Information processing device, determination method, and determination program

Abstract

An information processing device (100) is provided with: an acquisition unit (120) that acquires an XYZ value, a spectral distribution, a spectral reflectance when the spectral reflectance is a completely diffuse reflection surface, and a determination table (111a), the XYZ value being a value corresponding to a region to be recognized, which is an image region in an image obtained by capturing an object under first illumination and which is represented by an XYZ color system, and the determination table (111a) being a value corresponding to a region to be recognized, which is an image region in an image obtained by capturing an object under second illumination and which is a value represented by an XYZ color system; a determination table (111a) that shows a correspondence relationship between a color and a Lab value, which is a value in an L * a * b * color space, and a spectral distribution obtained using spectral distribution data including data of the first illumination or data similar to the data, and principal component analysis; a calculation unit (140) that uses the XYZ value, the spectral distribution, and the spectral reflectance to calculate a Lab value, which is a value corresponding to the region to be recognized in the L * a * b * color space; and a determination unit (170) that determines the color of the region to be recognized using the calculated Lab value and the determination table (111a).

Description

Technical Field

[0001] The present disclosure relates to an information processing device, a determination method, and a determination program. Background Art

[0002] There is a known technology for determining the color of an object contained in an image. In addition, the color of an object contained in an image is sometimes different from the original color due to the influence of lighting. For example, when the original color of the object is blue and the lighting is yellow, the color of the object contained in the image becomes a black color due to the influence of lighting. Therefore, color correction has been proposed (see patent document 1). The color correction device of patent document 1 calculates the color information of each pixel of the output image based on the color information of each pixel of the input image, the spectral distribution of the lighting in the restored input image, and the spectral distribution of the lighting in the output image. In the calculation of the spectral distribution of the lighting in the output image, the spectral distribution of the lighting specified as the target lighting is used. The spectral distribution of the specified lighting is calculated based on the correlated color temperature of CIE daylight.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: International Publication No. 2007 / 007788 Summary of the invention

[0006] Problem that the invention aims to solve

[0007] In the above-mentioned technology, color correction can be performed under normal lighting such as CIE daylight. However, there are various types of lighting. Therefore, in the above-mentioned technology, the original color cannot be determined under various types of lighting.

[0008] The purpose of the present disclosure is to determine the original color.

[0009] Means used to solve problems

[0010] An information processing device according to an embodiment of the present disclosure is provided. The information processing device comprises: an acquisition unit that acquires XYZ values, spectral distribution, spectral reflectance when the object is a completely diffuse reflection surface, and determination information, wherein the XYZ values ​​are values ​​corresponding to an image area, that is, an identification target area, in an image obtained by photographing the object under a first illumination, and are values ​​expressed in an XYZ colorimetric system, the spectral distribution is obtained using spectral distribution data including data of the first illumination or data similar to the data and principal component analysis, and the determination information indicates L * a * b *The value in the color space, that is, the correspondence between the Lab value and the color; a calculation unit, which uses the XYZ value, the spectral distribution and the spectral reflectivity to calculate the L * a * b * a Lab value that is a value corresponding to the recognition target area in a color space; and a determination unit that determines a color of the recognition target area using the calculated Lab value and the determination information.

[0011] Effects of the Invention

[0012] According to the present disclosure, the original color can be determined. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a diagram showing hardware included in the information processing device.

[0014] Figure 2 is a block diagram showing the functions of the information processing device.

[0015] Figure 3 This is a diagram showing an example (part 1) of a determination table.

[0016] Figure 4 : is a flowchart showing an example of color determination processing.

[0017] Figure 5 This is a diagram showing an example (part 2) of a determination table.

[0018] Figure 6 This is a diagram showing an example (part 1) of a management table.

[0019] Figure 7 This is a diagram showing an example (part 2) of a management table. DETAILED DESCRIPTION

[0020] Hereinafter, embodiments will be described with reference to the drawings. The following embodiments are merely examples, and various modifications can be made within the scope of the present disclosure.

[0021] Implementation method.

[0022] Figure 1 1 is a diagram showing hardware included in an information processing device. The information processing device 100 is a device that executes the determination method. The information processing device 100 is a PC (Personal Computer), a smartphone, a tablet terminal, a server, etc. For example, when the information processing device 100 is a server, the information processing device 100 transmits and receives data with the tablet terminal.

[0023] The information processing device 100 includes a processor 101 , a volatile storage device 102 , and a nonvolatile storage device 103 .

