JP7265857B2 - Image processing apparatus for sheet material having single portion and double portion and image processing method for sheet material - Google Patents

Description

TECHNICAL FIELD The present invention relates to an image processing apparatus and an image processing method for a sheet material having a single portion and a double portion, such as a picture frame covering having a single cloth portion and a double cloth portion.

In the linen supply industry, a large amount of laundry such as towels (bath towels, face towels) and sheets is processed. If the laundry has holes or stains as a result of use, it is checked by a person and excluded as a defective item. Attempts have also been made to automate this laundry check (see, for example, Patent Document 1).

JP-A-2000-329701

Sheets include flat sheets made of one piece of cloth, and bag-like sheets partially made of two pieces of cloth (double portion). For example, there are so-called boxed sheets and fitted sheets in which the double portion has a picture frame shape, and structures called quick sheets, pocket sheets, M sheets, etc. in which at least one edge has a bag shape.
However, in the inspection apparatus described in Patent Document 1, in the case of a bag-like sheet having a single cloth portion (single-ply portion) and a two-ply cloth portion (double portion) as described above, the single-ply portion and the double-ply portion are used. Shadows on the boundary between parts may be erroneously detected as dirt.

Therefore, the present invention provides image processing capable of obtaining an image capable of suppressing erroneous detection of the boundary between the single-layered portion and the double-layered portion as dirt, etc., even for a sheet material having a single-layered portion and a double-layered portion. The purpose is to provide an apparatus.

An image processing apparatus for a sheet material having a single portion and a double portion according to the present invention is a conveying section for conveying a sheet material having a single portion of a single sheet material and a double portion of a double sheet material. and,
an imaging unit that captures an image of the sheet material conveyed by the conveying unit to obtain a sheet material image;
a mask applying unit for obtaining a masked image in which a boundary between the single portion and the double portion is masked from the sheet material image;
Prepare.

An image processing method for a sheet material according to the present invention comprises the steps of obtaining an image of a sheet material having a single portion of a single planar material and a double portion of a double planar material;
calculating the brightness near the center of gravity of the sheet material image;
a step of extracting an area brighter than a predetermined threshold value or more than the brightness near the center of gravity as the area of the double portion;
a step of setting a region other than the double portion region in the sheet material image as the single portion region;
detecting a boundary between the double portion area and the single portion area;
obtaining a masked image by adding the masked area to the sheet material image by creating a masked area over a predetermined range from the boundary;
including.

According to the sheet material image processing apparatus and the sheet material image processing method according to the present invention, even in a sheet material having a single-layered portion and a double-layered portion, the boundary between the single-layered portion and the double-layered portion is It is possible to obtain an image capable of suppressing erroneous detection of dirt or the like.

1 is a plan view showing the configuration of an image processing apparatus according to Embodiment 1; FIG. 2 is a schematic diagram showing the configuration of an imaging optical system 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; FIG. 1 is a block diagram showing the configuration of an image processing apparatus according to Embodiment 1; FIG. 4 is a flowchart of a mask applying method executed by a mask applying unit of the image processing apparatus of FIG. 3; 5 is an example of an image of a sheet material having a single portion and a double portion in Example 1. FIG. Figure 5B shows a double portion extracted from the image of Figure 5A; FIG. 5B is a diagram showing a masked image obtained by masking a boundary between a single portion and a double portion in the image of FIG. 5A; 10 is an example of an image of a sheet material having a single portion and a double portion in Example 2. FIG. 7B is a diagram showing a masked image obtained by masking a boundary between a single portion and a double portion in the image of FIG. 7A; FIG. 11 is an example of an image of a sheet material having a single portion and a double portion in Example 3. FIG. FIG. 8B is a diagram showing a masked image obtained by masking a boundary between a single portion and a double portion in the image of FIG. 8A;

An image processing apparatus for a sheet material having a single portion and a double portion according to a first aspect conveys a sheet material having a single portion with a single sheet material and a double portion with a double sheet material. a conveying unit;
an imaging unit that captures an image of the sheet material conveyed by the conveying unit to obtain a sheet material image;
a mask applying unit for obtaining a masked image in which a boundary between the single portion and the double portion is masked from the sheet material image;
Prepare.

Usually, the double bag-shaped opening of the sheet material is folded back and sewn to form a triple layer. Due to the effect of this thickened triple portion, the boundary between the single portion and the double portion is imaged darker than the surroundings, like a shadow. Therefore, as in the above configuration, by extracting the shadow of this triple portion with an edge enhancement filter or the like, the boundary can be detected and the boundary can be masked.

