Method, device, equipment and medium for detecting horizontal stripes of non-uniform glass fiber cloth

Abstract

The present invention relates to the technical field of composite material production, and in particular to a method, device, equipment and medium for detecting horizontal stripes of non-uniform glass fiber cloth. The method comprises: collecting a cloth surface image, performing frequency domain conversion on the image, and obtaining a frequency domain image of the cloth surface; generating a standard spatial domain image of horizontal stripes according to the longitude and latitude angles of the glass fiber cloth; performing frequency domain conversion on the spatial domain image of horizontal stripes, and obtaining a frequency domain image of horizontal stripes; convolving the frequency domain image of horizontal stripes with the frequency domain image of the cloth surface, and obtaining a frequency domain image of the cloth surface after noise reduction; performing spatial domain conversion on the frequency domain image of the cloth surface after noise reduction, and obtaining a frequency domain image of the cloth surface after noise reduction; judging whether there are horizontal stripes on the cloth surface by using a gray value threshold on the frequency domain image of the cloth surface after noise reduction. In the present invention, the frequency domain image of the horizontal stripes is convolved with the frequency domain image of the cloth surface, and other textures of the glass fiber cloth surface are removed, thereby eliminating the interference caused by the change of the cloth surface texture and light, and accurately detecting the horizontal stripes.

Description

Technical Field

[0001] The present invention relates to the technical field of composite material production, and in particular to a method, device, equipment and medium for detecting horizontal stripes of non-uniform glass fiber cloth. Background Art

[0002] Glass fiber is made of glass balls or waste glass through high-temperature melting, wire drawing, winding, weaving and other processes. It is a very good metal substitute and has broad application prospects in the fields of construction, shipbuilding, chemical pipelines, automobiles, aviation, wind power generation, etc. Its application areas are still expanding, and the global market space is huge.

[0003] In the process of glass fiber cloth production, due to the weft laying, some yarns in the middle are often not laid. Figure 1 As shown, there will be a situation where the gap on the fabric is too large, which is called horizontal stripes in the field. In the prior art, manual inspection or visual inspection is generally used. Manual inspection has low efficiency and cannot be carried out in real time along the production line. In the existing visual inspection, since the fiberglass fabric and horizontal stripes are both white, false alarms often occur due to changes in light.

[0004] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art already known to those skilled in the art. Summary of the invention

[0005] The present invention provides a method, device, equipment and medium for detecting horizontal stripes of non-uniform glass fiber cloth, thereby effectively solving the problems in the background technology.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is: a method for detecting horizontal stripes of non-uniform glass fiber cloth, comprising the following steps:

[0007] Collecting cloth surface images, performing frequency domain conversion on the images, and obtaining cloth surface frequency domain images;

[0008] According to the longitude and latitude angles of the fiberglass cloth, a standard horizontal stripe spatial domain image is generated;

[0009] Performing frequency domain conversion on the horizontal stripe spatial domain image to obtain a horizontal stripe frequency domain image;

[0010] Convolving the horizontal stripe frequency domain image with the cloth surface frequency domain image to obtain a denoised cloth surface frequency domain image;

[0011] Performing spatial domain conversion on the denoised cloth surface frequency domain image to obtain a denoised cloth surface image;

[0012] The denoised cloth image is judged by a gray value threshold to determine whether there are horizontal stripes on the cloth.

[0013] Furthermore, generating a standard horizontal stripe space domain image according to the longitude and latitude angles of the glass fiber cloth includes:

[0014] Generate an image with the same pixel accuracy as the cloth image;

[0015] Among them, the background gray value is 0, the horizontal stripe gray value is 255, and the angle of the horizontal stripe is consistent with the angle of the horizontal stripe on the glass fiber cloth.

[0016] Further, the frequency domain conversion includes:

[0017]

[0018] Among them, s is -1; C is the normalization parameter, equal to M is the row of the image, N is the column of the image; f(k,l) is the image in the spatial domain, k and l are the horizontal and vertical coordinates of the pixel points in the image; F(m,n) is the frequency domain image, m and n are the real and imaginary parts in the complex coordinate system.

