Image recognition-based furniture structure quality detection method and device

Abstract

The application relates to the field of furniture quality detection, and discloses a furniture structure quality detection method and device based on image recognition. The method comprises the following steps: acquiring a plurality of sample furniture images of a plurality of furniture products, segmenting the sample furniture images into a plurality of sub-sample area images, and dividing the plurality of sub-sample area images into a plurality of sub-sample groups; labeling the sub-sample area images in the plurality of sub-sample groups, and training a sub-detection system according to the labeled sub-sample area images in the sub-sample groups; determining a plurality of sub-detection systems corresponding to furniture structures according to the furniture structures, and deploying the plurality of sub-detection systems corresponding to the furniture structures, wherein the plurality of sub-detection systems are used for detecting the product quality of hole positions, frame corners and frame connecting positions of the furniture structures respectively. The application can quickly detect the furniture quality according to the product structures of the rapidly developing and changing furniture.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of furniture quality detection, more specifically, to a furniture structure quality detection method and device based on image recognition. BACKGROUND

[0002] In the production of small furniture, the quality of furniture is generally detected by artificial quality inspection to ensure that it meets certain quality standards. When checking the appearance of furniture by artificial inspection, it is necessary to detect whether the shape conforms to the regulations, whether the surface has scratches, cracks or other defects by the naked eye, and even to measure the size of the furniture using a tape measure, calipers and other tools to ensure that the furniture meets the design specifications. It is time-consuming and laborious to check and evaluate the quality of small furniture by artificial inspection, and it is easy to miss the size and structure of small furniture.

[0003] With the development of technology, image recognition technology has been widely used in furniture quality inspection, especially on the production line of small furniture. Image recognition quality inspection uses cameras and computer vision algorithms to automatically detect quality problems of furniture, improving efficiency and consistency. However, the existing image recognition technology cannot adapt to the rapid changes in the structural design of small furniture when inspecting the quality of furniture, and cannot quickly detect the rapidly developing and changing product structure of furniture. For example, patent CN118823029B (application number: CN202411314735.1) provides a furniture surface quality detection method based on machine vision, which includes: acquiring a target gray image of a target furniture surface to be detected, and determining the first number of other pixel points in the target gray image that have the same gray value as the target pixel point; determining the first parameter value of the target pixel point according to the gray values of other pixel points in the neighborhood of the target pixel point and the first number; determining the gradient feature difference value between the target pixel point and other pixel points in the neighborhood, and determining the second parameter value of the target pixel point according to the first parameter value and the gradient feature difference value; performing saliency detection on the target gray image using the second parameter value of the target pixel point to obtain a saliency region in the target gray image, and taking the saliency region as a scratch region of the surface to be detected. The method in patent CN118823029B focuses on detecting the quality of the surface of the furniture, and cannot quickly detect the quality of the furniture for the rapidly developing and changing product structure of the furniture. SUMMARY

[0004] The purpose of the present application is to provide a furniture structure quality detection method and device based on image recognition, which solves the technical problem of being unable to quickly detect the quality of furniture for the rapidly developing and changing product structure of furniture, and achieves the technical effect of quickly detecting the quality of furniture for the rapidly developing and changing product structure of furniture.

[0005] The embodiment of the application provides a furniture structure quality detection method based on image recognition, which comprises the following steps: obtaining a plurality of sample furniture images of a plurality of furniture products, and segmenting the sample furniture images into a plurality of sub-sample area images, and dividing the plurality of sub-sample area images into a plurality of sub-sample groups; wherein the sub-sample area images comprise area images of hole positions, frame corners and frame connecting positions of the furniture products; labeling the sub-sample area images in the plurality of sub-sample groups, and training a sub-detection system according to the labeled sub-sample area images in the sub-sample groups; determining a plurality of sub-detection systems corresponding to the furniture structure according to the furniture structure, and deploying the plurality of sub-detection systems corresponding to the furniture structure, and the plurality of sub-detection systems are used for detecting the product quality of the hole positions, the frame corners and the frame connecting positions of the furniture structure respectively.

[0006] In a possible implementation, the obtaining a plurality of sample furniture images of a plurality of furniture products, and segmenting the sample furniture images into a plurality of sub-sample area images, and dividing the plurality of sub-sample area images into a plurality of sub-sample groups comprises: obtaining a plurality of sample furniture images of a planar frame structure of a plurality of furniture products, and segmenting the sample furniture images into a plurality of sub-sample area images according to positions of hole positions, frame corners and frame connecting positions of the planar frame structure of the furniture products; and dividing the plurality of sub-sample area images into a plurality of sub-sample groups according to similarities of the hole positions, the frame corners and the frame connecting positions.

[0007] In another possible implementation, the obtaining a plurality of sample furniture images of a plurality of furniture products, and segmenting the sample furniture images into a plurality of sub-sample area images, and dividing the plurality of sub-sample area images into a plurality of sub-sample groups further comprises: determining structure similarities of the planar frame structure of the plurality of furniture products, and segmenting the sample furniture images into a plurality of sub-sample area images according to the structure similarities, wherein the plurality of sub-sample area images correspond to positions of frame corners and frame connecting positions in the sample furniture images respectively; and dividing the plurality of sub-sample area images into a plurality of sub-sample groups according to similarities of the frame corners and the frame connecting positions respectively.

