JP7350146B2 - Image processing device for sheet material with patterns - Google Patents

Description

The present invention relates to an image processing device for a sheet material having a pattern.

In the linen supply industry, large quantities of laundry such as towels (bath towels, face towels), sheets, etc. are processed. If the laundry has holes or stains as a result of being used, it is checked by a person and rejected as defective. Furthermore, attempts have been made to automate the checking of the laundry (for example, see Patent Document 1).

Furthermore, a color pattern discrimination device is known that uses the amplitude of the waveform of color values in a cloth region of a cloth image to determine whether it is a plain object or a patterned object (for example, see Patent Document 2). .

Japanese Patent Application Publication No. 2000-329701 Japanese Patent Application Publication No. 2014-202700

However, since sheet materials such as sheets are frequently washed, the color value of the laundry pattern decreases compared to the color value of a new pattern due to fading, and the amplitude of the color value waveform also becomes narrower. Therefore, there is a problem that stable determination cannot be made by simple comparison with a threshold value or a registered waveform.

SUMMARY OF THE INVENTION Therefore, an object of the present invention is to provide an image processing apparatus for sheet materials that can determine the pattern not only of new sheets but also of laundry items.

An image processing apparatus for sheet material according to the present invention includes a conveying section that conveys a sheet material having a pattern;
an imaging unit that images the sheet material conveyed by the conveyance unit to obtain a color image of the sheet material;
Calculate the maximum value, minimum value, and average value for each color value of a plurality of pixels in a predetermined area from the color image of the sheet material, and calculate the difference value between the maximum value and the minimum value for each color value to the average value. a color feature amount calculation unit that calculates the color feature amount divided by;
a pattern determination unit that compares the calculated color feature amount with color feature amounts of a plurality of patterns recorded in advance, and determines that a pattern with the closest color feature amount is included in the sheet material;
Equipped with

According to the image processing apparatus for sheet material according to the present invention, the pattern can be stably determined not only when the sheet material is new, but also when the sheet material has faded or faded due to washing or aging.

1 is a plan view showing the configuration of an image processing device according to Embodiment 1. FIG. FIG. 2 is a schematic diagram showing the configuration of an imaging optical system when viewed from a direction perpendicular to the vertical direction of the image processing apparatus of FIG. 1 and the conveying direction of a sheet material. 1 is a block diagram showing the configuration of a sheet material image processing apparatus according to Embodiment 1. FIG. This is an image of pattern 1 stored in advance in the storage unit. This is an image of pattern 2 stored in advance in the storage unit. This is an image of pattern 3 stored in advance in the storage unit. This is an image of pattern 4 stored in advance in the storage unit. This is an image of pattern 5 (plain color) stored in advance in the storage unit. This is an image of a new sheet material having pattern 1. This is an image of a laundry item made of a sheet material having a pattern 1. This is an image of a new sheet material having a pattern 2. This is an image of a laundry item made of a sheet material having a pattern 2. This is an image of a new sheet material having a pattern 3. This is an image of a laundry item made of a sheet material having a pattern 3. This is an image of a new sheet material having a pattern 4. This is an image of a laundry item made of a sheet material having a pattern 4. This is an image of a new sheet material having pattern 5 (plain color). This is an image of a laundry item made of a sheet material having a pattern 5 (plain color). 3 is a flowchart of a tristimulus value feature amount calculation method in the sheet material image processing method according to Embodiment 1. FIG. 3 is a flowchart of a pattern determination method in the sheet material image processing method according to Embodiment 1. FIG. FIG. 7 is a schematic diagram showing an optical system in a sheet material image processing apparatus according to Embodiment 2, viewed from a direction perpendicular to the conveyance direction. FIG. 12B is a schematic diagram of the optical system in FIG. 12A viewed from the downstream side in the transport direction. FIG. 2 is a block diagram showing the configuration of a sheet material image processing apparatus according to a second embodiment. This is an image having a texture pattern 1. This is an image having a texture pattern 2. FIG. 3 is a block diagram showing the configuration of a sheet material image processing apparatus according to Embodiment 3. FIG. 7 is a flowchart of a pattern determination method in a sheet material image processing method according to Embodiment 3;

