Demoulding cloth cover weft missing detection method, device, equipment and medium

Abstract

The invention relates to the technical field of pultrusion, in particular to a method, a device, equipment and a medium for detecting wefting missing of a de-molding cloth cover, and the method comprises the following steps: acquiring a de-molding cloth cover image, and converting the de-molding cloth cover image into a grayscale image; performing mean filtering on the grayscale image, and performing image enhancement on a low-frequency part of the image to obtain an enhanced image; performing mean filtering on the enhanced image, and extracting pixel points in the image through a gray value threshold; and carrying out morphological expansion operation on the extracted pixel points, judging whether the expanded area is greater than a set value, and if so, judging that the defect is the cloth cover missing weft defect. According to the method, image enhancement is carried out on the low-frequency part of the image, so that the potential wefting missing defect is more obvious, morphological expansion operation is carried out on the extracted pixel points, so that a possible defect area is enlarged and is more obvious, the wefting missing defect of the de-molding cloth surface can be automatically detected in real time, the detection accuracy and efficiency are effectively improved, and the method is suitable for large-scale popularization and application. And the omission ratio of manual detection is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of pultrusion, and in particular to a method, device, equipment and medium for detecting weft missing on a demoulding cloth. Background Art

[0002] The purpose of using release cloth for pultruded parts is, on the one hand, to prevent the surface from being worn or damaged and to ensure the strength of the pultruded parts for subsequent use; on the other hand, to increase the roughness requirements on the surface of the pultruded parts and to increase the adhesion performance with other products.

[0003] Sometimes, the release cloth may be missing weft, which may cause defects in the pultruded product. Therefore, the release cloth needs to be inspected in real time. However, manual inspection will inevitably lead to missed inspections, and it is impossible to perform real-time inspection of the missing weft on the surface of the release cloth for a long time.

[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 missing weft on the surface of a demoulding 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 missing weft on the surface of a demoulding cloth, comprising the following steps:

[0007] Acquire a surface image of the demoulding cloth, and convert the surface image into a grayscale image;

[0008] Performing mean filtering on the grayscale image and performing image enhancement on the low-frequency portion of the image to obtain an enhanced image;

[0009] Performing mean filtering on the enhanced image, and extracting pixel points in the image by gray value threshold;

[0010] The extracted pixel points are subjected to morphological dilation operation, and it is determined whether the expanded area is larger than the set value. If it is larger, it is determined as a weft missing defect on the cloth surface.

[0011] Furthermore, the step of enhancing the low-frequency portion of the image includes:

[0012] Convolve the image using a convolution kernel consisting of a horizontal filter vector and a vertical filter vector;

[0013] The grayscale value of each pixel in the convolved image is divided by a set value to obtain the enhanced image.

[0014] Furthermore, the lateral filtering vector is:

[0015] e = [-1 -4 -5 0 5 4 1];

[0016] The longitudinal filtering vector is:

[0017]

[0018] The convolution kernel is composed of:

[0019]

[0020] Furthermore, after the convolution, the grayscale value of each pixel in the image is divided by 6 to obtain the enhanced image.

[0021] Furthermore, extracting pixels in the image by using a gray value threshold comprises:

[0022] Comparing the grayscale value difference of each corresponding pixel point in the enhanced image and the mean filtered image of the enhanced image;

[0023] When the gray value difference exceeds the gray value threshold, the pixel point is extracted from the enhanced image.

[0024] Furthermore, the performing a morphological dilation operation on the extracted pixel points includes:

[0025] Segment the connected domains of the extracted pixels to obtain several regions;

[0026] Perform morphological dilation operations on several regions and segment connected domains to obtain several dilated regions;

[0027] The area of ​​several expanded regions is determined.

[0028] The present invention also includes a device for detecting missing weft on the surface of a demoulding cloth, using the above method, the detection device includes:

[0029] An acquisition unit, used for acquiring a surface image of the demoulding cloth and converting the surface image into a grayscale image;

[0030] An enhancement unit, used for performing mean filtering on the grayscale image and performing image enhancement on the low-frequency part of the image to obtain an enhanced image;

[0031] An extraction unit, used for performing mean filtering on the enhanced image and extracting pixel points in the image by gray value threshold;

[0032] The judging unit is used to perform a morphological dilation operation on the extracted pixel points and judge whether the expanded area is larger than a set value. If so, it is judged as a weft missing defect on the cloth surface.