[0024] The processor 101 controls the entire information processing device 100. For example, the processor 101 is a CPU (Central Processing Unit), an FPGA (Field Programmable Gate Array), etc. The processor 101 may also be a multiprocessor. In addition, the information processing device 100 may also have a processing circuit.

[0025] The volatile storage device 102 is a main storage device of the information processing device 100. For example, the volatile storage device 102 is a RAM (Random Access Memory). The nonvolatile storage device 103 is an auxiliary storage device of the information processing device 100. For example, the nonvolatile storage device 103 is a HDD (Hard Disk Drive) or an SSD (Solid State Drive).

[0026] Next, the functions of the information processing device 100 will be described.

[0027] Figure 2 The information processing device 100 includes a storage unit 110 , an acquisition unit 120 , a generation unit 130 , a calculation unit 140 , a determination unit 150 , a conversion unit 160 , and a determination unit 170 .

[0028] The storage unit 110 may be realized as a storage area reserved in the volatile storage device 102 or the nonvolatile storage device 103 .

[0029] Part or all of the acquisition unit 120, the generation unit 130, the calculation unit 140, the determination unit 150, the conversion unit 160, and the determination unit 170 may also be implemented by a processing circuit. In addition, part or all of the acquisition unit 120, the generation unit 130, the calculation unit 140, the determination unit 150, the conversion unit 160, and the determination unit 170 may also be implemented as a module of a program executed by the processor 101. For example, the program executed by the processor 101 is also referred to as a determination program. For example, the determination program is recorded in a recording medium.

[0030] The information processing device 100 uses the spectral distribution P in the color determination process. E (λ). Therefore, the following is the spectral distribution P E The generation of (λ) is described below.

[0031] <Light distribution PE Generation of (λ)>

[0032] The storage unit 110 stores various information.

[0033] The acquisition unit 120 acquires the XYZ value of the reference color. The XYZ value is a value expressed in the XYZ color system. For example, the acquisition unit 120 acquires the XYZ value from the storage unit 110 or an external device. For example, the external device is a cloud server. In addition, the figure of the external device is omitted.

[0034] In addition, the acquisition unit 120 can also acquire the calculated XYZ values. In detail, the acquisition unit 120 acquires an image. In addition, the image is an image obtained by photographing an object under a first lighting. The first lighting is lighting in a factory, etc. For example, the first lighting is sodium lighting, white LED (Light Emitting Diode) lighting, etc. The acquisition unit 120 acquires RGB values ​​from an image area of ​​a reference color (for example, an image area representing a shell). In addition, the image area of ​​the reference color can also be predetermined. In the case where the camera that generates the image generates the image based on sRGB ITU-R BT.709, the calculation unit 140 uses formula (1) to calculate the XYZ values ​​based on the RGB values.

[0035] [Formula 1]

[0036]

[0037] In this way, the acquisition unit 120 can also acquire the calculated XYZ values.

[0038] The acquisition unit 120 acquires the spectral distribution data including the data of the first lighting from the storage unit 110 or the external device. In addition, the spectral distribution data may also be expressed as the data of the first lighting (i.e., the spectral distribution data of the first lighting). The spectral distribution data may also include data similar to the data of the first lighting. For example, in the case where the first lighting is sodium lighting, the spectral distribution data may also include data similar to the data of the sodium lighting. In addition, the spectral distribution data may also include data of multiple lightings. For example, the spectral distribution data includes data of multiple lightings such as sodium lighting and white LED lighting installed in the factory. In addition, for example, the external device is a spectroradiometer or the like.

[0039] The generating unit 130 generates an equation representing the top three principal components using the spectral distribution data and principal component analysis. This equation is represented by equation (2). 1 、a 2 and a 3 are parameters. In addition, the three parameters are unclear values. As described below, the three parameters are calculated. 1 , P 2 and P3 These are the top three principal components.

[0040] [Formula 2]

[0041] P(λ)=a 1 *P 1 +a 2 *P 2 +a 3 *P 3 …(2)

[0042] In this way, P(λ) is obtained by applying principal component analysis to the spectral distribution data. Here, P(λ) is called a spectral distribution model. The generator 130 may generate the spectral distribution model P(λ) using a value obtained by dividing the spectral distribution data including data of one or more illuminations by an energy average value and principal component analysis.

[0043] The acquisition unit 120 acquires the spectral reflectance p(λ) of a portion of the reference color (eg, a portion of the housing). For example, the acquisition unit 120 acquires the spectral reflectance p(λ) from the storage unit 110 or an external device.