A sheet material image processing device according to a first aspect includes a conveying section that conveys a sheet material having a pattern;
an imaging unit that images the sheet material conveyed by the conveyance unit to obtain a color image of the sheet material;
Calculate the maximum value, minimum value, and average value for each color value of a plurality of pixels in a predetermined area from the color image of the sheet material, and calculate the difference value between the maximum value and the minimum value for each color value to the average value. a color feature amount calculation unit that calculates the color feature amount divided by;
a pattern determination unit that compares the calculated color feature amount with color feature amounts of a plurality of patterns recorded in advance, and determines that a pattern with the closest color feature amount is included in the sheet material;
Equipped with

In the sheet material image processing device according to the second aspect, in the first aspect, the color feature amount calculation unit calculates a tristimulus based on an RGB color system of a plurality of pixels in a predetermined area from the color image of the sheet material. Calculate the maximum value (Ar, Ag, Ab), minimum value (Br, Bg, Bb), and average value (Cr, Cg, Cb) for each value R, G, B, and use the following formula,
R component feature amount = ((Ar-Br))/Cr
G component feature amount = ((Ag-Bg))/Cg
B component feature amount = ((Ab-Bb))/Cb
A tristimulus value feature calculation unit that calculates tristimulus value features of an R component feature, a G component feature, and a B component feature as the color feature,
The pattern determination unit compares the calculated tristimulus value feature amount with tristimulus value feature amounts of a plurality of patterns recorded in advance, and determines that the pattern with the closest tristimulus value feature amount is on the sheet material. It is determined that it is included.

In the sheet material image processing apparatus according to the third aspect, in the second aspect, the pattern determination unit includes an R component feature amount, a G component feature amount, and a B component feature amount of the calculated tristimulus value feature amount. and the pattern with the smallest cumulative difference value, which is the sum of the absolute values of the differences between the R component feature, G component feature, and B component feature of the tristimulus feature values of multiple patterns recorded in advance. may be determined to be included in the sheet material.

In the sheet material image processing apparatus according to a fourth aspect, in the second aspect, the pattern determination unit includes an R component feature amount, a G component feature amount, and a B component feature amount of the calculated tristimulus value feature amount. The value of the inner product of the vector whose components are and the vector whose components are the R component feature, G component feature, and B component feature of the tristimulus value features of multiple patterns recorded in advance is the maximum value. It may be determined that the pattern is included in the sheet material.

A sheet material image processing apparatus according to a fifth aspect includes a conveying section that conveys the sheet material;
an imaging unit that images the sheet material conveyed by the conveyance unit to obtain a color image of the sheet material;
Calculating the total amount of change in color values in a predetermined area of the color image of the sheet material,
a pattern determination unit that determines that the sheet material is a plain object when the sum of the amount of change in the color value does not exceed a threshold value, and determines that the sheet material is a patterned object when it exceeds the threshold value;
Equipped with

Hereinafter, a sheet material image processing apparatus according to an embodiment will be described with reference to the accompanying drawings. In the drawings, substantially the same members are designated by the same reference numerals.

(Embodiment 1)
<Image processing device for sheet materials>
FIG. 1 is a plan view showing the configuration of a sheet material image processing apparatus 10 according to the first embodiment. FIG. 2 is a schematic diagram showing the configuration of the imaging optical system as viewed from a direction perpendicular to the vertical direction of the image processing apparatus of FIG. 1 and the conveyance direction of the sheet material. FIG. 3 is a block diagram showing the configuration of the image processing device 10 according to the first embodiment. In addition, in the figure, for convenience, the conveyance direction of the sheet material 1 is shown as the X direction, the width direction perpendicular to the conveyance direction of the sheet material is shown as the Y direction, and the vertically upward direction is shown as the Z direction.
This sheet material image processing device 10 includes a conveying section 11 that conveys a sheet material having a pattern, an imaging section 14 that obtains a color image of the sheet material, and a tristimulus value feature amount that calculates the tristimulus value feature amount of the color image of the sheet material. It includes a stimulus value feature calculation section 35a and a pattern determination section 35b that determines the pattern included in the sheet material. The imaging section 14 images the sheet material 1 conveyed by the conveyance section 11 to obtain a color image of the sheet material. The tristimulus value feature calculation unit 35a calculates the color value of each pixel in a predetermined area from the color image of the sheet material, for example, the maximum value of the distribution of tristimulus values R, G, and B according to the RGB color system (Ar, Ag, Ab), the minimum value (Br, Bg, Bb), and the average value (Cr, Cg, Cb), the following formula,
R component feature amount = ((Ar-Br))/Cr
G component feature amount = ((Ag-Bg))/Cg
B component feature amount = ((Ab-Bb))/Cb
The tristimulus value features of the R component feature amount, G component feature amount, and B component feature amount are calculated by. The pattern determination unit 35b compares the calculated tristimulus value feature amount with tristimulus value feature amounts of a plurality of patterns recorded in advance, and determines whether the pattern with the closest tristimulus value feature amount is included in the sheet material. It is determined that the