[0008] In another possible implementation, the determining a plurality of sub-detection systems corresponding to the furniture structure according to the furniture structure comprises: determining a configuration file corresponding to the furniture structure according to a furniture structure image of the furniture structure by using a furniture structure recognition model; and determining the plurality of sub-detection systems corresponding to the furniture structure according to the configuration file.

[0009] In another possible implementation, the method further comprises: displaying the furniture structure image of the furniture structure and the plurality of sub-detection systems corresponding to the furniture structure, and displaying a corresponding relationship between the image area of the furniture structure image and the plurality of sub-detection systems, and checking the corresponding relationship between the image area of the furniture structure image and the plurality of sub-detection systems by using artificial verification.

[0010] In another possible implementation, the method further includes: when the plurality of sub-detection systems respectively detect the product quality of the hole positions, the frame corners and the frame connections of the furniture structure, outputting a furniture structure image of the furniture structure and a corresponding relationship between the detection results of the plurality of sub-detection systems corresponding to the furniture structure; and checking, by the detection checking unit, the corresponding relationship between the furniture structure image of the furniture structure and the detection results of the plurality of sub-detection systems corresponding to the furniture structure according to the image area of the furniture structure image manually checked and the corresponding relationship of the plurality of sub-detection systems.

[0011] In another possible implementation, the checking, by the detection checking component, the corresponding relationship between the furniture structure image of the furniture structure and the detection results of the plurality of sub-detection systems corresponding to the furniture structure according to the image area of the furniture structure image manually checked and the corresponding relationship of the plurality of sub-detection systems includes: determining first area coordinates of the detection results of the first sub-detection system, and determining second area coordinates of the first sub-detection system of the furniture structure image manually checked, determining that the first sub-detection system has a detection fault and prompting maintenance of the first sub-detection system when a distance between the first area coordinates and the second area coordinates is greater than or equal to a preset distance, and determining that the first sub-detection system is in normal operation when the distance between the first area coordinates and the second area coordinates is less than the preset distance.

[0012] In another possible implementation, the checking, by the detection checking component, the corresponding relationship between the furniture structure image of the furniture structure and the detection results of the plurality of sub-detection systems corresponding to the furniture structure according to the image area of the furniture structure image manually checked and the corresponding relationship of the plurality of sub-detection systems further includes: obtaining a plurality of output result area coordinates of a plurality of output result areas of the plurality of sub-detection systems, determining an output result distribution feature of the plurality of output result area coordinates, obtaining a plurality of standard result area coordinates of a plurality of standard result areas of the plurality of sub-detection systems manually checked, determining a standard result distribution feature of the plurality of standard result area coordinates, determining that the plurality of sub-detection systems are in normal operation when a similarity between the output result distribution feature and the standard result distribution feature is greater than or equal to a preset similarity, and determining that the plurality of sub-detection systems are not in normal operation and prompting maintenance of the plurality of sub-detection systems when the similarity between the output result distribution feature and the standard result distribution feature is less than the preset similarity.

[0013] The embodiment of the present application further provides a furniture structure quality detection device based on image recognition, which includes units for executing the method in any of the above.

[0014] The embodiment of the present application further provides a furniture structure quality detection device based on image recognition, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method in any of the above when executing the computer program.

[0015] The embodiment of the present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method according to any one of the above.

[0016] The embodiment of the present application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the method according to any one of the above.

[0017] Compared with the prior art, the embodiment of the present application has the beneficial effects that:

[0018] The embodiment of the present application provides a furniture structure quality detection method based on image recognition, which comprises the following steps: acquiring a plurality of sample furniture images of a plurality of furniture products, segmenting the sample furniture images into a plurality of sub-sample area images, and dividing the plurality of sub-sample area images into a plurality of sub-sample groups; wherein the sub-sample area images comprise area images of hole positions, frame corners and frame connecting positions of the furniture products; labeling the sub-sample area images in the plurality of sub-sample groups, and training a sub-detection system according to the labeled sub-sample area images in the sub-sample groups; determining a plurality of sub-detection systems corresponding to the furniture structure according to the furniture structure, and deploying the plurality of sub-detection systems corresponding to the furniture structure, wherein the plurality of sub-detection systems are used to detect the product quality of the hole positions, the frame corners and the frame connecting positions of the furniture structure respectively. The method in the embodiment of the present application can adapt to the rapid development of small furniture, can quickly configure a device capable of high-quality structure detection for small furniture, improve the quality detection efficiency and configuration efficiency of small furniture, and improve the production efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0020] Figure 1 A flowchart of a furniture structure quality detection method based on image recognition provided by the embodiment of the present application is shown in the figure.

[0021] Figure 2 A schematic diagram of a sub-sample area image obtained by a furniture structure quality detection method based on image recognition in the embodiment of the present application is shown in the figure.

[0022] Figure 3 A working schematic diagram of a furniture structure quality detection method based on image recognition in the embodiment of the present application during quality detection is shown in the figure.

[0023] Figure 4 Another flowchart of a furniture structure quality detection method based on image recognition provided by an embodiment of the present application is shown in FIG. 2.

[0024] Figure 5 A logic structure diagram of a furniture structure quality detection device based on image recognition provided by an embodiment of the present application is shown in FIG. 3.