In the image processing apparatus according to a second aspect, in the first aspect, the mask applying unit extracts the double portion region from the sheet material image,
Detecting a region other than the double portion as a single portion in the obtained image,
detecting a boundary between the double portion area and the single portion area;
A masked image may be obtained by creating a masked area covering a predetermined range from the boundary and adding the masked area to the sheet material image.

In the image processing apparatus according to a third aspect, in the above-described second aspect, in the sheet material image, a region brighter than or equal to a predetermined threshold or darker than or equal to a predetermined threshold than the brightness near the center of gravity is doubled. may be detected as a region of

It may be difficult to distinguish the shadow of the triple portion from wrinkles of the sheet material. Therefore, as in the above configuration, the boundary can be masked more robustly by detecting the double portion by comparing with the brightness near the center of gravity.

In the image processing apparatus according to a fourth aspect, in any one of the first to third aspects, the imaging section may obtain an image using diffusely reflected light.

An image processing apparatus according to a fifth aspect, in any one of the first to fourth aspects, may further include an inspection unit that detects defects in the sheet material based on the masked image.

A sheet material image processing method according to a sixth aspect includes the steps of obtaining a sheet material image having a single portion of a single sheet material and a double portion of a double sheet material;
calculating the brightness near the center of gravity of the sheet material image;
a step of extracting an area brighter than a predetermined threshold value or more than the brightness near the center of gravity as the area of the double portion;
a step of setting a region other than the double portion region in the sheet material image as the single portion region;
detecting a boundary between the double portion area and the single portion area;
obtaining a masked image by adding the masked area to the sheet material image by creating a masked area over a predetermined range from the boundary;
including.

An image processing apparatus for a sheet material having a single portion and a double portion and an image processing method for a sheet material according to an embodiment will be described below with reference to the accompanying drawings. In addition, the same code|symbol is attached|subjected about the substantially same member in drawing.

(Embodiment 1)
<Image processing device for sheet materials>
FIG. 1 is a plan view showing the configuration of an image processing apparatus 10 according to Embodiment 1. FIG. FIG. 2 is a schematic diagram showing the configuration of an imaging optical system viewed from a direction perpendicular to the vertical direction of the image processing apparatus of FIG. 1 and the conveying direction of the sheet material. FIG. 3 is a block diagram showing the configuration of the image processing apparatus 10 according to Embodiment 1. As shown in FIG. In the drawing, for convenience, the conveying direction of the sheet material 1 is shown as the X direction, the width direction perpendicular to the sheet material conveying direction is shown as the Y direction, and the vertically upward direction is shown as the Z direction.

The image processing apparatus 10 according to the first embodiment includes a conveying section 11 that conveys a sheet material 1 having a single portion and a double portion, and an image of the sheet material 1 conveyed by the conveying portion 11 to obtain a sheet material image. and a mask applying unit 35a for obtaining an image with a mask. For example, as shown in FIG. 5A, the sheet material 1 has a single portion 2 in which the planar material is single and a double portion 4 in which the planar material is double. The double portion 4 is shaped like a bag by closing both sides (upper and lower edges in FIG. 5A). The mask applying unit 35a detects the double portion region from the obtained image, and obtains a masked image in which the boundary between the single and double portion regions is masked. Note that the mask applying unit 35a may be a program that can be executed by a computer device, as will be described later.
As a result, as shown in FIG. 5A and the like, even in a sheet material 1 having a single portion 2 and a double portion 4, the boundary 3 between the single portion 2 and the double portion 4 is stained. An image that can suppress erroneous detection can be obtained.

Constituent members constituting the image processing apparatus 10 will be described below.

<Conveyor>
The sheet material 1 is conveyed to the inspection table 12 by the conveying unit 11 . For example, a belt conveyor can be used as the transport unit 11 .

<Inspection table>
A black inspection table, for example, can be used as the inspection table 12 .

<Light source part>
For the light source unit 13, for example, a normal light source such as a lamp or an LED can be used. Diffusion illumination that irradiates uniform diffused light is preferable.

<Imaging unit>
The imaging unit 14 is arranged above the light sources 13a and 13b, as shown in FIG. In addition, the imaging unit 14 is not in a specular reflection position with respect to the light sources 13a and 13b, and can obtain an image with diffusely reflected light. An image of the sheet material 1 can be obtained by the imaging unit 14 .
A line camera or an area camera can be used as the imaging unit 14 . The imaging unit 14 may also include, for example, an imaging device such as a CCD or CMOS, and imaging control means for controlling the imaging device.
Note that the imaging unit 14 may be installed on the opposite side of the sheet material 1 from the light sources 13a and 13b. In this case, the light sources 13a and 13b function as transmitted light illumination. When imaging with transmitted light illumination, the inspection table 12 may be installed at a position that does not interfere with the illumination (a position away from the sheet material 1, for example, the position of the imaging unit 14 in FIG. 2).