In this sheet material image processing device 10, for example, the difference between the maximum value Ar and the minimum value Br (Ar-Br) is determined based on the maximum value Ar, minimum value Br, and average value Cr of the distribution of tristimulus values R. The R-component feature amount is obtained by dividing Cr by the average value Cr. As mentioned above, the maximum value Ar for laundry decreases compared to when the laundry is new, so the mere difference between the maximum value Ar and the minimum value Br (Ar - Br) indicates that there is no change between the new laundry and the laundry. arise. On the other hand, the present inventor found that for laundry, although the average value Cr also decreases in the same way as the maximum value Ar, the change in the minimum value Br is small.
Therefore, as mentioned above, by dividing the difference (Ar-Br) by the average value Cr, the three stimuli are less likely to change compared to when they are new, even if they have faded or discolored due to washing or aging. By using value features, the pattern can be determined more accurately whether it is new or laundry.

The constituent members constituting this sheet material image processing device 10 will be described below.

<Sheet material>
The sheet material 1 is, for example, a towel (bath towel, face towel), sheet, or the like. Further, the sheet material 1 has patterns 1 to 5 shown in FIGS. 4A to 4E.
FIG. 4A is an image of the pattern 1 stored in advance in the storage unit. FIG. 4B is an image of pattern 2 stored in advance in the storage unit. FIG. 4C is an image of the pattern 3 stored in advance in the storage unit. FIG. 4D is an image of the pattern 4 stored in advance in the storage unit. FIG. 4E is an image of pattern 5 (plain color) stored in advance in the storage unit.
Moreover, FIG. 5A is an image of a new sheet material having the pattern 1. FIG. 5B is an image of a laundry item made of a sheet material having pattern 1. FIG. 6A is an image of a new sheet material having the pattern 2. FIG. 6B is an image of a laundry item made of a sheet material having pattern 2. FIG. 7A is an image of a new sheet material having a pattern 3. FIG. 7B is an image of a laundry item made of a sheet material having a pattern 3. FIG. 8A is an image of a new sheet material having the pattern 4. FIG. 8B is an image of a laundry item made of a sheet material having a pattern 4. FIG. 9A is an image of a new sheet material having a pattern 5 (plain color). FIG. 9B is an image of a laundry item made of a sheet material having a pattern 5 (plain color).
As shown in FIGS. 5A to 9B, it can be seen that the change in brightness of laundry is smaller than that of new laundry even though the pattern is the same. In other words, it can be seen that the maximum values (Ar, Ag, Ab) of the distribution of each stimulus value are decreasing.
Note that patterns include not only colored patterns but also "woven patterns" created by the unevenness of the weave. The optical system for determining this "weave pattern" will be described later.

<Transport section>
The sheet material 1 is transported to the inspection table 12 by the transport section 11 . In the figure, for convenience, this transport direction is shown as the X direction. For example, a belt conveyor can be used as the conveyance unit 11.

<Inspection table>
As the inspection table 12, as shown in FIGS. 1 and 2, for example, a black inspection table 12 can be used.

<Light source section>
For the light source sections 13, 13a, and 13b, for example, any ordinary light source such as a lamp or an LED can be used. Diffused lighting that emits diffused light is preferable.

<Imaging section>
As shown in FIG. 2, the imaging section 14 is arranged above the light source sections 13a and 13b. Further, the imaging unit 14 is not located at a specular reflection position with respect to the light sources 13a and 13b, and can obtain an image using diffusely reflected light. An image of the sheet material 1 can be obtained by the imaging unit 14.
The imaging unit 14 can use a line camera or an area camera that can capture color images. Further, the imaging unit 14 may include, for example, an imaging device such as a CCD or CMOS, and an imaging control means for controlling the imaging device.

<Control unit (computer device)>
The control unit 30 is, for example, a computer device. A general-purpose computer device can be used as this computer device, and includes, for example, a processing section 31, a storage section 32, and a display section 33, as shown in FIG. Note that it may further include an input device, a storage device, an interface, and the like.
The control unit 30 controls the transport unit 11, the light source unit 13, and the imaging unit 14.

<Processing section>
The processing unit 31 may be, for example, a central processing operator (CPU), a microcomputer, or a processing device capable of executing computer-executable instructions.