[0025] Figure 6 An entity structure diagram of a furniture structure quality detection device based on image recognition provided by an embodiment of the present application is shown in FIG. 4. DETAILED DESCRIPTION

[0026] It should be understood that the term "comprises" as used in the specification and the appended claims indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0027] It should also be understood that the term "and / or" as used in the specification and the appended claims, means any one or more of the associated listed items, as well as all possible combinations of the items, and includes the possibility of no items.

[0028] As used in the specification and the appended claims, the term "if' can be interpreted as meaning "when" or "once" or "in response to a determination" or "in response to a detection" depending on the context. Similarly, the phrase "if determined" or "if detected [the described condition or event]" can be interpreted as meaning "once determined" or "in response to a determination" or "once detected [the described condition or event]" or "in response to a detection [the described condition or event]" depending on the context.

[0029] In addition, in the description of the specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0030] The reference in the specification to "one embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. Thus, the appearances of the phrases "in one embodiment", "in some embodiments", "in other embodiments", "in additional embodiments", etc. in various places in the specification are not necessarily all referring to the same embodiment, unless otherwise specifically stated. The terms "comprise", "comprises", "comprising", "include", "includes", "including" and their variants are meant to be synonymous with "including but not limited to", unless otherwise specifically stated.

[0031] The existing image recognition technology cannot adapt to the rapid changes in the structural design of small furniture when detecting the quality of furniture, and cannot quickly detect the product structure of rapidly developing and changing furniture.

[0032] Based on the above reasons, the embodiment of the present application provides a furniture structure quality detection method based on image recognition, which comprises: acquiring a plurality of sample furniture images of a plurality of furniture products, and dividing the sample furniture images into a plurality of sub-sample area images, and dividing the plurality of sub-sample area images into a plurality of sub-sample groups; wherein the sub-sample area image includes the area image of the hole site, the frame corner and the frame connection of the furniture product; labeling the sub-sample area images in the plurality of sub-sample groups, and training a sub-detection system according to the labeled sub-sample area images in the sub-sample groups; determining a plurality of sub-detection systems corresponding to the furniture structure according to the furniture structure, and deploying the plurality of sub-detection systems corresponding to the furniture structure, and the plurality of sub-detection systems are used to detect the product quality of the hole site, the frame corner and the frame connection of the furniture structure. The method in the embodiment of the present application can adapt to the rapid development of small furniture, can quickly configure a device capable of high-quality structure detection for small furniture, improve the quality detection efficiency and configuration efficiency of small furniture, and improve the production efficiency.

[0033] In some scenarios, the furniture structure quality detection method based on image recognition of the embodiment of the present application can be applied to the quality detection of small furniture, which can quickly configure the corresponding quality detection device in the production of small furniture, and can adapt to the rapid iteration and product upgrading of small furniture products.

[0034] The furniture structure quality detection method based on image recognition provided by the embodiment of the present application will be described in detail below with specific examples.

[0035] Figure 1 The flowchart of the furniture structure quality detection method based on image recognition provided by the embodiment of the present application is shown in Figure 1 As shown, the method comprises S110 to S130, which will be described in detail below.

[0036] S110, acquiring a plurality of sample furniture images of a plurality of furniture products, and dividing the sample furniture images into a plurality of sub-sample area images, and dividing the plurality of sub-sample area images into a plurality of sub-sample groups. Wherein the sub-sample area image includes the area image of the hole site, the frame corner and the frame connection of the furniture product.

[0037] In the method embodiment, when the small furniture product is rapidly iterated, the overall structure of the small furniture product is often changed, and the local area of the small furniture product is often similar. In order to improve the adaptability to the small furniture product, the small furniture product is split into multiple reusable image detection areas for quality detection, thereby improving the adaptability to the rapid iteration of the small furniture product and improving the detection effect of the structure of the small furniture product.

[0038] In the method embodiment, multiple sample furniture images of multiple furniture products can be obtained first, the multiple furniture products are furniture products of different product series, and the multiple sample furniture images are furniture images from different furniture product wholes. Then, the image detection model for quality detection of the furniture product can be trained through the multiple sample furniture images, thereby realizing efficient detection of the furniture product.

[0039] After obtaining the sample furniture images from different furniture product wholes, the sample furniture images can be segmented into multiple sub-sample area images, and the multiple sub-sample area images are local areas of the sample furniture images respectively. The sub-sample area image can be used to detect the local quality characteristics of the sample furniture image. Then, the multiple sub-sample area images can be divided into multiple sub-sample groups, and the images of each sub-sample group are images with similar characteristics. Then, the different areas of the furniture product can be detected in quality through the sample furniture images of the multiple sub-sample groups.

[0040] Figure 2 A schematic diagram of the sub-sample area image obtained by the furniture structure quality detection method based on image recognition in the embodiment of the present application is shown in Figure 2 As shown, the multiple sub-sample area images can be sub-sample area image A1, sub-sample area image A2, sub-sample area image A3 and sub-sample area image A4 on sample furniture image 1.

[0041] Exemplarily, as shown in Figure 2 The sub-sample area image can include the area image of the hole site, the frame corner and the frame connection of the furniture product. Then, the product quality of the hole site, the frame corner and the frame connection of the furniture product can be detected respectively through the sub-sample area image.

[0042] S120, label the sub-sample area images in the multiple sub-sample groups, and train the sub-detection system according to the labeled sub-sample area images in the sub-sample groups.

