WO2013145295A1 - カラーチャート検出装置、カラーチャート検出方法及びカラーチャート検出用コンピュータプログラム - Google Patents
カラーチャート検出装置、カラーチャート検出方法及びカラーチャート検出用コンピュータプログラム Download PDFInfo
- Publication number
- WO2013145295A1 WO2013145295A1 PCT/JP2012/058689 JP2012058689W WO2013145295A1 WO 2013145295 A1 WO2013145295 A1 WO 2013145295A1 JP 2012058689 W JP2012058689 W JP 2012058689W WO 2013145295 A1 WO2013145295 A1 WO 2013145295A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- palette
- palettes
- image
- color
- pixels
- Prior art date
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 259
- 238000004590 computer program Methods 0.000 title claims description 13
- 238000004364 calculation method Methods 0.000 claims description 41
- 238000013213 extrapolation Methods 0.000 claims description 33
- 230000009467 reduction Effects 0.000 claims description 28
- 238000000605 extraction Methods 0.000 claims description 23
- 239000000284 extract Substances 0.000 claims description 8
- 239000003086 colorant Substances 0.000 abstract description 6
- 238000000034 method Methods 0.000 description 52
- 230000008569 process Effects 0.000 description 44
- 238000010586 diagram Methods 0.000 description 30
- 238000012545 processing Methods 0.000 description 22
- 238000004891 communication Methods 0.000 description 16
- 238000003384 imaging method Methods 0.000 description 15
- 230000010354 integration Effects 0.000 description 14
- 238000006243 chemical reaction Methods 0.000 description 13
- 230000004048 modification Effects 0.000 description 11
- 238000012986 modification Methods 0.000 description 11
- 239000013598 vector Substances 0.000 description 11
- 230000005484 gravity Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 239000004065 semiconductor Substances 0.000 description 6
- 238000012937 correction Methods 0.000 description 5
- 239000000470 constituent Substances 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- H04N1/603—Colour correction or control controlled by characteristics of the picture signal generator or the picture reproducer
- H04N1/6033—Colour correction or control controlled by characteristics of the picture signal generator or the picture reproducer using test pattern analysis
-
- 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
- G01J3/52—Measurement of colour; Colour measuring devices, e.g. colorimeters using colour charts
- G01J3/524—Calibration of colorimeters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
- G09G5/00—Control arrangements or circuits for visual indicators common to cathode-ray tube indicators and other visual indicators
- G09G5/02—Control arrangements or circuits for visual indicators common to cathode-ray tube indicators and other visual indicators characterised by the way in which colour is displayed
- G09G5/06—Control arrangements or circuits for visual indicators common to cathode-ray tube indicators and other visual indicators characterised by the way in which colour is displayed using colour palettes, e.g. look-up tables
-
- 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
- G01J2003/466—Coded colour; Recognition of predetermined colour; Determining proximity to predetermined colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Definitions
- the present invention relates to, for example, a color chart detection apparatus, a color chart detection method, and a computer program for color chart detection that detect a color chart in an image.
- color charts have been used to perform image color correction.
- the color chart has a plurality of palettes, and each palette is given a different color.
- each pallet by comparing the color of the area where the pallet is shown in the image showing the color chart with the actual color of the pallet, the change in hue that occurs during image generation is measured. Then, by correcting the color of the image so as to cancel the color change, the color of the subject in the image becomes a natural color.
- Patent Document 1 discloses that pattern matching is performed on an image showing a color chart to detect the position of the color chart.
- Patent Document 2 discloses a technique for determining whether or not a color chart image is obtained by converting a sampled image signal into a chromaticity signal and examining the distribution shape of the chromaticity signal.
- Patent Document 3 proposes a technique for specifying a color reference pattern from an image obtained by photographing a two-dimensional code in which a color reference pattern is arranged, extracting the color information, and using it for color correction.
- pattern matching is computationally intensive.
- the apparatus for detecting the color chart examines the degree of coincidence while changing the position of the template corresponding to the color chart with respect to the image so as to scan the entire image. . Therefore, the amount of calculation for specifying the position of the color chart is enormous.
- the amount of calculation is as small as possible due to restrictions such as power consumption.
- the hardware resources that can be used for color chart detection are limited in portable terminals or digital cameras, the greater the amount of calculation, the longer the time required for color chart detection and the lower the convenience for the user. .
- the technique disclosed in Patent Document 2 determines whether or not a color chart is shown based on a color distribution statistic, and does not specify the position of the color chart on the image. Furthermore, the color chart may be photographed together with another subject. In such a case, the area occupied by the color chart on the image is smaller than the area occupied by the other subject or the background. Since the shape of the color distribution obtained from such an image depends on the color distribution of other subjects or backgrounds rather than the color chart, the technique disclosed in Patent Document 2 determines whether or not the color chart is captured. There was a risk that it could not be determined accurately.
- an object of the present specification is to provide a color chart detection device capable of detecting a color chart reflected in an image while suppressing a calculation amount.
- a color chart detection device that detects a color chart from an image showing a color chart having a plurality of palettes arranged according to a predetermined arrangement.
- the color chart detection device includes a palette color pixel extraction unit that extracts, from an image, a pixel having a color component corresponding to the palette for each of a predetermined number of palettes of at least three of a plurality of palettes, and a predetermined number of palettes.
- the palettes at least three palettes are set as the first group, and a combination of pixels selected for each palette from the pixels extracted for each of the palettes included in the first group is a predetermined arrangement of the palettes.
- a combination detection unit that detects pixels included in the combination as a candidate pixel in which the corresponding palette of the first group may be reflected, and corresponds to the candidate pixel based on the candidate pixel Color information representing the color of the palette on the palette and the position information representing the position of the palette on the image
- a palette information calculator for determining the.
- the color chart detection apparatus disclosed in this specification can detect a color chart in an image while suppressing the amount of calculation.
- FIG. 1 is a configuration diagram of an imaging device in which a color chart detection device is incorporated.
- FIG. 2 is a diagram illustrating an example of a color chart.
- FIG. 3 is a configuration diagram of the color chart detection apparatus according to the first embodiment.
- FIG. 4 is a diagram illustrating an example of color chart information.
- FIG. 5A is a diagram illustrating an example of an image in which a color chart is captured.
- FIG. 5B is a diagram showing a palette candidate area image representing a set of pixels having color components corresponding to the palette with green color extracted from the image shown in FIG.
- FIG. 5C is a diagram showing a palette candidate area image representing a set of pixels having color components corresponding to a palette with a red color extracted from the image shown in FIG.
- FIG. 5D is a diagram showing a palette candidate area image representing a set of pixels having color components corresponding to the palette with yellow color extracted from the image shown in FIG.
- FIGS. 6A to 6C are schematic diagrams of palette candidate area images each representing a set of pixels extracted for three palettes from an image obtained by photographing a color chart.
- FIG. 6D is a schematic diagram showing the pixels extracted in the palette candidate region images shown in FIGS. 6A to 6C as one image.
- FIG. 7 is an operation flowchart of the combination detection process.
- FIG. 8A is a diagram illustrating an example of a combination of palettes selected from the color chart
- FIG. 8B is a schematic diagram of an image in which the color chart is captured.
- FIG. 9A is a diagram illustrating an example of an output image generated for a palette k2 generated as a result of the combination detection process for a combination of palettes including three palettes k1 to k3.
- FIG. 9B is a diagram illustrating another example of the output image generated for the palette k2 generated as a result of the combination detection process for the combination of other palettes including the palette k2.
- FIG. 9C is a diagram showing an example of a product image of the output image shown in FIG. 9A and the output image shown in FIG. 9B.
- FIG. 10 is an operation flowchart of color chart detection processing according to the first embodiment.
- FIG. 11 is a configuration diagram of a color chart detection apparatus according to the second embodiment.
- FIG. 12 is an operation flowchart of extrapolation processing.
- FIG. 10 is an operation flowchart of color chart detection processing according to the first embodiment.
- FIG. 11 is a configuration diagram of a color chart detection apparatus according to the second embodiment.
- FIG. 12 is an operation
- FIG. 13 is a configuration diagram of a color chart detection apparatus according to the third embodiment.
- FIG. 14 is an operation flowchart of color chart detection processing according to the third embodiment.
- FIG. 15 is a configuration diagram of a computer that operates as a color chart detection apparatus by operating a computer program that realizes the functions of each unit of the color chart detection apparatus according to each embodiment or a modification thereof.
- This color chart detection device extracts regions having colors corresponding to several palettes including a specific palette among a plurality of palettes included in the color chart from an image in which the color chart is captured. And this color chart detection apparatus, as an area where the palette may actually appear in the area corresponding to the palette arrangement among the areas corresponding to the color of each palette of the combination of palettes including a specific palette To detect. And this color chart detection apparatus performs the same processing for a plurality of combinations including a specific pallet, and detects the area detected as the possibility that the specific pallet is reflected for all the combinations. Judged as the area where the palette is reflected.
- FIG. 1 is a schematic configuration diagram of an imaging device in which a color chart detection device according to each embodiment or a modification thereof is incorporated.
- the imaging device 1 is, for example, a mobile phone equipped with a camera or a digital camera. As illustrated in FIG. 1, the imaging device 1 includes a camera module 2, an operation unit 3, a display unit 4, a storage unit 5, a color chart detection device 6, and a control unit 7. Furthermore, the imaging device 1 may have an interface circuit (not shown) according to a serial bus standard such as a universal serial bus in order to connect the imaging device 1 to another device such as a computer or a television.
- the control unit 7 and other units of the imaging device 1 are connected by, for example, a bus.