<Storage section>
The storage unit 32 may be, for example, at least one of a ROM, an EEPROM, a RAM, a flash SSD, a hard disk, a USB memory, a magnetic disk, an optical disk, a magneto-optical disk, and the like.
The storage unit 32 includes a tristimulus value feature amount 34 of the pattern and a program 35. Note that if the control unit 30 is connected to a network, the program 35 may be downloaded from the network as necessary.

<Tristimulus value features of the pattern>
The tristimulus value feature amount 34 of the pattern includes, for example, the tristimulus value feature amount 34a of the pattern 1, the tristimulus value feature amount 34b of the pattern 2, the tristimulus value feature amount 34c of the pattern 3, and the tristimulus value feature amount of the pattern 4. 34d, and a tristimulus value feature amount 34e of pattern 5 (plain color).
From the color image of the sheet material, the maximum value (Ar, Ag, Ab) of the distribution of tristimulus values R, G, B according to the RGB color system of each pixel in a predetermined area, for example, the center location (near the center of gravity of the sheet material) Based on the minimum value (Br, Bg, Bb) and average value (Cr, Cg, Cb), the following formula,
R component feature amount = ((Ar-Br))/Cr
G component feature amount = ((Ag-Bg))/Cg
B component feature amount = ((Ab-Bb))/Cb
The tristimulus value features of the R component feature amount, G component feature amount, and B component feature amount are calculated by.
That is, the tristimulus value feature includes an R component feature, a G component feature, and a B component feature.

Note that although the RGB color system has been described here as the color system, the color system is not limited to the RGB color system. For example, the color system may be a CMYK color system, an XYZ color system, a Lab color system, or the like, which can be quantified. Further, the color system may be a color system that is mutually convertible with the RGB color system.
Furthermore, when using a color system other than the RGB color system, a color feature corresponding to the tristimulus value feature is used.

<Program>
The program 35 includes a tristimulus value feature calculation section 35a and a pattern determination section 35b. When executed, the tristimulus value feature value calculation section 35a and the pattern determination section 35b are read out from the storage section 32 and executed by the processing section 31.
FIG. 10 is a flowchart of a tristimulus value feature calculation method in the sheet material image processing method according to the first embodiment.
The tristimulus value feature amount calculation unit 35a calculates the tristimulus value feature amount by the following steps.
(1) Maximum values (Ar, Ag, Ab) and minimum values (Br, Bg, Bb) of the distribution of tristimulus values R, G, B according to the RGB color system of each pixel in a predetermined area from the color image of the sheet material and average values (Cr, Cg, Cb) are obtained (S01).
Note that in the case of a color image of a sheet material serving as a reference to be stored in the storage unit 32, the predetermined area may be, for example, a center area. Further, in the case of a color image of a sheet material whose pattern is to be determined, the predetermined area may be, for example, a center area. Alternatively, a plurality of predetermined areas may be set from one end to the other end. Furthermore, for example, 2,500 sections of the color image of the sheet material may be each set as a predetermined area.
(2) Based on the maximum value (Ar, Ag, Ab), minimum value (Br, Bg, Bb), and average value (Cr, Cg, Cb) of the distribution of tristimulus values R, G, B, the following formula is used. ,
R component feature amount = ((Ar-Br))/Cr
G component feature amount = ((Ag-Bg))/Cg
B component feature amount = ((Ab-Bb))/Cb
Tristimulus value features of the R component feature amount, G component feature amount, and B component feature amount are calculated by (S02).

Note that when using another color system instead of the RGB color system, a color feature calculation section corresponding to the tristimulus value feature calculation section is used. In this case, the color feature amount calculation unit divides the difference value between the maximum value and the minimum value for each color value by the average value, based on the maximum value, minimum value, and average value for each color value in the color system. Calculate the color feature amount.

FIG. 11 is a flowchart of a pattern determination method in the sheet material image processing method according to the first embodiment.
The pattern determination unit 35b determines the pattern included in the sheet material through the following steps.
(a) Compare the calculated tristimulus value feature with the tristimulus value feature of a plurality of patterns recorded in advance (S11).
(b) It is determined that the pattern of the tristimulus value feature closest to the calculated tristimulus value feature is included in the sheet material (S12).
In addition, when a plurality of locations are used as the above-mentioned predetermined area, the pattern may be determined to be the best matching pattern based on the pattern determination performed for the plurality of locations. For example, when 2500 locations are used as the predetermined area, the pattern that is found most frequently among the patterns determined in each area may be determined to be the pattern included in the sheet material.

