Optical sorting machine

Abstract

The optical sorting machine comprises: a light source; a color sensor; a determination unit for foreign matter and / or defective products; a color deviation amount calculation unit, which calculates, for a color image obtained by the color sensor, the amount of color deviation caused by the separation of at least two element groups among the R element group, the G element group and the B element group in the transfer direction of the sorting object; a speed calculation unit, which calculates the transfer speed of the sorting object based on the separation distance of at least two element groups in the transfer direction, the color deviation amount, and the scanning time which is the time required for one scan of the color sensor; and a sorting device, which performs a track changing action at a time point determined based on the transfer speed calculated by the speed calculation unit, and the track changing action is used to change the track of a specific sorting object determined based on the determination result of the determination unit.

Description

Technical Field

[0001] The present invention relates to an optical sorting machine. Background Art

[0002] In the past, there is a known optical sorting machine (hereinafter, also referred to as a sorting machine) that uses light information obtained by an optical sensor when a sorting object being transferred is irradiated with light to determine whether the sorting object is a foreign object or a defective product, and removes the foreign object and the defective product. In this sorting machine, typically, the trajectory of the sorting object determined as a foreign object or a defective product is changed (that is, by changing it to a trajectory different from that of the sorting object determined as a qualified product) by spraying air on the sorting object determined as a foreign object or a defective product, thereby removing the foreign object and the defective product.

[0003] In the above-mentioned structure, on the transfer path of the sorting object, the position where the sorting object is photographed by the optical sensor (hereinafter also referred to as the photographing position) is different from the position where the track of the sorting object is changed by air (hereinafter also referred to as the track changing position). Therefore, the sorting machine needs to spray air at the time point when the sorting object judged as a foreign body or a defective product moves from the photographing position to the track changing position. That is, the sorting machine needs to perform a track change based on air injection at a time point delayed by a specified time (the time required to move from the photographing position to the track changing position) from the moment of photographing. The time from photographing the sorting object to spraying air is also called the delay time.

[0004] In the past, the delay time was set to an optimal value by conducting experiments. Such a setting operation requires temporary setting of multiple delay times that are staggered little by little, and repeated experiments such as measuring the sorting accuracy at each temporarily set delay time, which requires a lot of man-hours. Therefore, attempts are being made to develop a technology that can determine the delay time without repeated experiments.

[0005] For example, in the following patent documents 1 and 2, a sorting machine capable of automatically determining a delay time is disclosed. Specifically, the sorting machine described in patent documents 1 and 2 has two optical sensors (for the sake of convenience, referred to as the first optical sensor and the second optical sensor) that detect light respectively at two locations (for the sake of convenience, referred to as the first location and the second location) on the transfer path of the sorting object. The transfer speed of the sorting object is calculated based on the time from when a sorting object is detected by the first optical sensor at the first location to when it is detected by the second optical sensor at the second location. Since the distance between the first location and the second location is known, the transfer speed of the sorting object can be easily calculated by dividing the distance between the first location and the second location by the time required to move between the two locations. The delay time is determined based on the transfer speed of the sorting object obtained in this way.

[0006] Patent Document 1: Japanese Patent No. 3079932

[0007] Patent Document 2: Japanese Patent Application Laid-Open No. 2017-170400

[0008] However, in the technologies described in Patent Documents 1 and 2, it is necessary to determine the identity of the sorting object detected by the first optical sensor at the first location and the sorting object detected by the second optical sensor at the second location. If the sorting objects are transferred one by one with sufficient intervals, such identity determination is easy, but in an actual sorting machine, in order to ensure its processing capacity, a large number of sorting objects with roughly the same shape are transferred at the same time. Under such circumstances, since it is very difficult to determine the identity, the transfer speed may be calculated inaccurately. If the calculation accuracy of the transfer speed is reduced, the sorting accuracy will be reduced.

[0009] In view of such circumstances, a sorting machine capable of more accurately calculating the transfer speed of the sorting objects is required. Summary of the invention

[0010] The present invention has been made to solve the above-mentioned problems, and can be achieved, for example, in the following aspects.

[0011] According to a first technical solution of the present invention, an optical sorting machine is provided. The optical sorting machine includes a light source and a color sensor, and the light source is configured to emit light toward a granular sorting object being transferred. The color sensor includes a plurality of optical elements for detecting light having a wavelength corresponding to red, namely an R element group, a plurality of optical elements for detecting light having a wavelength corresponding to green, namely a G element group, and a plurality of optical elements for detecting light having a wavelength corresponding to blue, namely a B element group, and the color sensor is configured to detect light associated with the sorting object being transferred. At least two of the R element group, the G element group, and the B element group are arranged in a manner separated from each other in the transfer direction of the sorting object. The optical sorting machine also includes: a determination unit, configured to determine whether a foreign matter and / or defective product of a sorting object is present based on a signal obtained by a color sensor; a color deviation amount calculation unit, configured to calculate, for a color image obtained by the color sensor, an amount of color deviation caused by the separation of at least two component groups in a transfer direction of the sorting object; a speed calculation unit, configured to calculate a transfer speed of the sorting object based on a separation distance of at least two component groups in the transfer direction, the amount of color deviation, and a scanning time which is a time required for one scan of the color sensor; and a sorting device, configured to perform a track changing action at a time point determined based on the transfer speed calculated by the speed calculation unit, wherein the track changing action is used to change the track of a specific sorting object determined based on a determination result of the determination unit.