[0019] Furthermore, the performing of spatial domain conversion includes:

[0020]

[0021] Among them, s is 1; C is the normalization parameter, which is equal to M is the row of the image, N is the column of the image; f(k,l) is the image in the spatial domain, k and l are the horizontal and vertical coordinates of the pixel points in the image; F(m,n) is the frequency domain image, m and n are the real and imaginary parts in the complex coordinate system.

[0022] Furthermore, judging the denoised cloth image by using a gray value threshold comprises:

[0023] Set the gray value threshold to filter the gray value of the cloth image after noise reduction;

[0024] Divide the selected pixels into several continuous areas;

[0025] When the area of ​​the continuous region is greater than a set value, it is determined that there are horizontal stripes on the fabric.

[0026] The present invention also includes a device for detecting horizontal stripes of non-uniform glass fiber cloth, using the above method, including:

[0027] An image acquisition module, wherein the image acquisition module is used to acquire a cloth surface image;

[0028] A spatial domain to frequency domain conversion module, wherein the spatial domain to frequency domain conversion module is used to convert an image from the spatial domain to the frequency domain, or from the frequency domain to the spatial domain;

[0029] A horizontal stripe image generation module, wherein the horizontal stripe image generation module is used to generate a standard horizontal stripe space domain image according to the longitude and latitude angles of the glass fiber cloth;

[0030] A convolution module, the convolution module is used to convolve the horizontal stripe frequency domain image with the cloth surface frequency domain image to obtain a denoised cloth surface frequency domain image;

[0031] The horizontal stripe judging module is used to judge whether there are horizontal stripes on the cloth surface by using a gray value threshold value on the cloth surface image after noise reduction.

[0032] The present invention also includes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described above is implemented.

[0033] The present invention also includes a storage medium on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.

[0034] The beneficial effects of the present invention are as follows: the present invention converts the collected cloth image into the frequency domain to obtain the cloth frequency domain image, then generates a standard horizontal stripe space domain image, and converts it into the frequency domain to obtain the horizontal stripe frequency domain image, convolves the horizontal stripe frequency domain image with the cloth frequency domain image, thereby removing other textures of the glass fiber cloth, and only retains and enhances the features that meet the horizontal stripe angle, and then converts the denoised cloth frequency domain image into the space domain to obtain the denoised cloth image, and finally judges the horizontal stripe by the gray value threshold, thereby eliminating the interference caused by the cloth texture and light changes, and accurately detecting the horizontal stripe. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 It is an image of a fiberglass cloth with horizontal stripes;

[0037] Figure 2 is a flow chart of the method of the present invention;

[0038] Figure 3 for Figure 1 Frequency domain image of the image in ;

[0039] Figure 4 is the spatial domain image of the generated horizontal stripes;

[0040] Figure 5 for Figure 4 Frequency domain image of the image in ;

[0041] Figure 6 for Figure 3 and Figure 5 The image after convolution;

[0042] Figure 7 for Figure 6 The spatial domain image of

[0043] Figure 8 It is a structural schematic diagram of the device of the present invention;

[0044] Fig. 9 A schematic diagram of the structure of a computer device. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0046] like Figure 2 As shown: A method for detecting horizontal stripes of non-uniform glass fiber cloth includes the following steps:

[0047] Collecting cloth surface images, performing frequency domain conversion on the images, and obtaining cloth surface frequency domain images;

[0048] According to the longitude and latitude angles of the fiberglass cloth, a standard horizontal stripe spatial domain image is generated;

[0049] The horizontal stripe spatial domain image is converted into the frequency domain to obtain a horizontal stripe frequency domain image;

[0050] Convolve the horizontal stripe frequency domain image with the cloth surface frequency domain image to obtain a denoised cloth surface frequency domain image;

[0051] The denoised cloth surface frequency domain image is converted into a spatial domain to obtain a denoised cloth surface image;

[0052] Through the gray value threshold, the denoised cloth image is judged to see whether there are horizontal stripes on the cloth.