- the camera module 2 includes an image sensor having an array of solid-state imaging elements arranged in a two-dimensional manner, and an imaging optical system that forms an image of a subject on the image sensor. Then, the camera module 2 captures a subject with the aperture diameter and shutter speed notified from the control unit 7 and generates an image in which the subject image is reflected. The camera module 2 stores the image in the storage unit 5.
- the subject includes a color chart.
- the generated image is a color image that is expressed in the RGB color system and has an 8-bit gradation for each color.
- the number of bits representing the gradation of each color component is not limited to 8 bits, and may be 4 bits or 10 bits, for example.
- the image that is the target of color chart detection may be a color image that is expressed in another color system.
- FIG. 2 is a diagram showing an example of a color chart.
- a total of 24 pallets 201 are arranged in 6 rows ⁇ 4 columns.
- Each pallet 201 has a rectangular shape and is colored differently.
- the distance between the centers of two pallets adjacent in the vertical direction is a, while the distance between the centers of the two pallets adjacent in the horizontal direction is b.
- the operation unit 3 includes, for example, various operation buttons or dial switches for the user to operate the imaging device 1.
- the operation unit 3 transmits to the control unit 7 a control signal for setting the shutter speed, the aperture diameter, or the like, or a control signal for starting shooting or focusing, in accordance with a user operation.
- the display unit 4 includes, for example, a display device such as a liquid crystal display device, and displays various types of information received from the control unit 7 or an image generated by the camera module 2. Note that the operation unit 3 and the display unit 4 may be integrally formed using, for example, a touch panel display.
- the storage unit 5 includes, for example, a readable / writable volatile or nonvolatile semiconductor memory circuit.
- the storage unit 5 stores the image received from the camera module 2.
- the storage unit 5 passes the image to the color chart detection device 6 in response to a read request from the color chart detection device 6, and the storage unit 5 receives the color information and position information of each palette received from the color chart detection device 6. You may remember. Further, when each function of the color chart detection device 6 is realized by a computer program executed on the processor of the control unit 7, the computer program and various data used in the color chart detection process are stored. May be.
- the color chart detection device 6 detects a color chart from the image generated by the camera module 2.
- the color chart detection device 6 notifies the control unit 7 of position information and color information of each palette of the color chart on the image. The details of the color chart detection device 6 will be described later.
- the control unit 7 includes at least one processor and its peripheral circuits, and controls the entire imaging apparatus 1. For example, the control unit 7 sets the shutter speed or the aperture diameter according to the setting signal received from the operation unit 3 and the exposure amount of the subject. Further, the control unit 7 may execute processing such as edge enhancement or contrast enhancement on the image generated by the camera module 2. Alternatively, the control unit 7 may adjust the color correction processing on the image based on the color information of the area in which the specific palette received from the color chart detection device 6 is shown.
- FIG. 3 shows a configuration diagram of the color chart detection device 6.
- the color chart detection apparatus 6 includes a memory 10, a color conversion unit 11, a palette color pixel extraction unit 12, a combination detection unit 13, an integration determination unit 14, and a palette information calculation unit 15. These units included in the color chart detection device 6 are formed as one integrated circuit in which circuits corresponding to the units are integrated. In addition, each of these units included in the color chart detection device 6 may be formed as a separate circuit.
- the memory 10 includes, for example, a read-only nonvolatile semiconductor memory circuit and a readable / writable volatile semiconductor memory circuit.
- the memory 10 stores various data used by the color chart detection device 6 to detect the color chart from the image, for example, information on the color chart to be detected and information indicating a combination of palettes used for detecting the palette.
- the memory 10 stores various intermediate calculation results obtained during the execution of the color chart detection process, for example, a palette candidate area image representing a palette candidate area that is a set of pixels having colors corresponding to individual palettes. The details of the various information and the palette candidate area image will be described later.
- the color conversion unit 11 converts the color system of the image generated by the camera module 2 from the RGB color system to the HSV color system.
- the color conversion unit 11 converts the value of each pixel of the image according to the following equation.
- R, G, and B represent the red component, green component, and blue component of the pixel before conversion, respectively.
- MAX and MIN represent the maximum and minimum values of the red, green, and blue components of the pixel before conversion, respectively.
- H, S, and V represent the hue, saturation, and brightness of the pixel after conversion, respectively.
- the color conversion unit 11 outputs an image represented in the HSV color system to the palette color pixel extraction unit 12. Note that when the image read by the color chart detection device 6 is represented in the HSV color system from the beginning, the color conversion unit 11 may be omitted.
- the palette color pixel extraction unit 12 extracts pixels having a color component corresponding to the color of the palette from an image represented by the HSV color system for each palette and showing the color chart.
- a palette candidate area image representing a palette candidate area which is a set is generated.
- the palette color pixel extraction unit 12 refers to the color chart information stored in the memory 10 and specifies the representative values of the components H, S, and V of the detection target palette indicated by the color chart information. To do.
- FIG. 4 is a diagram illustrating an example of color chart information.
- the color chart information 400 is represented as a one-dimensional vector.
- the leading element 401 has a ratio of the distance b between the centers of two pallets adjacent in the horizontal direction to the distance a between the centers of the two pallets adjacent in the vertical direction, that is, the aspect ratio (b / a) of the pallet.
- information on each palette is stored in a set of five elements, for example, in raster scan order.
- the five elements that follow the element 401 include the H component, S component, V component representative values H (1), S (1), V (1) of the palette 1 at the upper left corner, and color.
- the pallet arrangement order from the left end on the chart and the pallet arrangement order from the top end are stored.
- the palette color pixel extraction unit 12 sets a detection range around the representative value of each component. For example, for the H component, the palette color pixel extraction unit 12 sets a range of ⁇ 10 degrees from the representative value of the H component as the detection range. Similarly, the palette color pixel extraction unit 12 sets a range of ⁇ 50 from the representative value of the S component as the detection range for the S component, and sets a range of ⁇ 80 from the representative value of the V component as the detection range for the V component.
- the detection range may be set as appropriate so that each component of the pixel in which the palette appears on the image is included in the detection range according to the characteristics of the camera module 2. Need not be symmetrical.
- the palette color pixel extraction unit 12 determines, for each palette of the image, whether or not each component of the pixel is included in the detection range set for the palette for the palette to be detected. When any component of the pixel is included in the detection range, the palette color pixel extraction unit 12 extracts the pixel for the palette to be detected. The palette color pixel extraction unit 12 generates a palette candidate area image to indicate each pixel extracted for the palette to be detected.
- the palette candidate area image is, for example, a gray image or a binary image having the same size as the image showing the color chart. The value of the pixel at the same position as the extracted pixel is set to “1”, and the values of the other pixels are set. Set to '0'.
- FIG. 5A is a diagram illustrating an example of an image in which a color chart is captured.
- an image 500 includes a color chart 501 to be detected.
- the color chart 501 includes a palette 502 with a green color, a palette 503 with a red color, and a palette 504 with a yellow color.
- FIG. 5B shows a palette candidate area image 510 representing a set of pixels having color components corresponding to the palette 502 colored green, extracted from the image 500 shown in FIG.
- FIG. 5C shows a palette candidate area image 520 representing a set of pixels having color components corresponding to the palette 503 given a red color extracted from the image 500 shown in FIG. Indicates.
- FIG. 5D shows a palette candidate area image 530 representing a set of pixels having color components corresponding to the palette 504 with a yellow color extracted from the image 500 shown in FIG. .
- pixels shown in white represent extracted pixels.
- FIGS. 5B to 5D in each palette candidate area image, pixels in which palettes 502 to 504 to be detected are shown are extracted. It can also be seen that in each palette candidate area image, pixels with a background that has a color close to the color assigned to the palette to be detected are also extracted.
- the palette color pixel extraction unit 12 stores the palette candidate area image generated for each palette in the memory 10.
- the pixels in which each palette appears on the image should follow the arrangement.
- what is reflected in the image other than the color chart may have a color similar to the color of any one of the palettes. Then, a pixel in which an object having a color similar to that of the palette is reflected is also extracted. However, these pixels are arranged regardless of the arrangement of the palette.
- FIGS. 6A to 6C are palettes representing sets of pixels extracted for palettes k1 to k3 from images obtained by photographing color charts arranged in order of palettes k1, k2, and k3 from the left.
- FIG. 6 is a schematic diagram of candidate area images 610 to 630. In the palette candidate area image 610, an area 611 where the palette k1 is shown and an area 612 where a background portion having a color similar to the color of the palette k1 is shown are extracted.
- an area 621 in which the palette k2 is shown and an area 622 in which a background portion having a color similar to the color of the palette k2 is shown are extracted.
- FIG. 6D is a schematic diagram showing pixels extracted in the palette candidate area images 610 to 630 as one image 640.
- Arbitrary pixels 615, 625, and 635 extracted from each of the regions 611, 621, and 631 in which the palettes k1 to k3 are shown are arranged in order from the left according to the arrangement of the palettes k1 to k3.
- arbitrary pixels 616, 626, and 636 extracted from each of the regions 612, 622, and 632 in which the background portion is reflected are arranged in an order different from the arrangement of the palettes k1 to k3. Therefore, it can be seen that the pallets k1 to k3 are not shown in the areas 612, 622, and 632.
- the combination detection unit 13 selects one pixel from the pixels extracted for each palette for a combination of palettes including three or more palettes, that is, a group of palettes, and whether or not the selected pixels conform to the arrangement of the palettes. Find out. Thereby, the combination detection part 13 detects the pixel which may actually show the palette among the pixels extracted about each palette contained in the combination.
- the distance from the imaging device 1 to the color chart is unknown, the size of the color chart on the image and the distance between the palettes are unknown. However, the ratio of the distance between two pallets and the distance between the other two pallets is unchanged regardless of the distance from the imaging device 1 to the color chart.