[0012] According to the optical sorter, the transfer speed of the sorting object can be calculated based on the amount of color deviation caused by the separation of at least two of the R element group, the G element group, and the B element group in the transfer direction of the sorting object. In other words, the transfer speed of the sorting object can be calculated using only one color sensor. Therefore, since it is not necessary to determine the identity of the sorting object at the two separated locations, the transfer speed of the sorting object can be calculated more accurately.

[0013] According to a second technical solution of the present invention, in the first technical solution, the R element group, the G element group, and the B element group are arranged in a manner separated from each other in the transfer direction. The amount of color deviation calculated by the color deviation amount calculation unit includes at least one of the following amounts of color deviation: the amount of color deviation between the R image obtained via the R element group and the G image obtained via the G element group; the amount of color deviation between the R image and the B image obtained via the B element group; and the amount of color deviation between the G image and the B image. According to this technical solution, the first technical solution can be applied to a three-line sensor or a four-line sensor in which the R element group, the G element group, and the B element group are arranged in parallel and separated from each other.

[0014] According to a third technical solution of the present invention, in the second technical solution, the amount of color deviation calculated by the color deviation amount calculation unit includes: the amount of color deviation between the R image and the G image; the amount of color deviation between the R image and the B image; and the amount of color deviation between the G image and the B image. According to this technical solution, since the amount of color deviation is calculated between images of relatively many colors and the transfer speed is calculated based on the amount of color deviation, a more average value can be obtained as the transfer speed. In other words, it is possible to make the calculated transfer speed less likely to have a large error.

[0015] According to a fourth technical solution of the present invention, in the first technical solution, the R element group, the G element group, and the B element group are arranged in a Bayer arrangement. The amount of color deviation calculated by the color deviation amount calculation unit is the amount of color deviation between the R image obtained via the R element group and the B image obtained via the B element group. According to this technical solution, the first technical solution can be applied to a two-line sensor in which the R element group, the G element group, and the B element group are arranged in a Bayer arrangement.

[0016] According to a fifth technical solution of the present invention, in any one of the first to fourth technical solutions, the color deviation amount calculation unit calculates the amount of color deviation for each particle of the sorting object and / or each particle group overlapping on the color image. The speed calculation unit calculates the transfer speed based on the representative values ​​of the multiple color deviation amounts calculated by the color deviation amount calculation unit. According to this technical solution, the amount of color deviation can be calculated with high accuracy, and further, the transfer speed reflecting the overall trend of the sorting objects existing on the color image can be calculated with high accuracy.

[0017] According to a sixth technical solution of the present invention, in any one of the first to fifth technical solutions, the determination unit determines both foreign matter and defective products. The color deviation amount calculation unit extracts a first area and a second area from a color image, wherein the first area includes a foreign matter image area as an image area representing a foreign matter, and does not include a non-foreign matter image area as an image area representing a sorting object other than a foreign matter, and the second area does not include an image area and includes a non-foreign matter image area, and the color deviation amount calculation unit calculates the color deviation amount of the first area and the color deviation amount of the second area, respectively. The speed calculation unit calculates the transfer speed of the foreign matter and the transfer speed of the sorting object other than the foreign matter, respectively, as the transfer speed of the sorting object. The specific sorting object includes foreign matter and defective products. The sorting device performs a track change action on the foreign matter at a time point determined based on the above-mentioned transfer speed of the foreign matter, and performs the above-mentioned track change action on the defective product at a time point determined based on the transfer speed of the sorting object other than the foreign matter. According to this technical solution, even when there is a large difference in transfer speed between foreign matter and defective products, since different transfer speeds are calculated for the foreign matter and the defective products, the difference in transfer speeds between the two can be reflected and sorting can be performed with high accuracy.

[0018] According to the seventh technical solution of the present invention, in any one of the first to sixth technical solutions, the speed calculation unit calculates the transfer speed each time a predetermined event occurs. The sorting device performs a track change action at a time point determined at least based on the latest transfer speed. According to this technical solution, the transfer speed is updated to a value reflecting the processing conditions at that time each time a predetermined event occurs. Therefore, the sorting accuracy can be improved. The above-mentioned time point can be determined only based on the latest transfer speed among the transfer speeds calculated in the past, or it can also be determined based on the latest transfer speed and at least one transfer speed calculated before that. In the latter case, for example, the above-mentioned time point can also be determined based on a moving average of multiple recently calculated transfer speeds (for example, the latest transfer speed, the previous transfer speed, and the moving average of the second transfer speed from the front).

[0019] According to the eighth technical solution of the present invention, in the seventh technical solution, the predetermined event includes the start of operation of the optical sorter. According to this technical solution, even if the processing conditions (for example, the properties and state of the sorting object) have changed compared with the last operation, the change in the processing conditions can be quickly responded to.

[0020] According to the ninth technical solution of the present invention, in the seventh or eighth technical solution, the predetermined event includes the optical sorter operating for a predetermined time. According to this technical solution, it is possible to respond more carefully to changes in processing conditions. For example, it is also possible to respond to changes in the moving speed that occur with changes in the supply amount (i.e., the transfer amount) of the sorting object.