[0043] After obtaining the plurality of sub-sample groups, the sub-sample region images in the plurality of sub-sample groups can be labeled, and then a data set for training an image recognition model can be formed, and then the sub-detection system can be trained according to the sub-sample region images in the labeled sub-sample groups. The sub-detection system is used for image recognition of the sub-sample region images of the furniture product to detect the structural quality of the furniture product.

[0044] Exemplarily, after the sub-sample region images in the plurality of sub-sample groups are labeled, the sub-detection system can be trained according to the sub-sample region images in the plurality of sub-sample groups respectively. Each sub-detection system is used for furniture quality detection of the sub-sample region images in each sub-sample group.

[0045] S130, according to the furniture structure, a plurality of sub-detection systems corresponding to the furniture structure are determined, and the plurality of sub-detection systems corresponding to the furniture structure are deployed. The plurality of sub-detection systems are used to detect the product quality of the hole position, the frame corner and the frame connection of the furniture structure respectively.

[0046] After obtaining the plurality of sub-detection systems, when the quality of the furniture product of the new structure design needs to be detected, the plurality of sub-detection systems corresponding to the furniture structure can be determined according to the furniture structure, and then the quality of the furniture product can be detected according to the plurality of sub-detection systems.

[0047] After determining the plurality of sub-detection systems, the plurality of sub-detection systems corresponding to the furniture structure can be deployed. The plurality of sub-detection systems are used to detect the product quality of the hole position, the frame corner and the frame connection of the furniture structure respectively, so that the plurality of sub-detection systems can be respectively applied to the quality detection of different local regions of the furniture product on the production line.

[0048] Exemplarily, Figure 3 A working schematic diagram of a furniture structure quality detection method based on image recognition in an embodiment of the present application is shown in Figure 3 As shown, each sub-detection system 2 can include a camera 21 and a computing component 22. The camera 21 is used to collect images of the local region of the furniture product 31 on the conveying line 32. The computing component 22 is used to detect the quality of the local region of the furniture product 31 according to the collected images of the local region of the furniture product.

[0049] The above-mentioned implementation manner has the beneficial effect that when the overall structure of the small furniture product changes due to the rapid iteration of the design of the small furniture product, and the hole position, the frame corner and the frame connection of the local region of the small furniture product are similar, the region images of the hole position, the frame corner and the frame connection of the furniture product can be repeatedly used for quality detection of the rapidly iterated furniture product, and the efficiency of the quality detection of the furniture product is improved.

[0050] The implementation manner has the beneficial effects that the quality of the rapidly iterated furniture product is detected by reusing the area images of the hole positions, the frame corners and the frame connection positions of the furniture product, the problem of a small sample quantity of the furniture product image is solved, and the quality of the furniture product is detected by the image recognition method.

[0051] The implementation manner has the beneficial effects that after the plurality of sub-detection systems are determined, the plurality of sub-detection systems corresponding to the furniture structure are deployed, when the product line of the furniture product is replaced, the quality detection device of the furniture product is quickly deployed, and the quality detection effect when the furniture product is changed is improved.

[0052] In some implementation manners, in the S110, the plurality of sample furniture images of the plurality of furniture products are obtained, the sample furniture images are segmented into a plurality of sub-sample area images, and the plurality of sub-sample area images are divided into a plurality of sub-sample groups, including S111 to S112, which are specifically described below.

[0053] The S111 obtains a plurality of sample furniture images of a planar frame structure of a plurality of furniture products, and segments the sample furniture images into a plurality of sub-sample area images according to positions of hole positions, frame corners and frame connection positions of the planar frame structure of the furniture product.

[0054] When the plurality of sub-sample area images are determined, the plurality of sample furniture images of the planar frame structure of the plurality of furniture products can be obtained first, and the sample furniture images can be segmented into the plurality of sub-sample area images according to the positions of the hole positions, the frame corners and the frame connection positions of the planar frame structure of the furniture product, and then the furniture quality can be detected according to the plurality of sub-sample area images.

[0055] For example, in order to ensure the accuracy of the image of the furniture product and reduce the distortion of the image of the furniture product, the furniture product can be first disassembled into a planar frame structure, so that the plurality of sample furniture images of the planar frame structure of the plurality of furniture products are used as the training data source of the quality detection model, and the detection effect of the furniture quality is ensured.

[0056] The S112 divides the plurality of sub-sample area images into a plurality of sub-sample groups according to the similarity of the hole positions, the frame corners and the frame connection positions.

[0057] After the plurality of sub-sample area images are obtained, the plurality of sub-sample area images can be divided into a plurality of sub-sample groups according to the similarity of the hole positions, the frame corners and the frame connection positions.

[0058] Exemplarily, by grouping the plurality of sub-sample region images, the sub-sample region images corresponding to the hole positions of the furniture product can be grouped into a first sub-sample group, the sub-sample region images corresponding to the frame corners of the furniture product can be grouped into a second sub-sample group, and the sub-sample region images corresponding to the frame connection positions of the furniture product can be grouped into a third sub-sample group.

[0059] Exemplarily, when the plurality of sub-sample region images are divided into the plurality of sub-sample groups, the sub-sample region images can be rotated to align the directions of the sub-sample region images, facilitating subsequent training of the image recognition model.