- the combination detection unit 13 determines other values based on the ratio between the distance between the pixels and the distance between the palettes selected from the palette candidate areas corresponding to two palettes among the palettes included in the combination of the palettes of interest. Estimate the position of the pixel where the palette is shown. Then, when the pixel at the estimated position is included in the palette candidate area of another palette, the combination detection unit 13 determines that the selected pixel and the pixel at the estimated position are highly likely to show the palette. .
- FIG. 7 is an operation flowchart of the combination detection process executed by the combination detection unit 13.
- the combination detection unit 13 selects two palette candidate area images from the palette candidate area images in order from the smallest number of pixels included in the palette candidate area. (Step S101). For example, in each pallet candidate area image shown in FIGS. 6A to 6C, the pallet candidate area image 610 corresponding to pallet k1 and the pallet candidate area image 630 corresponding to pallet k3 are displayed. The number is small. Therefore, the palette candidate area image 610 and the palette candidate area image 630 are selected. Thereby, since the number of pixel groups to be selected is minimized, the combination detection unit 13 can suppress an increase in the calculation amount.
- the combination detection unit 13 selects a set of unselected pixels, one pixel from each of the palette candidate areas of the two selected palette candidate area images (step S102). Then, the combination detection unit 13 estimates the positions of the remaining palettes included in the combination on the image according to the positional relationship between the two selected pixels and the arrangement of the palettes corresponding to the areas including them (step S103). ).
- the combination detection unit 13 is a vector (x1, y1) representing an amount of shifting in the horizontal direction by one palette on the image and a vector (x2) representing an amount of shifting in the vertical direction by one palette on the image. , y2).
- Each element x1, x2, y1, and y2 of the vector is expressed in units of pixels.
- (x1, y1) and (x2, y2) are calculated from the two selected pixels according to the following equation:
- (j1, i1) represents the horizontal coordinate and the vertical coordinate of the pixel selected for the palette k1, respectively.
- (j2, i2) represents the horizontal coordinate and the vertical coordinate of the pixel selected for the palette k2.
- Ph (k1) and Ph (k2) represent the number of palettes from the left end on the color chart of palettes k1 and k2, respectively.
- Pv (k1) and Pv (k2) represent the number of palettes from the upper end on the color chart of palettes k1 and k2, respectively.
- FIG. 8A is a diagram illustrating an example of a combination of palettes selected from the color chart 800
- FIG. 8B is a schematic diagram of an image 810 in which the color chart 800 is captured.
- the angle ⁇ formed by the vector (x1, y1) and the vector (j2-j1, i2-i1) representing the amount of positional deviation between the palettes k1 and k2 is expressed by the following equation.
- the relationship between the vectors (x1, y1) and (j2-j1, i2-i1) represented by the equation (3) and the angle ⁇ is as follows when the color chart 800 is tilted as shown in FIG. This also holds on the captured image 810. If the distance between the pallets k1 and k2 is L, the horizontal distance between k1 and k2, and the vertical distance are respectively L ⁇ cos (atan (q ⁇ a / b)) L ⁇ sin (atan (q ⁇ a / b)) It becomes.
- the distance to shift in the horizontal and vertical directions by one pallet is the horizontal distance and the vertical distance, respectively, which are the number of horizontal pallets and the number of vertical pallets between k1 and k2, respectively.
- L corresponds to the distance between the pixel (j1, i1) and the pixel (j2, i2). Therefore, the following equation is established.
- the vector (x1, y1) is calculated by the following equation.
- the vector (x1, y1) is calculated by the following equation.
- the vector (x2, y2) is calculated by the following equation.
- the vector (x2, y2) is calculated by the following equation.
- the estimated position (j, i) of the pixel in which the palette k3 is shown is calculated by the following equation.
- the combination detection unit 13 similarly applies the palette for each remaining palette other than the palette corresponding to the two selected pixels according to the equation (9). What is necessary is just to obtain the estimated position of the pixel in which.
- the combination detection unit 13 determines whether or not the pixel at the estimated position (j, i) is included in the palette candidate area for the remaining palette of the combination (step S104). When four or more palettes are included in the combination, the combination detection unit 13 determines, for each remaining palette, whether the pixel at the estimated position corresponding to the palette is included in the palette candidate area. . If all the pixels at the estimated position (j, i) are included in the palette candidate area (step S104—Yes), the selected two pixels and the pixel at the estimated position each have a palette. This is a possible candidate pixel.
- the combination detection unit 13 may have the palette showing the values of the two selected pixels and the pixel at the estimated position in the output image representing the candidate pixels that may correspond to the palette. Is rewritten to a value (eg, “1”) (step S105).
- the output image is, for example, a binary image having the same size as the image showing the palette, and in the initial state, all the pixels are set to a value (for example, “0”) indicating that the palette is not shown. ing.
- One output image is generated for each palette.
- any one of the pixels at the estimated position is not included in the palette candidate region (No in step S104), at least one of the two selected pixels and the pixel at the estimated position is not included. There is a high possibility that the palette is not shown. In this case, the combination detection unit 13 does not rewrite the output image.
- the combination detection unit 13 determines whether or not there is a set of unselected pixels for the two selected palette candidate region images (step S106). If there is a group of unselected pixels (step S106—Yes), the combination detection unit 13 repeats the processing after step S101. On the other hand, if there is no unselected pixel group (No in step S106), the combination detection unit 13 writes the output image of each palette in the memory 10 (step S107).
- the combination detection unit 13 may change the combination of pallets and execute the combination detection process a plurality of times. In that case, it is preferable that at least two combinations include the same pallet. For example, three types of combinations are set, the first combination G (1) includes palettes k (a), k (b), and k (c), and the second combination G (2) includes palette k The third combination G (3) includes (a), k (d), and k (e), and includes the palettes k (b), k (f), and k (g). In this case, the candidate G (1) and G (2) are used to examine candidate pixels that may appear in the palette k (a), and the combination G (1) and G (3) Candidate pixels that may contain (b) are examined. In the present embodiment, the combination detection unit 13 includes a palette for detecting the color and position on the image in any combination.
- the combination detection unit 13 may perform the combination detection process for only one combination.
- the combination detection unit 13 generates an output image for each palette included in the combination for each combination for which the combination detection process has been executed, and stores the output image in the memory 10.
- the integration determination unit 14 obtains, for each palette, a product of pixels at the same position in a plurality of output images generated for the palette. Then, the integrated determination unit 14 determines that a pixel whose product is “1” is a pixel in which the palette is reflected.
- FIG. 9A shows an example of an output image generated for the palette k2 generated as a result of the combination detection process for the combination of palettes including the palettes k1 to k3.
- FIG. 9B shows another example of the output image generated for the palette k2 generated as a result of the combination detection process for the combination of other palettes including the palette k2.
- FIG. 9C shows a product image of the output image shown in FIG. 9A and the output image shown in FIG.
- FIG. 9A for example, in the output image 900 for the palette k2, not only the area 621 but also the area 623 is extracted as a set of pixels that may contain the palette.
- the area 621 may be extracted but the area 623 may not be extracted as in the output image 910 illustrated in FIG. 9B, for example. Increases nature. Therefore, by obtaining a product between pixels at the same position in the output image 900 and the output image 910, only a region 621 in which the palette k2 is actually shown is obtained as in the product image 920 shown in FIG. 9C. The possibility of extraction increases. As a result, pallet detection accuracy is improved.
- the integrated determination unit 14 For each pallet, the integrated determination unit 14 outputs a product image representing the product of a plurality of output images generated for the pallet to the pallet information calculation unit 15 as pallet detection information representing pixels in which the pallet is reflected. For a palette for which only one output image has been generated, the integrated determination unit 14 outputs the one output image as it is to the palette information calculation unit 15 as palette detection information.
- the integration determination unit 14 may be omitted.
- the pallet information calculation unit 15 refers to the pallet detection information received from the integration determination unit 14 for each pallet, and obtains color information representing the color of the pallet on the image and position information representing the position on the image. Therefore, the palette information calculation unit 15 calculates an average value or a median value as color information of the palette for each of the H component, S component, and V component of the pixel in which the palette is shown, which is indicated in the palette detection information. To do. In addition, the palette information calculation unit 15 obtains the center of gravity of the pixel in which the palette is shown, which is indicated in the palette detection information, for each palette, and uses the center of gravity as the position information of the palette.
- the pallet information calculation unit 15 outputs the color information and the position information to the control unit 7 together with the pallet identification information for each pallet.
- the palette identification information can be, for example, the number of palettes in raster scan order from the upper left palette on the color chart.
- FIG. 10 is an operation flowchart of color chart detection processing executed by the color chart detection device 6.
- the color chart detection device 6 reads an image showing the color chart from the storage unit 5 (step S201). Then, the color converter 11 converts the image from the RGB color system to the HSV color system (step S202).
- the palette color pixel extraction unit 12 extracts pixels having a color corresponding to the palette for each of a predetermined number of three or more of a plurality of palettes included in the color chart from the image in which the color system is converted. (Step S203).
- the palette color pixel extraction unit 12 generates a palette candidate area image representing a palette candidate area that is a set of pixels having the palette color for each palette.
- the combination detection unit 13 performs a combination detection process on a combination of at least one pallet including three or more pallets (step S204). And the combination detection part 13 produces
- the integrated determination unit 14 determines, for each pallet, that the pallet is captured in all combinations including the pallet by obtaining a product for each pixel between the plurality of output images generated for the pallet. Extracted pixels are extracted (step S205). Then, the integrated determination unit 14 notifies the palette information calculation unit 15 of palette detection information indicating the position of the extracted pixel for each palette.