[0021] The present invention is not limited to the above technical solution, and can be implemented in various forms. For example, it can also be implemented in the form of a program or a storage medium storing the program in a computer-readable manner, wherein the program enables a computer to implement the following two functions: a color deviation amount calculation function that calculates the amount of color deviation for a color image obtained by a color sensor; and a speed calculation function that calculates the transfer speed of the sorting object based on the separation distance of at least two element groups of the color sensor, the color deviation amount, and the scanning time that is the time required for one scanning of the color sensor. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a schematic diagram showing a schematic configuration of an optical sorter according to one embodiment of the present invention.

[0023] Figure 2 is a schematic diagram showing the arrangement of optical elements in a color sensor.

[0024] Figure 3This is an explanatory diagram illustrating an area of ​​one sorting object that is imaged in one scan.

[0025] Figure 4 This is a diagram for explaining an example of a method for calculating the amount of color misregistration.

[0026] Figure 5 This is an explanatory diagram of an example of a method of calculating a transfer speed.

[0027] Figure 6 This is a diagram for explaining an example of a method for calculating the delay time. DETAILED DESCRIPTION

[0028] Figure 1 1 is a schematic diagram showing the schematic structure of an optical sorting machine (hereinafter referred to as a sorting machine) 10 as one embodiment of the present invention. In this embodiment, the sorting machine 10 is used to sort foreign matter (for example, pebbles, mud, glass pieces, etc.) and defective products (for example, immature grains, colored grains, damaged grains, dead rice, etc.) from rice grains (more specifically, brown rice or polished rice) as sorting objects (hereinafter referred to as objects) 90. However, the object 90 is not limited to brown rice or polished rice, and may be any granular object. For example, the object 90 may also be rice, wheat grains, beans (soybeans, chickpeas, edamame, etc.), resin (granules, etc.), rubber sheets, etc.

[0029] like Figure 1 As shown, the sorting machine 10 includes an optical detection unit 20, a storage box 71, a feeder 72, a chute 73, a qualified product discharge slot 74, a defective product discharge slot 75, a sorting device 60, and a control device 80. The control device 80 controls the overall operation of the sorting machine 10. The control device 80 also functions as a determination unit 81, a color deviation calculation unit 82, and a speed calculation unit 83. The functions of the control device 80 can be implemented by the CPU executing a prescribed program, can be implemented by a dedicated circuit (for example, PLD, ASIC, etc.), or can be implemented by a combination of a CPU and a dedicated circuit. In addition, the functions of the control device 80 can be assigned to an integrated device, or can be distributed to multiple devices in a dispersed manner. The details of the functions of the control device 80 will be described later.

[0030] The storage box 71 temporarily stores the object 90. The feeder 72 supplies the object 90 stored in the storage box 71 to the chute 73. The optical detection unit 20 irradiates light to the object 90 sliding down the chute 73, and detects light associated with the object 90 (specifically, the transmitted light that has passed through the object 90 and / or the reflected light reflected by the object 90). The output from the optical detection unit 20, that is, the analog signal representing the intensity of the detected light is converted into a digital signal by an AC / DC converter (not shown). The digital signal is input to the control device 80. As a process of the determination unit 81, the control device 80 determines whether the object 90 is a qualified product (that is, a rice grain with relatively high quality), a foreign body (that is, not a rice grain), or a defective product (that is, a rice grain with relatively low quality) based on the detection result of the input light (that is, an image). This determination is performed separately for each object 90. This determination is typically performed by comparing the grayscale value of the image data with a predetermined threshold value. However, any known determination method may be used for this determination.

[0031] The sorting device 60 performs a track change action at a specified time point, and the track change action is used to change the track of a specific object 90 determined based on the determination result of the determination unit 81. The determination method for the specified time point will be described later. In the present embodiment, the sorting device 60 is in the form of an ejector, and the track of the object 90 is changed by ejecting air 61 toward the specific object 90. In addition, in the present embodiment, the specific object 90 is an object 90 determined as a foreign body or a defective product by the determination unit 81. The object 90 determined as a foreign body or a defective product is blown away by the track change action performed by the sorting device 60, that is, the ejection of air 61, so that it is separated from the falling track falling from the chute 73 and guided to the defective product discharge chute 75. On the other hand, when the object 90 is determined to be a qualified product, the air 61 is not ejected. Therefore, the object 90 determined to be a qualified product does not change the falling track and is guided to the qualified product discharge chute 74. Instead of spraying air 61 on object 90 determined as foreign matter or defective, air 61 may be sprayed on object 90 determined as qualified (so-called reverse spray). In addition, the track changing operation is not limited to the spraying of air 61, and any other known method may be used.

[0032] The optical detection unit 20 is described in detail below. Figure 1 As shown, the optical detection unit 20 includes light sources 31, 32 and color sensors 40, 50. The light source 31 and the color sensor 40 are arranged on one side (also referred to as the front side) with respect to the transfer path of the object 90 (in other words, the falling trajectory from the chute 73). On the other hand, the light source 32 and the color sensor 50 are arranged on the other side (also referred to as the rear side) with respect to the transfer path of the object 90.

[0033] The light source 31 emits light 33 toward the multiple objects 90 being transported (i.e., falling from the chute 73). Similarly, the light source 32 emits light 34 toward the multiple objects 90 being transported. The lights 33 and 34 each have a wavelength corresponding to red, a wavelength corresponding to green, and a wavelength corresponding to blue. In the present embodiment, the light sources 31 and 32 are so-called color LEDs. However, the light sources 31 and 32 may also be any other light-emitting element (e.g., a halogen lamp). In addition, in Figure 1 In the figure, the number of light sources 31 and 32 is respectively shown as one, but the number of at least one of the light sources 31 and 32 may be multiple.