[0060] The above-mentioned implementation manner has the beneficial effect that quality detection is performed according to the plurality of sample furniture images of the planar frame structure of the plurality of furniture products, which can ensure the accuracy of the images of the furniture products and reduce errors caused by image distortion of the furniture products, and ensure the accuracy of quality detection of the furniture products.

[0061] The above-mentioned implementation manner also has the beneficial effect that small furniture is often shipped in a split structure when sold on the network, and quality detection of the furniture is performed after the furniture product is first disassembled into a planar frame structure, which can perform quality detection of the furniture according to the shipping state, and ensure the quality detection effect of the furniture product.

[0062] In some implementation manners, in the S110, the plurality of sample furniture images of the plurality of furniture products are obtained, the sample furniture images are segmented into a plurality of sub-sample region images, and the plurality of sub-sample region images are divided into a plurality of sub-sample groups, and the S113 to S114 are further included, which are specifically described as follows.

[0063] The S113 determines the structural similarity of the planar frame structure of the plurality of furniture products, and segments the sample furniture images into a plurality of sub-sample region images according to the structural similarity, and the plurality of sub-sample region images respectively correspond to positions of the frame corners and the frame connection positions in the sample furniture images.

[0064] When quality detection is performed on similar furniture products, for example, quality detection is performed on furniture products of the same series, in order to increase the area of the local region of the detected furniture product, the area of the local region of the detected furniture product can be enlarged according to the similarity of the furniture product, and the efficiency of quality detection of the furniture product is improved.

[0065] When the area of the local region of the detected furniture product is enlarged, the structural similarity of the planar frame structure of the plurality of furniture products can be determined, and the sample furniture images are segmented into a plurality of sub-sample region images according to the structural similarity, and each sub-sample region image corresponds to a position with high structural similarity of the plurality of furniture products.

[0066] Exemplarily, when the sample furniture image is segmented into a plurality of sub-sample area images according to the structural similarity, the sample furniture image corresponding to the position with the structural similarity of 100% (i.e., the structure is completely the same) can be segmented into a sub-sample area image.

[0067] Exemplarily, when the sample furniture image is segmented into a plurality of sub-sample area images according to the structural similarity, the sample furniture image corresponding to the position with the same structural shape and different sizes can be segmented into a sub-sample area image.

[0068] Exemplarily, the plurality of sub-sample area images can respectively correspond to positions of the frame corners and the frame connections in the sample furniture image, and then the frame corners and the frame connections of the furniture product can be quality detected according to the plurality of sub-sample area images.

[0069] S114, respectively according to the similarity of the frame corners and the frame connections, the plurality of sub-sample area images are divided into a plurality of sub-sample groups.

[0070] After obtaining the plurality of sub-sample area images, the plurality of sub-sample area images can be divided into a plurality of sub-sample groups according to the similarity of the frame corners and the frame connections, and then the furniture product can be quality detected by the sub-sample group including the plurality of sub-sample area images.

[0071] Exemplarily, when the similarity of the frame corners and the frame connections is respectively determined, the similarity of the frame corners can be determined according to the size and shape of the frame corners, and the similarity of the frame connections can be determined according to the size and shape of the frame connections.

[0072] The beneficial effects of the above implementation manner are that the structural similarity of the planar frame structure of the plurality of furniture products is determined, and the sample furniture image is segmented into a plurality of sub-sample area images according to the structural similarity, which can expand the area of the region for quality detection of the furniture product and improve the efficiency of quality detection of the furniture product.

[0073] The beneficial effects of the above implementation manner are also that the plurality of sub-sample area images are divided into a plurality of sub-sample groups according to the similarity of the frame corners and the frame connections, which can ensure the training effect of the image detection model and ensure the quality detection effect of the sub-sample group of the plurality of sub-sample area images on the furniture product.

[0074] In some implementation manners, in the above S130, the plurality of sub-detection systems corresponding to the furniture structure are determined according to the furniture structure, including S131 to S132, which are specifically described as follows.

[0075] S131, the configuration file corresponding to the furniture structure is determined according to the furniture structure image of the furniture structure by the furniture structure recognition model.

[0076] In the embodiments of the present application, when quality detection needs to be performed on a new structure of a furniture product, in order to quickly determine a sub-detection system for performing quality detection on the furniture product, a furniture structure recognition model can be used to determine a configuration file corresponding to the furniture structure according to a furniture structure image of the furniture structure, and the configuration file corresponding to the furniture structure is used to determine a plurality of sub-detection systems corresponding to the furniture structure.

[0077] For example, the furniture structure recognition model can be trained by a furniture structure image and a plurality of sub-detection systems corresponding to the furniture structure image.

[0078] For example, the configuration file can be a text file recording information of the plurality of sub-detection systems.

[0079] S132, determining a plurality of sub-detection systems corresponding to the furniture structure according to the configuration file.

[0080] After obtaining the configuration file, the plurality of sub-detection systems corresponding to the furniture structure can be determined according to the configuration file, and then the quality detection of the new structure of the furniture structure can be performed according to the plurality of sub-detection systems.

[0081] The above-mentioned implementation manner has the beneficial effect that the plurality of sub-detection systems corresponding to the furniture structure are determined by the furniture structure recognition model, and efficient quality detection of the new structure of the furniture product can be achieved.

