WO2013145873A1 - 光学式粒状物選別機 - Google Patents
光学式粒状物選別機 Download PDFInfo
- Publication number
- WO2013145873A1 WO2013145873A1 PCT/JP2013/052838 JP2013052838W WO2013145873A1 WO 2013145873 A1 WO2013145873 A1 WO 2013145873A1 JP 2013052838 W JP2013052838 W JP 2013052838W WO 2013145873 A1 WO2013145873 A1 WO 2013145873A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- granular material
- defective
- unit
- boundary surface
- dimensional color
- Prior art date
Links
- 239000008187 granular material Substances 0.000 title claims abstract description 81
- 230000003287 optical effect Effects 0.000 title claims abstract description 34
- 230000002950 deficient Effects 0.000 claims abstract description 161
- 238000009826 distribution Methods 0.000 claims abstract description 31
- 238000000926 separation method Methods 0.000 claims abstract description 19
- 230000005484 gravity Effects 0.000 claims abstract description 14
- 238000012546 transfer Methods 0.000 claims description 18
- 239000002994 raw material Substances 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 15
- 238000007689 inspection Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 10
- 230000007717 exclusion Effects 0.000 claims description 4
- 238000005286 illumination Methods 0.000 claims description 4
- 238000005192 partition Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 3
- 230000007547 defect Effects 0.000 claims 1
- 238000000638 solvent extraction Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 23
- 230000035945 sensitivity Effects 0.000 abstract description 10
- 235000013339 cereals Nutrition 0.000 description 12
- 238000000034 method Methods 0.000 description 10
- 238000013500 data storage Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 239000013598 vector Substances 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 239000004973 liquid crystal related substance Substances 0.000 description 7
- 238000003384 imaging method Methods 0.000 description 5
- 241000209094 Oryza Species 0.000 description 4
- 235000007164 Oryza sativa Nutrition 0.000 description 4
- 235000021329 brown rice Nutrition 0.000 description 4
- 239000002245 particle Substances 0.000 description 4
- 235000009566 rice Nutrition 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 241000209140 Triticum Species 0.000 description 2
- 235000021307 Triticum Nutrition 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 229910052736 halogen Inorganic materials 0.000 description 2
- 150000002367 halogens Chemical class 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 239000008188 pellet Substances 0.000 description 2
- 239000011347 resin Substances 0.000 description 2
- 229920005989 resin Polymers 0.000 description 2
- 244000046052 Phaseolus vulgaris Species 0.000 description 1
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 1
- 239000011324 bead Substances 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000001143 conditioned effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 235000014571 nuts Nutrition 0.000 description 1
- 239000013618 particulate matter Substances 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
- B07C5/3425—Sorting according to other particular properties according to optical properties, e.g. colour of granular material, e.g. ore particles, grain
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J3/465—Measurement of colour; Colour measuring devices, e.g. colorimeters taking into account the colour perception of the eye; using tristimulus detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J3/50—Measurement of colour; Colour measuring devices, e.g. colorimeters using electric radiation detectors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/27—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands using photo-electric detection ; circuits for computing concentration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/85—Investigating moving fluids or granular solids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/001—Texturing; Colouring; Generation of texture or colour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/46—Colour picture communication systems
- H04N1/56—Processing of colour picture signals
- H04N1/60—Colour correction or control
- H04N1/6058—Reduction of colour to a range of reproducible colours, e.g. to ink- reproducible colour gamut
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/85—Investigating moving fluids or granular solids
- G01N2021/8592—Grain or other flowing solid samples
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S209/00—Classifying, separating, and assorting solids
- Y10S209/932—Fluid applied to items
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S209/00—Classifying, separating, and assorting solids
- Y10S209/938—Illuminating means facilitating visual inspection
Definitions
- the present invention sorts grains such as rice and wheat and granular materials such as resin pellets into non-defective products and defective products, or removes foreign particles mixed in the granular materials by blowing them off with a blast. Related to the machine.
- a transfer means for transferring a raw material, a light source unit for irradiating light of a plurality of wavelengths to the raw material transferred by the transfer means,
- An optical detector having an imaging unit that captures reflected light and / or transmitted light, and two-wavelength density values in the imaging data captured by the optical detection means and the predetermined two-wavelength density values.
- the determination unit draws each density value of any two wavelengths in the imaging data on a two-dimensional graph, and targets all the pixels of each density value drawn on the two-dimensional graph. It is determined whether there is a pixel other than the two-point pixel in the circle between the two points whose diameters are two different pixels, and the two-point pixel in the circle between the two points by the determination Only when there is no other pixel, the two-point pixels are connected by connection lines, and a closed region drawn by joining these connection lines is set as the threshold region.
- the outer shape of the threshold region set by the discriminating unit is accurately specified so as not to include the discriminating region. Can be discriminated, and there is an operation and effect that makes sorting based on the discrimination accurate.
- the present invention is an optical granularity capable of easily making sensitivity setting by effectively using RGB three-dimensional color space information close to human eyes and greatly simplifying signal processing.
- Providing an object sorter is a technical issue.
- the present invention provides a transfer means for transferring a granular material containing a non-defective product, a defective product, and a foreign substance so as to have a continuous flow, and an inspection means for inspecting the granular material transferred by the transfer means.
- a discriminating means for discriminating whether or not to be a separation object based on the individual color information of the granular material inspected by the inspection means, and the separation object discriminated by the discrimination means is excluded from the continuous flow
- An optical granular material sorter equipped with an exclusion means, While the inspection means includes an illumination unit that illuminates the granular material with light, and a light detection unit that detects light transmitted through the granular material or light reflected from the granular material, The discriminating means plots each wavelength component of R, G, and B light of the granular material detected by the light detection unit on a three-dimensional color space, and creates three-dimensional color distribution data of the granular material sample.
- An original color distribution data creation unit, and a boundary surface calculated by the Mahalanobis distance to the 3D color distribution data created by the 3D color distribution data creation unit, and a first good product cluster region containing many good products A Mahalanobis distance boundary surface creation section that partitions into a defective product and a first defective product cluster area containing a large amount of foreign matter, and a first non-defective cluster area and a first defective product cluster area formed by the Mahalanobis distance boundary surface creation section.
- the boundary plane calculated by the Euclidean distance at which the distance between the center of gravity positions is the longest, and the second non-defective cluster region and the second defective product class are determined.
- a technical means includes a threshold value determination unit that determines a threshold value for determining whether or not.