<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 unit 31, a storage unit 32, and a display unit 33, as shown in FIG. Furthermore, an input device, a storage device, an interface, etc. may be included.
The control unit 30 controls the transport unit 11 , the light source unit 13 and the imaging unit 14 .

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

<Memory part>
The storage unit 32 may be, for example, at least one of ROM, EEPROM, RAM, flash SSD, hard disk, USB memory, magnetic disk, optical disk, magneto-optical disk, and the like.
The storage unit 32 contains a program 35 . In addition, when the control unit 30 is connected to a network, the program 35 may be downloaded from the network as necessary.

<Program>
It is sufficient that the program 35 includes a mask applying section 35a. The mask applying unit 35a is read from the storage unit 32 and executed by the processing unit 31 at the time of execution. A masked image can be obtained by the mask applying unit 35a.
<Mask applying unit (mask applying method)>
FIG. 4 is a flowchart of a mask applying method executed by the mask applying unit of the image processing apparatus of FIG. The program of this mask applying unit 35a will be described with reference to the flow chart of FIG.
(1) First, an image of the black background of the sheet material is obtained when the inspection table is a black background (S01). For example, images as shown in FIGS. 5A, 7A, and 8A are obtained.
(2) Next, for example, the average brightness (average density) is calculated as the brightness near the center of gravity of the sheet material of the obtained black background image (S02). Here, it is assumed that the center of gravity of the sheet material, that is, the center, usually has a single-ply portion where there is only one piece of cloth. In other words, the "average lightness" referred to here is the average density of the single-ply portion of a piece of cloth. Therefore, when there is a double portion of the two-ply cloth in the center, the average brightness should be calculated from the single-ply portion having only one piece of cloth instead of the center of gravity. The region for which the average brightness is calculated may be the entire single portion or a predetermined partial region.
(3) Next, an area brighter than a predetermined threshold value is extracted from the average brightness near the center of gravity of the sheet material (S03, FIG. 5B). This extracted region is the double portion of the sheet material. In other words, since it is a black background, the brightness of the double portion of the two-ply cloth is higher than that of the single-ply portion of the single cloth. When the image is captured with transmitted light illumination, a region darker than the average brightness near the center of gravity of the sheet is extracted by a predetermined threshold value or less. This is because, since transmitted light illumination is used, the brightness of the double-layered portion of the two-layered cloth is lower than that of the single-layered portion of the single-layered cloth.
(4) In the black background image, the area other than the double portion is defined as a single portion (S04).
(5) Further, the boundary between the extracted double portion area and the other single portion area is extracted (S05). In this case the boundary is between the double and single parts.
(6) Next, a masked area is created over a predetermined range from the boundary, and a masked image is obtained by adding the masked area to the image (S06, FIGS. 6, 7B, and 8B). In this case, a mask area is created based on the shape of the boundary (boundary shape). For example, pixels forming the boundary shape to a predetermined number of pixels may be used as the mask region, or expansion processing may be performed based on the pixels forming the boundary shape to create the mask region. Note that the mask area is an area extending over a predetermined range from the boundary between the single portion and the double portion. Therefore, the mask area can be added not only when the double portion is at one end of the sheet portion, but also when it is at both ends and even when it is on the periphery.
As described above, it is possible to obtain a masked image in which the boundary between the single portion and the double portion is masked. As a result, it is possible to suppress erroneous detection that the boundary between the single portion and the double portion is soiled or the like.

In addition, the inspection part 35b may be included as needed. The inspection unit 35b can inspect the sheet material for defects, for example, based on the masked image 8 obtained by the mask applying unit 35a. Defects in the sheet material include, for example, holes and stains. The inspection unit 35b is also read from the storage unit 32 and executed by the processing unit 31 at the time of execution.
Since the present invention can accurately extract the boundary shape of the single portion and the double portion, by creating the mask area based on the boundary shape, the mask area can be minimized and more accurate inspection can be performed. It becomes possible.

<Display section>
The display unit 33 may display the masked image 8 obtained by the mask applying unit 35a, for example.