[0082] The above-mentioned implementation manner also has the beneficial effect that the information of the plurality of sub-detection systems is recorded by the configuration file, and the processing efficiency of the information of the plurality of sub-detection systems can be improved.

[0083] In some implementation manners, the above-mentioned method further includes displaying the furniture structure image of the furniture structure and the plurality of sub-detection systems corresponding to the furniture structure, and displaying a correspondence between the image area of the furniture structure image and the plurality of sub-detection systems, and manually checking the correspondence between the image area of the furniture structure image and the plurality of sub-detection systems.

[0084] After determining the plurality of sub-detection systems corresponding to the furniture structure image, the furniture structure image of the furniture structure and the plurality of sub-detection systems corresponding to the furniture structure can be displayed, the real-time display of the furniture structure image and the plurality of sub-detection systems is realized, and the quality detection effect of the furniture product can be displayed in real time, so as to manually verify the detection effect of the plurality of sub-detection systems.

[0085] After the furniture structure image of the furniture structure and the plurality of sub-detection systems corresponding to the furniture structure are displayed, a corresponding relationship between the image area of the furniture structure image and the plurality of sub-detection systems can be displayed, the corresponding relationship between the image area of the furniture structure image and the plurality of sub-detection systems is a position corresponding relationship between the image area of the furniture structure image and the plurality of sub-detection systems, and then the corresponding relationship between the image area of the furniture structure image and the plurality of sub-detection systems can be conveniently checked by manual verification, so that the accuracy of the detection area of the plurality of sub-detection systems is ensured.

[0086] Exemplarily, when the corresponding relationship between the image area of the furniture structure image and the plurality of sub-detection systems is displayed, the image area of the furniture structure image and the plurality of sub-detection systems can be connected by lines to intuitively display the corresponding relationship between the image area of the furniture structure image and the plurality of sub-detection systems connected by the lines.

[0087] The above-mentioned implementation manner has the beneficial effect that the corresponding relationship between the image area of the furniture structure image and the plurality of sub-detection systems connected by the lines is intuitively displayed, so that the position corresponding relationship of the image area of the furniture structure image detected by the plurality of sub-detection systems can be conveniently verified by manual verification.

[0088] The above-mentioned implementation manner also has the beneficial effect that the corresponding relationship between the image area of the furniture structure image and the plurality of sub-detection systems connected by the lines is intuitively displayed, so that the plurality of sub-detection systems can be arranged according to the image area of the furniture structure image, and the arrangement efficiency of the quality detection system of the furniture product is improved.

[0089] Figure 4 Another flowchart of a furniture structure quality detection method based on image recognition provided by the embodiment is shown in FIG. 10. Figure 4 The above-mentioned method further includes S210 to S220, which are specifically described below.

[0090] S210, when the plurality of sub-detection systems respectively detect the product quality of the hole position, the frame corner and the frame connection of the furniture structure, the corresponding relationship between the furniture structure image of the furniture structure and the detection result of the plurality of sub-detection systems corresponding to the furniture structure is output.

[0091] When the quality of the furniture product is detected, the product quality of the hole position, the frame corner and the frame connection of the furniture structure can be detected by the plurality of sub-detection systems respectively, and the detection result of the plurality of sub-detection systems can be directly displayed on the furniture structure image, that is, the corresponding relationship between the furniture structure image of the furniture structure and the detection result of the plurality of sub-detection systems corresponding to the furniture structure can be directly output, and then the detection result of the plurality of sub-detection systems can be conveniently checked.

[0092] Exemplarily, the detection result of the sub-detection system can be directly marked on the furniture structure image by a label to display the region on the furniture structure image.

[0093] S220, by the detection checking unit, according to the correspondence between the image region of the manually checked furniture structure image and the plurality of sub-detection systems, checking the correspondence between the furniture structure image of the furniture structure and the detection result of the plurality of sub-detection systems corresponding to the furniture structure.

[0094] When checking the detection result of the plurality of sub-detection systems, the detection checking unit can check the correspondence between the furniture structure image of the furniture structure and the detection result of the plurality of sub-detection systems corresponding to the furniture structure according to the correspondence between the image region of the manually checked furniture structure image and the plurality of sub-detection systems, so as to realize accurate checking of the detection result of the plurality of sub-detection systems.

[0095] In work, the correspondence between the image region of the manually checked furniture structure image and the plurality of sub-detection systems is the accurate position of the detection result that should be output by the plurality of sub-detection systems, and then the correspondence between the furniture structure image of the furniture structure and the detection result of the plurality of sub-detection systems corresponding to the furniture structure can be checked through the accurate position of the detection result that should be output, so as to avoid the detection position of the plurality of sub-detection systems from being offset, and ensure the normal working state of the sub-detection system.

[0096] The above-mentioned implementation mode has the beneficial effect that the actual detection result of the plurality of sub-detection systems is checked through the accurate position of the detection result that should be output, which can avoid the detection position of the plurality of sub-detection systems from being offset, and ensure the normal working state of the sub-detection system.