- the three-dimensional color distribution data creation unit plots the wavelength components of the R, G, and B light of the granular material on the three-dimensional color space, thereby obtaining the entire three-dimensional color distribution of the granular material sample.
- the boundary surface calculated by the Mahalanobis distance is set for the entire three-dimensional color distribution, and the first non-defective product cluster region including many non-defective products and granular material samples. This is divided into roughly two clusters including the first defective product cluster area containing foreign matter.
- the respective center of gravity positions of the newly formed first non-defective cluster region and the newly formed first defective product cluster region are obtained, and the distance between the center of gravity positions is the longest.
- the boundary surface calculated by the distance is set for the entire three-dimensional color distribution, and two regions, a second non-defective cluster region containing many non-defective products and a second non-defective product cluster region containing many defective products and foreign substances This is divided into roughly two clusters different from those described above.
- the threshold value determination unit an intersection line between the boundary surface of the Mahalanobis distance and the boundary surface of the Euclidean distance is obtained, and is set as a threshold value for determining whether or not the intersection line itself is a separation object. . That is, the granular material sample plotted on the three-dimensional color space is roughly separated into the first good cluster region and the first defective cluster region by the Mahalanobis distance boundary surface, and then the sensitivity is effective by the Euclidean distance boundary surface. A boundary surface having a wide range is searched and separated into a second cluster region and a second cluster region, and further, the threshold value determination unit determines whether the boundary surface between the Mahalanobis distance and the boundary surface at the Euclidean distance.
- the threshold value in the two-dimensional color space can be calculated.
- the sensitivity is obtained by effectively using the RGB three-dimensional color space information close to human eyes. It is possible to provide an optical granular material sorter that can be easily set and signal processing is greatly simplified.
- the transfer means for transferring the granular material containing the non-defective product, the defective product and the foreign matter so as to be a continuous flow
- the inspection means for inspecting the granular material transferred by the transfer means
- Discriminating means for discriminating whether or not to be a separation object based on individual color information of the granular material inspected by the inspection means
- exclusion means for excluding the separation object discriminated by the discrimination means from a continuous flow
- the original color distribution data creation unit and the good, defective, and foreign samples prepared in advance by the operator are passed to the transfer means, and each sample is detected by the light detection unit to create three-dimensional color distribution data.
- a learning / storage unit that performs learning in association with the three-dimensional color distribution data by classifying the sample as a non-defective product, a defective product, or a foreign object when the sample is displayed on the image;
- a Mahalanobis distance boundary surface creation unit that divides it into a raster region, and obtains each center of gravity position of the first good product cluster region and the first defective product cluster region formed by the Mahalanobis distance boundary surface creation unit, and each center of gravity position Euclidean distance boundary that sets the boundary surface calculated by the Euclidean distance where the distance between them is farthest and divides
- FIG. 4 is a block diagram conceptually illustrating a signal processing unit, a CPU, and a memory in FIG. 3. It is a flowchart which shows the operation
- FIG. 1 is a perspective view showing the entire optical granular material sorter of the present invention
- FIG. 2 is a schematic longitudinal sectional view showing the internal structure of the sorter
- FIG. 3 is obtained from the camera of the sorter.
- FIG. 4 is a block diagram of signal processing means for processing signals
- FIG. 4 is a conceptual diagram showing the internal configuration of the signal processing unit and CPU / memory shown in FIG.
- the optical granular material sorter 1 includes a plurality of primary sorting units 3 ⁇ / b> A (the sorting units from the left end to the third in FIG. 1), and a plurality of trapezoidal machine frames 2.
- Secondary sorting sections 3B (second sorting section from the right end in FIG. 1) are arranged in parallel, and each sorting section 3A, 3B has the same components as in the prior art. Yes.
- a plurality of primary sorting units 3A and a plurality of secondary sorting units 3B are arranged side by side.
- the present invention is not limited to this, and a plurality of primary sorting units and a single secondary sorting unit are provided.
- various variations such as a configuration in which a single tertiary sorting unit is arranged in parallel can be set.
- each component of the primary sorting unit 3A will be described with reference to FIG. 3 A of primary selection parts are the chute
- a vibration feeder 6 for transporting an object to the chute 4, an optical detection unit 7 (7a, 7b) provided on both sides of the drop trajectory of the granular material falling from the lower end of the chute 4, and an ejector nozzle provided further below 8 and a non-defective product collecting rod 9 which is on the same inclination line as the chute 4 below the ejector nozzle 8 and receives the particulate matter of the falling trajectory without receiving the blast from the ejector nozzle 8;
- a defective product collecting rod 10 for receiving defective air from normal particles by receiving a blast from the ejector nozzle 8 and receiving a blast from the ejector nozzle 8 Te, is provided with an
- the chute 4 is formed in a flat plate shape without a groove for sliding the granular material in a wide band shape. And in order to prevent the overflow of the granular material from the chute 4 and to prevent the granular material to be selected from floating from the bottom surface while sliding the chute 4, the chute cover 4a is spaced from the bottom surface at a predetermined interval. May be provided.
- the vibration feeder 6 has a structure in which a feeder trough 6a is supported on a support portion 6b, and granular materials can be supplied to the chute 4 by operating a vibration device such as an electromagnetic drive coil 6c.
- the optical detectors 7a and 7b are surrounded by box bodies 12a and 12b, respectively.
- a box 12a on the upper side of the grain drop trajectory has a visible light CCD camera 13a, a near infrared light NIR camera 14, visible light sources 15a and 15b made of fluorescent light, a halogen lamp, and the like.
- the near-infrared light source 16a which consists of this, and the background 17a for opposition of the optical detection part 7b are equipped internally.
- a box 12b below the grain flow trajectory has a visible light CCD camera 13b, visible light sources 15c and 15d made of fluorescent lights, and a near infrared light source 16b made of halogen lamps.
- the opposing backgrounds 17b and 17c of the optical detector 7a are internally provided.
- the window members 18a and 18b which consist of transparent glass are engage
- the ejector nozzle 8 is supplied with air from an air compressor (not shown) from a tube 22 through a sub tank 19, an air pipe 20 and a solenoid valve 21.
- the sub-tank 19 temporarily stores air from the air compressor.
- a front door 24 that can be turned up and down by an air cylinder 23 is provided on the inclined wall in front of the machine casing 2, thereby enabling maintenance work such as cleaning to be easily performed.
