Method for detecting gap, gap detector, and program

Abstract

To easily acquire detailed information on a gap in the surface of a rubber with a gap in the surface or in the inside.SOLUTION: The method for detecting a gap includes the steps of: acquiring an image of a rubber surface 4 of a rubber having a gap 5 in the inside and in the surface; binarizing the image into black and in white; detecting a gap region from the binarized image, the gap region including a black region with at least one white region and at least one white region surrounded by a black region in the inside. The method for detecting a gas includes calculating a feature of the detected gap region.SELECTED DRAWING: Figure 6

Description

[Technical field]

[0001] The present disclosure relates to a gap detection method, a gap detection device, and a program for detecting a gap in a rubber surface image. [Background technology]

[0002] Rubber tires with voids inside and on the surface (for example, foam rubber tires) have a high coefficient of friction even on snowy or icy roads. In the development of rubber tires with voids inside and on the surface, the shape of the voids on the rubber surface is an important performance indicator that contributes greatly to the grip performance of the tire. Also, in the vulcanization process of rubber manufacturing, voids can appear on the rubber surface during the process of applying heat to the rubber. Since voids in rubber during the vulcanization process are not good for the quality of the rubber, it is necessary to analyze whether or not voids have appeared on the rubber surface.

[0003] As a method for measuring the void shape on the rubber surface, Patent Document 1 discloses an external appearance quality detection method and device for foamed rubber material. Patent Document 1 describes that foamed rubber is heated at a constant temperature, and the foaming speed and the uneven shape of the product surface are estimated from the change in the volume of the rubber.

[0004] Patent Document 2 discloses a method for measuring the foam shape from an image of a foamed resin surface. Patent Document 2 describes that foamed and non-foamed parts on the foamed resin surface are distinguished from each other based on the difference in pixel values ​​between the two parts, and information on the foam shape is obtained. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 02-176561 [Patent Document 2] Japanese Patent Application Publication No. 07-077489 Summary of the Invention [Problem to be solved by the invention]

[0006] The method described in Patent Document 1 cannot obtain detailed information such as the size or number of bubbles. In addition, a dedicated device and sensor are required to capture the volume change of the rubber. The method described in Patent Document 2 cannot accurately distinguish between foamed and non-foamed parts if the rubber surface is dirty. Furthermore, if multiple bubbles are adhered to the surface of the foamed resin, the adhered bubbles are detected as a single bubble. Therefore, the size and number of bubbles cannot be accurately calculated.

[0007] The rubber surface has undulations other than voids or bubbles, and there are also light and dark areas other than voids or bubbles. Therefore, voids or bubbles on the rubber surface cannot be detected by simple color difference (brightness difference). Furthermore, in product development, there is a demand for a simple measurement method with higher throughput that can obtain detailed information about voids on the rubber surface for rubber that has voids inside and on the surface.

[0008] The object of the present disclosure, made in consideration of the above circumstances, is to provide a gap detection method, a gap detection device, and a program that can easily obtain detailed information about voids on the surface of rubber that has voids inside and on its surface. [Means for solving the problem]

[0009] A foaming detection method according to one embodiment of the present disclosure includes the steps of: [1] Obtaining an image of a rubber surface of rubber having internal and surface voids; binarizing the image into black and white; Detecting a void region from the binarized image, the void region having a black region containing at least one white region therein, and the at least one white region surrounded by the black region; calculating features for the detected void regions; A method for detecting a gap, comprising: This configuration makes it possible to distinguish between rubber surface stains and voids on the rubber surface. In other words, it makes it possible to prevent erroneous detection, such as erroneously recognizing rubber surface stains as voids. Therefore, it makes it possible to easily and accurately detect voids.

[0010] A foaming detection method according to one embodiment of the present disclosure includes the steps of: [2] In the gap detection method according to the above item [1], Detecting the void region includes: Calculating the circularity of the white area within the void area; removing the white area having the circularity exceeding an appropriate range as noise; A method for detecting a gap, comprising: This configuration makes it possible to detect voids having a shape close to a sphere, and therefore to more accurately detect voids in the rubber surface.