[0097] In some implementation modes, in S210, the detection checking unit checks the correspondence between the furniture structure image of the furniture structure and the detection result of the plurality of sub-detection systems corresponding to the furniture structure according to the correspondence between the image region of the manually checked furniture structure image and the plurality of sub-detection systems, including: determining the first region coordinate of the detection result of the first sub-detection system, and determining the second region coordinate of the first sub-detection system of the manually checked furniture structure image, when the distance between the first region coordinate and the second region coordinate is greater than or equal to the preset distance, it is judged that the first sub-detection system has a detection fault, and maintenance of the first sub-detection system is prompted. When the distance between the first region coordinate and the second region coordinate is less than the preset distance, it is judged that the first sub-detection system is in normal operation.

[0098] When the actual detection results of the plurality of sub-detection systems are verified according to the accurate position of the detection result that should be output, the first region coordinate of the detection result of the first sub-detection system can be determined, and the second region coordinate of the first sub-detection system of the furniture structure image verified manually can be determined, and then the actual detection results of the plurality of sub-detection systems can be verified according to the accurate position of the detection result that should be output through the first region coordinate and the second region coordinate.

[0099] When the actual detection results of the plurality of sub-detection systems are verified according to the accurate position of the detection result that should be output, when the distance between the first region coordinate and the second region coordinate is greater than or equal to the preset distance, it indicates that the actual output result position of the first sub-detection system has a large deviation, and then it can be judged that the first sub-detection system has a detection fault, prompting maintenance of the first sub-detection system, and realizing adjustment of the first sub-detection system.

[0100] Exemplarily, when the first sub-detection system is maintained, the detection position of the camera of the first sub-detection system can be adjusted.

[0101] When the actual detection results of the plurality of sub-detection systems are verified according to the accurate position of the detection result that should be output, when the distance between the first region coordinate and the second region coordinate is less than the preset distance, it indicates that the actual output result position of the first sub-detection system does not have a large deviation, and then it can be judged that the first sub-detection system is in normal operation.

[0102] The beneficial effects of the above implementation manner are that by determining the first region coordinate of the detection result of the first sub-detection system and the second region coordinate of the first sub-detection system of the furniture structure image verified manually, the accurate verification of the position of the actual detection result of the first sub-detection system can be realized, and the efficiency of monitoring the working state of the plurality of sub-detection systems is improved.

[0103] In some implementation manners, in the S210, the correspondence between the furniture structure image of the furniture structure and the detection result of the plurality of sub-detection systems corresponding to the furniture structure image is verified according to the image region of the furniture structure image verified manually and the correspondence between the plurality of sub-detection systems, and the S211 to S212 are further included, and the S211 to S212 are specifically described below.

[0104] S211, a plurality of output result region coordinates of a plurality of output result regions of a plurality of sub-detection systems are acquired, and an output result distribution feature of the plurality of output result region coordinates is determined, and a plurality of standard result region coordinates of a plurality of standard result regions of the plurality of sub-detection systems verified manually are acquired, and a standard result distribution feature of the plurality of standard result region coordinates is determined.

[0105] In the checking of the positions of the actual output results of the plurality of sub-detection systems, a plurality of output result region coordinates of a plurality of output result regions of the plurality of sub-detection systems can be obtained, and an output result distribution feature of the plurality of output result region coordinates can be determined, the output result distribution feature representing a position distribution feature of the actual output results of the plurality of sub-detection systems.

[0106] In the checking of the positions of the actual output results of the plurality of sub-detection systems, a plurality of standard result region coordinates of a plurality of standard result regions of the plurality of sub-detection systems checked by the manual checking can also be obtained, and a standard result distribution feature of the plurality of standard result region coordinates can be determined, the standard result distribution feature representing a position distribution feature of the target output results of the plurality of sub-detection systems.

[0107] In the checking of the positions of the actual output results of the plurality of sub-detection systems, when the similarity between the output result distribution feature and the standard result distribution feature is greater than or equal to a preset similarity, it is determined that the plurality of sub-detection systems are in normal operation.

[0108] In the checking of the positions of the actual output results of the plurality of sub-detection systems, when the similarity between the output result distribution feature and the standard result distribution feature is greater than or equal to a preset similarity, it is determined that the plurality of sub-detection systems are in normal operation, and there is no need to adjust the plurality of sub-detection systems.

[0109] In the checking of the positions of the actual output results of the plurality of sub-detection systems, when the similarity between the output result distribution feature and the standard result distribution feature is less than a preset similarity, it is determined that the plurality of sub-detection systems are not in normal operation, and it is prompted to maintain the plurality of sub-detection systems, and the plurality of sub-detection systems need to be adjusted to ensure the stability of the working state of the plurality of sub-detection systems.

[0110] Exemplarily, in the checking of the positions of the actual output results of the plurality of sub-detection systems, the output result distribution feature and the standard result distribution feature can be distance matrices between a plurality of detection results, and then the similarity of the distance matrices corresponding to the output result distribution feature and the standard result distribution feature can be determined as the similarity between the output result distribution feature and the standard result distribution feature.

[0111] The above-mentioned implementation manner has the beneficial effect that the positions of the output results of the plurality of sub-detection systems are checked through the similarity between the output result distribution feature and the standard result distribution feature, and the accuracy of checking the working state of the plurality of sub-detection systems is improved.

[0112] The embodiment of the present application also provides a furniture structure quality detection device based on image recognition, comprising a unit for executing the method according to any one of the above.