- a liquid crystal display 25 and a power switch 26 which are also used as an operation panel and a monitor made of a touch panel, so that the liquid crystal display 25 and the power switch 26 are placed at the level of the operator's eyes. By being arranged, the machine can be easily operated.
- a point different from the primary sorting unit 3A is the shape of the chute 4, and the chute 4 for the secondary sorting unit 3B is formed with a plurality of grooves for sliding the grains in a plurality of rows. ing.
- As the cross-sectional shape of the groove portion a U-shaped shape, a V-shaped shape, a concave shape, or the like can be appropriately employed.
- the rest of the configuration is substantially the same as the primary sorting unit 3A.
- Reference numeral 27 in FIG. 2 is a defective product receptacle
- reference numeral 28 is a non-defective product receptacle
- reference numeral 29 is an auxiliary defective product receptacle
- reference numeral 30 is a sample take-out portion.
- the visible light CCD cameras 13a and 13b and the NIR camera 14 are electrically connected to a signal processing unit 31 for binarizing an image acquired by the camera, and 2 from the signal processing unit 31. It electrically connects to the CPU 32 and the memory unit 32 that store the digitized image and apply necessary processing.
- the liquid crystal display 25 is electrically connected to the CPU and memory unit 32.
- the signal processing unit 31 includes an image data acquisition mechanism 33 that temporarily stores image data, and threshold data that determines whether the acquired image data is a good product or a defective product. Includes a threshold data storage memory 34, a binarization calculation mechanism 35 for binarizing the acquired image data, and a non-defective / defective product discriminating mechanism 36 for discriminating whether the product is a good product or a defective product. ing.
- the CPU and memory unit 32 is based on an image data storage memory 37 for storing the data from the image data acquisition mechanism 33 as necessary, and the image data stored in the image data storage memory 37.
- a threshold data calculation mechanism 38 that calculates a threshold value, and a touch operation signal of the liquid crystal display 25 are received, and processed image data is output to a monitor. And an operation signal receiving mechanism 39 is provided.
- An ejector drive circuit 40 is electrically connected to the non-defective / defective product discriminating mechanism 36 in the signal processing unit 31, and the ejector drive circuit 40 is connected to the ejector nozzle 8 based on a signal from the drive circuit 40.
- An electromagnetic valve 21 for injecting air is electrically connected.
- FIG. 5 is a flowchart showing the work procedure of the signal processing unit.
- steps 101 to 103 are performed after flowing samples of good, defective, and foreign materials prepared in advance by the operator to the chute.
- This is a non-defective product / defective product pattern learning process in which a three-dimensional color distribution pattern related to good products, defective products, and foreign matters is learned by a sorter.
- Steps 104 to 108 are boundaries between the good product pattern and the defective product pattern.
- This is a threshold value calculation step for automatically calculating the threshold value
- step 109 is a threshold value determination step in which the operator finely adjusts the threshold value calculated in the threshold value calculation step.
- step 101 a good sample prepared and selected in advance by a skilled worker is flowed from the storage tank 5 onto the chute 4, and a good sample that falls from the lower end of the chute 4 is transferred to the CCD camera 13a, 13b, imaged by the NIR camera 14.
- step 101 a good sample prepared and selected in advance by a skilled worker is flowed from the storage tank 5 onto the chute 4, and a good sample that falls from the lower end of the chute 4 is transferred to the CCD camera 13a, 13b, imaged by the NIR camera 14.
- a large number of non-defective sample image data picked up by the CCD cameras 13a and 13b and the NIR camera 14 is input to the image data storage memory 37 via the image data acquisition mechanism 33, and the image is input to the monitor of the liquid crystal display 25. Will be displayed.
- the defective sample (including the foreign material sample) is selected and prepared in advance by a skilled worker, and the same operation as described above is performed to perform the defective sample (including the foreign material sample). ) Image data is acquired.
- step 102 the process proceeds to step 102, and for the sample displayed on the liquid crystal display 25, what should be a non-defective product, what should be a defective product, and what should be a foreign object is designated on the image again by the operator's visual observation.
- step 103 the designated non-defective sample image is regarded as one region and the defective sample image is also regarded as one region, and this is regarded as a three-dimensional color space (in the embodiment, each of R, G, B). Many plots on the axis color space. As a result, aggregates in the RGB color space as shown in FIG. 6 are sequentially formed.
- step 104 the non-defective product cluster 51 (aggregate) formed by the non-defective product dots (black dots in FIG. 6) and the defective product cluster formed by the defective product dots (gray dots in FIG. 6). 52 (aggregate) is roughly classified (see FIG. 6), and in step 105, the statistics of the multivariate data for each cluster of the non-defective product cluster 51 / defective product cluster 52 is calculated.
- the calculation of this statistic may be performed by calculating the centroid vector or variance-covariance matrix.
- the centroid vector is arithmetic expression of the centroid vector.
- the Mahalanobis square distance from the center-of-gravity vector for each non-defective / defective product cluster is obtained.
- the Mahalanobis square distance is a function of the value of the multivariate data, and the formula for calculating the Mahalanobis square distance is
- a boundary surface between each cluster is obtained (step 106).
- the multivariate data values are classified into clusters having the smallest Mahalanobis square distance, and clusters belonging to all the multivariate data values in the multivariate space are determined. And the boundary surface shown by the code
- the Euclidean distance at which the distance between the centers of gravity of the non-defective product cluster 51 and the defective product cluster 52 is the longest is selected, and a boundary surface with a wide sensitivity effective range is searched (step 107).
- the center of gravity vector of the non-defective cluster is P (Xp1, Xp2, Xp3,... Xpn) and the center of gravity vector of the defective cluster is Q (Xq1, Xq2, Xq3,.
- the distance is
- a boundary surface between each cluster is obtained (step 107).
- the multivariate data values are classified into clusters having the maximum Euclidean square distance, and the boundary surface indicated by the symbol u in FIG. 6 is determined.
- intersection line L When the intersection line L is obtained as described above, it can be converted into an RGB correlation diagram on the optimum two-dimensional display surface in which the viewpoint is placed on the intersection line L (see FIG. 7).
- the operator determines a threshold value for determining whether the product is good or defective (step 109 in FIG. 5).
- This makes it possible to obtain an optimal threshold value with a reduced dimension from the three-dimensional color space of FIG. 6 to the two-dimensional color space of FIG. 7, greatly simplifies signal processing, and is optimal for the operator. It is possible to provide an easy-to-use optical granular sorter that is easy to set a threshold value. The above is the threshold setting operation before the full-scale operation of the optical granular material sorter.