[0044] The calculation unit 140 uses the XYZ value, the spectral distribution model P(λ), and the spectral reflectance ρ(λ) acquired by the acquisition unit 120 to calculate the parameter a 1 、a 2 and a 3 Specifically, the calculation unit 140 uses equation (3) to calculate the parameter a 1 、a 2 and a 3 Perform calculations.

[0045] [Formula 3]

[0046]

[0047] K is a constant. The overlined x(λ), y(λ), and z(λ) are isochromatic functions.

[0048] Since there are three equations, the calculation unit 140 can calculate the three unknown parameters. The calculation unit 140 calculates the parameter a 1 、a 2 and a 3 Substitute into the spectral distribution model P(λ). Thus, the spectral distribution model P(λ) with three parameters becoming clear is obtained. The spectral distribution model P(λ) with three parameters becoming clear is called the spectral distribution P E (λ). The calculation unit 140 may also convert the spectral distribution P E (λ) is stored in the storage unit 110 or an external device.

[0049] Next, the color determination process will be described.

[0050] <Color determination processing>

[0051] The acquisition unit 120 acquires an image. For example, the acquisition unit 120 acquires the image from a camera that generates the image. The image is obtained by capturing an object under the first illumination.

[0052] The determination unit 150 determines the recognition target area from the image. For example, the determination unit 150 determines a predetermined area as the recognition target area. In addition, for example, the determination unit 150 determines a marked area in the image as the recognition target area. The determination unit 150 may also determine a plurality of recognition target areas. In addition, the recognition target area is an image area.

[0053] The calculation unit 140 calculates the value corresponding to the identification target area, that is, the XYZ value, based on the identification target area. In detail, the calculation unit 140 calculates the XYZ value based on the RGB value of the identification target area. For example, the calculation unit 140 calculates the XYZ value using formula (1). In addition, the XYZ value is a value expressed in the XYZ color system.

[0054] The acquisition unit 120 acquires the calculated XYZ value. Here, the XYZ value may be calculated by an external device. When the external device calculates the XYZ value, the acquisition unit 120 acquires the XYZ value from the external device.

[0055] The acquisition unit 120 acquires the spectral distribution P from the storage unit 110 or an external device. E (λ).

[0056] The acquisition unit 120 acquires the spectral reflectance ρ1 (λ) when the surface is a complete diffuse reflection surface from the storage unit 110 or an external device.

[0057] The calculation unit 140 uses the XYZ value and the spectral distribution P E (λ) and spectral reflectance ρ1(λ), ​​calculate L * a * b * The value corresponding to the identification target area in the color space is the Lab value. Specifically, the calculation unit 140 calculates the Lab value using equation (4). In addition, the Lab value is also called L * a * b * value.

[0058] [Formula 4]

[0059]

[0060] Xn, Yn and Zn are expressed using formula (5).

[0061] [Formula 5]

[0062]

[0063] The conversion unit 160 converts the calculated Lab value into L * C * The value corresponding to the identification target area in the h color space is the LCh value. Specifically, the conversion unit 160 uses equation (6) to convert the Lab value into the LCh value. In addition, the LCh value is also called the L * C * h value.

[0064] [Formula 6]

[0065]

[0066] The acquisition unit 120 acquires the determination table from the storage unit 110 or an external device. An example of the determination table is shown below.

[0067] Figure 3 1 is a diagram showing an example of a determination table (part 1). For example, a determination table 111 is stored in the storage unit 110. The determination table 111 is also referred to as determination information. The determination table 111 shows L * C * The value in the h color space is the corresponding relationship between the LCh value and the color.

[0068] The determination unit 170 determines the color of the recognition target area using the LCh value obtained by conversion and the determination table 111. * Value, C * The color of the recognition target area is determined by using the value, h value and the determination table 111.

[0069] Next, the color determination process executed by the information processing apparatus 100 will be described using a flowchart.

[0070] Figure 4 : is a flowchart showing an example of color determination processing.

[0071] (Step S11 ) The acquisition unit 120 acquires an image.

[0072] (Step S12 ) The identification unit 150 identifies the identification target region from the image.

[0073] (Step S13 ) The calculation unit 140 calculates XYZ values ​​based on the recognition target area.

[0074] (Step S14) The acquisition unit 120 acquires the spectral distribution P from the storage unit 110. E (λ).

[0075] (Step S15 ) The acquisition unit 120 acquires the spectral reflectance ρ1 (λ) from the storage unit 110 .

[0076] (Step S16) The calculation unit 140 uses the XYZ value and the spectral distribution P E (λ) and spectral reflectance ρ1(λ), ​​calculate the Lab value.