[0011] A foaming detection method according to one embodiment of the present disclosure includes the steps of: [3] In the gap detection method according to the above-mentioned [1] or [2], determining whether the void region is a single void region, the single void region having a black region containing a single white region therein, and the single white region surrounded by the black region; When it is determined that the void region is not the single void region, dividing the void region into the single void region based on a center of the white region within the void region; calculating a feature for the single void region; and A method for detecting a gap, comprising: This configuration makes it possible to divide the voids into those in a bonded state and those in a non-bonded state, and to calculate the characteristics of a single void that includes both the voids divided into non-bonded states and the voids that were not bonded to begin with, thereby making it possible to more accurately detect the voids in the rubber surface.

[0012] As an embodiment of the present disclosure, a foam detection device includes: [4] A gap detection device for detecting gaps in a rubber surface, comprising a control unit, the control unit comprising: Obtaining an image of a rubber surface of rubber having internal and surface voids; binarizing the image into black and white; Detecting a void region from the binarized image, the void region having a black region containing at least one white region therein, and the at least one white region surrounded by the black region; calculating features for the detected void regions; a gap detection device that performs operations including: This configuration makes it possible to distinguish between rubber surface stains and voids on the rubber surface. In other words, it makes it possible to prevent erroneous detection, such as erroneously recognizing rubber surface stains as voids. Therefore, it makes it possible to easily and accurately detect voids.

[0013] A program according to an embodiment of the present disclosure includes: [5] On the computer, Obtaining an image of a rubber surface of rubber having internal and surface voids; binarizing the image into black and white; Detecting a void region from the binarized image, the void region having a black region containing at least one white region therein, and the at least one white region surrounded by the black region; calculating features for the detected void regions; A program that causes the program to execute operations including the steps of: This configuration makes it possible to distinguish between rubber surface stains and voids on the rubber surface. In other words, it makes it possible to prevent erroneous detection, such as erroneously recognizing rubber surface stains as voids. Therefore, it makes it possible to easily and accurately detect voids. Effect of the Invention

[0014] According to one embodiment of the present disclosure, it is possible to provide a void detection method, a void detection device, and a program that can easily obtain detailed information about voids on the rubber surface for rubber that has voids inside and on its surface. [Brief description of the drawings]

[0015] [Figure 1] 1 is a schematic diagram of a gap detection system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram showing an example of an image of a rubber surface of rubber having voids inside and on the surface according to the present embodiment. [Diagram 3] 1 is a diagram showing a method of photographing a rubber surface using an imaging device from a horizontal direction according to the present embodiment. FIG. [Figure 4] FIG. 2 is a diagram showing a binarized image of a rubber surface according to the present embodiment. [Diagram 5] 10A to 10C are diagrams showing examples of results of gaps on a rubber surface detected by the gap detection method according to the present embodiment. [Figure 6] 5 is a flowchart showing an operation performed by the gap detection device according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] 1 is a schematic diagram of a gap detection system S of the present embodiment. The gap detection system S includes a gap detection device 1 and an imaging device 2 that can communicate with each other via a network 3. The network 3 includes, for example, a mobile communication network, the Internet, or a fixed communication network. Note that the gap detection device 1 and the imaging device 2 may be directly connected by a signal line or the like.

[0017] For ease of explanation, one gap detection device 1 and one imaging device 2 are illustrated in FIG. 1. However, the number of gap detection devices 1 and imaging devices 2 is not limited to this. For example, the process executed by the gap detection device 1 of the present embodiment may be executed by a plurality of gap detection devices 1 that are distributed. The gap detection device 1 may communicate with or be connected to a plurality of imaging devices 2.

[0018] The gap detection device 1 is an information processing device that detects gaps 5 in a rubber surface 4 by a predetermined method described in this specification. In this embodiment, the gap detection device 1 is described as being configured by one computer. However, the gap detection device 1 may be configured by multiple computers, such as a cloud computing system.

[0019] 1, the gap detection device 1 includes a control unit 11, a communication unit 12, a storage unit 13, a display unit 14, and an input unit 15. The components of the gap detection device 1 are communicatively connected to each other via, for example, a dedicated line.