- the raw material flowing down between the optical detectors 7a and 7b is imaged by the CCD cameras 13a and 13b and the NIR camera 14, and this imaged data is primarily stored in the image data storage memory 37 via the image data acquisition mechanism 33. Memorized. Then, as described in the non-defective product pattern / defective product pattern learning step and the threshold value calculating step, the raw material is plotted on the three-dimensional color space and then converted to the two-dimensional color space. That is, the granular material to be selected / determined is the granular material A or the granular material B in FIG.
- the current threshold value stored in the threshold data storage memory 34 is schematically shown as an intersection line L in FIG. 7.
- the intersection line L becomes a boundary line
- the boundary line L The upper part shows the non-defective product region
- the lower part than the boundary line L shows the defective product region.
- the non-defective product / defective product discriminating mechanism 36 in FIG. 4 determines that “the granular material A is non-defective”, and the ejector drive circuit A removal signal is not issued from 41 and is collected as a non-defective product into the non-defective product receiving port 9 (see FIG. 2).
- the non-defective product / defective product discrimination mechanism 36 in FIG. 4 determines that “the granular material B is a defective product”.
- a removal signal is transmitted from the ejector nozzle 8 to the electromagnetic valve 21 and is removed from the raw material flowing down by the high-pressure air blast from the ejector nozzle 8 and recovered as a defective product from the defective product receiving port 27 (see FIG. 2). .
- the non-defective product cluster in FIGS. 6 and 7 may be regarded as a defective product cluster, and the defective product cluster may be regarded as a non-defective product cluster and set in reverse.
- defective products occupy a much smaller proportion of raw materials than non-defective products, and therefore can be sorted and removed by jetting high-pressure air from the ejector nozzle 8.
- the non-defective product occupies a very small percentage of the raw material compared to the defective product, it is more efficient to classify and remove the non-defective granular material as a defective product by using a jet of high-pressure air from the ejector nozzle 8. Good.
- the non-defective product cluster in FIGS. 6 and 7 can be regarded as a defective product cluster and the defective product cluster can be regarded as a non-defective product cluster. This can be easily set only by rewriting data in the threshold data storage memory 34.
- the non-defective product receives the blast of high-pressure air from the ejector nozzle 8 and is collected at the defective product receiving port 27, while the defective product is not collected by the high-pressure air from the ejector nozzle 8. Without receiving a blast, it will be recovered to the non-defective product receiving port 9 as it is.
- the discriminating means for discriminating whether or not to make the separation object based on the individual color information of the granular material includes the three-dimensional color distribution data creation unit and the Mahalanobis distance boundary surface. Since the creation unit, the Euclidean distance boundary surface creation unit, and the threshold value determination unit are provided, in the 3D color distribution data creation unit, each wavelength component of the R, G, and B light of the granular material is 3D Plot on the color space to create the entire three-dimensional color distribution of the particulate sample, and then set the boundary surface calculated by the Mahalanobis distance in the Mahalanobis distance boundary surface creation unit, and the non-defective product cluster area and the defective product cluster. The Euclidean distance boundary plane creation unit obtains the centroid positions of the non-defective cluster area and the defective cluster area and calculates the centroid position between the centroid positions.
- the boundary surface calculated by the Euclidean distance that is the farthest distance is set for the entire three-dimensional color distribution, and the threshold value determination unit obtains an intersection line between the boundary surface of the Mahalanobis distance and the boundary surface of the Euclidean distance, This is a threshold value for determining whether or not the intersection line is a separation object. Therefore, the granular material sample plotted in the three-dimensional color space is roughly separated into the non-defective cluster region and the defective cluster region by the Mahalanobis distance boundary surface, and then the boundary surface having a wide sensitivity effective range by the Euclidean distance boundary surface.
- the threshold value determination unit can calculate the threshold value in the two-dimensional color space, and the operator can effectively use RGB three-dimensional color space information close to human eyes. Thus, it is possible to provide an optical granular material sorter in which sensitivity can be easily set and signal processing is greatly simplified.
- the color sorter of the present invention is not limited to the above embodiment, and various design changes are possible.
- a chute is adopted as the transfer means, but the chute may have a plurality of stages such as upper and lower two stages and upper and lower three stages, or may be constituted by a belt conveyor or the like as the transfer means.
- a high-speed air ejector nozzle that injects high-pressure air is used as a means for removing the separation target from the continuous flow.
- the separation target is excluded from the continuous flow.
- Push type ejecting means such as an air cylinder may be used.
- sensitivity can be easily set by effectively using RGB three-dimensional color space information close to the human eye, and signal processing can be greatly simplified.
- signal processing can be greatly simplified.
- it is a new and useful optical particulate sorter.
- the present invention relates to raw materials consisting of grains such as rice, wheat, beans, and nuts, resin pieces such as pellets and beads, fine articles such as pharmaceuticals, ores, and shirasu, and other granular materials. It is possible to apply to an optical granular material sorter that sorts out or removes foreign matters or the like mixed in the raw material.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Sorting Of Articles (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Spectrometry And Color Measurement (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
Description
前記検査手段は、前記粒状物に光を照明する照明部と、前記粒状物を透過した光又は前記粒状物から反射した光を検知する光検知部とを備える一方、
前記判別手段は、前記光検知部により検知した前記粒状物のR、G及びBの光の各波長成分を三次元色空間上にプロットして粒状物サンプルの三次元色分布データを作成する三次元色分布データ作成部と、該三次元色分布データ作成部により作成された三次元色分布データにマハラノビス距離で算出された境界面を設定し、良品を多く含む第一の良品クラスタ領域と、不良品及び異物を多く含む第一の不良品クラスタ領域とに仕切るマハラノビス距離境界面作成部と、該マハラノビス距離境界面作成部により形成された第一の良品クラスタ領域及び第一の不良品クラスタ領域の各重心位置を求めるとともに、当該各重心位置間の距離が最も離れるユークリッド距離で算出された境界面を設定し、第二の良品クラスタ領域と、第二の不良品クラスタ領域とに仕切るユークリッド距離境界面作成部と、前記マハラノビス距離で算出された境界面と前記ユークリッド距離で算出された境界面との交線を求め、該交線を分離対象物とするか否かを決定する判別しきい値として決定するしきい値決定部とを備える、という技術的手段を講じた。
前記検査手段は、前記粒状物に光を照明する照明部と、前記粒状物を透過した光又は前記粒状物から反射した光を検知する光検知部とを備える一方、
前記判別手段は、前記光検知部により検知した前記粒状物のR、G及びBの光の各波長成分を三次元色空間上にプロットして粒状物サンプルの三次元色分布データを作成する三次元色分布データ作成部と、作業者があらかじめ準備した良品、不良品及び異物のそれぞれのサンプルを移送手段に流し、前記光検知部により前記各サンプルが検知されて三次元色分布データが作成されるとともに、画像上に当該サンプルが表示されたときに目視により良品、不良品及び異物のいずれかに類別して三次元色分布データと対応させて学習を行う学習・記憶部と、該学習・記憶部により作成された三次元色分布データにマハラノビス距離で算出された境界面を設定し、良品を多く含む第一の良品クラスタ領域と、不良品及び異物を多く含む第一の不良品クラスタ領域とに仕切るマハラノビス距離境界面作成部と、該マハラノビス距離境界面作成部により形成された第一の良品クラスタ領域及び第一の不良品クラスタ領域の各重心位置を求めるとともに、当該各重心位置間の距離が最も離れるユークリッド距離で算出された境界面を設定し、良品を多く含む第二の良品クラスタ領域と、不良品及び異物を多く含む第二の不良品クラスタ領域とに仕切るユークリッド距離境界面作成部と、前記マハラノビス距離で算出された境界面と前記ユークリッド距離で算出された境界面との交線を求め、該交線を分離対象物とするか否かを決定する判別しきい値として決定するしきい値決定部と、原料を前記移送手段に流して選別動作を行ったときに、前記三次元色分布データ上に作成されたデータが前記しきい値決定部で決定したしきい値に属さないと判断された場合、当該粒状物を分離対象物とみなす良品/不良品判別部とを備える、という技術的手段を講じた。
このパターン学習工程においては、選別前の準備作業であるので、エジェクターノズル8は作動させない。作業が開始されると、まず、ステップ101において、熟練した作業者があらかじめ選り分けて準備した良品サンプルを貯留タンク5からシュート4上に流すとともに、シュート4下端から落下する良品サンプルをCCDカメラ13a,13b、NIRカメラ14により撮像する。次に、CCDカメラ13a,13b及びNIRカメラ14により撮像された良品サンプルの多数の画像データは、画像データ取得機構33を経て画像データ格納メモリ37に入力され、当該画像は液晶ディスプレイ25のモニタに表示されることになる。良品サンプルの画像データ取得が終了すると、次に、熟練した作業者があらかじめ選り分けて準備した不良品サンプル(異物サンプルを含む)について、上述と同様の作業を行って不良品サンプル(異物サンプルを含む)の画像データの取得を行う。
ステップ104に進むと、良品に係るドット(図6の黒の点)で形成される良品クラスタ51(集合体)と不良品に係るドット(図6のグレーの点)で形成される不良品クラスタ52(集合体)とに大まかな分類が行われ(図6参照)、ステップ105では、良品クラスタ51/不良品クラスタ52のクラスタ毎の多変量データの統計量が算出される。
上述のように図7の二次元空間上での交線Lに基づき、作業者は良品と不良品との判別しきい値を決定することになる(図5のステップ109)。これにより、図6の三次元色空間から図7の二次元色空間に次元を減少させた最適なしきい値を求めることが可能となり、信号処理を大幅に簡略化し、しかも、操作者にとっては最適なしきい値を設定しやすく、使いやすい光学式粒状物選別機の提供が可能となる。以上が光学式粒状物選別機を本格稼働する前のしきい値設定作業である。
上記しきい値設定作業後は、原料の指定(穀粒か粒状物か、穀粒の品種など)、流量(目標流量の設定)の調整、選別物の感度(被選別物から異物(ガラス、石)や、着色粒(不良粒、しらた米、薄焼け米等)を選別・除去対象とするか否か)の調整、エジェクタの遅れ時間の調整などを行い、その後、貯留タンク5に原料を供給し、タッチパネルからなる操作盤の選別スイッチを選択する。これにより、選別作業開始のプログラムが開始され、図4のしきい値格納メモリ34から上述のように設定された良品か不良品かを判定するしきい値が読み込まれる。そして、CPU及びメモリ部32によりしきい値を基準に良品か不良品かを判定されることになる。
2 機枠
3A 一次選別部
3B 二次選別部
4 シュート
5 貯留タンク
6 振動フィーダ
7 光学検出部
8 エジェクターノズル
9 良品回収樋
10 不良品回収樋
11 補助不良品回収樋
12 箱体
13 CCDカメラ
14 NIRカメラ
15 可視光源
16 近赤外光源
17 バックグラウンド
18 窓部材
19 サブタンク
20 エア管
21 電磁弁
22 チューブ
23 エアシリンダ
24 前面ドア
25 液晶ディスプレイ
26 電源スイッチ
27 不良品受口
28 良品受口
29 補助不良品受口
30 サンプル取出部
31 信号処理部
32 CPU及びメモリ部
33 画像データ取得機構
34 しきい値データ格納メモリ
35 2値化計算機構
36 良品/不良品判別機構
37 画像データ格納メモリ
38 しきい値データ計算機構
39 操作信号受信機構
40 エジェクタ駆動回路
51 良品クラスタ
52 不良品クラスタ
Claims (2)
- 良品、不良品及び異物を含む粒状物を連続した流れとなるように移送する移送手段と、該移送手段により移送された前記粒状物を検査する検査手段と、該検査手段により検査された粒状物の個々の色情報に基づき分離対象物とするか否かを判別する判別手段と、該判別手段により判別された分離対象物を連続した流れから排除する排除手段とを備えた光学式粒状物選別機であって、
前記検査手段は、前記粒状物に光を照明する照明部と、前記粒状物を透過した光又は前記粒状物から反射した光を検知する光検知部とを備える一方、
前記判別手段は、前記光検知部により検知した前記粒状物のR、G及びBの光の各波長成分を三次元色空間上にプロットして粒状物サンプルの三次元色分布データを作成する三次元色分布データ作成部と、
該三次元色分布データ作成部により作成された三次元色分布データにマハラノビス距離で算出された境界面を設定し、良品を多く含む第一の良品クラスタ領域と、不良品及び異物を多く含む第一の不良品クラスタ領域とに仕切るマハラノビス距離境界面作成部と、
該マハラノビス距離境界面作成部により形成された第一の良品クラスタ領域及び第一の不良品クラスタ領域の各重心位置を求めるとともに、当該各重心位置間の距離が最も離れるユークリッド距離で算出された境界面を設定して、第二の良品クラスタ領域と、第二の不良品クラスタ領域とに仕切るユークリッド距離境界面作成部と、
前記マハラノビス距離で算出された境界面と前記ユークリッド距離で算出された境界面との交線を求め、該交線を分離対象物とするか否かを決定する判別しきい値として決定するしきい値決定部とを備えたことを特徴とする光学式粒状物選別機。 - 良品、不良品及び異物を含む粒状物を連続した流れとなるように移送する移送手段と、該移送手段により移送された前記粒状物を検査する検査手段と、該検査手段により検査された粒状物の個々の色情報に基づき分離対象物とするか否かを判別する判別手段と、該判別手段により判別された分離対象物を連続した流れから排除する排除手段とを備えた光学式粒状物選別機であって、
前記検査手段は、前記粒状物に光を照明する照明部と、前記粒状物を透過した光又は前記粒状物から反射した光を検知する光検知部とを備える一方、
前記判別手段は、前記光検知部により検知した前記粒状物のR、G及びBの光の各波長成分を三次元色空間上にプロットして粒状物サンプルの三次元色分布データを作成する三次元色分布データ作成部と、
作業者があらかじめ準備した良品、不良品及び異物のそれぞれのサンプルを移送手段に流し、前記光検知部により前記各サンプルが検知されて三次元色分布データが作成されるとともに、画像上に当該サンプルが表示されたときに目視により良品、不良品及び異物のいずれかに類別して三次元色分布データと対応させて学習を行う学習・記憶部と、
該学習・記憶部により作成された三次元色分布データにマハラノビス距離で算出された境界面を設定し、良品を多く含む第一の良品クラスタ領域と、不良品及び異物を多く含む第一の不良品クラスタ領域とに仕切るマハラノビス距離境界面作成部と、
該マハラノビス距離境界面作成部により形成された第一の良品クラスタ領域及び第一の不良品クラスタ領域の各重心位置を求めるとともに、当該各重心位置間の距離が最も離れるユークリッド距離で算出された境界面を設定し、良品を多く含む第二の良品クラスタ領域と、不良品及び異物を多く含む第二の不良品クラスタ領域とに仕切るユークリッド距離境界面作成部と、
前記マハラノビス距離で算出された境界面と前記ユークリッド距離で算出された境界面との交線を求め、該交線を分離対象物とするか否かを決定する判別しきい値として決定するしきい値決定部と、
原料を前記移送手段に流して選別動作を行ったときに、前記三次元色分布データ上に作成されたデータが前記しきい値決定部で決定したしきい値に属さないと判断された場合、当該粒状物を分離対象物とみなす良品/不良品判別部とを備えたとこを特徴とする光学式粒状物選別機。
Priority Applications (7)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
ES13767511T ES2704429T3 (es) | 2012-03-27 | 2013-02-07 | Máquina clasificadora de gránulos de tipo óptico |
KR1020147029102A KR101998910B1 (ko) | 2012-03-27 | 2013-02-07 | 광학식 입상물 선별기 |
JP2014507488A JP6152845B2 (ja) | 2012-03-27 | 2013-02-07 | 光学式粒状物選別機 |
US14/387,545 US9024223B2 (en) | 2012-03-27 | 2013-02-07 | Optical type granule sorting machine |
EP13767511.2A EP2832458B1 (en) | 2012-03-27 | 2013-02-07 | Optical type granule sorting machine |
BR112014024083-3A BR112014024083B1 (pt) | 2012-03-27 | 2013-02-07 | Máquina de classificação de tipo de grânulo óptica |
CN201380017680.1A CN104203436B (zh) | 2012-03-27 | 2013-02-07 | 光学式粒状物分选机 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2012070766 | 2012-03-27 | ||
JP2012-070766 | 2012-03-27 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2013145873A1 true WO2013145873A1 (ja) | 2013-10-03 |
Family
ID=49259158
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2013/052838 WO2013145873A1 (ja) | 2012-03-27 | 2013-02-07 | 光学式粒状物選別機 |
Country Status (9)
Country | Link |
---|---|
US (1) | US9024223B2 (ja) |
EP (1) | EP2832458B1 (ja) |
JP (1) | JP6152845B2 (ja) |
KR (1) | KR101998910B1 (ja) |
CN (1) | CN104203436B (ja) |
BR (1) | BR112014024083B1 (ja) |
ES (1) | ES2704429T3 (ja) |
TW (1) | TWI573634B (ja) |
WO (1) | WO2013145873A1 (ja) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014126232A1 (ja) * | 2013-02-18 | 2014-08-21 | 株式会社サタケ | 光学式粒状物選別機 |
WO2015186708A1 (ja) * | 2014-06-05 | 2015-12-10 | 株式会社サタケ | 粒状物外観品位判別装置における品位判別基準の作成方法 |
WO2015200111A1 (en) * | 2014-06-23 | 2015-12-30 | Tsi, Inc. | Rapid material analysis using libs spectroscopy |
WO2017169758A1 (ja) * | 2016-03-31 | 2017-10-05 | 株式会社サタケ | 穀類の搗精度評価方法及びその装置 |
WO2019097981A1 (ja) * | 2017-11-14 | 2019-05-23 | 新東工業株式会社 | 検査対象物の表面状態の評価方法、評価装置、評価装置の制御方法及び評価装置の制御プログラム |
JP2023115692A (ja) * | 2022-02-08 | 2023-08-21 | ユーシーシー上島珈琲株式会社 | コーヒー豆類の良品識別機能を備える良品検査システムおよび良品検査方法 |
WO2023195215A1 (ja) * | 2022-04-08 | 2023-10-12 | 住友化学株式会社 | 透明度評価方法 |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130056398A1 (en) * | 2006-12-08 | 2013-03-07 | Visys Nv | Apparatus and method for inspecting and sorting a stream of products |
USD746339S1 (en) * | 2013-07-11 | 2015-12-29 | Buhler Sortex Ltd | Combined sorting and classifying machine |
CN103464385B (zh) * | 2013-09-13 | 2015-11-25 | 佐竹机械(苏州)有限公司 | 光学式粒状物选别机 |
JP1510912S (ja) * | 2014-05-09 | 2014-11-10 | ||
JP1525031S (ja) * | 2014-08-07 | 2015-06-01 | ||
JP1527131S (ja) * | 2014-11-21 | 2015-06-22 | ||
US10512942B2 (en) * | 2017-10-30 | 2019-12-24 | Optisort, Llc | System and method for sorting objects |
JP7151089B2 (ja) * | 2018-02-06 | 2022-10-12 | 株式会社サタケ | 光学式選別機 |
CN112041093B (zh) * | 2018-04-27 | 2022-09-16 | 株式会社久保田 | 农业管理系统以及显示装置 |
EP3887069B1 (fr) * | 2018-11-27 | 2024-06-05 | Suez International | Systeme et procede de tri et de caracterisation de dechets, en particulier des emballages |
KR102009757B1 (ko) * | 2019-03-21 | 2019-08-12 | (주)싸이젠텍 | 인공지능 프로그램 기반 이물선별장치 |
JP7306158B2 (ja) * | 2019-08-27 | 2023-07-11 | 株式会社サタケ | 光学式粒状物選別機 |
CN115210007A (zh) * | 2020-03-05 | 2022-10-18 | 株式会社佐竹 | 光学式分选机 |
KR102316688B1 (ko) * | 2020-05-07 | 2021-10-25 | (주)일성테크 | 광학식 색채 선별기 전용 머신 비전 카메라의 3축 미세 조절장치 |
TWI759108B (zh) * | 2021-02-17 | 2022-03-21 | 明志科技大學 | 可調速之粉體光學檢測系統 |
EP4304348A1 (en) | 2021-03-07 | 2024-01-17 | Reeldata Inc. | Ai based feeding system and method for land based fish farms |
CN113080190A (zh) * | 2021-05-17 | 2021-07-09 | 河北联兴佳垚农业科技有限公司 | 基于温度自调节的菊苣菜仔根低温贮藏系统 |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001283153A (ja) * | 2000-01-27 | 2001-10-12 | Fujitsu Ltd | カラー画像から文字列パターンを抽出する装置および方法 |
JP2004178050A (ja) * | 2002-11-25 | 2004-06-24 | Fuji Xerox Co Ltd | 色データ精度算出方法、色データ精度算出装置、色処理方法、色処理装置、色データ精度算出プログラム、色処理プログラム、記憶媒体 |
JP2005186053A (ja) * | 2003-12-03 | 2005-07-14 | Satake Corp | 粒状物色彩選別機 |
JP2007006142A (ja) * | 2005-06-23 | 2007-01-11 | Ricoh Co Ltd | 画像処理方法、画像形成装置、プログラム及び記録媒体 |
WO2008001889A1 (fr) * | 2006-06-29 | 2008-01-03 | Fujitsu Limited | procédé de classification de couleur, procédé de reconnaissance de couleur, dispositif de classification de couleur, dispositif de reconnaissance de couleur, système de reconnaissance de couleur, programme informatique et support d'enregistrement |
JP2009119410A (ja) | 2007-11-16 | 2009-06-04 | Satake Corp | 粒状物等の光学判別装置及び粒状物等の光学式選別装置 |
JP2010050832A (ja) * | 2008-08-22 | 2010-03-04 | Ricoh Co Ltd | 画像処理装置、画像処理方法、プログラムおよび記録媒体 |
JP2010062929A (ja) * | 2008-09-04 | 2010-03-18 | Ricoh Co Ltd | 画像処理装置、画像処理プログラム、及び記録媒体 |
JP2010288163A (ja) * | 2009-06-15 | 2010-12-24 | Internatl Business Mach Corp <Ibm> | 評価システム、マーカー表示の制御方法およびプログラム |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3722354B2 (ja) * | 1999-09-10 | 2005-11-30 | 株式会社サタケ | 粒状物選別方法及び粒状物選別装置 |
JP2004283153A (ja) | 2003-03-19 | 2004-10-14 | Shigeta Animal Pharmaceuticals Inc | Q熱菌のPCR(Polymerasechainreaction)法による高精度迅速検出法 |
JP4438358B2 (ja) * | 2003-09-04 | 2010-03-24 | 株式会社サタケ | 表示調整機構を具えた粒状物色彩選別機 |
CN2740303Y (zh) * | 2004-11-16 | 2005-11-16 | 许大红 | 颗粒物料色选机 |
CN101279321B (zh) * | 2008-05-14 | 2012-10-10 | 合肥泰禾光电科技股份有限公司 | 颗粒物料光学色选机 |
CN101786084A (zh) * | 2009-12-25 | 2010-07-28 | 北京经纬纺机新技术有限公司 | 双ccd物料色选方法及色选机 |
CN102284428B (zh) * | 2011-05-12 | 2013-04-17 | 浙江大学 | 谷物实时检测与分级的机器视觉系统 |
-
2013
- 2013-02-07 KR KR1020147029102A patent/KR101998910B1/ko active IP Right Grant
- 2013-02-07 CN CN201380017680.1A patent/CN104203436B/zh active Active
- 2013-02-07 EP EP13767511.2A patent/EP2832458B1/en active Active
- 2013-02-07 JP JP2014507488A patent/JP6152845B2/ja active Active
- 2013-02-07 WO PCT/JP2013/052838 patent/WO2013145873A1/ja active Application Filing
- 2013-02-07 US US14/387,545 patent/US9024223B2/en active Active
- 2013-02-07 BR BR112014024083-3A patent/BR112014024083B1/pt active IP Right Grant
- 2013-02-07 ES ES13767511T patent/ES2704429T3/es active Active
- 2013-03-15 TW TW102109290A patent/TWI573634B/zh active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001283153A (ja) * | 2000-01-27 | 2001-10-12 | Fujitsu Ltd | カラー画像から文字列パターンを抽出する装置および方法 |
JP2004178050A (ja) * | 2002-11-25 | 2004-06-24 | Fuji Xerox Co Ltd | 色データ精度算出方法、色データ精度算出装置、色処理方法、色処理装置、色データ精度算出プログラム、色処理プログラム、記憶媒体 |
JP2005186053A (ja) * | 2003-12-03 | 2005-07-14 | Satake Corp | 粒状物色彩選別機 |
JP2007006142A (ja) * | 2005-06-23 | 2007-01-11 | Ricoh Co Ltd | 画像処理方法、画像形成装置、プログラム及び記録媒体 |
WO2008001889A1 (fr) * | 2006-06-29 | 2008-01-03 | Fujitsu Limited | procédé de classification de couleur, procédé de reconnaissance de couleur, dispositif de classification de couleur, dispositif de reconnaissance de couleur, système de reconnaissance de couleur, programme informatique et support d'enregistrement |
JP2009119410A (ja) | 2007-11-16 | 2009-06-04 | Satake Corp | 粒状物等の光学判別装置及び粒状物等の光学式選別装置 |
JP2010050832A (ja) * | 2008-08-22 | 2010-03-04 | Ricoh Co Ltd | 画像処理装置、画像処理方法、プログラムおよび記録媒体 |
JP2010062929A (ja) * | 2008-09-04 | 2010-03-18 | Ricoh Co Ltd | 画像処理装置、画像処理プログラム、及び記録媒体 |