- the palette information calculation unit 15 calculates, for each palette, an average value or a median value as color information of the palette for each of the H component, S component, and V component of the pixel in which the palette is reflected. Further, the palette information calculation unit 15 calculates the coordinates of the center of gravity of the pixel in which the palette is reflected as the position information of the palette (step S206). The palette information calculation unit 15 outputs the color information and the position information to the control unit 7 together with the identification information of each palette. Thereafter, the color chart detection device 6 ends the color chart detection process.
- this color chart detection apparatus uses the information related to the palette arrangement to detect pixels that match the palette arrangement among the pixels having colors corresponding to each palette. Therefore, this color chart detection apparatus can accurately detect individual pallets of the color chart even if the position of the color chart is unknown. Further, this color chart detection apparatus does not need to perform processing with a large amount of calculation such as pattern matching on the entire image, so that the amount of calculation can be reduced.
- the color chart detection apparatus specifies the position of an undetected pallet that has not been subjected to combination detection from the position of the pallet specified by combination detection according to the arrangement of the pallets, thereby detecting the undetected Detect palettes.
- FIG. 11 is a configuration diagram of a color chart detection device 61 according to the second embodiment.
- the color chart detection device 61 includes a memory 10, a color conversion unit 11, a palette color pixel extraction unit 12, a combination detection unit 13, an integration determination unit 14, a palette information calculation unit 15, and an extrapolation unit 16. Have. These units included in the color chart detection device 61 are formed as one integrated circuit in which circuits corresponding to the units are integrated. In addition, each of these units included in the color chart detection device 61 may be formed as a separate circuit.
- the constituent elements of the color chart detection device 61 are given the same reference numerals as the corresponding constituent elements of the color chart detection device 6 according to the first embodiment shown in FIG. .
- the color chart detection device 61 according to the second embodiment is different from the color chart detection device 6 according to the first embodiment in that an extrapolation unit 16 is provided. Therefore, in the following, the extrapolation unit 16 and related parts will be described.
- the extrapolation unit 16 sets (j1, i1) and (j2, i2) as the coordinates of the centroid positions of two pallets among the pallets whose centroids have been obtained by the pallet information calculation unit 15, respectively. Or, input in the equation (6). Thereby, the extrapolation unit 16 calculates the shift amount (x1, y1) for one horizontal pallet on the image. Similarly, the extrapolation unit 16 inputs the coordinates (j1, i1) and (j2, i2) of the center of gravity positions of the two pallets into the equation (7) or (8), so that The shift amount (x2, y2) for one vertical pallet is calculated.
- the extrapolation unit 16 calculates the coordinates (j, i) of the center position of the detection range of any undetected pallet k according to the equation (9).
- Ph (k3) and Pv (k3) in the equation (9) are the number of palettes from the left end and the number of palettes from the upper end of the undetected palette k on the color chart.
- the extrapolation unit 16 determines the detection range of the palette k on the image according to the following equation based on the coordinates (j, i) of the center position of the detection range of the detection target palette k calculated according to the equation (9).
- the function min (a, b, c, d) is a function that outputs the minimum value of the parameters a, b, c, d.
- the function max (a, b, c, d) is a function that outputs the maximum value among the parameters a, b, c, d.
- Xl and Xr are the coordinates of the left end and the right end of the detection range, respectively, and Yt and Yb are the coordinates of the upper end and the lower end of the detection range, respectively.
- the extrapolation unit 16 detects a pixel included in the detection range among pixels included in the palette candidate area for the palette to be detected as a pixel in which the palette is reflected. Then, the extrapolation unit 16 obtains the center of gravity of the detected pixel, and uses the center of gravity as the position information of the palette. Further, the extrapolation unit 16 calculates an average value or median value for each of the detected H component, S component, and V component of the detected pixel as color information of the palette. Then, the extrapolation unit 16 outputs the pallet position information and color information to the control unit 7 together with the pallet identification information.
- FIG. 12 is an operation flowchart of extrapolation processing executed by the extrapolation unit 16. This extrapolation process is performed subsequent to step S206 of the color chart detection process shown in FIG. 10, for example.
- the extrapolation unit 16 shifts one pallet in the horizontal direction (x1, y1) and one pallet in the vertical direction based on the center of gravity of the two pallets detected in step S206. A shift amount (x2, y2) is calculated (step S301). Then, the extrapolation unit 16 sets any of the undetected palettes as a noticed palette (step S302).
- the extrapolation unit 16 determines the center of the detection range of the target palette on the image based on the shift amounts (x1, y1) and (x2, y2) and the arrangement of the target palette and the detected palette. (Step S303). The extrapolation unit 16 sets the detection range based on the center of the detection range so that the entire pallet of interest is included in the detection range (step S304).
- the extrapolation unit 16 detects the pixels included in the detection range among the pixels included in the palette candidate area for the target palette as the pixels in which the target palette is reflected (step S305). The extrapolation unit 16 obtains position information and color information of the noticed palette based on the detected center of gravity of the pixel and each color component (step S306). Then, the extrapolation unit 16 outputs position information and color information to the control unit 7 together with the identification information of the palette.
- the extrapolation unit 16 determines whether or not there is an undetected pallet (step S307). If there is an undetected pallet (step S307—Yes), the extrapolation unit 16 repeats the processing after step S302. On the other hand, if there is no undetected pallet (step S307-No), the extrapolation unit 16 ends the extrapolation process.
- the color chart detection apparatus can obtain the position information and color information of the palette not detected by the combination detection process with a smaller amount of calculation than the combination detection process.
- the extrapolation unit 16 detects the maximum set from the set of detected pixels adjacent to each other by performing a labeling process on the pixels detected within the detection range. May be. Then, the extrapolation unit 16 may obtain the color information and the position information based only on the pixels included in the largest set. As a result, the extrapolation unit 16 allows the palette to be detected even when a color close to the color of the palette to be detected (including other palettes adjacent to the palette to be detected) is near the palette. It is possible to more appropriately detect only the pixels in which is shown.
- the color chart detection apparatus generates a reduced image of a palette candidate area image and performs a combination detection process on the reduced image, thereby reducing the amount of calculation.
- FIG. 13 shows a configuration diagram of a color chart detection device 62 according to the third embodiment.
- the color chart detection device 62 includes a memory 10, a color conversion unit 11, a palette color pixel extraction unit 12, a combination detection unit 13, an integration determination unit 14, a palette information calculation unit 15, and an area size counting unit 17.
- a region size setting unit 18, a reduced image generation unit 19, and an interpolation unit 20 are formed as one integrated circuit in which circuits corresponding to the respective units are integrated.
- each of these units included in the color chart detection device 62 may be formed as a separate circuit.
- the constituent elements of the color chart detection device 62 are given the same reference numbers as the corresponding constituent elements of the color chart detection device 6 according to the first embodiment shown in FIG. .
- the color chart detection device 62 according to the third embodiment has a region size counting unit 17, a region size setting unit 18, a reduced image generation unit 19, and an interpolation unit 20. It is different in having. Therefore, hereinafter, the region size counting unit 17, the region size setting unit 18, the reduced image generation unit 19, the interpolation unit 20, and related portions will be described.
- the area size counting unit 17 performs a labeling process on pixels having colors corresponding to the corresponding palette for each palette candidate area image, and attaches a different label to each independent palette candidate area. Then, the area size counting unit 17 obtains the number of pixels belonging to the palette candidate area as the size of the palette candidate area for each palette candidate area to which each label is attached. Then, the area size counting unit 17 generates a size table for associating the label with the size of each area for each palette candidate area, and stores the size table in the memory 10. For example, referring to FIG. 6A again, in the palette candidate region image 610, different labels are assigned to the region 611 and the region 612, respectively. The number of pixels included in the region 611 is the size of the region 611, and the number of pixels included in the region 612 is the size of the region 612.
- the area size setting unit 18 sets, for each reduced image, an upper limit value and a lower limit value of the size of the palette candidate area to be detected in the reduced image. For example, a first reduced image with a reduction ratio of 1/8 (length unit), a second reduced image with a reduction ratio of 1/4 (length unit), and a reduction ratio of 1/2 (length unit). A third reduced image and a fourth reduced image having a reduction ratio of 1/1 are used.
- the color chart detection device 62 uses each reduced image to detect a color chart having a maximum width from Cmax% to Cmin% with respect to the number of pixels of the original image in which the color chart is captured.
- the upper limit value of the detection target size for one palette is given by ⁇ Cmax / 100 ⁇ Total / N ⁇ , while the lower limit value of the detection target size is , ⁇ Cmax / 100 ⁇ Total / N ⁇ / 4.
- N is the total number of palettes included in the color chart. Total is the number of pixels of the original image in which the color chart is shown.
- the upper limit value of the detection target size for one palette is given by ⁇ Cmax / 100 ⁇ Total / N ⁇ / 4, and the lower limit value of the detection target size is ⁇ It is given by Cmax / 100 ⁇ Total / N ⁇ / 16.
- the upper limit value of the detection target size for one palette is given by ⁇ Cmax / 100 ⁇ Total / N ⁇ / 16
- the lower limit value of the detection target size is ⁇ It is given by Cmax / 100 ⁇ Total / N ⁇ / 64.
- the upper limit value of the detection target size for one palette is given by ⁇ Cmax / 100 ⁇ Total / N ⁇ / 64
- the detection target size The lower limit of is given by ⁇ Cmin / 100 ⁇ Total / N ⁇ .
- the size to be detected is changed from (number of pixels of the original image / N) to (number of pixels of the original image / N) / 4.
- the size to be detected is from (number of pixels of the original image / N) / 4 to (number of pixels of the original image / N) / 16.
- the size to be detected is from (number of pixels of the original image / N) / 16 to (number of pixels of the original image / N) / 64.