In comparing the above tristimulus value features, the R component feature amount, G component feature amount, and B component feature amount of the calculated tristimulus value feature amount and the R component feature amount of the tristimulus value feature amount of multiple patterns recorded in advance. The determination may be made using an integrated difference value obtained by integrating the absolute values of the differences between the component feature amount, the G component feature amount, and the B component feature amount.

Furthermore, a vector whose components are the R component feature, G component feature, and B component feature of the calculated tristimulus feature, and the R component feature of the tristimulus feature of multiple patterns recorded in advance. , the G component feature, and the B component feature. It can be determined that the pattern with the maximum inner product value is included in the sheet material. In this case, although it is necessary to calculate the inner product, it is possible to reflect the unique characteristics of the tristimulus values for each pattern, so that the pattern can be determined more accurately.
Through the above steps, the pattern included in the sheet material can be determined.

Further, the program 35 may include a sheet material image acquisition section 35c. At the time of execution, the sheet material image acquisition section 35c is read out from the storage section 32 and executed by the processing section 31. The sheet material image acquisition unit 35c may, for example, determine the boundary between the inspection table and the sheet material through the following steps, and acquire the image inside the boundary as a color image of the sheet material.
(i) In the captured image, calculate the amount of change ΔL in brightness L for each pixel along the direction (Y direction) that intersects the transport direction (X direction).
(ii) Next, pixels in which the amount of change ΔL exceeds a predetermined threshold are detected as boundaries between the inspection table and the sheet material.
(iii) Obtain a color image of the sheet material between the two boundaries between the inspection table and the sheet material detected along the direction (Y direction) intersecting the transport direction (X direction).
As described above, a color image of the sheet material can be obtained from the captured image.

Note that an inspection section 35d may be included if necessary. The inspection section 35d inspects the sheet material for defects, for example, based on the color image of the sheet material obtained by the sheet material image acquisition section. Examples of defects in the sheet material include holes, stains, and the like. This inspection section 35d is also read out from the storage section 32 and executed by the processing section 31 during execution.

<Display section>
The display section 33 only needs to be able to display the image obtained by the sheet material image acquisition section 35c, for example.

(Example 1)
Tristimulus value features were calculated for a color image of a new sheet material having pattern 1 in FIG. 5A. Next, an integrated difference value with each of the tristimulus value feature amounts 34a, 34b, 34c, 34d, and 34e stored in the storage unit 32 was calculated. The integrated difference value with the tristimulus value feature amount of pattern 1 was 1. The cumulative difference value from the tristimulus value feature amount of pattern 2 was 179. The cumulative difference value with the tristimulus value feature amount of pattern 3 was 361. The integrated difference value with the tristimulus value feature amount of pattern 4 was 844. The cumulative difference value from the tristimulus value feature amount of pattern 5 (plain color) was 132.
Therefore, in this case, it was found that the sheet material in FIG. 5A includes pattern 1 with the smallest cumulative difference value.
In addition, tristimulus value feature amounts were calculated for the color image of the sheet material in the case of laundry of the sheet material having pattern 1 in FIG. 5B. Next, an integrated difference value with each of the tristimulus value feature amounts 34a, 34b, 34c, 34d, and 34e stored in the storage unit 32 was calculated. The integrated difference value from the tristimulus value feature amount of pattern 1 was 0. The cumulative difference value from the tristimulus value feature amount of pattern 2 was 871. The cumulative difference value from the tristimulus value feature amount of pattern 3 was 693. The cumulative difference value from the tristimulus value feature amount of pattern 4 was 1630. The cumulative difference value from the tristimulus value feature amount of pattern 5 (plain color) was 96.
Therefore, in this case, it was found that the sheet material in FIG. 5B includes pattern 1 with the smallest integrated difference value.
In other words, in Example 1, it was possible to accurately determine that the laundry was pattern 1 not only when the laundry was new in FIG. 5A but also when the maximum value of each stimulation value was decreasing in the laundry in FIG. 5B.