[0053] The collected cloth image is converted into the frequency domain to obtain the cloth frequency domain image, and then a standard horizontal stripe space domain image is generated and converted into the frequency domain to obtain the horizontal stripe frequency domain image. The horizontal stripe frequency domain image is convolved with the cloth frequency domain image to remove other textures of the fiberglass cloth and only retain and enhance the features that meet the angle of the horizontal stripe. The denoised cloth frequency domain image is then converted into the space domain to obtain the denoised cloth image. Finally, the horizontal stripes are judged by the gray value threshold, thereby eliminating the interference caused by the change of cloth texture and light, and accurately detecting the horizontal stripes.

[0054] In this embodiment, a standard horizontal stripe space domain image is generated according to the longitude and latitude angles of the glass fiber cloth, including:

[0055] Generate an image with the same pixel accuracy as the cloth image;

[0056] Among them, the background gray value is 0, the horizontal stripe gray value is 255, and the angle of the horizontal stripe is consistent with the angle of the horizontal stripe on the glass fiber cloth.

[0057] Perform frequency domain transformations, including:

[0058]

[0059] Among them, s is -1; C is the normalization parameter, equal to M is the row of the image, N is the column of the image; f(k,l) is the image in the spatial domain, k and l are the horizontal and vertical coordinates of the pixel points in the image; F(m,n) is the frequency domain image, m and n are the real and imaginary parts in the complex coordinate system.

[0060] In contrast to frequency domain conversion, when performing spatial domain conversion, the original frequency domain conversion needs to be reversed, including:

[0061]

[0062] Among them, s is 1; C is the normalization parameter, which is equal to M is the row of the image, N is the column of the image; f(k,l) is the image in the spatial domain, k and l are the horizontal and vertical coordinates of the pixel points in the image; F(m,n) is the frequency domain image, m and n are the real and imaginary parts in the complex coordinate system.

[0063] In this embodiment, the denoised cloth image is judged by using the gray value threshold, including:

[0064] Set the gray value threshold to filter the gray value of the cloth image after noise reduction;

[0065] Divide the selected pixels into several continuous areas;

[0066] When the area of ​​the continuous region is larger than the set value, it is determined that there are horizontal stripes on the fabric.

[0067] By filtering the grayscale values ​​of the denoised cloth image and dividing the filtered pixels into several continuous regions, the area of ​​the continuous regions is judged to accurately judge the horizontal stripes, prevent false detection, and ensure the accuracy of horizontal stripe detection.

[0068] like Figure 3 As shown, Figure 1 After the cloth image in the frequency domain is transformed, we get Figure 3 In the frequency domain image, the middle of the image is a low-frequency signal, and the surroundings are high-frequency signals. The brighter the brightness, the more this frequency. At this time, a standard horizontal stripe image needs to be generated. Since filtering is performed in the frequency domain image, the position of the horizontal stripe does not matter. After the frequency domain conversion, the high frequency will always be moved to the surroundings of the frequency domain image, and the low frequency will be moved to the center. The generated standard horizontal stripe spatial domain image is as follows: Figure 4 As shown, Figure 4 Perform frequency domain conversion to obtain Figure 5 The horizontal stripe frequency domain image in the image is then multiplied with the cloth surface frequency domain image, that is, convolution is performed, and filtering is performed. After convolution, the image is obtained Figure 6 In this case, only the frequency information of the angle corresponding to the horizontal bar is retained in the image, and it is enhanced. Figure 6 After the image in is converted to the spatial domain, we can get Figure 7 The cloth image after noise reduction, from Figure 7 It can be seen that most of the texture in the image has been removed, and the information consistent with the angle of the horizontal bar has been retained and strengthened to a certain extent. The horizontal bar can be clearly distinguished from other features. At this time, the detection of the horizontal bar can be completed by means such as gray value threshold.

[0069] like Figure 8 As shown, a device for detecting horizontal stripes of non-uniform glass fiber cloth, using the above method, includes:

[0070] An image acquisition module, which is used to acquire cloth surface images;

[0071] The spatial domain to frequency domain conversion module is used to convert the image from the spatial domain to the frequency domain, or from the frequency domain to the spatial domain;

[0072] A horizontal stripe image generation module is used to generate a standard horizontal stripe spatial domain image according to the longitude and latitude angles of the glass fiber cloth;

[0073] A convolution module, which is used to convolve the horizontal stripe frequency domain image with the cloth surface frequency domain image to obtain a denoised cloth surface frequency domain image;

[0074] The horizontal stripe judgment module is used to judge whether there are horizontal stripes on the cloth surface through the gray value threshold value of the denoised cloth surface image.