[0020] The control unit 11 can detect the voids 5 in the rubber surface 4 by being executed as described below. The control unit 11 includes, for example, one or more general-purpose processors including a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or a GPU (Graphics Processing Unit). The control unit 11 may include one or more dedicated processors specialized for specific processing. Instead of including a processor, the control unit 11 may include one or more dedicated circuits. The dedicated circuits may be, for example, a FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). The control unit 11 may include an ECU (Electronic Control Unit).

[0021] The communication unit 12 can be connected to the imaging device 2 or another computer, etc., via the network 3. The communication unit 12 includes one or more communication modules for connecting to the network 3. The communication unit 12 may include a module compatible with one or more mobile communication standards including LTE (Long Term Evolution), 4G (4th Generation), or 5G (5th Generation). The communication unit 12 may include a communication module compatible with one or more short-range communication standards or specifications including Bluetooth (registered trademark), AirDrop (registered trademark), IrDA, ZigBee (registered trademark), Felica (registered trademark), or RFID.

[0022] The memory unit 13 may store, for example, information on the results of analysis or processing by the control unit 11. The memory unit 13 may store various information related to the operation or control of the gap detection device 1. The memory unit 13 may store system programs, application programs, embedded software, and the like. The memory unit 13 includes, for example, a semiconductor memory, a magnetic memory, an optical memory, or a combination of at least two of these, but is not limited to these. The semiconductor memory is, for example, a RAM or a ROM. "RAM" is an abbreviation for random access memory. "ROM" is an abbreviation for read only memory. The RAM is, for example, an SRAM or a DRAM. "SRAM" is an abbreviation for static random access memory. "DRAM" is an abbreviation for dynamic random access memory. The ROM is, for example, an EEPROM. "EEPROM" is an abbreviation for electrically erasable programmable read only memory. The memory unit 13 may function, for example, as a main memory device, an auxiliary memory device, or a cache memory. The storage unit 13 may be provided outside the gap detection device 1 and may be accessed by the gap detection device 1 .

[0023] The display unit 14 displays, for example, information on the results of analysis or processing by the control unit 11. The display unit 14 is, for example, a display. The display is, for example, an LCD or an organic EL display. "LCD" is an abbreviation for liquid crystal display. "EL" is an abbreviation for electro luminescence. The display unit 14 may be connected to the gap detection device 1 as an external output device instead of being provided in the gap detection device 1. As a connection method, any method such as USB, HDMI (registered trademark), or Bluetooth (registered trademark) can be used. "USB" is an abbreviation for Universal Serial Bus. "HDMI (registered trademark)" is an abbreviation for High-Definition Multimedia Interface.

[0024] The input unit 15 accepts an operation to input information used in the operation of the gap detection device 1. The input unit 15 is, for example, a physical key, a capacitive key, a pointing device, a touch screen integral with a display, or a microphone. Instead of being provided in the gap detection device 1, the input unit 15 may be connected to the gap detection device 1 as an external input device. As a connection method, any method such as USB, HDMI (registered trademark), or Bluetooth (registered trademark) can be used.

[0025] The imaging device 2 includes a camera and captures an image of the imaging target (for example, a rubber surface in this embodiment). The imaging device 2 further includes a light source and can irradiate light onto the imaging target. In this embodiment, the imaging device 2 is installed above the imaging target surface in a vertical direction, and can capture the imaging target surface by irradiating light onto the imaging target surface in a vertical direction. The captured image includes a still image or a video.

[0026] The imaging device 2 may be a general-purpose terminal. The imaging device 2 may be, for example, a digital camera, or a mobile device such as a mobile phone, a smartphone, a wearable device, or a tablet.

[0027] The imaging device 2 may be provided in the gap detection device 1 or may be provided outside the gap detection device 1. The imaging device 2 can transmit any information including an image to the gap detection device 1 via the network 3 or via a connection such as a signal line for image analysis.

[0028] The imaging device 2 may perform imaging via input of a button, an icon, or the like. Alternatively, the imaging device 2 may perform imaging by receiving a signal from the gap detection device 1. The imaging device 2 may store the captured image in any storage unit. The imaging device 2 may display the captured image on a display device such as a display.

[0029] The method for detecting air gap foaming according to the present embodiment will be described in detail below.

[0030] FIG. 2 shows an example of an image of a rubber surface 4 of rubber having voids 5 inside and on the surface. This image was taken by irradiating light perpendicularly to the rubber surface 4, as described later. As shown in FIG. 2, the voids 5 in the rubber surface 4 include those in which the voids are bonded together and those in which the voids are not bonded together. Therefore, as shown in FIG. 2, the region of the void 5 in the rubber surface 4 has a black (i.e., relatively low brightness) ring-shaped region and a white (i.e., relatively high brightness) round region in the black ring-shaped region. Alternatively, the region of the void 5 in the rubber surface 4 has a black region and a white region in the black region. The rubber having voids 5 inside and on the surface may be, for example, foamed rubber having foam inside and on the surface of the rubber.

[0031] A user who performs the gap detection of this embodiment photographs the rubber surface 4 through the imaging device 2. FIG. 3 is a diagram showing a method of photographing the rubber surface 4 by the imaging device 2 from a horizontal direction. FIG. 3 shows the imaging device 2, the rubber surface 4, the gap 5, the gap wall surface 51, and the gap bottom surface 52. As shown in FIG. 3, the user of this embodiment installs the imaging device 2 equipped with a camera and a light source at an upper portion in a vertical direction relative to the rubber surface 4, and irradiates light in a vertical direction relative to the rubber surface 4 to photograph the rubber surface 4. The image photographed of the rubber surface 4 may be a still image or a video. In an alternative embodiment, a video of the rubber surface 4 may be photographed as described above, and a frame of the photographed video may be cut out as a still image. The rubber surface 4 may be a horizontal surface or a horizontally cut rubber surface. As shown in FIG. 3, the gap 5 of the rubber surface 4 is concave or recessed with respect to the rubber surface 4. Furthermore, as shown in FIG. 3, the gap 5 in the rubber surface 4 has a gap wall surface 51 and a gap bottom surface 52. Photographing the rubber surface 4 as described above makes it possible to utilize the color difference (brightness difference) between the gap wall surface 51 and the gap bottom surface 52. Specifically, when an imaging device 2 equipped with a camera and a light source is installed above the rubber surface 4 and light is irradiated vertically to the rubber surface 4, the rubber surface 4 and the gap bottom surface 52 become white because they reflect light toward the camera, while the gap wall surface 51 becomes black because it does not reflect light toward the camera, as shown by the arrow in FIG. 3. Furthermore, the rubber surface dirt 41 on the rubber surface 4 becomes black because it does not reflect light toward the camera. Therefore, in the photographed image, the gap 5 in the rubber surface 4 has a characteristic that a white round area exists within a black ring-shaped area. Alternatively, the gap 5 in the rubber surface 4 has a characteristic that a white area exists within a black area. As will be described in detail later, when the voids 5 in the rubber surface 4 are adhered, they are characterized by the presence of multiple white regions within a black region. When the voids 5 in the rubber surface 4 are not adhered, they are characterized by the presence of one white region within a black region. These characteristics make it possible to distinguish between surface dirt on the rubber surface 4 and the voids 5. Furthermore, by detecting the black region indicating the void wall surface 51 and the white region indicating the void bottom surface 52, when the void 5 is adhered, it becomes possible to separate and detect the void 5.

[0032] The imaging device 2 transmits an image of the rubber surface 4 to the gap detection device 1 via a network 3 or via a connection such as a signal line.

[0033] The control unit 11 of the gap detection device 1 acquires an image of the rubber surface 4 of the rubber having voids 5 inside and on its surface. In this embodiment, the control unit 11 receives or acquires an image of the rubber surface 4 from the imaging device 2. In an alternative embodiment, the control unit 11 may acquire the image by reading image data from any medium or the like.