(Example 2)
Tristimulus value features were calculated for a color image of a new sheet material having pattern 2 in FIG. 6A. Next, an integrated difference value with each of the tristimulus value feature amounts 34a, 34b, 34c, 34d, and 34e stored in the storage unit 32 was calculated. The cumulative difference value from the tristimulus value feature amount of pattern 1 was 350. The integrated difference value with the tristimulus value feature amount of pattern 2 was 1. The integrated difference value with the tristimulus value feature amount of pattern 3 was 106. The cumulative difference value from the tristimulus value feature amount of pattern 4 was 260. The cumulative difference value from the tristimulus value feature amount of pattern 5 (plain color) was 1633.
Therefore, in this case, it was found that the sheet material in FIG. 6A includes pattern 2 with the smallest cumulative difference value.
Furthermore, the tristimulus value feature amount for the color image of the sheet material in the case of laundry of the sheet material having pattern 1 in FIG. 6B was calculated. Next, an integrated difference value with each of the tristimulus value feature amounts 34a, 34b, 34c, 34d, and 34e stored in the storage unit 32 was calculated. The cumulative difference value from the tristimulus value feature amount of pattern 1 was 153. The cumulative difference value from the tristimulus value feature amount of pattern 2 was 12. The cumulative difference value from the tristimulus value feature amount of pattern 3 was 83. The cumulative difference value from the tristimulus value feature amount of pattern 4 was 131. The cumulative difference value from the tristimulus value feature amount of pattern 5 (plain color) was 2226.
Therefore, in this case, it was found that the sheet material in FIG. 6B includes pattern 2 with the smallest cumulative difference value.
In other words, in Example 2, it was possible to accurately determine that the laundry was pattern 2 not only in the case of the new item in FIG. 6A but also in the case in which the maximum value of each stimulus value decreased in the laundry in FIG. 6B.

(Example 3)
Tristimulus value features were calculated for a color image of a new sheet material having pattern 3 in FIG. 7A. Next, an integrated difference value with each of the tristimulus value feature amounts 34a, 34b, 34c, 34d, and 34e stored in the storage unit 32 was calculated. The cumulative difference value from the tristimulus value feature amount of pattern 1 was 2901. The cumulative difference value from the tristimulus value feature amount of pattern 2 was 68. The integrated difference value with the tristimulus value feature amount of pattern 3 was 7. The integrated difference value with the tristimulus value feature amount of pattern 4 was 15. The cumulative difference value from the tristimulus value feature amount of pattern 5 (plain color) was 6502.
Therefore, in this case, it was found that the sheet material in FIG. 7A includes the pattern 3 with the smallest cumulative difference value.
Further, the tristimulus value feature amount was calculated for the color image of the sheet material in the case of the sheet material laundry having pattern 3 in FIG. 7B. Next, an integrated difference value with each of the tristimulus value feature amounts 34a, 34b, 34c, 34d, and 34e stored in the storage unit 32 was calculated. The integrated difference value from the tristimulus value feature amount of pattern 1 was 1109. The cumulative difference value from the tristimulus value feature amount of pattern 2 was 17. The cumulative difference value from the tristimulus value feature amount of pattern 3 was 6. The cumulative difference value with the tristimulus value feature amount of pattern 4 was 23. The cumulative difference value from the tristimulus value feature amount of pattern 5 (plain color) was 2,847.
Therefore, in this case, it was found that the sheet material in FIG. 7B includes pattern 3 with the smallest integrated difference value.
In other words, in Example 3, it was possible to accurately determine that the laundry was pattern 3 not only in the case of the new item in FIG. 7A but also in the case in which the maximum value of each stimulation value decreased in the laundry in FIG. 7B.

(Example 4)
Tristimulus value features were calculated for a color image of a new sheet material having pattern 4 in FIG. 8A. Next, an integrated difference value with each of the tristimulus value feature amounts 34a, 34b, 34c, 34d, and 34e stored in the storage unit 32 was calculated. The cumulative difference value from the tristimulus value feature amount of pattern 1 was 2416. The cumulative difference value from the tristimulus value feature amount of pattern 2 was 173. The integrated difference value with the tristimulus value feature amount of pattern 3 was 7. The integrated difference value with the tristimulus value feature amount of pattern 4 was 0. The cumulative difference value from the tristimulus value feature amount of pattern 5 (plain color) was 4779.
Therefore, in this case, it was found that the sheet material in FIG. 8A includes the pattern 4 with the smallest cumulative difference value.
Further, the tristimulus value feature amount was calculated for the color image of the sheet material in the case of the sheet material laundry having the pattern 4 in FIG. 8B. Next, an integrated difference value with each of the tristimulus value feature amounts 34a, 34b, 34c, 34d, and 34e stored in the storage unit 32 was calculated. The integrated difference value from the tristimulus value feature amount of pattern 1 was 2,720. The cumulative difference value from the tristimulus value feature amount of pattern 2 was 540. The cumulative difference value from the tristimulus value feature amount of pattern 3 was 51. The integrated difference value with the tristimulus value feature amount of pattern 4 was 1. The cumulative difference value from the tristimulus value feature amount of pattern 5 (plain color) was 4,664.
Therefore, in this case, it was found that the sheet material in FIG. 8B includes the pattern 4 with the smallest cumulative difference value.
In other words, in Example 4, it was possible to accurately determine that the laundry was pattern 4 not only in the case of the new item in FIG. 8A but also in the case in which the maximum value of each stimulus value decreased in the laundry in FIG. 8B.