[0075] See also Fig. 9 A computer device 400 provided in an embodiment of the present application includes: a processor 410 and a memory 420, wherein the memory 420 stores a computer program executable by the processor 410, and when the computer program is executed by the processor 410, the above method is executed.

[0076] The embodiment of the present application further provides a storage medium 430 on which a computer program is stored. When the computer program is run by the processor 410, the above method is executed.

[0077] Among them, the storage medium 430 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, disk or optical disk.

[0078] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0079] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0080] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0081] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0082] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0083] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0084] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0085] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for detecting horizontal stripes of non-uniform glass fiber cloth, characterized in that: The steps include: Collecting cloth surface images, performing frequency domain conversion on the images, and obtaining cloth surface frequency domain images; According to the longitude and latitude angles of the fiberglass cloth, a standard horizontal stripe spatial domain image is generated; Performing frequency domain conversion on the horizontal stripe spatial domain image to obtain a horizontal stripe frequency domain image; Convolving the horizontal stripe frequency domain image with the cloth surface frequency domain image to obtain a denoised cloth surface frequency domain image; Performing spatial domain conversion on the denoised cloth surface frequency domain image to obtain a denoised cloth surface image; By using a gray value threshold, judging whether there are horizontal stripes on the fabric surface of the de-noised fabric image; According to the latitude and longitude angles of the glass fiber cloth, a standard horizontal stripe space domain image is generated, including: Generate an image with the same pixel accuracy as the cloth image; Among them, the background gray value is 0, the horizontal bar gray value is 255, and the angle of the horizontal bar is consistent with the angle of the horizontal bar on the glass fiber cloth; The step of judging the denoised cloth image by using a gray value threshold comprises: Set the gray value threshold to filter the gray value of the cloth image after noise reduction; Divide the selected pixels into several continuous areas; When the area of ​​the continuous region is greater than a set value, it is determined that there are horizontal stripes on the fabric.

2. The method for detecting horizontal stripes of non-uniform glass fiber cloth according to claim 1, characterized in that: The frequency domain conversion comprises: Among them, s is -1; C is the normalization parameter, equal to M is the row of the image, N is the column of the image; f(k,l) is the image in the spatial domain, k and l are the horizontal and vertical coordinates of the pixel points in the image; F(m,n) is the frequency domain image, m and n are the real and imaginary parts in the complex coordinate system.

3. The method for detecting horizontal stripes of non-uniform glass fiber cloth according to claim 1, characterized in that: The performing of spatial domain conversion includes: Among them, s is 1; C is the normalization parameter, which is equal to M is the row of the image, N is the column of the image; f(k,l) is the image in the spatial domain, k and l are the horizontal and vertical coordinates of the pixel points in the image; F(m,n) is the frequency domain image, m and n are the real and imaginary parts in the complex coordinate system.

4. A device for detecting horizontal stripes of non-uniform glass fiber cloth, characterized in that: Using the method according to any one of claims 1 to 3, comprising: An image acquisition module, wherein the image acquisition module is used to acquire a cloth surface image; A spatial domain to frequency domain conversion module, wherein the spatial domain to frequency domain conversion module is used to convert an image from the spatial domain to the frequency domain, or from the frequency domain to the spatial domain; A horizontal stripe image generation module, wherein the horizontal stripe image generation module is used to generate a standard horizontal stripe space domain image according to the longitude and latitude angles of the glass fiber cloth; A convolution module, the convolution module is used to convolve the horizontal stripe frequency domain image with the cloth surface frequency domain image to obtain a denoised cloth surface frequency domain image; The horizontal stripe judging module is used to judge whether there are horizontal stripes on the cloth surface by using a gray value threshold value on the cloth surface image after noise reduction.

5. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 3 is implemented.

6. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images