- a palette candidate area having a pixel size smaller than (number of pixels of the original image / N) / 64 is a detection target.
- the reduced image generation unit 19 generates a reduced image of each palette candidate area image. For example, the reduced image generation unit 19 first generates a first reduced image. At that time, the reduced image generation unit 19 refers to the label and size table of an arbitrary pixel for each palette candidate area, and this label corresponds to the palette candidate area having the detection target size set by the area size setting unit 18. In this case, “1” is stored in the corresponding pixel of the reduced image. The reduced image generation unit 19 stores the first reduced image for each palette candidate area image in the memory 10.
- the interpolation unit 20 If the number of pixels detected based on the first reduced image is equal to or larger than the number obtained by multiplying the lower limit value of the detection target size by the reduction ratio (1/8), the interpolation unit 20 The coordinates in the image of the original size are obtained by multiplying the coordinate and the horizontal coordinate by 8 respectively. Then, the interpolation unit 20 notifies the palette information calculation unit 15 of the detected coordinates of each pixel. The palette information calculation unit 15 obtains position information and color information from the detected pixels for each palette. Then, the color chart detection device 62 ends the color chart detection process. On the other hand, if the number of detected pixels is less than the lower limit of the detection target size multiplied by the reduction ratio (1/8), the palette is actually reflected in the palette candidate area having the detection target size. It is judged that it is not. Therefore, the color chart detection device 62 doubles the denominator M of the reduction ratio (1 / M) (length unit).
- the area size setting unit 18 uses the image size used in the second reduced image, the upper limit value ⁇ Cmax / 100 ⁇ (number of pixels of the original image) / N ⁇ / 4 of the detection target size, and the lower limit value ⁇ Cmax / 100 X (number of pixels in the original image) / N ⁇ / 16 is set.
- the reduced image generation unit 19 has a reduction ratio of 1/4 (length unit) for each pallet candidate region image, and represents only the pallet candidate region having the detection target size set by the region size setting unit 18. 2 reduced images are generated. Then, the reduced image generation unit 19 stores a second reduced image for each palette candidate area image in the memory 10.
- the color chart detection device 62 performs the processes of the combination detection unit 13, the integration determination unit 14, and the interpolation unit 20 for the second reduced image.
- the size of the color chart is included in a range from 1/4 of the entire image to 1/16 of the image by area ratio, each palette of the color chart is detected.
- the interpolation unit 20 If the number of pixels detected based on the second reduced image is equal to or greater than the number obtained by multiplying the lower limit value of the detection target size by the reduction rate (1/4), the interpolation unit 20 The coordinates in the image of the original size are obtained by multiplying the coordinates and the lateral coordinates by 4 times, respectively. Then, the interpolation unit 20 notifies the palette information calculation unit 15 of the detected coordinates of each pixel. The palette information calculation unit 15 obtains position information and color information from the detected pixels for each palette. Then, the color chart detection device 62 ends the color chart detection process.
- the color chart detection device 62 doubles the denominator M of the reduction ratio (1 / M) (length unit). Thereafter, the reduced image generation unit 19 reduces the reduction ratio for each palette candidate area image to 1/2 (length unit), and the detection target size set for the third reduced image by the area size setting unit 18. A third reduced image that represents only the palette candidate area having is generated.
- the reduced image generation unit 19 stores the third reduced image for each palette candidate area image in the memory 10.
- the color chart detection device 62 executes the processes of the combination detection unit 13, the integration determination unit 14, and the interpolation unit 20 for the third reduced image. Thereby, when the size of the color chart is included in a range from 1/16 of the entire image to 1/64 of the image in area ratio, each palette of the color chart is detected.
- the interpolation unit 20 If the number of pixels detected based on the third reduced image is equal to or larger than the number obtained by multiplying the lower limit of the detection target size by the reduction ratio (1/2), the interpolation unit 20 And the coordinate in the image of an original size is calculated
- the color chart detection device 62 doubles the denominator M of the reduction ratio (1 / M) (length unit). After that, the color chart detection device 62 uses only the fourth reduced image of the actual image size, and only the palette candidate area having the detection target size set for the fourth reduced image by the area setting unit 18. As a target, the processing of the combination detection unit 13, the integration determination unit 14, and the interpolation unit 20 is executed. Thereby, each palette of the color chart smaller than 1/64 of the entire image is detected.
- FIG. 14 is an operation flowchart of color chart detection processing executed by the color chart detection device 62 according to the third embodiment.
- the color chart detection device 62 reads an image showing the color chart from the storage unit 5 (step S401). Then, the color conversion unit 11 converts the image from the RGB color system to the HSV color system (step S402).
- the palette color pixel extraction unit 12 extracts pixels having a color corresponding to the palette for each of a predetermined number of three or more of a plurality of palettes included in the color chart from the image in which the color system is converted. (Step S403).
- the palette color pixel extraction unit 12 generates a palette candidate area image representing a palette candidate area that is a set of pixels having the palette color for each palette.
- the area size counting unit 17 performs a labeling process on pixels having colors corresponding to the corresponding palette for each palette candidate area image, and attaches a different label to each independent palette candidate area. Then, the area size counting unit 17 obtains the number of pixels belonging to the palette candidate area as the size of the palette candidate area for each palette candidate area to which each label is attached (step S404). Then, the area size counting unit 17 generates a size table for associating the label with the size of each area for each palette candidate area, and stores the size table in the memory 10.
- the area size setting unit 18 sets the upper limit value and the lower limit value of the size of the palette candidate area to be detected in the reduced image (step S405).
- the reduced image generation unit 19 has a reduction ratio (1 / M) representing only a palette candidate area having a size included in the range between the upper limit value and the lower limit value of the detection target size for each palette candidate area image.
- a reduced image is generated (step 406).
- the combination detection unit 13 executes a combination detection process on at least one combination of palettes using the reduced image (step S407). And the combination detection part 13 produces
- the integrated determination unit 14 determines, for each pallet, that the pallet is captured in all combinations including the pallet by obtaining a product for each pixel between the plurality of output images generated for the pallet. Extracted pixels are extracted (step S408). Then, the integrated determination unit 14 notifies the interpolation unit 20 of palette detection information indicating the extracted pixel position for each palette.
- the interpolation unit 20 determines whether or not the palette detection information includes more than the number of pixels obtained by multiplying the lower limit of the detection target size by the reduction rate (1 / M), or whether the reduction rate (1 / M) is 1. (Step S409). If the number of pixels corresponding to the lower limit value of the size to be detected is not included in the palette position information and the reduction ratio (1 / M) is not 1 (No in step S409), the color chart detection device 62 reduces M to 1/2 (step S410). Thereafter, the color chart detection device 62 repeats the processing after step S405.
- the interpolation unit 20 uses the palette.
- the vertical and horizontal coordinates of each pixel included in the position information are multiplied by M (step S411). Then, the interpolation unit 20 notifies the palette information calculation unit 15 of the coordinates of these pixels.
- the palette information calculation unit 15 calculates, for each palette, the average value or median value of each of the notified H component, S component, and V component of the notified pixel as color information of the palette. Further, the palette information calculation unit 15 calculates the coordinates of the center of gravity of the pixel in which the palette is reflected as the position information of the palette (step S412). Then, the palette information calculation unit 15 outputs the color information and position information of each palette to the control unit 7. Thereafter, the color chart detection device 62 ends the color chart detection process.
- the color chart detection apparatus executes combination detection processing on a reduced image, the number of pixel combinations for checking whether or not they match the palette arrangement can be reduced. As a result, this color chart detection apparatus can reduce the amount of calculation.
- the reduced image generation unit 19 may generate a first reduced image for the HSV color system image created by the color conversion unit 11. .
- the processes of the palette color pixel extraction unit 12, the combination detection unit 13, and the integration determination unit 14 are performed on the first reduced image.
- the reduced image generation unit 19 sequentially reduces the reduction rate to generate the second and third reduced images, and the reduced image generation unit 19 generates the second and third reduced images. Processing is executed.
- the color chart detection device may also include the extrapolation unit according to the second embodiment.
- the combination detection unit 13 selects the two selected pixels and the estimated position of the palette candidate area image in step S105 of the combination detection process illustrated in FIG.
- the value of the pixel may be set to “2”.
- the combination detection unit 13 can distinguish between a pixel that may have a palette and a pixel that has no possibility without generating an output image separately from the palette candidate area image.
- the combination detection unit 13 has a positive value among the pixels of each palette candidate area image corresponding to each palette included in the palette combination of interest. Subtract 1 from the pixel value.
- the color chart detection apparatus does not have to generate an output image separately from the palette candidate area image, so that the memory capacity of the memory 10 can be reduced.
- the combination detection unit 13 may use a palette candidate area image that has been subjected to the combination detection process for one pallet combination for another pallet combination.
- the pixels that are determined not to show the palette by considering the arrangement of the palettes are deleted from the palette candidate area. The number of pairs can be reduced.
- the processing performed by the integration determination unit since the processing performed by the integration determination unit is also executed, the palette candidate area image when the combination detection processing is completed for all the combinations of palettes is the product output by the integration determination unit. It is equivalent to an image. Therefore, the integrated determination unit may be omitted. As a result, the calculation amount of the entire color chart detection process is also reduced.
- the combination detection unit 13 may select two palette candidate area images in order from the smallest number of pixels included in the palette candidate area from among all palette candidate area images. Good. And the combination detection part 13 may perform a combination detection process with respect to the combination containing the two palettes corresponding to the two palette candidate area
- each unit of the color chart detection device may be realized by a computer program executed on a processor.
- a computer program may be provided in a form recorded on a computer-readable recording medium such as a magnetic recording medium or an optical recording medium.