[0033] 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.

[0034] 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.

[0035] The beneficial effects of the present invention are as follows: the present invention collects the surface image of the demoulding cloth through a camera or other image acquisition device, and converts it into a grayscale image to simplify subsequent image processing operations. The grayscale image is mean filtered to reduce the noise in the image and make the image smoother. Subsequently, the low-frequency part of the image is enhanced to make the potential missing weft defect more obvious. The pixel points in the image are extracted through the grayscale value threshold to screen out the area where the missing weft may exist. The extracted pixel points are morphologically expanded to expand the possible defective area to make it more obvious. The area of ​​the expanded area is calculated, and it is determined whether the area is greater than the set threshold. If the area is greater than the threshold, it is determined that there is a missing weft defect in the area. Through the above steps, the method can automatically and real-time detect the missing weft defect on the surface of the demoulding cloth, effectively improve the accuracy and efficiency of detection, and reduce the missed detection rate of manual detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] 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.

[0037] Figure 1 is a flow chart of the method of the present invention;

[0038] Figure 2 is the grayscale image of the surface of the release cloth;

[0039] Figure 3 For Figure 2 Image after mean filtering;

[0040] Figure 4 For Figure 3 An enhanced image after image enhancement;

[0041] Figure 5 for Figure 4 The mean filtered image of

[0042] Figure 6An image with pixels extracted by gray value threshold;

[0043] Figure 7 for Figure 6 The image after dilation;

[0044] Figure 8 It is a structural schematic diagram of the device of the present invention;

[0045] Fig. 9 It is a schematic diagram of the structure of the computer device of the present invention. DETAILED DESCRIPTION

[0046] 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.

[0047] like Figure 1 As shown: A method for detecting missing weft on a demoulding cloth comprises the following steps:

[0048] Get the demoulding cloth surface image and convert it into a grayscale image. Figure 2 As shown;

[0049] The grayscale image is mean filtered, where the size of the slide film is 32*1. Figure 2 The mean filtered image is Figure 3 As shown, the low-frequency part of the image is enhanced to obtain an enhanced image. The enhanced image is as shown in Figure 4 As shown;

[0050] The enhanced image is mean filtered, where the size of the synovial membrane is 64*64, and the mean filtered image of the enhanced image is as follows Figure 5 As shown, the pixels in the image are extracted by gray value threshold, and the image of the extracted pixels is shown in Figure 6 As shown;

[0051] The extracted pixels are subjected to morphological dilation operation, and the dilated image is as follows: Figure 7 As shown, it is determined whether the expanded area is larger than the set value. If it is larger, it is determined as a weft missing defect on the cloth surface.

[0052] The surface image of the demoulding cloth is collected by a camera or other image acquisition device and converted into a grayscale image to simplify subsequent image processing operations. The grayscale image is mean filtered to reduce the noise in the image and make the image smoother. Subsequently, the low-frequency part of the image is enhanced to make the potential missing weft defect more obvious. The pixel points in the image are extracted through the grayscale value threshold to screen out the area where the missing weft may exist. The extracted pixel points are morphologically expanded to expand the possible defect area to make it more obvious. The area of ​​the expanded area is calculated, and it is determined whether the area is greater than the set threshold. If the area is greater than the threshold, it is determined that there is a missing weft defect in the area. Through the above steps, the method can automatically and real-time detect the missing weft defect on the surface of the demoulding cloth, effectively improve the accuracy and efficiency of detection, and reduce the missed detection rate of manual detection.

[0053] Among them, the low-frequency part of the image is enhanced, including:

[0054] Convolve the image using a convolution kernel consisting of a horizontal filter vector and a vertical filter vector;

[0055] The gray value of each pixel in the convolved image is divided by the set value to obtain an enhanced image.

[0056] The grayscale image is convolved using a convolution kernel consisting of a transverse filter vector and a longitudinal filter vector. The transverse filter vector is mainly used to capture the transverse features of the image, while the longitudinal filter vector is used to capture the longitudinal features of the image. By combining the filter vectors in these two directions into a convolution kernel, the low-frequency part of the image can be effectively enhanced, making the potential missing weft defects more prominent. The convolved image is processed by dividing the grayscale value of each pixel in the image by a set value. This set value is usually a constant, which is used to adjust the contrast of the image so that the enhanced image is clearer and the defective area is highlighted. Through this process, the enhanced image can better show the missing weft area on the fabric, thereby improving the accuracy of subsequent detection steps. This preferred embodiment combines directional filtering and grayscale value normalization to make the enhancement of the low-frequency part of the image more effective, laying the foundation for the accurate detection of missing weft defects.

[0057] As a preference of the above embodiment, the lateral filtering vector is:

[0058] e = [-1 -4 -5 0 5 4 1];

[0059] The vertical filter vector is:

[0060]

[0061] The convolution kernel is composed of:

[0062]

[0063] After convolution, the grayscale value of each pixel in the image is divided by 6 to obtain an enhanced image.

[0064] The lateral filter vector is used to capture the lateral feature changes of the image. By giving a larger weight to the central value, i.e. 0, and symmetrically distributing the weights on both sides, it helps to enhance the edges and details in the image. The longitudinal filter vector is used to capture the longitudinal features of the image. This vector is symmetrical, similar to a weighted average filter, which is used to smooth the image while retaining important longitudinal structural information. After the convolution process, the grayscale value of each pixel is divided by 6. This can balance the enhancement effect brought by the convolution operation and avoid excessive image enhancement resulting in loss of details or noise. Through this preferred filtering and enhancement process, the method for detecting missing weft on the surface of the demoulding cloth of pultruded parts can more accurately identify potential defective areas, thereby improving the reliability and efficiency of the overall detection.

[0065] As a preferred embodiment of the above, extracting pixels in the image by gray value threshold includes:

[0066] Compare the grayscale value difference of each corresponding pixel in the enhanced image and the mean filtered image of the enhanced image;

[0067] When the gray value difference exceeds the gray value threshold, the pixel is extracted in the enhanced image.

[0068] First, obtain the enhanced image and its corresponding mean-filtered image. The enhanced image has been low-frequency enhanced by the aforementioned convolution operation, while the mean-filtered image is the result of mean-filtering the enhanced image. This process smoothes the noise and fine textures in the image. Calculate the grayscale value difference of each corresponding pixel in the enhanced image and the mean-filtered image. Perform a threshold judgment on the calculated grayscale value difference. If the grayscale value difference of a pixel exceeds the preset grayscale value threshold, it is considered that the pixel may have a defect.

[0069] In this way, the pixels that may represent missing weft defects in the enhanced image can be effectively extracted. This is because in the enhanced image, the grayscale value of the defective area is usually significantly different from the surrounding area. Through difference calculation and threshold judgment, these abnormal areas can be accurately identified.

[0070] In this embodiment, a morphological dilation operation is performed on the extracted pixel points, including:

[0071] Segment the connected domains of the extracted pixels to obtain several regions;

[0072] Perform morphological dilation operations on several regions and segment connected domains to obtain several dilated regions;

[0073] The area of ​​several expanded regions is determined.

[0074] The pixels extracted from the enhanced image are segmented into connected domains. A connected domain refers to a set of pixels in an image that are connected to a certain pixel and meet certain conditions (for example, gray value similarity or binarization). Through connected domain segmentation, the pixels extracted from the image can be segmented into several regions, each of which represents an independent area where missing latitudes may exist.

[0075] A morphological dilation operation is performed on each segmented connected domain region. The purpose of the dilation operation is to expand the boundaries of the connected domain regions, making the morphological features of these regions more obvious and helping to connect regions that have been segmented due to noise or discontinuities. Specifically, morphological dilation can be achieved by adding neighboring pixels around each pixel, which makes the region "expand", fills in small holes that may exist, and enhances the visibility of defects. After the dilation operation, regions may become connected or more obvious, so it is necessary to segment the connected domains again. This step divides the dilated image region into several new connected domains again to ensure that each connected domain region is independent and can be analyzed separately.

[0076] The area of ​​each connected domain after expansion is calculated and determined. By calculating the area of ​​these areas, it is possible to determine which areas may be missing weft defects. If the area of ​​a certain area is greater than the set threshold, it is considered that there is a missing weft defect in the area. Through the morphological expansion operation, not only the area where there may be missing weft defects is expanded, but also the accuracy and reliability of detection are further improved through the segmentation and area determination of the connected domain. The introduction of the expansion operation helps to reduce missed detections caused by noise or image discontinuity, making the detection system more stable and effective.

[0077] like Figure 8 As shown, this embodiment also includes a device for detecting missing weft on the surface of a demoulding cloth. Using the above method, the detection device includes:

[0078] An acquisition unit, used for acquiring a surface image of the demoulding cloth and converting the surface image into a grayscale image;

[0079] An enhancement unit, used for performing mean filtering on the grayscale image and enhancing the low-frequency part of the image to obtain an enhanced image;

[0080] An extraction unit, used for performing mean filtering on the enhanced image and extracting pixel points in the image through a gray value threshold;

[0081] The judging unit is used to perform a morphological dilation operation on the extracted pixel points and judge whether the expanded area is larger than a set value. If so, it is judged as a weft missing defect on the cloth surface.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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 missing weft on a demoulding cloth, characterized in that: The steps include: Acquire a surface image of the demoulding cloth, and convert the surface image into a grayscale image; Performing mean filtering on the grayscale image and performing image enhancement on the low-frequency portion of the image to obtain an enhanced image; Performing mean filtering on the enhanced image, and extracting pixel points in the image by gray value threshold; The extracted pixel points are subjected to morphological dilation operation, and it is determined whether the expanded area is larger than the set value. If it is larger, it is determined as a weft missing defect on the cloth surface.

2. The method for detecting missing weft on the surface of a demoulding cloth according to claim 1, characterized in that: The step of performing image enhancement on the low-frequency part of the image comprises: Convolve the image using a convolution kernel consisting of a horizontal filter vector and a vertical filter vector; The grayscale value of each pixel in the convolved image is divided by a set value to obtain the enhanced image.

3. The method for detecting missing weft on the surface of a demoulding cloth according to claim 2, characterized in that: The lateral filtering vector is: e＝[-1-4-5 0 5 4 1]； The longitudinal filtering vector is: The convolution kernel is composed of:

4. The method for detecting missing weft on the surface of a demoulding cloth according to claim 3, characterized in that: After the convolution, the grayscale value of each pixel in the image is divided by 6 to obtain the enhanced image.

5. The method for detecting missing weft on the surface of a demoulding cloth according to claim 1, characterized in that: The step of extracting pixels from an image by using a gray value threshold comprises: Comparing the grayscale value difference of each corresponding pixel point in the enhanced image and the mean filtered image of the enhanced image; When the gray value difference exceeds the gray value threshold, the pixel point is extracted from the enhanced image.

6. The method for detecting missing weft on the surface of a demoulding cloth according to claim 5, characterized in that: The performing a morphological dilation operation on the extracted pixel points includes: Segment the connected domains of the extracted pixels to obtain several regions; Perform morphological dilation operations on several regions and segment connected domains to obtain several dilated regions; The area of ​​several expanded regions is determined.

7. A device for detecting missing weft on the surface of a demoulding cloth, characterized in that: Using the method according to any one of claims 1 to 6, the detection device comprises: An acquisition unit, used for acquiring a surface image of the demoulding cloth and converting the surface image into a grayscale image; An enhancement unit, used for performing mean filtering on the grayscale image and performing image enhancement on the low-frequency part of the image to obtain an enhanced image; An extraction unit, used for performing mean filtering on the enhanced image and extracting pixel points in the image by gray value threshold; The judging unit is used to perform a morphological dilation operation on the extracted pixel points and judge whether the expanded area is larger than a set value. If so, it is judged as a weft missing defect on the cloth surface.

8. 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 6 is implemented.

9. 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 6 is implemented.

Images