[0034] The color sensors 40 and 50 detect light associated with the object 90 being transferred. The front color sensor 40 can detect light 33 emitted from the front light source 31 and reflected by the object 90 (hereinafter, also referred to as reflected light 33), and light 34 emitted from the rear light source 32 and transmitted through the object 90 (hereinafter, also referred to as transmitted light 34). The rear color sensor 50 can detect light 34 emitted from the rear light source 32 and reflected by the object 90 (hereinafter, also referred to as reflected light 34), and light 33 emitted from the front light source 31 and transmitted through the object 90 (hereinafter, also referred to as transmitted light 33).

[0035] What kind of light is detected by the color sensors 40 and 50 is determined by the lighting mode of the light sources 31 and 32. In the first lighting mode in which the light sources 31 and 32 are lit at the same time, the color sensor 40 detects the light synthesized by the reflected light 33 and the transmitted light 34 (hereinafter also referred to as the reflected transmitted light), and the color sensor 50 detects the reflected transmitted light synthesized by the reflected light 34 and the transmitted light 33. In the second lighting mode in which the light source 31 is lit and the light source 32 is extinguished, the color sensor 40 detects the reflected light 33, and the color sensor 50 detects the transmitted light 33. In the third lighting mode in which the light source 31 is extinguished and the light source 32 is lit, the color sensor 40 detects the transmitted light 34, and the color sensor 50 detects the reflected light 34. Which of the first to third lighting modes to be used can be arbitrarily determined according to the type, nature and state of the object 90, and the type of foreign matter or defective products to be removed. Alternatively, only any one of the first to third lighting modes may be used. Alternatively, two or more lighting patterns among the first to third lighting patterns may appear alternately at a predetermined time interval or according to a predetermined repetition rule.

[0036] In the present embodiment, the color sensors 40 and 50 are color CCD sensors. More specifically, the color sensors 40 and 50 each have: a plurality of optical elements (hereinafter referred to as R elements) for detecting light having a wavelength corresponding to red, a plurality of optical elements (hereinafter referred to as G elements) for detecting light having a wavelength corresponding to green, and a plurality of optical elements (hereinafter referred to as B elements) for detecting light having a wavelength corresponding to blue. The so-called R, G, and B refer to R, G, and B in the RGB color space, respectively. Each of these optical elements has a focusing lens, a color filter, and a photoelectric conversion element. Each color filter has the characteristic of transmitting light of a wavelength corresponding to the color of the light to be detected (for example, red in the case of the R element) and not transmitting light of other wavelengths. The color sensors 40 and 50 are not limited to color CCD sensors, but may also be other forms of color sensors such as color CMOS sensors.

[0037] Figure 2 : is a schematic diagram showing the arrangement of optical elements in the color sensor 40. As shown in the figure, the color sensor 40 includes an R element group 44 in which a plurality of R elements 41 are arranged in a row, a G element group 45 in which a plurality of G elements 42 are arranged in a row, and a B element group 46 in which a plurality of B elements 43 are arranged in a row. The plurality of R elements 41, the plurality of G elements 42, and the plurality of B elements 43 are arranged in a row in a direction orthogonal to the transfer direction D1 of the object 90. In other words, the R element group 44, the G element group 45, and the B element group 46 are arranged in parallel so as to be separated from each other in the transfer direction D1 of the object 90. As can be seen from this description, the color sensor 40 is a so-called three-line sensor. The separation distance between the R element group 44 and the G element group 45 is L1, the separation distance between the G element group 45 and the B element group 46 is L2, and the separation distance between the R element group 44 and the B element group 46 is L3 (=L1+L2). Generally, L1=L2, but L1 and L2 may be different values. The color sensor 50 has the same structure as the color sensor 40, and therefore the description thereof is omitted.

[0038] As is well known, the color sensors 40 and 50 detect light associated with one object 90 by performing multiple scans. Figure 3 As shown, in the present embodiment, image data is acquired by scanning one object 90 10 times (the number is shown to be smaller than the actual number for the sake of simplicity of description). Figure 3 The numbers 1 to 10 shown indicate the number of scans in which the region labeled with the number was imaged. For example, the region labeled with "2" indicates that image data was acquired in the second scan.

[0039] In the above-mentioned sorting machine 10, the control device 80 determines the transfer speed of the object 90 during operation (more specifically, the transfer speed at the moment when the image is captured by the color sensor 40 or the color sensor 50). Then, when the control device 80 determines that a specific object 90 is to be the object of the track change operation as the processing of the determination unit 81, it sends a command to the sorting device 60, and causes the sorting device 60 to perform a track change operation (i.e., the injection of the air 61) on the specific object 90 at a time point determined based on the determined transfer speed (i.e., at a delay time determined based on the determined transfer speed). The method of determining the transfer speed for setting the delay time is described in detail below.

[0040] In order to determine the transfer speed, the control device 80 first calculates the amount of color deviation for the color image obtained by the color sensor 40 as a process of the color deviation amount calculation unit 82. In the color sensor 40, the R element group 44, the G element group 45, and the B element group 46 scan simultaneously, but since the R element group 44, the G element group 45, and the B element group 46 are separated from each other in the transfer direction D1, strictly speaking, the imaged portion of the object 90 is deviated between the colors according to the separation distance. Therefore, a deviation occurs in the direction corresponding to the transfer direction D1 on the image between the red image obtained by the R element group 44, the green image obtained by the G element group 45, and the blue image obtained by the B element group 46. The amount of color deviation is calculated in units smaller than one pixel, which is a unit constituting an image.