(Example 5)
Tristimulus value feature amounts were calculated for a color image of a new sheet material having pattern 5 (plain color) in FIG. 9A. Next, an integrated difference value with each of the tristimulus value feature amounts 34a, 34b, 34c, 34d, and 34e stored in the storage unit 32 was calculated. The cumulative difference value from the tristimulus value feature amount of pattern 1 was 71. The cumulative difference value from the tristimulus value feature amount of pattern 2 was 114. The cumulative difference value from the tristimulus value feature amount of pattern 3 was 680. The cumulative difference value from the tristimulus value feature amount of pattern 4 was 1226. The cumulative difference value from the tristimulus value feature amount of pattern 5 (plain color) was 7.
Therefore, in this case, it was found that the sheet material shown in FIG. 9A includes pattern 5 (plain color) with the smallest cumulative difference value.
Further, the tristimulus value feature amount was calculated for the color image of the sheet material in the case of the sheet material laundry having pattern 5 (plain color) in FIG. 9B. Next, an integrated difference value with each of the tristimulus value feature amounts 34a, 34b, 34c, 34d, and 34e stored in the storage unit 32 was calculated. The cumulative difference value from the tristimulus value feature amount of pattern 1 was 85. The cumulative difference value from the tristimulus value feature amount of pattern 2 was 203. The cumulative difference value with the tristimulus value feature amount of pattern 3 was 164. The cumulative difference value from the tristimulus value feature amount of pattern 4 was 345. The cumulative difference value from the tristimulus value feature amount of pattern 5 (plain color) was 18.
Therefore, in this case, it was found that the sheet material in FIG. 9B includes the pattern 5 with the smallest cumulative difference value.
In other words, in Example 5, it was accurately determined that the laundry was pattern 5 (plain color) not only when the laundry was new in FIG. 9A but also when the maximum value of each stimulus value was decreasing in the laundry in FIG. 9B.

(Embodiment 2)
FIG. 12A is a schematic diagram showing the optical system of the sheet material image processing apparatus 10a according to Embodiment 2, viewed from the direction (Y direction) perpendicular to the conveyance direction (X direction). FIG. 12B is a schematic diagram of the optical system of FIG. 12A viewed from the downstream side in the transport direction (X direction). FIG. 13 is a block diagram showing the configuration of a sheet material image processing apparatus 10a according to the second embodiment.
In contrast to the sheet material image processing device 10a according to the second embodiment, as shown in FIGS. 12A and 12B, the sheet material image processing device 10a according to the second embodiment has two light source sections 23a provided on one side. , 23b. Further, as shown in FIG. 13, the sheet material image processing device 10a stores the tristimulus value feature amount 34f of the weave pattern 1 and the tristimulus value feature amount of the weave pattern 2, as shown in FIG. The difference is that the amount is 34g.

The optical system of the sheet material image processing apparatus 10a according to the second embodiment will be described.
As shown in FIG. 12A, the height H1 of the imaging section 24 from the sheet material 1 may be, for example, 160 mm. Further, as shown in FIG. 12B, the height H2 of the imaging section 24 from the sheet material 1 is, for example, 160 mm, and the inclination θ1 of the imaging section 24 from the vertical direction is, for example, 16 degrees. The height H3 of the first light source section 23a from the sheet material is, for example, 160 mm, and the inclination θ2 of the first light source section 23a from the vertical direction is, for example, 7 degrees. The height H4 of the second light source section 23b from the sheet material is, for example, 200 mm, and the inclination θ3 of the second light source section 23b from the vertical direction is, for example, 10 degrees. Further, the distance D1 between the first light source section 23a and the imaging section 24 is, for example, 240 mm, and the distance D2 between the second light source section 23b and the imaging section 24 is, for example, 410 mm.
Note that the imaging section 24 and the first and second light source sections 23a and 23b are arranged so as to face each other away from the regular reflection position.