[0034] The control unit 11 of the gap detection device 1 executes binarization of the image of the rubber surface 4. In this embodiment, for example, the binarization of the image is to distinguish low and high brightness parts of the image of the rubber surface 4 into black and white by a certain threshold. This threshold can be set appropriately according to the image. FIG. 4 shows the binarized image of the rubber surface 4. FIG. 4 shows the rubber surface 4, the rubber surface dirt 41, the gap 5, the gap wall surface 51, and the gap bottom surface 52. By binarizing the captured image, as shown in FIG. 4, the rubber surface dirt 41 and the gap wall surface 51 of the gap 5 are represented in black, and the rubber surface 4 and the gap bottom surface 52 of the gap 5 are represented in white. As described above, there are gaps 5 in the rubber surface 4 in which the gaps are adhered to each other and gaps in which the gaps are not adhered to each other. In binarizing the image, when the gap 5 is not adhered, one white area indicating the gap bottom surface 52 is present in the black area indicating the gap wall surface 51, as shown in the lower left of Fig. 4. On the other hand, when the gap 5 is adhered, for example, as shown in the lower right of Fig. 4, multiple white areas indicating the gap bottom surface 52 are present in the black area indicating the gap wall surface 51. Therefore, the gap area indicating the gap 5 on the rubber surface 4 has a black area including at least one white area therein, and at least one white area surrounded by a black area.

[0035] The control unit 11 of the gap detection device 1 executes gap detection. In this embodiment, for example, the gap detection detects or extracts the above-mentioned gap region from the binarized image. That is, a gap region having a black region including at least one white region therein and at least one white region surrounded by the black region is detected or extracted. This makes it possible to detect a gap 5 including both non-adhered and adhered gaps. A region consisting only of black regions, that is, rubber surface dirt 41, is not detected. In an alternative embodiment, for example, the gap detection may detect or extract a white region surrounded by a black region (i.e., the gap bottom surface 52) as a gap bottom surface candidate from the binarized image.

[0036] The control unit 11 of the gap detection device 1 executes a roundness calculation. As shown in FIG. 2 to FIG. 4, the shape of the gap 5 in the rubber surface 4 (that is, the shape when the gap 5 is not adhered or when it is divided into an unadhered state) tends to be a shape close to a sphere. Accordingly, the gap bottom surface 52 has a characteristic that it tends to be a shape close to a circle. By utilizing this characteristic, for example, in the present embodiment, the roundness calculation is performed by excluding a white area that is not substantially circular in the shape of the white area indicating the gap bottom surface 52 as a rubber surface stain 41 or noise. In an alternative embodiment, for example, a white area that is not substantially circular in the shape of the white area detected as a gap bottom surface candidate may be excluded from the gap bottom surface candidates. Specifically, the control unit 11 executes the following steps as the roundness calculation. Obtain the area of ​​the white area in the void area detected in the void detection, i.e., the size (A) or the number of dots (number of pixels in the image). In an alternative embodiment, the size of the void bottom candidate (i.e., the white area surrounded by a black area detected as a void bottom candidate) may be obtained. The perimeter (L a That is, the perimeter (L) of a perfect circle having the same size as the size (A) of the white area is calculated. a In this embodiment, the perimeter (L a ) is derived, for example, by equation (1).

[0037]

number

[0038] In an alternative embodiment, the perimeter of a perfect circle having the same size as the size of the potential bottom of the gap may be calculated. The perimeter of the white area in the gap area detected during gap detection (L t ) or the number of dots on the perimeter. In an alternative embodiment, the perimeter of the candidate bottom of the gap may be obtained or calculated. The perimeter of the white area (L t ) and the perimeter (L a ) is compared with. Specifically, in this embodiment, the comparison is performed by calculating, for example, the perimeter ratio. The perimeter ratio is calculated by the formula (2).

[0039]

number

[0040] In an alternative embodiment, the perimeter of the candidate gap bottom surface may be compared to the perimeter of a perfect circle having the same size as the candidate gap bottom surface. If the comparison results in a large difference, the white area is excluded as a rubber surface stain 41 or noise. Specifically, when the white area in the detected gap area has a structure other than a circle, the above-mentioned perimeter ratio, i.e., formula (2), increases from 1. In this embodiment, when the perimeter ratio is equal to or greater than a predetermined threshold, the white area is determined to be noise and excluded. That is, a white area whose roundness exceeds an appropriate range is excluded as noise. In an alternative embodiment, the perimeter of the gap bottom candidate may be compared with the perimeter of a perfect circle having the same size as the gap bottom candidate, and if the difference is determined to be large, the gap bottom candidate may be discarded from the gap bottom candidates. The criteria for the determination may be set appropriately, and for example, a white area whose perimeter ratio is 2 or more may be determined to be noise.

[0041] The calculation of circularity makes it possible to detect a void region including a white region that satisfies circularity, i.e., to remove noise and to detect a void 5 including a void bottom surface 52 having a shape close to a circle.

[0042] The control unit 11 of the void detection device 1 executes adhesion separation. The adhesion separation is executed to divide or separate the voids 5 into a single void when they are adhered. A single void is a state in which the voids 5 are not adhered or are not adhered. In other words, a single void refers to the presence of one white area in a black area. Therefore, a single void area indicating a single void has a black area containing one white area therein and one white area surrounded by the black area. In this embodiment, for example, the control unit 11 executes the following steps as adhesion separation. It is determined whether the void region is the above-mentioned single void region. Alternatively, it may be determined whether the black region in the void region has multiple white regions inside. In other words, it is determined whether the voids 5 are fused. Next, if it is determined that the void region is not a single void region (or that the black region in the void region has multiple white regions inside, i.e., the voids 5 are fused), the void region is divided into single void regions based on the position of the center of the white region indicating the void bottom surface 52. In other words, when the voids 5 are fused, the voids 5 are divided into single voids. This division may be performed by any method. For example, it may be performed using a Watershed algorithm starting from the region of the void bottom surface, or it may be performed by determining a region related to a single void including the void wall surface by expansion processing in image morphology processing.

[0043] FIG. 5 is a diagram showing an example of the result of detecting a void 5 on a rubber surface 4 by the void detection method according to the present embodiment. In FIG. 5, the detected void 5 is surrounded by a rectangle. As each rectangle in FIG. 5 shows, adhesion separation makes it possible to detect a single void. That is, it is possible to detect a void 5 that is originally a single void, and a void 5 that is divided into a single void when the original void 5 is not a single void. That is, when the void 5 is adhered, it is possible to separate the void 5 into a non-adhered state and detect a single void that includes a void 5 that is not originally adhered and a void 5 that is separated into a non-adhered state.

[0044] The control unit 11 of the gap detection device 1 executes a gap characteristic calculation. In this embodiment, for example, the characteristics of a gap region or a single gap region are calculated. The calculation of the characteristics of the gap region is, for example, to quantify the coordinates or size of each of the gap regions or a single gap region, the total number of the gap regions or a single gap region, or the number of the gap regions or a single gap region in a unit area of ​​the rubber surface 4. Therefore, the gap detection device 1 can calculate or detect detailed information about the gap 5 by image analysis using a general-purpose camera. This provides a simple method for measuring the gap 5.

[0045] A gap detection method using the gap detection device 1 will be described with reference to FIG.

[0046] In step S1, the control unit 11 of the gap detection device 1 acquires an image of the rubber surface 4 of rubber having gaps 5 inside and on its surface. In this embodiment, for example, the image of the rubber surface 4 is an image of the rubber surface 4 captured by placing the imaging device 2 equipped with a camera and a light source above the rubber surface 4 in a direction perpendicular to the rubber surface 4 and irradiating the rubber surface 4 with light in a direction perpendicular to the rubber surface 4.

[0047] In step S2, the control unit 11 binarizes the image acquired in step S1 into black and white.

[0048] In step S3, the control unit 11 of the gap detection device 1 executes gap detection. In this embodiment, the control unit 11 detects a gap region having a black region containing at least one white region therein and at least one white region surrounded by the black region, from the image binarized in step S2.

[0049] In step S4, the control unit 11 executes a circularity calculation. In this embodiment, the control unit 11 calculates the circularity of the white area in the gap area, and excludes the white area having a circularity outside the appropriate range as noise.

[0050] In step S5, the control unit 11 executes adhesion separation. In this embodiment, when the control unit 11 determines that the void region is not a single void region having a black region containing a white region therein and a white region surrounded by the black region, the control unit 11 divides the void region into a single void region.