JP2010288163A (ja) * | 2009-06-15 | 2010-12-24 | Internatl Business Mach Corp <Ibm> | 評価システム、マーカー表示の制御方法およびプログラム |
Non-Patent Citations (1)
Title |
---|
See also references of EP2832458A4 |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014126232A1 (ja) * | 2013-02-18 | 2014-08-21 | 株式会社サタケ | 光学式粒状物選別機 |
US9676005B2 (en) | 2013-02-18 | 2017-06-13 | Satake Corporation | Optical type granule sorting machine |
WO2015186708A1 (ja) * | 2014-06-05 | 2015-12-10 | 株式会社サタケ | 粒状物外観品位判別装置における品位判別基準の作成方法 |
JP2015230265A (ja) * | 2014-06-05 | 2015-12-21 | 株式会社サタケ | 粒状物外観品位判別装置における品位判別基準の作成方法 |
KR102382399B1 (ko) * | 2014-06-05 | 2022-04-01 | 가부시끼가이샤 사따께 | 입상물 외관 품위 판별 장치에 있어서의 품위 판별 기준의 작성 방법 |
KR20170015338A (ko) * | 2014-06-05 | 2017-02-08 | 가부시끼가이샤 사따께 | 입상물 외관 품위 판별 장치에 있어서의 품위 판별 기준의 작성 방법 |
CN106662534A (zh) * | 2014-06-05 | 2017-05-10 | 株式会社佐竹 | 粒状物外观等级判别装置的等级判别基准的生成方法 |
US10386307B2 (en) | 2014-06-05 | 2019-08-20 | Satake Corporation | Method of creating quality grade discrimination criteria in granular material appearance quality grade discrimination device |
US10088425B2 (en) | 2014-06-23 | 2018-10-02 | Tsi, Incorporated | Rapid material analysis using LIBS spectroscopy |
WO2015200111A1 (en) * | 2014-06-23 | 2015-12-30 | Tsi, Inc. | Rapid material analysis using libs spectroscopy |
JPWO2017169758A1 (ja) * | 2016-03-31 | 2019-02-07 | 株式会社サタケ | 穀類の搗精度評価方法及びその装置 |
WO2017169758A1 (ja) * | 2016-03-31 | 2017-10-05 | 株式会社サタケ | 穀類の搗精度評価方法及びその装置 |
WO2019097981A1 (ja) * | 2017-11-14 | 2019-05-23 | 新東工業株式会社 | 検査対象物の表面状態の評価方法、評価装置、評価装置の制御方法及び評価装置の制御プログラム |
JPWO2019097981A1 (ja) * | 2017-11-14 | 2020-09-24 | 新東工業株式会社 | 検査対象物の表面状態の評価方法、評価装置、評価装置の制御方法及び評価装置の制御プログラム |
JP7184048B2 (ja) | 2017-11-14 | 2022-12-06 | 新東工業株式会社 | 検査対象物の表面状態の評価方法、評価装置、評価装置の制御方法及び評価装置の制御プログラム |
JP2023115692A (ja) * | 2022-02-08 | 2023-08-21 | ユーシーシー上島珈琲株式会社 | コーヒー豆類の良品識別機能を備える良品検査システムおよび良品検査方法 |
JP7440044B2 (ja) | 2022-02-08 | 2024-02-28 | ユーシーシー上島珈琲株式会社 | コーヒー豆類の良品識別機能を備える良品検査システムおよび良品検査方法 |
WO2023195215A1 (ja) * | 2022-04-08 | 2023-10-12 | 住友化学株式会社 | 透明度評価方法 |
Also Published As
Publication number | Publication date |
---|---|
EP2832458A4 (en) | 2015-11-25 |
CN104203436A (zh) | 2014-12-10 |
EP2832458A1 (en) | 2015-02-04 |
KR20140145163A (ko) | 2014-12-22 |
KR101998910B1 (ko) | 2019-07-10 |
EP2832458B1 (en) | 2018-10-10 |
US20150076042A1 (en) | 2015-03-19 |
JP6152845B2 (ja) | 2017-06-28 |
CN104203436B (zh) | 2016-05-04 |
BR112014024083B1 (pt) | 2021-10-26 |
US9024223B2 (en) | 2015-05-05 |
BR112014024083A2 (pt) | 2017-06-20 |
TWI573634B (zh) | 2017-03-11 |
ES2704429T3 (es) | 2019-03-18 |
JPWO2013145873A1 (ja) | 2015-12-10 |
TW201400198A (zh) | 2014-01-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6152845B2 (ja) | 光学式粒状物選別機 | |
JP6037125B2 (ja) | 光学式粒状物選別機 | |
JP5569799B2 (ja) | 色彩選別機 | |
US20090050540A1 (en) | Optical grain sorter | |
JP4915129B2 (ja) | 色彩選別機 | |
JP5332268B2 (ja) | 光学式米粒選別機 | |
JP2010042326A (ja) | 光学式穀粒選別装置 | |
JP2001145855A (ja) | 粒状物選別方法及び粒状物選別装置 | |
RU2699751C1 (ru) | Способ сортировки объектов по их цветовым характеристикам | |
RU2403100C2 (ru) | Устройство для сортировки зерна по цвету | |
Chen et al. | Sensor-based sorting | |
WO2021149820A1 (ja) | 光学式粒状物判別装置 | |
JP7392495B2 (ja) | 光学式粒状物判別装置 | |
JP7392494B2 (ja) | 光学式粒状物判別装置 | |
CN103464385B (zh) | 光学式粒状物选别机 | |
CN203678707U (zh) | 光学式粒状物选别机 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201380017680.1 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13767511 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2014507488 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14387545 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2013767511 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 20147029102 Country of ref document: KR Kind code of ref document: A |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112014024083 Country of ref document: BR |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 112014024083 Country of ref document: BR Kind code of ref document: A2 Effective date: 20140926 |