With the above-mentioned optical system, it is possible to obtain a color image of the sheet material in which the lightness differs between the concave portions and the convex portions of the weave pattern created by the concave and convex portions of the weave.
Therefore, according to the sheet material image processing device 10a, by obtaining a color image of the sheet material using the optical system shown in FIGS. 12A and 12B, in the case of weave pattern 1 and weave pattern 2 shown in FIGS. 14A and 14B, It is also possible to calculate tristimulus value features and make judgments.

(Embodiment 3)
FIG. 15 is a block diagram showing the configuration of a sheet material image processing apparatus 10b according to the third embodiment. FIG. 16 is a flowchart of a pattern determination method in the sheet material image processing method according to the third embodiment.
The sheet material image processing apparatus 10b according to the third embodiment includes a conveyance section 11 that conveys the sheet material, and an imaging section 12 that images the sheet material conveyed by the conveyance section and obtains a color image of the sheet material. Then, the total amount of change in color values is calculated in a predetermined area of the color image of the sheet material, and if the total amount of change in color values does not exceed a threshold value, the sheet material is determined to be a plain object, and if it exceeds the threshold value, the sheet material is determined to be a plain object. includes a pattern determination section 35b that determines that the sheet material has a pattern.

The pattern determination section 35b is read out from the storage section 32 and executed by the processing section 31 during execution. The pattern determining section 35b may determine whether the sheet material is plain or patterned, for example, by the following steps.
(i) Color values for each pixel (for example, tristimulus values R, G, B according to the RGB color system) in a predetermined area of the captured image along the direction (Y direction) that intersects the transport direction (X direction) The amount of change ΔC is calculated (S21). Here, the amount of change may be the absolute value of the difference in color value with an adjacent pixel along the Y direction.
(ii) The amount of change is calculated for all pixels within the predetermined area along the Y direction, and the total sum ΣΔC of the amount of change within the predetermined area is determined (S22).
(iii) ΣΔC is compared with a predetermined threshold, and if it does not exceed the threshold, it is determined to be a plain object, and if it exceeds the threshold, it is determined to be a patterned object (S23).
Through the above steps, it is possible to determine whether the imaged sheet material is plain or patterned.

In addition, in the pattern determination section 35b, even if there is a defect such as dirt, stain, or hole within a predetermined area, the amount of change ΔC (noise) in the color value at the boundary is relatively small with respect to the integrated value ΣΔC. It is something. Conventional methods of determining color value amplitudes are susceptible to noise, making it particularly difficult to accurately determine patterns with small color differences. According to the pattern determination unit 35b of the third embodiment, even for sheet materials with small color differences, the influence of noise can be suppressed, and it is possible to accurately determine whether a plain object or a patterned object is present.

Note that the present disclosure includes appropriate combinations of any of the various embodiments and/or examples described above, and includes the combination of the various embodiments and/or examples described above. The effects of the embodiments can be achieved.

According to the sheet material image processing apparatus according to the present invention, a pattern included in a sheet material can be determined more accurately.

1, 1a, 1b Sheet materials 10, 10a, 10b Image processing device 11 Transport section 12 Examination table 13, 13a, 13b Light source section 14, 14a, 14b, 14c Imaging section 23, 23a, 23b Light source section 24 Imaging section 30 Control section (computer equipment)
31 Processing unit 32 Storage unit 33 Display unit 34 Tristimulus value feature amount of pattern 34a Tristimulus value feature amount of pattern 1 34b Tristimulus value feature amount of pattern 2 34c Tristimulus value feature amount of pattern 3 34d Tristimulus value feature amount of pattern 4 Value feature quantity 34e Tristimulus value feature quantity 34f of pattern 5 Tristimulus value feature quantity 34g of fabric pattern 1 Tristimulus value feature quantity 35 of fabric pattern 2 Program 35a Tristimulus value feature quantity calculation section 35b Pattern determination section 35c Sheet material image Acquisition section 35d Inspection section

Claims (2)

a conveyance unit that conveys the sheet material;
an imaging unit that images the sheet material conveyed by the conveyance unit to obtain a color image of the sheet material;
Calculate the total amount of change in color values in a predetermined area of the color image of the sheet material, and if the total amount of change in color values does not exceed a threshold value, determine the sheet material as a plain object, and if it exceeds the threshold value. a pattern determination unit that determines that the sheet material is a patterned object having a pattern;
An image processing device for sheet materials. The sheet material image processing apparatus according to claim 1, wherein the amount of change in the color value is the amount of change in tristimulus values R, G, and B according to an RGB color system.