- FIG. 15 is a configuration diagram of a computer that operates as a color chart detection apparatus by operating a computer program that realizes the functions of the respective units of the color chart detection apparatus according to the above-described embodiment or its modification.
- the computer 100 includes a user interface unit 101, a communication interface unit 102, a storage unit 103, a storage medium access device 104, and a processor 105.
- the processor 105 is connected to the user interface unit 101, the communication interface unit 102, the storage unit 103, and the storage medium access device 104 via, for example, a bus.
- the user interface unit 101 includes, for example, an input device such as a keyboard and a mouse, and a display device such as a liquid crystal display. Alternatively, the user interface unit 101 may include a device such as a touch panel display in which an input device and a display device are integrated.
- the user interface unit 101 outputs, to the processor 105, a signal for selecting an image that is a target for detecting the color chart and an operation signal for starting the color chart detection process, for example, in accordance with a user operation.
- the communication interface unit 102 may include a communication interface for connecting the computer 100 to an imaging device (not shown) and its control circuit. Such a communication interface can be, for example, Universal Serial Bus (Universal Serial Bus, USB). Furthermore, the communication interface unit 102 may include a communication interface for connecting to a communication network according to a communication standard such as Ethernet (registered trademark) and a control circuit thereof. In this case, the communication interface unit 102 acquires an image showing a color chart from another device connected to the communication network, and stores the image in the storage unit 103. Further, the communication interface unit 102 may output the identification information, position information, and color information of each pallet of the color chart received from the processor 105 to other devices via the communication network.
- a communication standard such as Ethernet (registered trademark)
- the storage unit 103 includes, for example, a readable / writable semiconductor memory and a read-only semiconductor memory.
- the storage unit 103 stores a computer program for executing a color chart detection process executed on the processor 105, an intermediate calculation result obtained during the color chart detection process, and the like.
- the storage unit 103 stores the image received from the communication interface unit 102 or identification information, position information, color information, and the like of each palette of the color chart detected by the processor 105.
- the storage medium access device 104 is a device that accesses a storage medium 106 such as a magnetic disk, a semiconductor memory card, and an optical storage medium. For example, the storage medium access device 104 reads a computer program for color chart detection processing executed on the processor 105 stored in the storage medium 106 and passes the computer program to the processor 105.
- a storage medium 106 such as a magnetic disk, a semiconductor memory card, and an optical storage medium.
- the processor 105 obtains position information and color information of each palette of the color chart on the image by executing the computer program for color chart detection processing according to the above-described embodiment or modification. Then, the processor 105 stores the identification information, position information, and color information of each pallet in the storage unit 103 or outputs them to other devices via the communication interface unit 102.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Color Image Communication Systems (AREA)
- Processing Of Color Television Signals (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
Description
上記の一般的な記述及び下記の詳細な記述の何れも、例示的かつ説明的なものであり、請求項のように、本発明を限定するものではないことを理解されたい。
このカラーチャート検出装置は、カラーチャートが写った画像から、カラーチャートに含まれる複数のパレットのうちの特定のパレットを含む幾つかのパレットに相当する色を持つ領域をそれぞれ抽出する。そしてこのカラーチャート検出装置は、特定のパレットを含むパレットの組み合わせのそれぞれのパレットの色に相当する領域のうち、パレットの配列と一致する領域を実際にパレットが写っている可能性がある領域として検出する。そしてこのカラーチャート検出装置は、特定のパレットを含む複数の組み合わせについて同様の処理を行って、全ての組み合わせについてその特定のパレットが写っている可能性があるとして検出された領域を、その特定のパレットが写っている領域と判定する。
なお、各色成分の階調を表すビット数は8ビットに限られず、例えば、4ビットあるいは10ビットでもよい。またカラーチャート検出の対象となる画像は、他の表色系で表されるカラー画像であってもよい。
カラーチャート検出装置6が有するこれらの各部は、その各部に対応する回路が集積された一つの集積回路として形成される。また、カラーチャート検出装置6が有するこれらの各部は、それぞれ、別個の回路として形成されてもよい。
色変換部11は、HSV表色系で表された画像をパレット色画素抽出部12へ出力する。
なお、カラーチャート検出装置6が読み込む画像が最初からHSV表色系で表されている場合、色変換部11は省略されてもよい。
そのために、パレット色画素抽出部12は、メモリ10に記憶されているカラーチャート情報を参照し、そのカラーチャート情報に示される、検出対象パレットのH、S、Vそれぞれの成分の代表値を特定する。
パレット色画素抽出部12は、検出対象とするパレットについて抽出された各画素を示すために、パレット候補領域画像を生成する。パレット候補領域画像は、例えば、カラーチャートが写った画像と同じサイズのグレー画像または2値画像であり、抽出された画素と同位置の画素の値を'1'とし、その他の画素の値を'0'とする。
図5(B)は、図5(A)に示された画像500から抽出された、緑色が付されたパレット502に相当する色成分を持つ画素の集合を表すパレット候補領域画像510を示す。同様に、図5(C)は、図5(A)に示された画像500から抽出された、赤色が付されたパレット503に相当する色成分を持つ画素の集合を表すパレット候補領域画像520を示す。また図5(D)は、図5(A)に示された画像500から抽出された、黄色が付されたパレット504に相当する色成分を持つ画素の集合を表すパレット候補領域画像530を示す。各パレット候補領域画像510~530において、白で示されている画素が抽出された画素を表す。図5(B)~図5(D)に示されるように、各パレット候補領域画像では、検出対象となるパレット502~504が写っている画素が抽出されている。また、各パレット候補領域画像では、検出対象となるパレットに付された色と近い色を持つ背景が写った画素も抽出されていることが分かる。
先ず、組み合わせ検出部13は、画像上でパレット一つ分だけ横方向にシフトする量を表すベクトル(x1,y1)及び画像上でパレット一つ分だけ縦方向にシフトする量を表すベクトル(x2,y2)を求める。なお、ベクトルの各要素x1、x2、y1、y2は、それぞれ、画素単位で表される。
図8(A)は、カラーチャート800から選択されるパレットの組み合わせの一例を示す図であり、図8(B)は、カラーチャート800が写った画像810の模式図である。この例では、カラーチャート800の左端から2列目かつ上端から2行目のパレットk1{Ph(k1)=1,Pv(k1)=1}と、左端から6列目かつ上端から3行目のパレットk2{Ph(k2)=5,Pv(k2)=2}と、左端から4列目かつ上端から4行目のパレットk3{Ph(k3)=3,Pv(k3)=3}が選択される。そして、パレットk1についてのパレット候補領域に含まれる画素とパレットk2についてのパレット候補領域に含まれる画素とから、パレットk3が写っている画素の位置が推定される。
L×cos(atan(q×a/b))
L×sin(atan(q×a/b))
となる。したがって、パレット一つ分だけ横方向、縦方向にシフトする距離は、上記の横方向の距離及び縦方向の距離を、それぞれ、k1、k2間の横方向のパレット数及び縦方向のパレット数で除した値となる。また画像810上では、Lは、画素(j1,i1)と画素(j2,i2)間の距離に相当する。したがって次式が成立する。
一方、未選択の画素の組がなければ(ステップS106-No)、組み合わせ検出部13は、各パレットの出力画像をメモリ10に書き込む(ステップS107)。
また、本実施形態では、組み合わせ検出部13は、画像上での色及び位置を検出するパレットを何れかの組み合わせに含める。
この場合、図9(A)に示されるように、例えば、パレットk2に対する出力画像900では、領域621だけでなく、領域623もパレットが写っている可能性がある画素の集合として抽出される。しかし、パレットk2を含む他のパレットの組み合わせについて組み合わせ検出処理が行われると、例えば図9(B)に示される出力画像910のように、領域621は抽出されるものの、領域623は抽出されない可能性が高くなる。
したがって、出力画像900と出力画像910とで同位置の画素間の積を求めることにより、図9(C)に示した積画像920のように、実際にパレットk2が写っている領域621のみが抽出される可能性が高くなる。その結果、パレットの検出精度が向上する。
なお、組み合わせ検出部13が一つの組み合わせについてのみ組み合わせ検出処理を実行する場合には、統合判定部14は省略されてもよい。
カラーチャート検出装置6は、記憶部5からカラーチャートが写った画像を読み込む(ステップS201)。そして色変換部11は、その画像をRGB表色系からHSV表色系に変換する(ステップS202)。
カラーチャート検出装置61が有するこれらの各部は、その各部に対応する回路が集積された一つの集積回路として形成される。また、カラーチャート検出装置61が有するこれらの各部は、それぞれ、別個の回路として形成されてもよい。
カラーチャート検出装置62が有するこれらの各部は、その各部に対応する回路が集積された一つの集積回路として形成される。また、カラーチャート検出装置62が有するこれらの各部は、それぞれ、別個の回路として形成されてもよい。
一方、検出された画素の数が検出対象サイズの下限値に縮小率(1/8)を乗じた数未満の場合には、検出対象サイズを持つパレット候補領域には、実際にはパレットが写っていないと判断される。そこでカラーチャート検出装置62は、縮小率(1/M)(長さ単位)の分母Mを1/2倍する。
カラーチャート検出装置62は、記憶部5からカラーチャートが写った画像を読み込む(ステップS401)。そして色変換部11は、その画像をRGB表色系からHSV表色系に変換する(ステップS402)。
このような処理を行うことにより、カラーチャート検出装置は、パレット候補領域画像と別個に出力画像を生成しなくてもよくなるので、メモリ10のメモリ容量を削減することが可能となる。
コンピュータ100は、ユーザインターフェース部101と、通信インターフェース部102と、記憶部103と、記憶媒体アクセス装置104と、プロセッサ105とを有する。プロセッサ105は、ユーザインターフェース部101、通信インターフェース部102、記憶部103及び記憶媒体アクセス装置104と、例えば、バスを介して接続される。
さらに、通信インターフェース部102は、イーサネット(登録商標)などの通信規格に従った通信ネットワークに接続するための通信インターフェース及びその制御回路を有してもよい。
この場合には、通信インターフェース部102は、通信ネットワークに接続された他の機器から、カラーチャートが写った画像を取得し、その画像を記憶部103に記憶させる。また通信インターフェース部102は、プロセッサ105から受け取ったカラーチャートの各パレットの識別情報、位置情報及び色情報を通信ネットワークを介して他の機器へ出力してもよい。
2 カメラモジュール
3 操作部
4 表示部
5 記憶部
6、61、62 カラーチャート検出装置
7 制御部
10 メモリ
11 色変換部
12 パレット色画素抽出部
13 組み合わせ検出部
14 統合判定部
15 パレット情報算出部
16 外挿部
17 領域サイズ計数部
18 領域サイズ設定部
19 縮小画像生成部
20 補間部
100 コンピュータ
101 ユーザインターフェース部
102 通信インターフェース部
103 記憶部
104 記憶媒体アクセス装置
105 プロセッサ
106 記憶媒体
Claims (8)
- 所定の配列に従って配置された複数のパレットを有するカラーチャートが写った画像から、該カラーチャートを検出するカラーチャート検出装置であって、
前記複数のパレットのうちの少なくとも3以上の所定数のパレットのそれぞれについて、当該パレットに相当する色成分を持つ画素を前記画像から抽出するパレット色画素抽出部と、
前記所定数のパレットのうち、少なくとも3個のパレットを第1のグループとし、該第1のグループに含まれるパレットのそれぞれについて抽出された画素の中から、パレットごとに選択した画素の組み合わせが前記所定の配列に従って並んでいる場合、当該組み合わせに含まれる画素を前記第1のグループの対応するパレットが写っている可能性がある候補画素として検出する組み合わせ検出部と、
前記候補画素に基づいて、該候補画素に対応するパレットの前記画像上での色を表す色情報及び当該パレットの前記画像上での位置を表す位置情報を求めるパレット情報算出部と、
を有するカラーチャート検出装置。 - 前記所定数のパレットのうち、少なくとも3個のパレットを第2のグループとするとともに、前記第1のグループ及び前記第2のグループの何れも第1のパレットを含み、
前記組み合わせ検出部は、前記第2のグループに含まれるパレットのそれぞれについて抽出された画素の中から、パレットごとに選択した画素の組み合わせが前記所定の配列に従って並んでいる場合、当該組み合わせに含まれる画素を前記第2のグループの対応するパレットが写っている可能性がある候補画素として検出し、
前記第1のグループに関して検出された前記第1のパレットの候補画素のうち、前記第2のグループに関して前記第1のパレットの候補画素として検出された画素を前記第1のパレットが写っている画素と判定する統合判定部をさらに有する、請求項1に記載のカラーチャート検出装置。 - 前記組み合わせ検出部は、前記第1のグループに含まれる前記少なくとも3個のパレットのうちの抽出された画素の数が少ない方から順に二つのパレットについて抽出された画素からそれぞれ選択された第1の画素及び第2の画素と前記所定の配列に従って前記第1のグループ内の他のパレットの前記画像上の位置を推定し、該推定した位置の画素が当該他のパレットについて抽出された第3の画素である場合、前記第1、第2及び第3の画素をそれぞれ前記第1のグループに含まれる各パレットの前記候補画素とする、請求項1または2に記載のカラーチャート検出装置。
- 前記複数のパレットのうち、前記第1のグループに含まれない未検出パレットの前記画像上の位置及び範囲を、前記第1のグループに含まれる第2及び第3のパレットの前記画像上の位置と前記所定の配列に従って推定し、該推定された位置及び範囲に含まれる前記未検出パレットに相当する色を持つ画素に基づいて当該未検出パレットの前記画像上での色を表す色情報を求める外挿部をさらに有する、請求項1~3の何れか一項に記載のカラーチャート検出装置。
- 前記画像及び前記パレット色画素抽出部により前記所定数のパレットのそれぞれについて抽出された画素の集合を表すパレット候補領域画像の何れかを所定の縮小率で縮小した縮小画像を生成する縮小画像生成部をさらに有し、
前記組み合わせ検出部は、前記縮小画像に基づいて前記第1のグループに含まれるパレットのそれぞれについて前記候補画素を検出し、
前記第1のグループに含まれるパレットのそれぞれについて所定画素数以上の候補画素が検出されない場合、前記縮小画像生成部は、前記縮小率を低下させてさらに前記縮小画像を生成し、前記組み合わせ検出部は、当該低下した縮小率で生成された縮小画像に基づいて前記第1のグループに含まれるパレットのそれぞれについて前記候補画素を検出する、請求項1~4の何れか一項に記載のカラーチャート検出装置。 - 前記組み合わせ検出部は、前記所定数のパレットのうち、前記パレット色画素抽出部により抽出された画素の数が少ない方から順に二つのパレットを前記第1のグループに含める、請求項1~5の何れか一項に記載のカラーチャート検出装置。
- 所定の配列に従って配置された複数のパレットを有するカラーチャートが写った画像から、該カラーチャートを検出するカラーチャート検出方法であって、
前記複数のパレットのうちの少なくとも3以上の所定数のパレットのそれぞれについて、当該パレットに相当する色成分を持つ画素を前記画像から抽出し、
前記所定数のパレットのうち、少なくとも3個のパレットを第1のグループとし、該第1のグループに含まれるパレットのそれぞれについて抽出された画素の中から、パレットごとに選択した画素の組み合わせが前記所定の配列に従って並んでいる場合、当該組み合わせに含まれる画素を前記第1のグループの対応するパレットが写っている可能性がある候補画素として検出し、
前記候補画素に基づいて、該候補画素に対応するパレットの前記画像上での色を表す色情報及び当該パレットの前記画像上での位置を表す位置情報を求める、
ことを含むカラーチャート検出方法。 - 所定の配列に従って配置された複数のパレットを有するカラーチャートが写った画像から、前記複数のパレットのうちの少なくとも3以上の所定数のパレットのそれぞれについて、当該パレットに相当する色成分を持つ画素を抽出し、
前記所定数のパレットのうち、少なくとも3個のパレットを第1のグループとし、該第1のグループに含まれるパレットのそれぞれについて抽出された画素の中から、パレットごとに選択した画素の組み合わせが前記所定の配列に従って並んでいる場合、当該組み合わせに含まれる画素を前記第1のグループの対応するパレットが写っている可能性がある候補画素として検出し、
前記候補画素に基づいて、該候補画素に対応するパレットの前記画像上での色を表す色情報及び当該パレットの前記画像上での位置を表す位置情報を求める、
ことをコンピュータに実行させるためのカラーチャート検出用コンピュータプログラム。
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP12872913.4A EP2833636B1 (en) | 2012-03-30 | 2012-03-30 | Color chart detection device, color chart detection method and color chart detection computer program |
CN201280071928.8A CN104247410B (zh) | 2012-03-30 | 2012-03-30 | 彩色图表检测装置和彩色图表检测方法 |
PCT/JP2012/058689 WO2013145295A1 (ja) | 2012-03-30 | 2012-03-30 | カラーチャート検出装置、カラーチャート検出方法及びカラーチャート検出用コンピュータプログラム |
JP2014507256A JP5843000B2 (ja) | 2012-03-30 | 2012-03-30 | カラーチャート検出装置、カラーチャート検出方法及びカラーチャート検出用コンピュータプログラム |
US14/493,809 US9721532B2 (en) | 2012-03-30 | 2014-09-23 | Color chart detection apparatus, color chart detection method, and color chart detection computer program |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2012/058689 WO2013145295A1 (ja) | 2012-03-30 | 2012-03-30 | カラーチャート検出装置、カラーチャート検出方法及びカラーチャート検出用コンピュータプログラム |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/493,809 Continuation US9721532B2 (en) | 2012-03-30 | 2014-09-23 | Color chart detection apparatus, color chart detection method, and color chart detection computer program |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2013145295A1 true WO2013145295A1 (ja) | 2013-10-03 |
Family
ID=49258658
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2012/058689 WO2013145295A1 (ja) | 2012-03-30 | 2012-03-30 | カラーチャート検出装置、カラーチャート検出方法及びカラーチャート検出用コンピュータプログラム |
Country Status (5)
Country | Link |
---|---|
US (1) | US9721532B2 (ja) |
EP (1) | EP2833636B1 (ja) |
JP (1) | JP5843000B2 (ja) |
CN (1) | CN104247410B (ja) |
WO (1) | WO2013145295A1 (ja) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105096348A (zh) * | 2014-04-30 | 2015-11-25 | 富士通株式会社 | 检测图像中的色彩板的装置和方法 |
WO2016076165A1 (ja) * | 2014-11-14 | 2016-05-19 | コニカミノルタ株式会社 | 測色装置および測色方法 |
WO2016076163A1 (ja) * | 2014-11-14 | 2016-05-19 | コニカミノルタ株式会社 | 測色装置および測色方法 |
US9407791B2 (en) | 2014-02-06 | 2016-08-02 | Fujitsu Limited | Information processing apparatus and computer-readable storage medium storing program for interpolating an input color |
WO2016152334A1 (ja) * | 2015-03-26 | 2016-09-29 | コニカミノルタ株式会社 | 測色装置および測色方法 |
WO2016158812A1 (ja) * | 2015-04-01 | 2016-10-06 | コニカミノルタ株式会社 | 測色装置および測色方法 |
US9542758B2 (en) | 2014-07-25 | 2017-01-10 | Fujitsu Limited | Image processing apparatus and light source identification method |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016106555A1 (zh) * | 2014-12-30 | 2016-07-07 | 富士通株式会社 | 图像编码方法、装置以及图像处理设备 |
CN105828079B (zh) * | 2015-01-27 | 2020-06-16 | 同济大学 | 图像处理方法及装置 |
WO2016119667A1 (zh) * | 2015-01-27 | 2016-08-04 | 同济大学 | 图像处理方法及装置 |