[0041] In the present embodiment, the color misregistration amount calculation unit 82 calculates the color misregistration amount Srg between the red image and the green image, the color misregistration amount Sgb between the green image and the blue image, and the color misregistration amount Srb between the red image and the blue image. Figure 4 FIG. 2 is an explanatory diagram showing an example of a method for calculating the amount of color shift. Figure 4 , the case where the color deviation amount Srg of the red image 92R and the green image 92G is calculated in units of particles of the object 90 is described. In the calculation of the color deviation amount, the color deviation amount calculation unit 82 first sets common coordinates for the red image 92R of one particle of the object 90 and the green image 92G of the one particle of the object 90 with a resolution finer than one pixel. For example, coordinate points of 1 / 1000 pixel units may be set in the x direction (the direction orthogonal to the direction corresponding to the transfer direction D1) and the y direction (the direction corresponding to the transfer direction D1). In this case, 1000000 (=1000×1000) coordinate points are assigned to one pixel. The resolution can be set to an arbitrary value according to the desired calculation accuracy of the color deviation amount.

[0042] Next, the color deviation amount calculation unit 82 calculates the red density centroid coordinates 93R of the red image 92R and the green density centroid coordinates 93G of the green image 92G based on the gradation values ​​of the coordinate points (the grayscale values ​​of 100 coordinate points corresponding to one pixel are the same). The density centroid coordinates can be calculated by dividing the sum of the values ​​obtained by multiplying the coordinate value of each coordinate point of each coordinate point in the x-coordinate and the y-coordinate by the grayscale value by the sum of the grayscale values ​​of each coordinate.

[0043] Then, if Figure 4 As shown in FIG. 1 , the color deviation amount calculation unit 82 obtains the separation distance between the red density centroid coordinate 93R and the green density centroid coordinate 93G in the y direction, that is, the direction corresponding to the transfer direction D1, as the color deviation amount Srg (in pixels) of the red image 92R and the green image 92G. However, the calculation of the color deviation amount is not limited to the above method using the density centroid, and can be performed by any known method.

[0044] In the present embodiment, such a method is used to calculate the amount of color deviation for each particle of the object 90 and / or each particle group overlapping on the color image. The image area other than the image area representing the particle or particle group of the object 90 (hereinafter also referred to as the blank area) is removed from the calculation target area of ​​the color deviation amount. The blank area can be easily removed by binarizing the color image. In this way, if the color deviation amount is calculated in units of particles or particle groups, the color deviation amount can be calculated with high accuracy. However, the color deviation amount calculation unit 82 can also divide the color image into multiple areas (the area is a size that can contain multiple particles) and calculate the color deviation amount for each of the multiple areas.

[0045] If the color deviation amount Srg of the red image 92R and the green image 92G is calculated for each particle and / or each overlapping particle group, the color deviation amount calculation unit 82 calculates a representative value Rrg of the calculated plurality of color deviation amounts Srg. Similarly, the color deviation amount calculation unit 82 calculates a representative value Rgb of the plurality of color deviation amounts Sgb and a representative value Rrb of the plurality of color deviation amounts Srb. These representative values ​​are average values ​​in the present embodiment, but may be medians or the like.

[0046] Next, as a process of the speed calculation unit 83, the control device 80 calculates the transfer speed of the object 90 based on the representative values ​​Rrg, Rgb, and Rrb of the color deviation amounts Srg, Sgb, and Srb. If the time required for one scan of the color sensor 40 is set to the scanning time T, the transfer speed Vrg of the object 90 calculated based on the color deviation amounts Srg of the red image 92R and the green image 92G is obtained by, for example, the following formula (1). In the formula (1), L1>0. In addition, in the formula (1), the unit of the color deviation amount Srg is a unit representing a distance. For example, the units of the separation distance L1 and the color deviation amount Srg are "mm", and the unit of the scanning time T is "ms". In this case, the unit of the obtained transfer speed Vrg is "m / s". As described above, when the color misregistration amount calculation unit 82 obtains the color misregistration amount Srg in "pixel", the color misregistration amount Srg in "mm" is obtained by multiplying the color misregistration amount Srg in "pixel" by the pixel size (mm) of the color sensor 40 (i.e., the size of each pixel). The transfer speed Vrg is not limited to the formula (1), and can also be calculated by other formulas including the color misregistration amount Srg as a variable based on experiments or the like.

[0047] Vrg=(L1+Srg) / T…(1)

[0048] Similarly, the transfer speed Vgb of the object 90 calculated based on the color misregistration amount Sgb is obtained by the following equation (2), and the transfer speed Vrb of the object 90 calculated based on the color misregistration amount Srb is obtained by the following equation (3). In equations (2) and (3), L2>0 and L3>0.

[0049] Vgb=(L2+Sgb) / T…(2)

[0050] Vrb=(L3+Srb) / T…(3)

[0051] In this embodiment, the above-mentioned representative values ​​Rrg, Rgb, Rgb are used as the values ​​of Srg, Sgb, Sgb to be substituted into equations (1) to (3), and as a result, the average transfer speeds Vrg, Vgb, Vgb of a plurality of particles and / or a particle group are obtained. In addition, the speed calculation unit 83 determines the representative value (the average value in this embodiment) of the transfer speeds Vrg, Vgb, Vgb as the transfer speed for setting the delay time.