[0051] In step S6, the control unit 11 executes a gap characteristic calculation. In this embodiment, the control unit 11 calculates the coordinates or size of each of the gap regions or a single gap region, the total number of the gap regions or a single gap region, or the number of the gap regions or a single gap region in a unit area of ​​the rubber surface 4.

[0052] Although the present disclosure will be described based on various drawings and examples, it should be noted that those skilled in the art may make various modifications and alterations based on the present disclosure. Other modifications are possible within the scope of the present disclosure. For example, the functions included in each means or step can be rearranged so as not to cause logical inconsistencies, and multiple means or steps can be combined into one or divided.

[0053] As a modification of this embodiment, the execution of at least one of steps S4 and S5 is optional. That is, in the above-described gap detection method, the control unit 11 does not have to execute at least one of steps S4 and S5. As an additional modification of this embodiment, the order of steps S4 and S5 may be reversed.

[0054] For example, in the above embodiment, a program for executing all or part of the functions or processing of the gap detection device 1 can be recorded in a computer-readable recording medium. The computer-readable recording medium includes a non-transitory computer-readable medium, such as a magnetic recording device, an optical disk, a magneto-optical recording medium, or a semiconductor memory. The program is distributed, for example, by selling, transferring, or lending a portable recording medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory) on which the program is recorded. The program may also be distributed by storing the program in the storage of an arbitrary server and transmitting the program from the arbitrary server to another computer. The program may also be provided as a program product. The present disclosure can also be realized as a program executable by a processor.

[0055] A computer temporarily stores a program recorded on a portable recording medium or a program transferred from a server in a main storage device. Then, the computer reads the program stored in the main storage device with a processor and executes processing according to the read program with the processor. The computer may read the program directly from a portable recording medium and execute processing according to the program. The computer may execute processing according to the received program each time a program is transferred from the server to the computer. Processing may be executed by a so-called ASP-type service that realizes functions only by execution instructions and result acquisition without transferring a program from the server to the computer. "ASP" is an abbreviation for application service provider. Programs include information used for processing by a computer and equivalent to a program. For example, data that is not a direct instruction to a computer but has the property of defining computer processing falls under " equivalent to a program.

[0056] [Contribution to the United Nations-led Sustainable Development Goals (SDGs)] The SDGs have been proposed to realize a sustainable society. One embodiment of the present invention is expected to contribute to "No. 9 - Building a foundation for industry and technological innovation." [Explanation of symbols]

[0057] S Void Detection System 1. Gap detection device 11 Control section 12 Communications Department 13 Storage section 14 Display section 15 Input section 2. Imaging device 3. Network 4 Rubber Surface 41 Rubber surface stains 5 void 51 Cavity wall surface 52 Bottom of void

Claims

1. Obtaining an image of a rubber surface of rubber having internal and surface voids; binarizing the image into black and white; Detecting a void region from the binarized image, the void region having a black region containing at least one white region therein, and the at least one white region surrounded by the black region; calculating features for the detected void regions; A method for detecting a void, comprising:

2. 2. The gap detection method according to claim 1, Detecting the void region includes: Calculating the circularity of the white area within the void area; removing the white area having the circularity exceeding an appropriate range as noise; A method for detecting a void, comprising:

3. 2. The gap detection method according to claim 1, determining whether the void region is a single void region, the single void region having a black region containing a single white region therein, and the single white region surrounded by the black region; When it is determined that the void region is not the single void region, dividing the void region into the single void region based on a center of the white region within the void region; calculating a feature for the single void region; and A method for detecting a void, comprising:

4. A gap detection device for detecting gaps in a rubber surface, comprising a control unit, the control unit comprising: Obtaining an image of a rubber surface of rubber having internal and surface voids; binarizing the image into black and white; Detecting a void region from the binarized image, the void region having a black region containing at least one white region therein, and the at least one white region surrounded by the black region; calculating features for the detected void regions; 16. An air gap detection device, the air gap detection device performing operations including:

5. On the computer, Obtaining an image of a rubber surface of rubber having internal and surface voids; binarizing the image into black and white; Detecting a void region from the binarized image, the void region having a black region containing at least one white region therein, and the at least one white region surrounded by the black region; calculating features for the detected void regions; A program that causes an operation including

Images