor, 12...main storage device, 13...communication interface 14...auxiliary storage device, 15...input / output device, 16...bus, 101...image acquisition unit, 10 2...Boundary identification unit, 103...Position identification unit, 104...Orbit determination unit, 151...Mouse, 152... Keyboard, 153...display, 154...photographic equipment, 155, 156, 157, 15 8...Lighting, 20...Food processing line, 200...Control device, 201...Belt conveyor, 202 ,203,204...Photoelectric sensor, M...Chicken thigh

Claims

1. an image acquisition unit that acquires an image depicting a subject including an element that needs to be cropped; a position specifying unit that superimposes on the image a predetermined figure that is different from the subject and whose sides circumscribe an area depicting a second element that is a portion of the subject other than the element, and specifies a position of the element in the subject using the predetermined figure; a boundary specifying unit that specifies a boundary between the element and a portion other than the element on the image by performing image processing on the image; a trajectory determination unit that determines a trajectory of a blade when cutting the element from the object based on the boundary; An image processing device comprising:

2. The predetermined figure is a combination of a plurality of figures that are identical to one another. The image processing device according to claim 1 .

3. the image acquisition unit acquires the image depicting the subject including at least two of the elements; the position specifying unit specifies the positions of the elements in the subject by utilizing a relative positional relationship between at least two of the elements; The image processing device according to claim 1 .

4. the orbit determination unit sets the orbit a predetermined distance away from the boundary.

4. The image processing device according to claim 1.

5. an image acquisition function for acquiring an image depicting a subject including an element that needs to be cropped; a position specifying function that superimposes on the image a predetermined figure that is different from the subject and whose sides circumscribe an area depicting a second element that is a part of the subject other than the element, and specifies the position of the element in the subject using the predetermined figure; a boundary specifying function for specifying a boundary between the element and a portion other than the element on the image by performing image processing on the image; a trajectory determination function that determines a trajectory of a blade when cutting the element from the object based on the boundary; An image processing program that enables a computer to achieve this.

6. An image depicting a subject including an element that needs to be cut out is acquired by an image acquisition unit or an image acquisition function; superimposing a predetermined figure on the image, the predetermined figure being a figure different from the subject and having sides circumscribing an area depicting a second element that is a portion of the subject other than the element, and identifying the position of the element in the subject using the predetermined figure; By performing image processing on the image, a boundary between the element and a portion other than the element on the image is identified by a boundary identifying unit or a boundary identifying function; a trajectory of a blade when cutting the element from the subject is determined by a trajectory determination unit or a trajectory determination function based on the boundary; Image processing methods.

Images