CN104639924B (zh) * | 2015-03-03 | 2017-06-20 | 中山大学花都产业科技研究院 | 一种降低对设备像素依赖程度提高颜色取值精度的方法 |
KR20170045521A (ko) * | 2015-10-19 | 2017-04-27 | 삼성전자주식회사 | 디스플레이 장치, 및 그 제어방법 |
KR102206780B1 (ko) * | 2017-03-13 | 2021-01-22 | 다이요 덴끼 산교 가부시키가이샤 | 제어 장치 및 검사 장치 |
TWI671621B (zh) * | 2017-05-24 | 2019-09-11 | 仁寶電腦工業股份有限公司 | 電子裝置與主機底座 |
WO2019125448A1 (en) * | 2017-12-20 | 2019-06-27 | Google Llc | Tonal palette generation |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0670345A (ja) | 1992-08-21 | 1994-03-11 | Matsushita Electric Ind Co Ltd | カラーチャート認識装置と画像データ判定装置と光源色度推定装置と光源推定装置 |
JP2002152768A (ja) | 2000-11-10 | 2002-05-24 | Mitsubishi Electric Corp | 画像補正装置および画像補正方法 |
WO2005124302A1 (ja) * | 2004-06-17 | 2005-12-29 | Digital Fashion Ltd. | 画像処理プログラム、画像処理装置、及び画像処理方法 |
JP2010226580A (ja) | 2009-03-25 | 2010-10-07 | Denso Wave Inc | 色補正方法及び撮像システム |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001358959A (ja) * | 2000-06-15 | 2001-12-26 | Dainippon Printing Co Ltd | 画像処理システム、画像変換方法および記録媒体 |
JP2002015768A (ja) * | 2000-06-30 | 2002-01-18 | Japan Storage Battery Co Ltd | 非水電解質二次電池の製造方法 |
JP4310707B2 (ja) * | 2005-04-12 | 2009-08-12 | ノーリツ鋼機株式会社 | 階調変換較正方法及びこの方法を用いた階調変換較正モジュール |
US8073248B2 (en) * | 2007-06-08 | 2011-12-06 | Apple Inc. | Automatic detection of calibration charts in images |
KR101427649B1 (ko) * | 2007-10-23 | 2014-08-07 | 삼성전자주식회사 | 색상 분포도를 표시하는 디지털 영상 처리 장치 및 방법 |
-
2012
- 2012-03-30 EP EP12872913.4A patent/EP2833636B1/en active Active
- 2012-03-30 WO PCT/JP2012/058689 patent/WO2013145295A1/ja active Application Filing
- 2012-03-30 CN CN201280071928.8A patent/CN104247410B/zh active Active
- 2012-03-30 JP JP2014507256A patent/JP5843000B2/ja active Active
-
2014
- 2014-09-23 US US14/493,809 patent/US9721532B2/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0670345A (ja) | 1992-08-21 | 1994-03-11 | Matsushita Electric Ind Co Ltd | カラーチャート認識装置と画像データ判定装置と光源色度推定装置と光源推定装置 |
JP2002152768A (ja) | 2000-11-10 | 2002-05-24 | Mitsubishi Electric Corp | 画像補正装置および画像補正方法 |
WO2005124302A1 (ja) * | 2004-06-17 | 2005-12-29 | Digital Fashion Ltd. | 画像処理プログラム、画像処理装置、及び画像処理方法 |
JP2010226580A (ja) | 2009-03-25 | 2010-10-07 | Denso Wave Inc | 色補正方法及び撮像システム |
Non-Patent Citations (2)
Title |
---|
PRANCHALEE RATTANASAKORNCHAI ET AL.: "Compensation Method for Illumination Change by Using Color Chart", THE JOURNAL OF IMAGING SOCIETY OF JAPAND, vol. 43, no. 3, 10 June 2004 (2004-06-10), pages 142 - 147, XP008173552 * |
See also references of EP2833636A4 |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9407791B2 (en) | 2014-02-06 | 2016-08-02 | Fujitsu Limited | Information processing apparatus and computer-readable storage medium storing program for interpolating an input color |
CN105096348B (zh) * | 2014-04-30 | 2018-06-29 | 富士通株式会社 | 检测图像中的色彩板的装置和方法 |
EP2940626A3 (en) * | 2014-04-30 | 2015-12-09 | Fujitsu Limited | Apparatus and method for detecting color checker in image |
US9633449B2 (en) | 2014-04-30 | 2017-04-25 | Fujitsu Limited | Apparatus and method for detecting color checker in image |
CN105096348A (zh) * | 2014-04-30 | 2015-11-25 | 富士通株式会社 | 检测图像中的色彩板的装置和方法 |
US9542758B2 (en) | 2014-07-25 | 2017-01-10 | Fujitsu Limited | Image processing apparatus and light source identification method |
WO2016076165A1 (ja) * | 2014-11-14 | 2016-05-19 | コニカミノルタ株式会社 | 測色装置および測色方法 |
WO2016076163A1 (ja) * | 2014-11-14 | 2016-05-19 | コニカミノルタ株式会社 | 測色装置および測色方法 |
US10267683B2 (en) | 2014-11-14 | 2019-04-23 | Konica Minolta, Inc. | Colorimetry device and colorimetry method having a patch quantity comparison processing unit and a second position correction processing unit |
US10254168B2 (en) | 2014-11-14 | 2019-04-09 | Konica Minolta, Inc. | Colorimeter device and colorimetery method |
JPWO2016152334A1 (ja) * | 2015-03-26 | 2018-01-25 | コニカミノルタ株式会社 | 測色装置および測色方法 |
WO2016152334A1 (ja) * | 2015-03-26 | 2016-09-29 | コニカミノルタ株式会社 | 測色装置および測色方法 |
US10401227B2 (en) | 2015-03-26 | 2019-09-03 | Konica Minolta, Inc. | Colorimetry device and colorimetry method |
WO2016158812A1 (ja) * | 2015-04-01 | 2016-10-06 | コニカミノルタ株式会社 | 測色装置および測色方法 |
US10578491B2 (en) | 2015-04-01 | 2020-03-03 | Konica Minolta, Inc. | Colorimetry device and colorimetry method |
Also Published As
Publication number | Publication date |
---|---|
EP2833636A4 (en) | 2015-04-01 |
EP2833636A1 (en) | 2015-02-04 |
US9721532B2 (en) | 2017-08-01 |
CN104247410A (zh) | 2014-12-24 |
CN104247410B (zh) | 2016-08-24 |
JPWO2013145295A1 (ja) | 2015-08-03 |
EP2833636B1 (en) | 2017-11-08 |
US20150009226A1 (en) | 2015-01-08 |
JP5843000B2 (ja) | 2016-01-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5843000B2 (ja) | カラーチャート検出装置、カラーチャート検出方法及びカラーチャート検出用コンピュータプログラム | |
US11070749B2 (en) | Image processing method and apparatus | |
CN110493595B (zh) | 摄像头的检测方法和装置、存储介质及电子装置 | |
CN104052979A (zh) | 用于图像处理的装置和技术 | |
JP2017084117A (ja) | 表示制御方法、表示制御プログラムおよび情報処理装置 | |
CN111582155B (zh) | 活体检测方法、装置、计算机设备和存储介质 | |
CN108965646A (zh) | 图像处理装置、图像处理方法和存储介质 | |
EP2924610A2 (en) | Flesh color detection condition determining apparatus, and flesh color detection condition determining method | |
CN114066823A (zh) | 检测色块的方法及其相关产品 | |
CN111080683B (zh) | 图像处理方法、装置、存储介质及电子设备 | |
EP2541469B1 (en) | Image recognition device, image recognition method and image recognition program | |
US9412036B2 (en) | Methods and systems for object detection based on column-wise and row-wise sums of pixel values | |
JP5240305B2 (ja) | 被写体特定用プログラム、およびカメラ | |
JP7163947B2 (ja) | 投写領域の設定支援方法、設定支援システム、及びプログラム | |
CN110059529A (zh) | 模拟计量器的指针的指向的识别方法及其影像获取设备 | |
JP2020003878A (ja) | マーカおよび画像処理装置 | |
JP2011124955A (ja) | 画像処理方法及び画像処理装置 | |
JP7478628B2 (ja) | 画像処理装置、制御方法及び制御プログラム | |
JP7223198B1 (ja) | メータ読取装置、メータ読取方法、及びメータ読取プログラム | |
KR101491334B1 (ko) | 영상에서 컬러차트 검출 방법 및 장치 | |
CN109544659B (zh) | 示意图的生成方法和装置 | |
RU2547703C2 (ru) | Способ, устройство и компьютерный программный продукт для компенсации дефектов цвета глаз | |
JP2015226219A (ja) | 画像処理装置、画像処理方法、及びプログラム | |
CN116708750A (zh) | 分辨率测试方法、装置、系统、电子设备和存储介质 | |
CN114299618A (zh) | 一种手势识别方法、装置及计算机可读存储介质 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 12872913 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2014507256 Country of ref document: JP Kind code of ref document: A |
|
REEP | Request for entry into the european phase |
Ref document number: 2012872913 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2012872913 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |