JP2024064235A - Concentration estimation method, concentration estimation program, and concentration estimation system - Google Patents

Abstract

[Problem] To provide a concentration estimation method, a concentration estimation program, and a concentration estimation system that can improve the accuracy of concentration estimation. [Solution] The concentration estimation method according to the present invention includes the steps of acquiring image data of a measurement object, acquiring first color information about the color of each of a plurality of color samples defined for each concentration, acquiring second color information about the color of the measurement object from the image data, estimating the concentration of the measurement object by comparing each of the first color information and the second color information using a plurality of estimation methods, and adopting the concentration estimated by the estimation method suitable for the concentration from among the concentrations estimated by the plurality of estimation methods as the estimation result. [Selected Figure] Figure 9

Description

The present invention relates to a concentration estimation method, a concentration estimation program, and a concentration estimation system.

The Water Supply Act requires that the chlorine concentration of tap water be maintained at 0.1 mg/L or more. Therefore, the chlorine concentration of tap water must be checked at various facilities. In order to easily check the chlorine concentration, Non-Patent Document 1 proposes an application that adds a chemical to tap water obtained, photographs the colored water, and estimates the chlorine concentration by comparing the color with a color sample.

Kyoritsu Rikagaku Kenkyusho Co., Ltd., "Smart Patch Test", [online], [Retrieved August 18, 2022], https://kyoritsu-lab.co.jp/smartpacktest

However, the estimated chlorine concentration is related to the operation plan of the water purification plant, so the estimation of chlorine concentration requires accuracy. For this reason, a method for estimating chlorine concentration with high accuracy has been demanded. This problem can occur not only with chlorine concentration, but also in all cases where the concentration is estimated for a measurement object where there is a correlation between color and concentration. The present invention has been made to solve this problem, and aims to provide a concentration estimation method, a concentration estimation program, and a concentration estimation system that can improve the accuracy of concentration estimation.

The concentration estimation method according to the present invention includes the steps of acquiring image data of a measurement object, acquiring first color information of the color of each of a plurality of color samples defined for each concentration, acquiring second color information of the color of the measurement object from the image data, estimating the concentration of the measurement object by comparing each of the first color information and the second color information using a plurality of estimation methods, and adopting the concentration estimated by the estimation method suitable for the concentration from among the concentrations estimated by the plurality of estimation methods as the estimation result.

The concentration estimation program of the present invention causes a computer to execute the steps of acquiring first color information about the color of each of a plurality of color samples defined for each concentration, acquiring second color information about the color of the object to be measured, estimating the concentration of the object to be measured by comparing each of the first color information and the second color information using a plurality of estimation methods, and adopting, as an estimation result, the concentration obtained by the estimation method appropriate for the concentration from among the concentrations estimated by the plurality of estimation methods.

The concentration estimation system according to the present invention includes a first color information acquisition unit that acquires a plurality of first color information related to the color of each of a plurality of color samples defined for each concentration, a second color information acquisition unit that acquires second color information related to the color of the object to be measured, a concentration estimation unit that estimates the concentration of the object to be measured by comparing each of the first color information and the second color information using a plurality of estimation methods, and an estimation result calculation unit that adopts, as an estimation result, the concentration estimated by the estimation method suitable for the concentration from among the concentrations estimated by the plurality of estimation methods.

The present invention can improve the accuracy of concentration estimation.

1 is a schematic diagram showing an embodiment of a concentration estimation system according to the present invention. FIG. 2 is a plan view showing an example of a mount. FIG. 2 is a block diagram showing a hardware configuration of a mobile terminal. FIG. 2 is a block diagram showing a hardware configuration of a server. FIG. 2 is a block diagram showing the software configuration of the mobile terminal. FIG. 2 is a block diagram showing a software configuration of a server. 1 is a graph showing the relationship between chlorine concentration and color difference. FIG. 13 is a diagram illustrating fitting of the relationship between chlorine concentration and color difference calculated using Euclidean distance. FIG. 13 is a diagram illustrating fitting of the relationship between chlorine concentration and color difference calculated using CIEDE2000. 10 is a flowchart showing a process for estimating the chlorine concentration of water.

Below, an embodiment in which the concentration estimation system according to the present invention is applied to a system for estimating the chlorine concentration in water will be described with reference to the drawings. The estimation system according to this embodiment is a system that estimates the chlorine concentration from the color of water obtained in various facilities such as homes, public facilities, and water purification plants.

<1. System Overview>
FIG. 1 is a schematic diagram of a chlorine concentration estimation system according to this embodiment. As shown in FIG. 1, the chlorine concentration estimation system according to this embodiment includes a mobile terminal 1 and a server 2 connected to the mobile terminal 1 via a line such as the Internet. In addition, this estimation system uses a test kit 3 as shown in FIG. 2. The test kit 3 includes a rectangular mount 31 and a container 32 for containing water to be measured. Seven rectangular color samples 311 to 317 are drawn on the upper part of the mount 31. Each color sample 311 to 317 is colored according to the chlorine concentration, and the higher the chlorine concentration, the darker the color of the color sample. Note that the higher the chlorine concentration, the darker the red the water becomes, but here it is represented by gray. However, the color of the color sample according to this embodiment is an example, and may be a different color, as long as at least the color of each color sample is different. In this embodiment, the chlorine concentration confirmed in advance is written above the seven color samples 311 to 317 arranged from left to right on the mount 31. Specifically, the chlorine concentrations of the color samples 311 to 317 are shown as 0.00 mg/L, 0.10 mg/L, 0.20 mg/L, 0.40 mg/L, 1.00 mg/L, 2.00 mg/L, and 5.00 mg/L.

In addition, a frame 34 is provided at the bottom of the mount 31 in which the container 32 to be measured as described above can be placed. The container 32 is made of a transparent resin material or the like, and can be sealed after water obtained with a syringe or the like is injected into the container 32. At this time, a chemical such as a DPD reagent is added to the water to color it. Since the container 32 is transparent, the color of the water contained therein can be seen from outside the container 32. Then, the container 32 with the water injected is placed in the frame 34, and then an image is taken as described below.

After placing the container 32 containing the sealed water on the mount 31 in this way, the user photographs the mount 31 with the camera of the mobile terminal 1. The mobile terminal 1 transmits the image data acquired by photographing to the server 2, and the server 2 estimates the chlorine concentration of the water. The estimated chlorine concentration is transmitted to the mobile terminal 1 and displayed. The mobile terminal 1 and server 2 according to this embodiment will be described in detail below.

2. Hardware configuration of mobile terminal
Fig. 3 is a block diagram showing the hardware configuration of a mobile terminal. As shown in Fig. 3, the mobile terminal 1 is a computer in which a control unit 11, a storage unit 12, a display unit 13, an input unit 14, an imaging unit 15, and a communication interface 16 are electrically connected, and may be configured as, for example, a smartphone, a tablet computer, or the like. In Fig. 3, the communication interface 17 is described as "communication I/F".

The control unit 11 includes a CPU, RAM, ROM, etc., and is configured to execute various information processing based on programs and data. The storage unit 12 is configured, for example, with an auxiliary storage device such as an HDD or SSD, and stores an input/output program 121, image data 122, and various data for driving the mobile terminal 1. The input/output program 121 is a program for acquiring image data 122 of the mount by photographing the mount 31 described above. The input/output program 121 is also a program for transmitting the acquired image data 122 to the server 2, and for receiving the water concentration estimated by the server 2 and displaying this on the display unit of the mobile terminal 1. The control unit 11 is configured to execute each process described below by interpreting and executing this input/output program 121.

The image data 122 is data that shows the entire photographed mount 31. In other words, this image data 122 is data that includes an image of the mount 31, images of the color samples 311 to 317 printed on the mount 31, and an image of the color of the water contained in the container 32.

The display unit 13 is, for example, a display, and is used to display input, output, and the like. The display may be a known liquid crystal display or the like. The input unit 14 is, for example, a keyboard, and is used to perform the above-mentioned input. A touch panel display that serves both the display unit 13 and the input unit 14 may also be used. In the following, as an example, input via the input unit 14 is performed by touch input. The imaging unit 15 includes a camera for photographing the mount 31.

The communication interface 16 is, for example, a wired LAN (Local Area Network) module, a wireless LAN module, etc., and is an interface for performing wired or wireless communication. In other words, the communication interface 17 is an example of a communication unit configured to communicate with the server 2 or other devices.

The specific hardware configuration of the mobile terminal 1 may include omitted, replaced, or added components as appropriate depending on the embodiment. For example, the control unit 11 may include multiple processors. The control unit 11 may be configured by an FPGA. The storage unit 12 may be configured by RAM and ROM included in the control unit 11. The mobile terminal 1 may be a mobile terminal dedicated to this system, or may be used by installing the above-mentioned input/output program on a general-purpose smartphone or the like.

<3. Server hardware configuration>
Fig. 4 shows an example of a hardware configuration of the server 2 according to this embodiment. The server 2 is a computer in which a control unit 21, a storage unit 22, an external interface 23, and a communication interface 24 are electrically connected, and may be configured, for example, as a general-purpose personal computer, a dedicated computer, or a tablet computer. The server 2 may also be configured with a plurality of computers. In Fig. 4, the external interface 23 and the communication interface 24 are described as "external I/F" and "communication I/F".

The control unit 21 includes a CPU, RAM, ROM, etc., and is configured to execute various information processing based on programs and data. The storage unit 22 is configured, for example, with an auxiliary storage device such as an HDD or SSD, and stores an estimation program 221, estimation result data 222, and various data for driving the server 2. In addition, data such as image data 122 transmitted from the mobile terminal 1 is also stored. The estimation program 221 is a program for estimating the chlorine concentration of water from the image data 122 transmitted from the mobile terminal 1.

The estimation result data 222 is the chlorine concentration estimated by the estimation program 221, and also includes chlorine concentrations estimated in the past.

The external interface 23 is an interface for connecting to an external device, and is configured appropriately according to the external device to be connected. In this embodiment, the external interface 23 is connected to the display device 4 and the input device 5. The display device 4 is, for example, a display, and is used to display the above-mentioned input, output, etc. The display is not particularly limited, and a known liquid crystal display or the like can be used. The input device 5 is, for example, a keyboard, a mouse, etc., and is used to perform the above-mentioned input. In addition, various external devices can be connected to the external interface 23 as appropriate. For example, a touch panel display that also serves as the display device 4 and the input device 5 can be used.

The communication interface 24 is, for example, a wired LAN (Local Area Network) module, a wireless LAN module, etc., and is an interface for performing wired or wireless communication. In other words, the communication interface 24 is an example of a communication unit configured to communicate with the mobile terminal 1 or other devices.

The specific hardware configuration of the server 2 may include omissions, substitutions, and additions of components as appropriate depending on the embodiment. For example, the control unit 21 may include multiple processors. The control unit 21 may also be configured with an FPGA. The storage unit 22 may be configured with RAM and ROM included in the control unit 21.

4. Software configuration of mobile terminal
5 shows an example of the software configuration of the mobile terminal according to this embodiment. The following process is performed in the mobile terminal 1. That is, when the control unit 11 of the mobile terminal 1 loads the input/output program 121 stored in the storage unit 12 into the RAM, the control unit 11 interprets and executes the input/output program 121 by the CPU, and functions as a screen control unit 111, a data acquisition unit 112, and a transmission/reception unit 113 as shown in FIG.

The screen control unit 111 controls the screen displayed on the display unit 13. For example, as described below, it performs processing such as displaying a screen for photographing the mount 31. The data acquisition unit 112 starts the imaging unit 15 and displays an image captured by the camera of the imaging unit 15 on the display unit 13. Then, the mount 31 is photographed by a user's operation and image data 122 is acquired. The acquired image data 122 is stored in the memory unit 12 or the RAM of the control unit 11. The transmission/reception unit 113 transmits the acquired image data 122 to the server 2. Furthermore, when the transmission/reception unit 113 acquires the estimation result data 223 from the server 2, the screen control unit 111 displays an output screen 43 that displays the estimation result on the display unit 13.

5. Server software configuration
Fig. 6 shows an example of the software configuration of the server according to this embodiment. The following processing is performed in the server 2. That is, when the control unit 21 of the server 2 loads the estimation program 221 stored in the storage unit 22 into the RAM, the control unit 21 interprets and executes the estimation program 221 by the CPU, and functions as a transmission/reception unit 211, a first color information acquisition unit 212, a second color information acquisition unit 213, a concentration estimation unit 214, and an estimation result calculation unit 215 as shown in Fig. 6.

The transmitting/receiving unit 211 receives image data 122 from the mobile terminal 1 and transmits estimation result data 223 to the mobile terminal 1. The first color information acquiring unit 212 extracts the color of each color sample 311-317 from the received image data 122 and acquires color information (first color information) of each color sample. There are various methods for acquiring color information, and the method is not particularly limited. An example is described below. First, histogram equalization is performed to darken the color of each color sample 311-317. Next, red is extracted from the darkened color. For example, in the HSV color space, the color part in the range of H: 0-108, S: 0-255, V: 0-255 is extracted as the area of the color sample 311-317. However, this example is an example in which the color sample 311-317 is red, and in the case of a color other than red, another numerical range of the HSV color space is applied. Alternatively, a color space other than the HSV color space can be used.

Next, a labeling process is performed to assign label numbers to the color samples 311-317 to identify each color sample and its chlorine concentration, and the RGB pixel values of each color sample 311-317 are obtained. Specifically, for example, the X coordinates of the upper left and upper right corners of the leftmost color sample 311, the average Y coordinate of the top and bottom sides, and the average distance between the centers of gravity of the color samples are calculated, and based on this, the coordinates of the rectangular areas of each color sample 311-317 are identified. Next, a specific area within the area of each color sample (for example, a square area that is about 60% of the width of each color sample) is trimmed, and the median value of the pixel group within that area (for example, a 60 pixel square) is calculated as color information. In this way, the RGB pixel values of each color sample 311-317 are obtained and associated with the chlorine concentration written on the mount 31.

Meanwhile, the second color information acquisition unit 213 extracts an image of the water in the container 32 included in the image data 122, and calculates color information of the water (second color information) by known image processing. The water color information in this embodiment is the RGB pixel value, the same as the color information of each color sample.

At this time, there are various methods for the second color information acquisition unit 213 to calculate the color information, but one example is shown below. First, the image data 122 is converted to grayscale to reduce unevenness. Next, a binarization process is performed on the image data 122, and the frame 34 is turned white to obtain its outline. Next, the area inside the container 32 that is within the outline is limited, and the color inside that area is extracted as an image of water. For example, the median R is calculated from all pixels contained in the image of water, and pixels having a pixel value equal to or greater than this median R are extracted. Then, from among the extracted pixels, a group of pixels with a median R (for example, an area with one side of 60 pixels) is identified, and the average RGB value of that group of pixels is calculated as color information.

The concentration estimation unit 214 first calculates the color difference between the color information of each color sample acquired by the first color information acquisition unit 212 and the color information of the water calculated by the second color information acquisition unit 213. A number of methods are used to calculate this color difference. In this embodiment, as an example, the well-known methods Euclidean distance and CIEDE2000 are used.

The Euclidean distance is calculated by the following formula: In this formula, α _r , α _g , and α _b are the RGB pixel values of the color sample, respectively, and β _r , β _g , and β _b are the RGB pixel values of the water color, respectively.