[0113] Figure 5 A logic structure diagram of a furniture structure quality detection device based on image recognition provided by an embodiment of the present application is shown in Figure 5 The device 4 of this embodiment includes a processing unit 41, a storage unit 42 and a transceiver unit 43, the processing unit 41 is used for processing data, the storage unit 42 is used for storing data, and the transceiver unit 43 is used for transceiving data. The processing unit 41, the storage unit 42 and the transceiver unit 43 cooperate with each other to realize the above-mentioned method. The beneficial effects of the embodiments of the present application have been described in the above-mentioned method, and will not be repeated here.

[0114] The embodiments of the present application also provide a furniture structure quality detection device based on image recognition, which includes a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in any one of the above embodiments is realized.

[0115] Figure 6 An entity structure diagram of a furniture structure quality detection device based on image recognition provided by an embodiment of the present application is shown in Figure 6 The device 5 of this embodiment includes at least one processor 50 (only one processor 50 is shown in the figure), a memory 51, and a computer program 52 stored in the memory 51 and executable on the at least one processor 50. The processor 50 executes the computer program 52 to realize the steps in any of the above-mentioned method embodiments. The beneficial effects of the embodiments of the present application have been described in the above-mentioned method, and will not be repeated here. Figure 6 It should be noted that the information interaction, execution process and the like between the above-mentioned devices / units are based on the same concept as the method embodiments of the present application. For specific functions and technical effects brought by them, please refer to the method embodiment part, which will not be repeated here.

[0116]

[0117] ​Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software functional unit. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the unit and module in the above system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0118] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to realize the steps in each of the above method embodiments.

[0119] The embodiment of the present application provides a computer program product. When the computer program product is run on a mobile terminal, the mobile terminal is caused to execute the steps in each of the above method embodiments.

[0120] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the present application realizes all or part of the processes in the above embodiment methods, which can be completed by a computer program instructing related hardware. The computer program can be stored in a computer readable storage medium. The computer program is executed by a processor to realize the steps in each of the above method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the photographing device / terminal equipment, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, the computer readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0121] In the above embodiments, the description of each embodiment is focused on, and the parts not described or recorded in a certain embodiment can be referred to the relevant description of other embodiments.

[0122] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0123] In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other ways. For example, the above-described apparatus embodiments are only schematic, for example, the division of the modules or units is only a logical function division, and there can be another division way in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection between the interfaces, devices or units can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0124] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0125] The above-described embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalent ones; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for inspecting the structural quality of furniture based on image recognition, characterized in that, The method includes: Acquire multiple sample furniture images of multiple furniture products, segment the sample furniture images into multiple sub-sample region images, and divide the multiple sub-sample region images into multiple sub-sample groups; wherein, the sub-sample region images include the area images of the holes, frame corners and frame connections of the furniture products; Acquire multiple sample furniture images from multiple furniture products, segment each sample furniture image into multiple sub-sample region images, and then divide these sub-sample region images into multiple sub-sample groups, including: Acquire multiple sample furniture images of the planar frame structure of multiple furniture products. Segment the sample furniture images into multiple sub-sample region images based on the location of holes, frame corners, and frame connections in the planar frame structure of the furniture products. Divide the multiple sub-sample region images into multiple sub-sample groups according to the similarity of holes, frame corners, and frame connections. The process involves acquiring multiple sample furniture images from multiple furniture products, segmenting these sample furniture images into multiple sub-sample region images, and further dividing these sub-sample region images into multiple sub-sample groups. Determine the structural similarity of the planar frame structure of multiple furniture products, and segment the sample furniture image into multiple sub-sample region images according to the structural similarity. The multiple sub-sample region images correspond to the positions of frame corners and frame connections in the sample furniture image, respectively. Based on the similarity of frame corners and frame connections, the images of multiple sub-sample regions are divided into multiple sub-sample groups; The sub-sample region images in multiple sub-sample groups are labeled, and the sub-detection system is trained based on the labeled sub-sample region images in the sub-sample groups; Based on the furniture structure, multiple sub-inspection systems are determined and deployed. These sub-inspection systems are used to inspect the product quality of the furniture structure's holes, frame corners, and frame connections, respectively. Based on the furniture structure, multiple sub-detection systems are determined, including: The furniture structure recognition model determines the corresponding configuration file based on the furniture structure image; and determines multiple sub-detection systems corresponding to the furniture structure based on the configuration file.

2. The method as described in claim 1, characterized in that, The method further includes: The system displays an image of the furniture structure and its corresponding multiple sub-detection systems, showing the correspondence between the image regions of the furniture structure image and the multiple sub-detection systems. The correspondence between the image regions of the furniture structure image and the multiple sub-detection systems is then manually verified.

3. The method as described in claim 2, characterized in that, The method further includes: When multiple sub-inspection systems inspect the product quality of the furniture structure's holes, frame corners, and frame connections, they output a furniture structure image and the correspondence between the inspection results of the multiple sub-inspection systems corresponding to the furniture structure. The detection and verification unit verifies the correspondence between the furniture structure image and the detection results of the corresponding multiple sub-detection systems, based on the image region of the manually verified furniture structure image and the correspondence between the two systems.

4. A furniture structural quality inspection device based on image recognition, characterized in that, Includes a unit for performing the method according to any one of claims 1 to 3.

5. A furniture structural quality inspection device based on image recognition, 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, it implements the method as described in any one of claims 1 to 3.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 3.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

Images