(Example 1)
FIG. 5A is an example of an image of a sheet material 1 having a single portion 2 and a double portion 4 in Example 1. FIG. FIG. 5B shows a double portion 4 extracted from the image of FIG. 5A. FIG. 6 is a diagram showing a masked image 8 obtained by masking the boundary between the single portion 2 and the double portion 4 in the image of FIG. 5A with a mask region 6. FIG.
As shown in FIG. 5A, when the sheet material 1 having the single layer 2 and the double layer 4 is imaged with a black background, an image of the double layer 4 is brighter than that of the single layer 2 is obtained. This is because when the image is captured with reflected light, the background color appears to be more transparent in the single-ply portion of the single piece of cloth. Especially in a black background image, a brightness difference exceeding a predetermined threshold occurs between the two. Conversely, when an image is captured with transmitted light, the single-layered portion 2 is brighter than the double-layered portion 4, resulting in a brighter image. This is because the single-layer portion has a higher transmittance.
Therefore, the average brightness in the vicinity of the center of gravity of the sheet material 1 in the sheet material image is calculated, and a region brighter than the average brightness by a predetermined threshold value or more is extracted as the double portion 4 region.
Next, in the sheet material image, the area other than the area of the double portion 4 is defined as the single portion 2, and the boundary 3 between the single portion 2 and the double portion 4 is detected.
A masked area 6 is created over a predetermined range from the boundary 3, and a masked image 8 is obtained by adding the masked area 6 to the sheet material image.

(Example 2)
FIG. 7A is an example of an image of a sheet material 1 having a single portion 2 and a double portion 4 in Example 2. FIG. 7B is a diagram showing a masked image obtained by masking the boundary between the single portion 2 and the double portion 4 in the image of FIG. 7A with a mask region 6. FIG.
In the second embodiment, as in the first embodiment, a masked image 8a can be obtained in which the boundary between the single portion 2 and the double portion 4 is masked with the mask area 6. FIG.

(Example 3)
FIG. 8A is an example of an image of a sheet material 1 having a single portion 2 and a double portion 4 in Example 3. FIG. 8B is a diagram showing a masked image obtained by masking the boundary between the single portion 2 and the double portion 4 in the image of FIG. 8A with a mask region 6. FIG.
In Example 3, as in Examples 1 and 2, a masked image 8b in which the boundary between the single portion 2 and the double portion 4 is masked with the mask area 6 can be obtained.

It should be noted that the present disclosure includes appropriate combinations of any of the various embodiments and / or examples described above, and each embodiment and / or The effects of the embodiment can be obtained.

According to the sheet material image processing apparatus and the sheet material image processing method according to the present invention, even in a sheet material having a single-layered portion and a double-layered portion, the boundary between the single-layered portion and the double-layered portion is It is possible to obtain an image capable of suppressing erroneous detection of dirt or the like. Therefore, it is useful for image processing of a sheet material having a single-ply portion and a double-ply portion, such as a picture frame wrapping cloth having a single cloth portion and a double cloth portion.

1, 1a, 1b Sheet material 2 Single portion 3 Boundary 4 Double portion 6 Mask area 8, 8a, 8b Masked image 10 Image processing device 11 Conveying unit 12 Inspection table 13, 13a, 13b Light source unit 14, 14a, 14b, 14c imaging unit 30 control unit (computer device)
31 processing unit 32 storage unit 33 display unit 35 program 35a mask applying unit 35b inspection unit

Claims (3)

a conveying unit for conveying a sheet material having a single portion with a single sheet material and a double portion with a double sheet material;
an imaging unit that captures an image of the sheet material conveyed by the conveying unit to obtain a sheet material image;
a mask applying unit for obtaining a masked image in which a boundary between the single portion and the double portion is masked from the sheet material image;
an inspection unit that detects defects in the sheet material based on the image with the mask;
with
The mask applying unit extracts, from the sheet material image, an area that is brighter than a predetermined threshold or darker than a predetermined threshold or darker than a predetermined threshold as the area of the double portion, and
extracting a region other than the double portion region as the single portion region;
detecting a boundary shape between the double portion area and the single portion area;
performing expansion processing based on the pixels forming the boundary shape, creating a mask region over a predetermined range from the pixels forming the boundary shape, and adding the mask region to the sheet material image to obtain a masked image;
An image processing apparatus for sheet material having a single portion and a double portion. 2. The sheet material image processing apparatus according to claim 1, wherein said imaging unit obtains an image using diffusely reflected light. obtaining a sheet material image having a single portion with a single sheet material and a double portion with a double sheet material;
calculating the brightness near the center of gravity of the sheet material image;
a step of extracting an area brighter than a predetermined threshold or darker than a predetermined threshold or darker than the brightness near the center of gravity as the double portion area;
a step of setting a region other than the double portion region in the sheet material image as the single portion region;
detecting a boundary shape between the double portion area and the single portion area;
a step of performing expansion processing based on the pixels forming the boundary shape, creating a mask area covering a predetermined range from the pixels forming the boundary shape, and obtaining a masked image in which the mask area is added to the sheet material image; and,
detecting defects in the sheet material based on the masked image;
An image processing method for sheet material, comprising:

Images