[0077] (Step S17) The conversion unit 160 converts the Lab value into an LCh value.

[0078] (Step S18 ) The determination unit 170 determines the color of the recognition target area using the LCh value and the determination table 111 .

[0079] According to the embodiment, the information processing device 100 uses the spectral distribution P E (λ), the influence of lighting can be eliminated. Therefore, the information processing device 100 can determine the original color. In addition, one or more spectral distribution P is generated based on the spectral distribution data of each type of lighting. E (λ), the information processing device 100 uses the spectral distribution P E (λ), it is possible to eliminate the influence of various types of lighting and determine the original color.

[0080] In the above description, the case where the color of the recognition target area is determined using the LCh value and the determination table 111 is described. The determination unit 170 may determine the color of the recognition target area using the Lab value and the determination table. An example of the determination table is shown below.

[0081] Figure 5 1 is a diagram showing an example of a determination table (part 2). For example, a determination table 111a is stored in the storage unit 110. The determination table 111a is also referred to as determination information. The determination table 111a shows L * a * b * The values ​​in the color space are the corresponding relationship between Lab values ​​and colors.

[0082] The acquisition unit 120 acquires the determination table 111a from the storage unit 110 or an external device. Then, the determination unit 170 uses the calculated Lab value and the determination table 111a to determine the color of the recognition target area. * value, a * Value, b * The information processing device 100 determines the color of the recognition target area by using the Lab value and the determination table 111a. The information processing device 100 determines the color by using the Lab value, thereby not performing the process of converting the Lab value into the LCh value. Therefore, the information processing device 100 can reduce the processing load of the information processing device 100.

[0083] Here, for example, the determination table 111 and the determination table 111a are generated by the user. LCh values ​​are easier to handle than Lab values. Therefore, it is easier for the user to generate the determination table 111 than to generate the determination table 111a. Therefore, when the information processing device 100 uses the LCh value to determine the color, the generation burden of the user is reduced. In addition, the determination table 111 and the determination table 111a can also be automatically updated. In addition, the determination table 111 and the determination table 111a can also be updated by the user.

[0084] Alternatively, the acquisition unit 120 may acquire the management table from the storage unit 110 or an external device. An example of the management table is shown below.

[0085] Figure 6 1 is a diagram showing an example of a management table (part 1). For example, a management table 112 is stored in the storage unit 110. The management table 112 is also called management information. The management table 112 shows the correspondence between positions and spectral distributions. The management table 112 can also be expressed as showing the correspondence between multiple positions and multiple spectral distributions.

[0086] The acquisition unit 120 acquires the imaging position of the object. The imaging position is the position when the object is imaged. For example, the acquisition unit 120 acquires the imaging position from a camera. The acquisition unit 120 acquires the spectral distribution corresponding to the imaging position based on the management table 112.

[0087] For example, sodium lighting is installed at location A in the factory. A user uses a camera to shoot an object under the sodium lighting. The acquisition unit 120 acquires the shooting position of the object from the camera. The shooting position is position L1. The acquisition unit 120 acquires the spectral distribution P corresponding to the shooting position based on the management table 112. E 1(λ). Spectral distribution P E 1(λ) is a spectral distribution obtained by using spectral distribution data including data of sodium illumination or data similar to the data and principal component analysis.

[0088] For example, a white LED lighting is installed at a location B in a factory. A user uses a camera to shoot an object under the white LED lighting. The acquisition unit 120 acquires the shooting position of the object from the camera. The shooting position is position L2. The acquisition unit 120 acquires the spectral distribution P corresponding to the shooting position based on the management table 112. E 2(λ). Spectral distribution P E 2(λ) is a spectral distribution obtained by using spectral distribution data including data of white LED illumination or data similar to the data and principal component analysis.

[0089] In this way, the information processing device 100 obtains different spectral distributions according to the imaging position. Then, the information processing device 100 can determine the color of the recognition target area using the spectral distribution corresponding to the imaging position.

[0090] Furthermore, the acquisition unit 120 may acquire a different management table from the storage unit 110 or an external device. An example of the management table is shown below.

[0091] Figure 7 1 is a diagram showing an example of a management table (part 2). For example, a management table 112a is stored in the storage unit 110. The management table 112a is also referred to as management information. The management table 112a shows the correspondence between time and spectral distribution. The management table 112a can also be expressed as showing the correspondence between a plurality of times and a plurality of spectral distributions.

[0092] The acquisition unit 120 acquires the imaging time of the object. The imaging time is the time when the object is imaged. For example, the acquisition unit 120 acquires the imaging time from a camera. The acquisition unit 120 acquires the spectral distribution corresponding to the imaging time based on the management table 112a.

[0093] Here, even when an object is photographed at the same position, the lighting may change with time. For example, at time T1, the sodium lighting is turned on. At time T2, the white LED lighting is turned on. When the imaging time is within time T1, the acquisition unit 120 acquires the spectral distribution P E 1(λ). In addition, when the imaging time is within the time T2, the acquisition unit 120 acquires the spectral distribution P E 2(λ).

[0094] In this way, the information processing device 100 obtains different spectral distributions according to the imaging time. Then, the information processing device 100 can determine the color of the recognition target area using the spectral distribution corresponding to the imaging time.

[0095] Description of Reference Numerals

[0096] 100 information processing device, 101 processor, 102 volatile storage device, 103 non-volatile storage device, 110 storage unit, 111 determination table, 111a determination table, 112 management table, 112a management table, 120 acquisition unit, 130 generation unit, 140 calculation unit, 150 determination unit, 160 conversion unit, 170 determination unit.

Claims

1. An information processing device, wherein: The information processing device comprises: an acquisition unit, which acquires an XYZ value, a spectral distribution, a spectral reflectance when the surface is a completely diffuse reflection surface, and determination information, wherein the XYZ value is a value corresponding to an identification target area and is expressed in an XYZ colorimetric system, wherein the identification target area is an image area in an image obtained by photographing an object under a first illumination, the spectral distribution is obtained using spectral distribution data including data of the first illumination or data similar to the data and principal component analysis, and the determination information indicates L * a * b * The values ​​in the color space, i.e., the correspondence between the Lab values ​​and the colors; a calculation unit, which calculates the L using the XYZ value, the spectral distribution and the spectral reflectance * a * b * A Lab value in a color space that is a value corresponding to the recognition target area; as well as A determination unit determines a color of the recognition target area using the calculated Lab value and the determination information.

2. The information processing device according to claim 1, wherein: The information processing device further includes a conversion unit. The determination information shows that L * C * h The value in the color space is the corresponding relationship between the LCh value and the color. The conversion unit converts the calculated Lab value into the L * C * An LCh value in the h color space that is a value corresponding to the identification target area, The determination unit determines the color of the recognition target area using the LCh value obtained by conversion and the determination information.

3. The information processing device according to claim 1 or 2, wherein: The acquisition unit acquires an imaging position of the object and management information indicating a correspondence relationship between the position and the spectral distribution, and acquires the spectral distribution corresponding to the imaging position based on the management information.

4. The information processing device according to claim 1 or 2, wherein: The acquisition unit acquires the imaging time of the object and management information indicating the correspondence relationship between time and the spectral distribution, and acquires the spectral distribution corresponding to the imaging time based on the management information.

5. A determination method, wherein: The information processing device performs the following processing: The XYZ value, the spectral distribution, the spectral reflectance when the surface is a completely diffuse reflection surface, and the judgment information are obtained, wherein the XYZ value is a value corresponding to the recognition target area and is expressed in an XYZ colorimetric system, wherein the recognition target area is an image area in an image obtained by photographing the object under the first illumination, the spectral distribution is obtained using spectral distribution data including data of the first illumination or data similar to the data and principal component analysis, and the judgment information shows L * a * b * The value in the color space is the corresponding relationship between the Lab value and the color. Using the XYZ value, the spectral distribution and the spectral reflectivity, calculate the L * a * b * A Lab value in a color space that is a value corresponding to the recognition target area, The color of the recognition target area is determined using the calculated Lab value and the determination information.

6. A determination procedure, The determination program causes the information processing device to execute the following processing: The XYZ value, the spectral distribution, the spectral reflectance when the surface is a completely diffuse reflection surface, and the judgment information are obtained, wherein the XYZ value is a value corresponding to the recognition target area and is expressed in an XYZ colorimetric system, wherein the recognition target area is an image area in an image obtained by photographing the object under the first illumination, the spectral distribution is obtained using spectral distribution data including data of the first illumination or data similar to the data and principal component analysis, and the judgment information shows L * a * b * The value in the color space is the corresponding relationship between the Lab value and the color. Using the XYZ value, the spectral distribution and the spectral reflectivity, calculate the L * a * b * A Lab value in a color space that is a value corresponding to the recognition target area, The color of the recognition target area is determined using the calculated Lab value and the determination information.

Images