[0052] When the light sources 31 and 32 are lit in two or more of the first to third lighting modes, the transfer speed may be calculated for each of the two or more lighting modes based on the images obtained in each lighting mode, and their representative values ​​(e.g., average values) may be set as the transfer speed for setting the delay time. Alternatively, the transfer speed may be calculated based on images obtained in only a portion of the two or more lighting modes (e.g., one lighting mode), and the transfer speed may be set as the transfer speed for setting the delay time. In this case, the determined transfer speed may also be shared in the two or more lighting modes.

[0053] In the present embodiment, the amount of color misalignment is calculated based only on the image obtained by the color sensor 40, and the transfer speed for setting the delay time is determined based on the amount of color misalignment. However, the amount of color misalignment may be calculated based on an image obtained by the color sensor 50 instead of or in addition to the image obtained by the color sensor 40. When the amount of color misalignment is calculated based on the image obtained by the color sensor 40 and the image obtained by the color sensor 50, an average value of the two amounts of color misalignment may be used, or an average value of two transfer speeds calculated based on the two amounts of color misalignment may be used.

[0054] Reference Figure 6 An example of a method for setting the delay time t based on the transfer speed determined in this way is described. The transfer speed determined by the above method is the speed at the shooting position P1. Here, the speed is set to the initial speed v0. In addition, the inclination angle of the chute 73 relative to the horizontal direction is set to θ. In addition, the two-dimensional coordinates (coordinates in the horizontal direction and the vertical direction) at the shooting position P1 are set to the origin, and the position of the track of the object 90 changed by the sorting device 60, that is, the coordinates of the track change position P2 are set to (x, y). At this time, considering the gravitational acceleration, the coordinate values ​​of x and y are expressed by the following equations (4) and (5). g represents the gravitational acceleration.

[0055] [Formula 1]

[0056] x=v0 cosθ·t···(4)

[0057]

[0058] Here, the distance d1 between the imaging position P1 and the track change position P2 is expressed by the following equation (6).

[0059] [Formula 2]

[0060]

[0061] In addition, if the angle between the horizontal direction and the straight line P1·P2 is set to θ1, the angle between the air injection direction (here, the direction perpendicular to the inclination of the slide groove 73) and the horizontal direction is set to θ2, and the angle between the air injection direction and the vertical direction is set to θ3, then θ1~θ3 are respectively expressed by the following equations (7)~(9).

[0062] [Formula 3]

[0063]

[0064] θ2=90-θ…(8)

[0065] θ3=180-90-θ2=90-θ2…(9)

[0066] Formula (10) is obtained from formula (8) and (9).

[0067] θ3=90-(90-θ)=θ…(10)

[0068] Furthermore, if the angle formed by the jetting direction of the air and the straight line P1·P2 is θ4, θ4 is expressed by the following formula (11).

[0069] θ4=θ3+(90-θ1)(θ4<90)…(11)

[0070] Formula (12) is obtained from formula (10) and (11).

[0071] θ4=θ+(90-θ1)…(12)

[0072] Here, if the distance from the imaging position P1 to the position of the sorting device 60 (more specifically, the air injection position) is d, then d is calculated according to Figure 6 The relationship of the triangle shown is expressed by equation (13).

[0073] d=d1sinθ4…(13)

[0074] Formula (14) is obtained from formula (6), (7), (12) and (13).

[0075] [Formula 4]

[0076]

[0077] d and θ are known, and v0 is determined by the processing of the speed calculation unit 83. Therefore, by finding t that satisfies equations (4), (5), and (14), the delay time t can be calculated. The calculated transfer speed and / or delay time is stored in the memory of the control device 80.

[0078] The above-described method of calculating the delay time t is merely an example, and the delay time t may be set by any method based on the transfer speed determined by the processing of the speed calculation unit 83. For example, correction may be performed taking air resistance into consideration.

[0079] According to the above-described sorting machine 10, the transfer speed for setting the delay time of the object 90 is calculated based on the separation distances L1 to L3 of the R element group 44, the G element group 45, and the B element group 46 in the transfer direction D1, the amount of color shift between the red image, the green image, and the blue image caused by the separation distances L1 to L3, and the scanning time which is the time required for one scanning of the color sensor 40 and / or the color sensor 50. Therefore, since it is not necessary to determine the identity of the object 90 at the two separated locations, the transfer speed of the object 90 can be calculated more accurately.

[0080] In addition, in the sorting machine 10, the transfer speed is calculated based on the color deviation amount Srg between the red image and the green image, the color deviation amount Sgb between the green image and the blue image, and the color deviation amount Srb between the red image and the blue image, so that a more average value can be obtained as the transfer speed. In other words, it is possible to make the calculated transfer speed less likely to have a large error. However, the transfer speed may be calculated based on one or both of the color deviation amounts Srg, Sgb, and Srb. In this way, the calculation load of the control device 80 can be reduced.

[0081] The above-mentioned transfer speed for setting the delay time can also be determined by processing the sample object 90 before shipping the sorting machine 10. In this way, it is not necessary to perform repeated experiments for determining the transfer speed before shipping the sorting machine 10 as was conventionally done.

[0082] Furthermore, the determination of the transfer speed for setting the delay time can also be performed each time a predetermined event occurs. In this case, the sorting machine 10 can also perform a track change action at a time point determined at least based on the latest transfer speed. The so-called "at least based on the latest transfer speed" includes only the latest transfer speed among the transfer speeds calculated in the past, and the latest transfer speed and at least one transfer speed calculated before that. In the latter case, for example, the above-mentioned time point can also be determined based on the moving average of multiple recently calculated transfer speeds (for example, the latest transfer speed, the previous transfer speed, and the moving average of the second transfer speed from the front). In this way, the transfer speed is updated to a value reflecting the processing conditions at this time each time a predetermined event occurs, thereby improving the sorting accuracy.

[0083] The predetermined event may also include the start of operation of the sorting machine 10. In this way, even if the processing conditions (for example, the properties and state of the object 90) are changed compared to the last operation, the change in the processing conditions can be quickly responded to. From the start of operation to the re-determination of the transfer speed, the previously determined transfer speed can be used, or the transfer speed set as the default value can be used.

[0084] In addition, the predetermined event may also include the sorting machine 10 continuing to operate for a specified time. The specified time can be set to any length of time. The specified time may be, for example, 1 minute or 5 minutes. In this way, changes in processing conditions can be dealt with more meticulously. For example, the transfer speed can be updated by following changes in the supply amount (i.e., transfer amount) of the object 90.

[0085] In the case where the predetermined event includes multiple types of events, the time point for determining the track change action based on which of the multiple most recent transfer speeds is used may also be changed according to the type of event that occurred. For example, when an event occurs that the operation of the sorting machine 10 has started, the above-mentioned time point may be determined based only on the latest transfer speed among the transfer speeds calculated in the past. In addition, when an event occurs that the sorting machine 10 has been operating for a specified period of time, the above-mentioned time point may be determined based on multiple transfer speeds that have been recently calculated after the start of the operation of the sorting machine 10 (for example, based on the moving average of the transfer speeds of the specified amount that have been recently calculated).

[0086] Furthermore, the transfer speed for setting the delay time may be determined in real time for each particle and / or each overlapping particle group, and the delay time may be set individually for each particle and / or each overlapping particle group. That is, during the period from when a specific particle or overlapping particle group of the object 90 is transferred from the imaging position P1 to the track change position P2, the transfer speed of the specific particle or overlapping particle group may be determined based on the image of the specific particle or overlapping particle group, the delay time may be set based on the transfer speed, and the track change operation may be performed on the specific particle or overlapping particle group based on the delay time. In this way, the sorting accuracy can be further improved.

[0087] Furthermore, the determination unit 81 determines both foreign matter and defective products, and in a form in which the control device 80 controls the sorting device 60 to perform air jetting on foreign matter and defective products, the color deviation amount calculation unit 82 may also determine different transfer speeds for foreign matter and defective products. Specifically, the color deviation amount calculation unit 82 may also extract a first area and a second area from the color image, and respectively calculate the color deviation amount of the first area and the color deviation amount of the second area, wherein the first area includes a foreign matter image area as an image area representing foreign matter, and does not include a non-foreign matter image area as an image area representing an object 90 other than a foreign matter, and the second area does not include a foreign matter image area, and includes a non-foreign matter image area. In this case, the speed calculation unit 83 respectively calculates the transfer speed of the foreign matter and the transfer speed of the object 90 other than the foreign matter (i.e., the transfer speed for defective products). Then, the control device 80 controls the sorting device 60 so that the air is sprayed on the foreign matter at a time point determined based on the transfer speed of the foreign matter, and the air is sprayed on the defective products at a time point determined based on the transfer speed of the object 90 other than the foreign matter. In this way, even if there is a large difference in the transfer speed between the foreign matter and the defective products, the difference in the transfer speed can be reflected and the sorting can be performed with high accuracy.

[0088] Above, the embodiments of the present invention have been described, but the above embodiments are for making the present invention easy to understand, and do not limit the present invention. The present invention can be changed and improved without departing from its purpose, and the present invention includes its equivalents. In addition, within the scope of at least a part of the above-mentioned problem that can be solved or within the scope of at least a part of the effect, any combination or any omission of the various components recorded in the technical solutions and the specification can be performed.

[0089] For example, the color sensors 40 and 50 may be any color sensors in which at least two of the R element group, the G element group, and the B element group are arranged in a manner separated from each other in the transfer direction D1, instead of the above-mentioned three-line sensor. For example, the color sensors 40 and 50 may be four-line sensors that include, in addition to the R element group, the G element group, and the B element group, a monochrome element group composed of a plurality of elements without a color filter. In this case, as in the above-mentioned embodiment, at least two of the red image, the green image, and the blue image obtained by the R element group, the G element group, and the B element group may be used to determine the transfer speed. Alternatively, the color sensors 40 and 50 may be color sensors with a Bayer arrangement. In this case, the transfer speed can be determined based on the color deviation of the red image and the blue image obtained by the R element group and the B element group.

[0090] Description of Reference Numerals

[0091] 10...optical sorter; 20...optical detection unit; 31, 32...light source; 33, 34...light; 40, 50...color sensor; 41...R element; 42...G element; 43...B element; 44...R element group; 45...G element group; 46...B element group; 50...color sensor; 60...sorting device; 61...air; 71...storage box; 72...feeder; 73...chute; 74...qualified product discharge slot; 75...unqualified product discharge slot; 80...control device; 81...judgment unit; 82...color deviation calculation unit; 83...speed calculation unit; 90...object; 92R...red image; 92G...green image; 93R...red concentration centroid coordinates; 93G...green concentration centroid coordinates.

Claims

1. An optical sorting machine, characterized in that: have: a light source configured to emit light toward the granular objects to be sorted being transferred; a color sensor comprising an R element group, a G element group, and a B element group, wherein the R element group is a plurality of optical elements for detecting light having a wavelength corresponding to red, the G element group is a plurality of optical elements for detecting light having a wavelength corresponding to green, and the B element group is a plurality of optical elements for detecting light having a wavelength corresponding to blue, the color sensor being configured to detect light associated with the objects to be sorted being transported, and at least two of the R element group, the G element group, and the B element group being arranged so as to be separated from each other in a transport direction of the objects to be sorted; a determination unit configured to determine whether the objects to be sorted are foreign matter and / or defective products based on the signal obtained by the color sensor; a color deviation amount calculation unit configured to calculate, with respect to the color image obtained by the color sensor, an amount of color deviation caused by the at least two element groups being separated from each other in the transfer direction of the sorting object; a speed calculation unit configured to calculate a transfer speed of the sorting object based on a separation distance of the at least two component groups in the transfer direction, the color deviation amount, and a scanning time that is a time required for one scan of the color sensor; and The sorting device is configured to perform a trajectory changing operation at a timing determined based on the transfer speed calculated by the speed calculation unit, the trajectory changing operation being for changing a trajectory of a specific sorting object determined based on a determination result of the determination unit.

2. The optical sorting machine according to claim 1, wherein: The R element group, the G element group, and the B element group are arranged to be separated from each other in the transfer direction. The amount of color shift calculated by the color shift amount calculation unit includes at least one of the following amounts of color shift: an amount of color shift between an R image obtained via the R element group and a G image obtained via the G element group; an amount of color shift between the R image and a B image obtained via the B element group; and The amount of color shift between the G image and the B image.

3. The optical sorting machine according to claim 2, characterized in that: The amount of color shift calculated by the color shift amount calculation unit includes: an amount of color shift between the R image and the G image; an amount of color shift between the R image and the B image; and an amount of color shift between the G image and the B image.

4. The optical sorting machine according to claim 1, wherein: The R element group, the G element group, and the B element group are arranged in a Bayer arrangement. The amount of color shift calculated by the color shift amount calculation unit is an amount of color shift between an R image obtained via the R element group and a B image obtained via the B element group.

5. The optical sorting machine according to any one of claims 1 to 4, characterized in that: The color deviation amount calculation unit calculates the amount of color deviation for each particle of the sorting object and / or each particle group overlapping on the color image. The speed calculation unit calculates the transfer speed based on representative values ​​of the plurality of color misregistration amounts calculated by the color misregistration amount calculation unit.

6. The optical sorting machine according to any one of claims 1 to 4, characterized in that: The determination unit determines both the foreign matter and the defective product. The color deviation amount calculation unit extracts a first area and a second area from the color image, wherein the first area includes a foreign matter image area as an image area representing the foreign matter and does not include a non-foreign matter image area as an image area representing a sorting object other than the foreign matter, and the second area does not include the foreign matter image area and includes the non-foreign matter image area. Furthermore, the color deviation calculation unit calculates the color deviation of the first region and the color deviation of the second region respectively. The speed calculation unit calculates a transfer speed of the foreign matter and a transfer speed of the objects to be sorted other than the foreign matter, respectively, as the transfer speed of the objects to be sorted. The specific objects to be sorted include the foreign matter and the defective products. The sorting device performs the track changing operation on the foreign matter at a timing determined based on the transfer speed of the foreign matter, and performs the track changing operation on the defective product at a timing determined based on the transfer speed of the sorting objects other than the foreign matter.

7. The optical sorting machine according to any one of claims 1 to 4, characterized in that: The speed calculation unit calculates the transfer speed each time a predetermined event occurs. The sorting device performs the track changing operation at a timing determined based on at least the latest transfer speed.

8. The optical sorting machine according to claim 7, wherein: The predetermined event includes the start of operation of the optical sorter.

9. The optical sorting machine according to claim 7, wherein: The predetermined event includes that the optical sorter has been operated continuously for a predetermined time.

10. The optical sorting machine according to claim 8, wherein: The predetermined event includes that the optical sorter has been operated continuously for a predetermined time.

11. The optical sorting machine according to claim 5, wherein: The determination unit determines both the foreign matter and the defective product. The color deviation amount calculation unit extracts a first area and a second area from the color image, wherein the first area includes a foreign matter image area as an image area representing the foreign matter and does not include a non-foreign matter image area as an image area representing a sorting object other than the foreign matter, and the second area does not include the foreign matter image area and includes the non-foreign matter image area. Furthermore, the color deviation calculation unit calculates the color deviation of the first region and the color deviation of the second region respectively. The speed calculation unit calculates a transfer speed of the foreign matter and a transfer speed of the objects to be sorted other than the foreign matter, respectively, as the transfer speed of the objects to be sorted. The specific objects to be sorted include the foreign matter and the defective products. The sorting device performs the track changing operation on the foreign matter at a timing determined based on the transfer speed of the foreign matter, and performs the track changing operation on the defective product at a timing determined based on the transfer speed of the sorting objects other than the foreign matter.

Images