On the other hand, CIEDE2000 is calculated by the following formula:

When the color difference is calculated by the above two methods, the following color difference data is obtained.

If the values in Table 1 are graphed, they will look like Figure 7. Here, the chlorine concentration that results in the smallest color difference is considered to be the estimated concentration, but to further improve the accuracy of the estimation, the following process is performed. That is, in the graph of Figure 7, three chlorine concentrations/color differences are selected with the chlorine concentration with the smallest color difference as the median (the three points enclosed in a frame in Figure 7), and fitting is performed to draw a quadratic function graph using these three points. Then, the chlorine concentration corresponding to the smallest color difference in the graph obtained by fitting is obtained as the estimated value. Note that the fitting is not limited to using a quadratic function, and a cubic function can also be used depending on the number of points used. Furthermore, the number of points used in fitting is not particularly limited.

Figure 8 shows an example of fitting three points obtained using Euclidean distance, and Figure 12 shows an example of fitting three points obtained using CIEDE2000. For example, as shown in Figure 8, the color difference calculated using Euclidean distance is smallest when the chlorine concentration is 1.00 mg/L, so this is used as the median and the two points before and after it, i.e., 0.40 mg/L and 2.00 mg/L, are adopted, and fitting using a quadratic function is performed using a total of three points. The color sample concentration at which the color difference is smallest in the quadratic function equation thus obtained is taken as the estimated value. In this example, the estimated value is 1.28.

On the other hand, as shown in Figure 9, the color difference calculated by CIEDE2000 is a chlorine concentration of 1.00 mg/L, so this is used as the median and the two points before and after it, i.e., 0.40 mg/L and 2.00 mg/L, are used, for a total of three points to perform fitting using a quadratic function. The color sample concentration that minimizes the color difference in the quadratic function thus obtained is taken as the estimated value. In this example, the estimated value is 1.16.

The inventors have studied these two methods and have obtained the following findings. The inventors have estimated the chlorine concentration as described above for a number of samples whose chlorine concentration and color are known, using Euclidean distance and CIEDE2000. As a result, the following evaluations have been obtained.

In Table 2, A indicates that an appropriate evaluation was obtained that was suitable for practical use, B indicates that an evaluation was obtained that was generally suitable for practical use, and C indicates that an evaluation was obtained that was inappropriate and unusable for practical use.

The Water Supply Act requires that the chlorine concentration of water be maintained at 0.1 mg/L or more. According to Table 2 above, for example, when CIEDE2000 is used, the estimated value is 0.00 g/mL even though the true concentration is 0.15 mg/L. Therefore, based on this estimated value, the chlorine concentration needs to be increased, and unnecessary operation and management work will be performed at the water purification plant. On the other hand, when Euclidean distance is used, when the true concentration is 0.15 mg/L, the estimated value is 0.22 mg/L, which exceeds 0.1 mg/L, so based on this estimated value, operation management to adjust the chlorine concentration is not necessary. Therefore, it is more appropriate to adopt Euclidean distance in order to perform correct operation management based on the standard value of 0.1 mg/L.

Therefore, at least an estimate rated C cannot be used in practice because it estimates the true concentration to be 0 even though it is greater than 0, but for A and B, the administrator can decide to adopt either estimate as appropriate based on the management policy. For example, A is a close match to the true concentration, but B is more different from the known concentration than A. However, the inventor has confirmed that even an estimate of B does not pose a problem in practice.

On the other hand, in the high concentration range, for example 0.20 to 0.60 mg/L, CIEDE2000 provides estimates that are closer to the true concentration.

Based on the above results, the inventors decided to use 0.15 mg/L as a reference value, and when a concentration equal to or less than this reference value is calculated as an estimated value, to adopt the estimated value calculated using Euclidean distance, and when a concentration equal to or more than this reference value is calculated as an estimated value, to adopt the estimated value calculated using CIEDE2000. Therefore, in this embodiment, the estimation method using Euclidean distance (first estimation method) is considered to be suitable for estimating low concentration ranges, and the estimation method using CIEDE2000 (second estimation method) is considered to be suitable for estimating high concentration ranges.

Note that the standard value of 0.15 mg/L is just an example, and other standard values can also be used.

As described above, the estimated values obtained by fitting (1.28 mg/L, 1.16 mg/L) are both greater than the reference value of 0.15 mg/L, so the estimated value calculated by CIEDE2000 is adopted. That is, in this embodiment, the chlorine concentration of the water is set to 1.16 mg/L as the estimated result. This chlorine concentration is stored in the memory unit 22 as the estimated result data 224.

Once the chlorine concentration of the water is thus obtained as an estimated result, the transceiver unit 211 transmits this together with the past history to the mobile terminal 1.

<6. Estimation of Water Chlorine Concentration>
Next, the process of estimating the concentration of water will be described with reference to the flowchart of FIG.

First, the water to be estimated is obtained using a syringe or the like and injected into the container 32. Next, this container 32 is placed on the mount 31. Next, an input/output program is started on the mobile terminal, and a password is entered into the login screen 41 of the mobile terminal 1. This causes the photographing screen 42 to be displayed on the display unit 13 of the mobile terminal 1. Next, the mobile terminal 1 photographs the mount 31, and the user answers the questions displayed on the photographing screen 42. This causes image data 122 to be acquired (step S1). When the user presses the upload button, the transmission/reception unit 113 of the mobile terminal 1 transmits the acquired image data 122 and the answers to the questions to the server 2 (step S2).

In the server 2 that has received the image data 122, color information of each color sample is obtained from the image data 122, and color information of the water is calculated (step S3). Next, the color difference is calculated from the obtained color information using Euclidean distance and CIEDE2000 (step S4). Next, the above-mentioned three points are selected from the relational equation between the obtained color difference and the chlorine concentration, and fitting is performed. Then, from the obtained graph, the concentration of the color sample that minimizes the color difference is obtained as an estimate (step S5).

Then, the estimated value obtained using Euclidean distance and CIEDE2000 is compared with the above-mentioned reference value of 0.15 mg/L, and if both estimated values are lower than the reference value, the estimated value calculated using Euclidean distance is adopted as the estimated result, and if both estimated values are higher than the reference value, the estimated value calculated using CIEDE2000 is adopted as the estimated result (step S6).

Then, the server 2 transmits the obtained estimation result together with the past history to the mobile terminal 1 (step S7). The mobile terminal 1 displays the obtained estimation result on the screen of the display unit 13 (step S8).

<7. Features>
As described above, according to this embodiment, the following effects can be obtained.
(1) Since two methods for calculating color difference are used, an estimated value calculated by an appropriate method can be adopted according to the calculated estimated value. Therefore, the accuracy of chlorine concentration estimation can be improved. As described above, in the estimation using CIEDE2000, although the error is small, the estimated value tends to be calculated low in the low concentration range. Therefore, even if the true chlorine concentration is 0.1 mg/L or more as specified by the Water Supply Act, there is a risk that an estimated value smaller than this is calculated. This may lead to an operation that erroneously increases the amount of chlorine, which is a safety issue.

On the other hand, in estimation using Euclidean distance, the color samples in high density areas are coarse, so there is a problem that the accuracy is low in high density areas and estimation errors are likely to occur. Therefore, as in this embodiment, by combining two methods with their own characteristics for low and high density areas, it is possible to obtain estimation results that are both safe and accurate.

(2) In each method, after calculating the color difference, fitting is performed using multiple points with smaller color differences, so that the chlorine concentration at which the color difference is minimized can be calculated more accurately.

(3) Because the processing for concentration estimation is performed by the server 2, not the mobile terminal 1, it is possible to speed up the calculation of the estimated value even if the processing power of the mobile terminal 1 is low.

8. Modifications
Although one embodiment of the present invention has been described above, the present invention is not limited to the above embodiment, and various modifications are possible without departing from the spirit of the present invention. In addition, the following modified examples can be appropriately combined.

(1) In the above embodiment, Euclidean distance and CIEDE2000 are used as methods for calculating color difference, but the present invention is not limited to these. In other words, other methods that can calculate color difference can also be used. For example, CIE76, CIE94, etc. can be used. In the above embodiment, multiple methods are used depending on the density range, but multiple methods can also be used from other perspectives than the density range. Also, three or more methods can be used in appropriate combination.

(2) When multiple estimation methods exist as described above, there are various methods for determining which estimation method to use, and for example, the method can be determined as follows. However, other determinations can also be made.
- Use an estimation method that produces an estimate that is closest to the known concentration.
- Adopt an estimation method that calculates an estimated value within a specified range from a known concentration. If there are multiple estimation methods, any of them can be adopted while taking into account the water management guidelines of the area in which the system is used.
- Do not use estimation methods that calculate an estimate of 0 when the known concentration is greater than 0.

In this way, when multiple estimation methods are used, a threshold value for determining which estimation method should be adopted (e.g., the above-mentioned 0.15 mg/L) can be set according to the above-mentioned judgment method.

(3) The number and types of color samples 311 to 317 printed on the backing sheet 31 are not particularly limited and can be changed as appropriate depending on, for example, the region or the conditions of the water purification plant.

(4) In the above embodiments, in each method, the chlorine concentration of the color sample with the smallest color difference is calculated, and then fitting is performed to find the chlorine concentration with an even smaller color difference. However, it is also possible to use the chlorine concentration of the color sample with the smallest color difference as the estimated value without using fitting. For example, when there are a large number of color samples, it is possible to calculate a highly accurate estimated value without using fitting.

(5) The color information of the color sample and the water to be measured is not limited to RGB, and may be, for example, hue, saturation, and brightness in the HSV color space, or L ^* , a ^* , and b ^* in the CIE LAB color system. Furthermore, the method of calculating the color information of the color sample and the water from the image data 122 is not particularly limited as long as it is possible to calculate the various types of color information described above.

(6) In the above embodiment, color information is calculated from each color sample 311-317 printed on the mount 31 and associated with each chlorine concentration, but other methods may be used. For example, an ID is printed on each mount 31, and the ID is identified from the image data 122, thereby identifying the relationship between the chlorine concentration and color information of each color sample printed on the mount 31. In this case, the image data 122 is transmitted from the mobile terminal 1 to the server 2, and the ID is extracted from the image data 122 in the server 2. Also, for example, the storage unit 22 of the server 2 stores a table related to color samples for each ID, as shown below, and by referring to this table, the relationship between the chlorine concentration of the color sample and color information (for example, RGB pixel values) can be identified.

Therefore, the server 2 can identify the relationship between the chlorine concentration and color information of each color sample printed on the mount 31 by reading the ID from the image data 122 and referring to the corresponding table. Then, as described above, an image of the color of the water in the container 32 is extracted from the image data 122, and the color information of the water is calculated. This makes it possible to estimate the chlorine concentration of the water as described above. Note that it is also possible to prepare multiple mounts 31 on which color samples of other color combinations are printed, assign different IDs to each, and prepare tables such as those described above corresponding to each ID. This makes it possible to estimate the chlorine concentration of multiple types of water with different colors depending on the environment, etc. Also, the ID can take various forms, such as a number, a symbol, a barcode, or a QR code (registered trademark). Alternatively, the chlorine concentrations of the color samples 311 to 317 printed on the mount 31 can be read, and the relationship with the color information can be identified using this.

In the above method, information about the color sample (such as the color image, ID, and chlorine concentration of the color sample described above) is extracted from the photographic data obtained by photographing the mount 31, and the first color information is obtained from this. Furthermore, the image data of the present invention is sufficient if it contains at least an image of the water that is the object to be measured. Therefore, the photographic data described above may be included in the image data, or may be obtained separately from the image data. For example, the photographic data may be obtained by photographing only the information about the color sample described above separately.

Alternatively, the user can input information identifying the color sample on the operation screen of the mobile terminal 1. For example, an ID can be written on the backing sheet 31, and the corresponding ID can be selected from a pull-down menu on the operation screen. By transmitting information about the color sample selected in this manner to the server 2, the chlorine concentration of the water can be estimated as described above.

The relationship between the chlorine concentration of the color sample and the color information (for example, the above-mentioned table) may be stored in the server 2 as described above, or may be stored in the mobile terminal 1. For example, if it is stored in the mobile terminal 1, the relationship between the chlorine concentration of the color sample and the color information may be transmitted to the server 2 together with the image data 122.

(7) In the above embodiment, the concentration is estimated by the server 2, but it can also be done by the mobile terminal 1. For example, the estimation program 221 and color sample data 222 stored in the server 2 can be stored in the mobile terminal 1, and the chlorine concentration can be estimated by using this. Also, part of the processing performed by the server 2, that is, the processing (functional configuration) shown in FIG. 6, can also be performed by the mobile terminal 1. In other words, the above-mentioned multiple processes can be assigned to multiple computers for execution.

(8) In the above embodiment, an example of estimating chlorine concentration was described, but the present invention is not limited to this and can be applied to estimating concentration in a measurement object where there is a correlation between concentration and color.

1: Portable terminal 2: Server 112: Data acquisition unit 122: Image data 212: First color information acquisition unit 213: Second color information acquisition unit 214: Density estimation unit 215: Estimation result calculation unit 221: Estimation programs 311 to 317: Color samples

Claims (7)

acquiring image data relating to a measurement object;
acquiring first color information regarding the color of each of a plurality of color samples defined for each density;
acquiring second color information relating to a color of the measurement object from the image data;
estimating a concentration of the object by comparing the first color information with the second color information using a plurality of estimation methods;
adopting, as an estimation result, the concentration estimated by the estimation method suitable for the concentration from among the concentrations estimated by the plurality of estimation methods;
The method for estimating concentration comprises: The plurality of estimation methods include a first estimation method suitable for estimating a low concentration region and a second estimation method suitable for estimating a high concentration region.
The method for estimating concentration according to claim 1 . the first estimation method is an estimation method using a Euclidean distance,
The second estimation method is an estimation method using CIEDE2000.
The method for estimating concentration according to claim 2 . The method for estimating concentration according to claim 1, wherein the first color information is obtained from image data obtained by photographing the color sample. In the estimating step,
calculating a relationship between a color difference calculated from each of the first color information and the second color information and a density of each of the color samples based on each of the estimation methods;
Calculating the density at which the color difference is minimum by fitting the relationship in the vicinity of the density of the color sample at which the color difference is smallest.
The method for estimating concentration according to claim 1 . At least one computer
acquiring first color information regarding the color of each of a plurality of color samples defined for each density;
obtaining second color information relating to a color of the measurement object;
estimating a concentration of the object by comparing the first color information with the second color information using a plurality of estimation methods;
adopting, as an estimation result, the concentration estimated by the estimation method suitable for the concentration from among the concentrations estimated by the plurality of estimation methods;
A concentration estimation program that runs a first color information acquisition unit that acquires first color information regarding the color of each of a plurality of color samples defined for each density;
a second color information acquisition unit that acquires second color information related to a color of the measurement object;
a concentration estimation unit that estimates the concentration of the object by comparing the first color information with the second color information using a plurality of estimation methods;
an estimation result calculation unit that adopts, as an estimation result, the concentration estimated by the estimation method suitable for the concentration from among the concentrations estimated by the plurality of estimation methods;
The concentration estimation system includes: