Automatic product quality evaluation method and system based on online identification technology

Abstract

The invention relates to an automatic product quality evaluation method and system based on an on-line identification technology, and the method comprises the steps: obtaining a product packaging image through an intelligent camera device, so as to locate the position of a product; identifying and positioning an area bearing a product identification code in the product packaging image according to a preset comparison strategy; identifying and calculating the offset of the area relative to a preset standard position, and comparing the offset with a preset threshold value; if the offset exceeds the preset threshold value, it is judged that the product package is unqualified, and a mechanical arm is triggered and controlled to remove the product from the production line; if the offset does not exceed the preset threshold value, it is judged that the product package is qualified, and quality inspection passing information is sent to an MES system. Manual quality inspection is replaced by judgment through shooting of the intelligent camera device, a large amount of manpower does not need to be input for quality inspection, the quality inspection cost is reduced, the judgment standards are consistent, the packaging quality of products subjected to quality inspection is consistent, and the intelligence of product quality inspection is improved.

Description

Technical Field

[0001] The present invention relates to the field of automated processing technology, and in particular to an automated product quality assessment method and system based on online recognition technology. Background Art

[0002] Product packaging quality is an important part of factory product quality inspection, for example: the integrity of the packaging, the position of the barcode or label on the packaging box, etc., especially the detection of the position of the barcode or label, which is usually inspected manually at present, which is highly subjective and each person's evaluation criteria are inconsistent, resulting in inconsistent packaging quality after quality inspection. In addition, manual operation is labor-intensive and costly, making it difficult to adapt to the needs of mass production and processing. Summary of the invention

[0003] In view of the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide an automated product quality assessment method and system based on online recognition technology, which is used to solve the technical problems of large manual quality inspection workload, high cost and inconsistent evaluation standards in the prior art.

[0004] To achieve the above-mentioned purpose and other related purposes, the first aspect of the disclosed embodiment of the present invention provides an automated product quality assessment method based on online recognition technology, comprising:

[0005] Using an intelligent camera device to acquire a product packaging image to locate the position of the product, the product packaging image including an image of an area carrying a product identification code;

[0006] Identifying and locating the area carrying the product identification code in the product packaging image according to a preset comparison strategy;

[0007] Identifying and calculating the offset of the area relative to a preset standard position, and comparing the offset with a preset threshold;

[0008] If the offset exceeds the preset threshold, the product packaging is determined to be unqualified, and the robot arm is triggered and controlled to remove the product from the production line;

[0009] If the offset does not exceed the preset threshold, the product packaging is determined to be qualified and a quality inspection pass information is sent to the MES system.

[0010] To implement the above technical solution, the packaging of the product to be tested is photographed by an intelligent camera device. At the same time, the position of the product can be determined during the photographing, and then the area carrying the product identification code in the product packaging image is identified and located, and then the actual position of the area is calculated, and the actual position is compared with the preset standard position, and the offset between the two is calculated, and then the offset is compared with the preset threshold value. If the offset exceeds the preset threshold value, the product packaging is judged to be unqualified. At this time, the robot arm on the production line is controlled to discharge the product for repackaging or further manual quality inspection. Otherwise, the product packaging is judged to be qualified, that is, the quality inspection pass information is sent to the MES system, and the subsequent processing process or shipment can be carried out. The intelligent camera device is used for shooting and judging instead of manual quality inspection, so there is no need to invest a large amount of manpower for quality inspection, which reduces the quality inspection cost, and the evaluation standards are consistent, so that the quality of product packaging after quality inspection is consistent, and the intelligence of product quality inspection is improved.

[0011] In some exemplary embodiments, the method of acquiring a product packaging image using an intelligent camera device to locate the position of the product specifically includes:

[0012] The intelligent camera device photographs the product packaging to generate a plurality of product packaging images;

[0013] Scan and identify each of the product packaging images and use the product packaging image with the product identification code scanned as the main processing object;

[0014] An area of ​​a predetermined size around the scanned product identification code is used as an initial area for carrying the product identification code.

[0015] To implement the above technical solution, the angles and directions of the products on the production line may be different. By taking photos at various angles, it is possible to ensure that the area containing the product identification code is photographed. At the same time, the product packaging image corresponding to the area is taken as the main processing object, and the area of ​​predetermined size around the scanned product identification code is used as the initial area for carrying the product identification code. The area can be pre-positioned to facilitate subsequent further positioning processing.

[0016] In some exemplary embodiments, the identifying and locating the area carrying the product identification code in the product packaging image according to the preset comparison strategy specifically includes:

[0017] Identify the area with the same color around the product identification code in the initial area and obtain the initial outer edge of the area;

[0018] Aligning an outer edge frame of a predetermined shape and a predetermined size with the initial outer edge to modify the initial outer edge;

[0019] The corrected initial outer edge is used as the actual edge of the area carrying the product identification code to locate the position of the area on the product packaging image.

[0020] To implement the above technical solution, since the colors of the product identification code or its surroundings are usually the same, the outer edge of the area can be preliminarily distinguished by color recognition. Furthermore, since the shape and size of the area carrying the product identification code are predetermined, the outer edge of the corresponding shape and size is corrected on the basis of the initial outer edge as the actual outer edge, and the actual outer edge and the area inside it can be determined as the area carrying the product identification code, and then the position of this area on the product packaging image can be located.

[0021] In some exemplary embodiments, the identifying and calculating the offset of the area relative to a preset standard position specifically includes:

[0022] Establishing a three-dimensional rectangular coordinate system according to the posture and imaging plane of the intelligent camera device;

[0023] Locating the coordinate value of the actual edge on the three-dimensional rectangular coordinate system in pixels;

[0024] The coordinate value of the actual edge is compared with the coordinate value corresponding to the preset standard position, and the deviation value between the two is used as the offset.

[0025] To implement the above technical solution, the coordinate value of the actual edge can be determined by establishing a rectangular coordinate system. The deviation between the coordinate value of the actual edge and the coordinate value of the preset standard position can be determined by comparing the coordinate value of the actual edge with the coordinate value of the preset standard position. The deviation value is then used as the offset to more accurately determine the offset.

[0026] In some exemplary embodiments, identifying and calculating the offset of the region relative to a preset standard position further includes:

[0027] Calculate the size between the actual edge and the edge of the product packaging image as a reference size value;

[0028] The comparison dimension value is compared with the standard dimension value corresponding to the preset standard position, and the deviation value between the two is used as the comparison offset.

[0029] To implement the above technical solution, the size between the actual edge and the edge of the product packaging image is calculated as the reference size value, which is then compared with the standard size value, and the deviation between the two is used as the reference offset, thereby providing further offset comparison and improving the comparison judgment accuracy.

[0030] In some exemplary embodiments, comparing the offset with a preset threshold specifically includes:

[0031] Comparing the offset with the preset threshold to form a first comparison result;

[0032] Comparing the control offset with the preset threshold to form a second comparison result;

[0033] If any one of the first comparison result and the second comparison result exceeds the preset threshold, it is determined that the offset exceeds the preset threshold.

[0034] When the above technical solution is implemented, when any one of the offset and the control offset exceeds the preset threshold, it means that the deviation of the position of the area carrying the product identification code is too large, and it can be judged as unqualified.

[0035] In some exemplary embodiments, the product identification code includes one or more of a barcode, a QR code, a logo text, or a logo graphic.

[0036] A second aspect of the disclosed embodiment of the present invention provides an automated product quality assessment system based on online recognition technology, comprising:

[0037] An image acquisition unit, used to control the intelligent camera device to acquire a product packaging image to locate the position of the product, wherein the product packaging image includes an image of an area carrying a product identification code;

[0038] A positioning and identifying unit, used to identify and locate the area carrying the product identification code in the product packaging image according to a preset comparison strategy;

[0039] a calculation and comparison unit, used for identifying and calculating the offset of the area relative to a preset standard position, and comparing the offset with a preset threshold;

[0040] The determination execution unit is used to determine that the product packaging is unqualified when the offset exceeds the preset threshold, trigger and control the robot arm to remove the product from the production line; and to determine that the product packaging is qualified when the offset does not exceed the preset threshold, and send quality inspection pass information to the MES system.

[0041] A third aspect of an embodiment disclosed in the present invention provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the automated product quality assessment method based on online identification technology as described in the first aspect.

[0042] A fourth aspect of an embodiment disclosed in the present invention provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, enables the one or more processors to perform the steps of the automated product quality assessment method based on online identification technology as described in the first aspect.

[0043] As described above, compared with the prior art, the present invention has the following beneficial effects:

[0044] The embodiment of the present invention provides an automated product quality assessment method and system based on online recognition technology, wherein the method comprises: using an intelligent camera device to acquire a product packaging image to locate the position of the product, wherein the product packaging image includes an image of an area carrying a product identification code; identifying and locating the area carrying the product identification code in the product packaging image according to a preset comparison strategy; identifying and calculating the offset of the area relative to a preset standard position, and comparing the offset with a preset threshold; if the offset exceeds the preset threshold, determining that the product packaging is unqualified, triggering and controlling a robotic arm to remove the product from the production line; if the offset does not exceed the preset threshold, determining that the product packaging is qualified, and sending quality inspection pass information to an MES system. The packaging of the product to be tested is photographed by an intelligent camera device. At the same time, the position of the product can be determined during the shooting. The area carrying the product identification code in the product packaging image is then identified and located. The actual position of the area is then calculated, and the actual position is compared with the preset standard position. The offset between the two is calculated, and the offset is compared with the preset threshold. If the offset exceeds the preset threshold, the product packaging is judged to be unqualified. At this time, the robot arm on the production line is controlled to discharge the product for repackaging or further manual quality inspection. Otherwise, the product packaging is judged to be qualified, that is, the quality inspection pass information is sent to the MES system, and subsequent processing or shipment can be carried out. The intelligent camera device is used for shooting and judging instead of manual quality inspection, so there is no need to invest a large amount of manpower for quality inspection, which reduces the quality inspection cost, and the evaluation standards are consistent, so that the quality of product packaging after quality inspection is consistent, which improves the intelligence of product quality inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] 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 of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 Shown is a flow chart of an automated product quality assessment method based on online recognition technology according to an embodiment of the present invention.

[0047] Figure 2 It shows a schematic diagram of establishing a three-dimensional rectangular coordinate system in an automated product quality assessment method based on online recognition technology according to an embodiment of the present invention.

[0048] Figure 3Shown is a structural schematic diagram of an automated product quality assessment system based on online recognition technology according to an embodiment of the present invention.

[0049] Figure 4 Shown is a basic structural block diagram of a computer device in an embodiment of the present invention.

[0050] The numbers and letters in the figure represent the corresponding component names:

[0051] 601, image acquisition unit; 602, positioning and identification unit; 603, calculation and comparison unit; 604, determination and execution unit. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0053] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0055] See also Figure 1 According to a first aspect of an embodiment of the present invention, there is provided an automated product quality assessment method based on online recognition technology, comprising:

[0056] S100. Use a smart camera device to obtain a product packaging image to locate the position of the product. The product packaging image includes an image of an area carrying a product identification code, wherein the product identification code includes one or more of a barcode, a QR code, a logo text, or a logo graphic. The product identification code is mainly a barcode. Of course, in some embodiments, it can also be a QR code, or an image or text used to identify the product, such as a LOGO mark, etc. Both the barcode and the QR code can identify product-related information and can better perform scanning, identification, and positioning. The product identification code can be affixed to the product packaging in the form of a label, or a fixed area can be set on the product packaging and presented in the area by printing or printing.

[0057] S100 specifically includes:

[0058] S101. The product packaging is photographed by an intelligent camera device to generate a plurality of product packaging images. The intelligent camera device may be, for example, an intelligent camera. The intelligent camera may be provided with one on each side of the production line and relatively tilted so as to photograph the two diagonal positions of the product packaging. Of course, two groups of intelligent cameras may be provided on each side of the production line, that is, they may correspond to the four corners of the product packaging respectively, so as to photograph images of the product packaging around. Of course, in some embodiments, the intelligent camera may also be arranged to be rotatable so as to track and photograph the product packaging. The photographed product packaging image may include two or three sides of the product. In actual processing, the product packaging image may also be segmented by corresponding image processing technology, and the image corresponding to each side may be segmented and extracted for recognition processing.

[0059] S102, scanning and identifying each product packaging image and taking the product packaging image with the product identification code scanned therein as the main processing object. Since the product identification code is usually set on a specific side of the product packaging, the side with the product identification code set is mainly processed during the identification process, and the product packaging image is taken as the main processing object, so that it is easier to identify and locate the product identification code.

[0060] S103. Using an area of ​​a predetermined size around the scanned product identification code as an initial area for carrying the product identification code. Since the size of the area for carrying the product identification code is fixed and the area must cover the product identification code, the size and area of ​​the area around the scanned product identification code are usually larger than the area for carrying the product identification code to facilitate targeted processing.

[0061] Since the angles and directions of the products on the production line may be different, photos are taken from various angles to ensure that the area containing the product identification code is captured. At the same time, the product packaging image corresponding to the area is used as the main processing object, and the area of ​​predetermined size around the scanned product identification code is used as the initial area carrying the product identification code. The area can be pre-positioned to facilitate subsequent further positioning processing.

[0062] S200: Identify and locate the area carrying the product identification code in the product packaging image according to a preset comparison strategy.

[0063] Among them, S200 specifically includes:

[0064] S201. Identify an area with the same color around the product identification code in the initial area and obtain an initial outer edge of the area. In actual applications, the area carrying the product identification code usually has a clear color difference from the surrounding packaging, so the color boundary can be used as the initial edge of the area.

[0065] S202. Align an outer edge frame of a predetermined shape and a predetermined size with the initial outer edge to correct the initial outer edge. Since the shape and size of the area carrying the product identification code are fixed, usually rectangular, the outer edge frame of the fixed shape and size is aligned with the initial outer edge to correct the initial outer edge. The initial outer edge can be corrected to the corresponding size and shape, that is, basically consistent with the shape and size of the actual area carrying the product identification code.

[0066] S203, using the corrected initial outer edge as the actual edge of the area carrying the product identification code to locate the position of the area on the product packaging image. Since the corrected initial outer edge is substantially consistent with the shape and size of the actual area carrying the product identification code, the corrected initial outer edge is used as the actual edge to locate the position of the area on the product packaging image.

[0067] Since the colors of the product identification code or its surroundings are usually the same, the outer edge of the area can be preliminarily distinguished through color recognition. Furthermore, since the shape and size of the area carrying the product identification code are predetermined, the outer edge of the corresponding shape and size is corrected on the basis of the initial outer edge as the actual outer edge, and the actual outer edge and the area inside it can be determined as the area carrying the product identification code, and then the position of this area on the product packaging image can be located.

[0068] S300, identifying and calculating the offset of the area relative to a preset standard position, and comparing the offset with a preset threshold.

[0069] The step of identifying and calculating the offset of the region relative to the preset standard position specifically includes:

[0070] S301, establish a three-dimensional rectangular coordinate system according to the posture and imaging plane of the intelligent camera device, such as Figure 2 As shown, Figure 2 A schematic diagram of establishing a three-dimensional rectangular coordinate system is shown. Since the posture and imaging plane of the intelligent camera device are fixed when shooting the product packaging image as the main processing object, establishing a three-dimensional rectangular coordinate system based on the posture and imaging plane of the intelligent camera device can correspond to the product packaging image more accurately.

[0071] S302 , locating the coordinate value of the actual edge in a three-dimensional rectangular coordinate system using pixels as units, where pixels are used as units in the three-dimensional rectangular coordinate system, thereby being able to accurately locate the coordinate value of the actual edge.

[0072] S303, compare the coordinate value of the actual edge with the coordinate value corresponding to the preset standard position, and use the deviation between the two as the offset. Since the coordinate value corresponding to the preset standard position is fixed, the accurate deviation can be obtained by comparing the coordinate values ​​of the two.

[0073] The coordinate value of the actual edge can be determined by establishing a rectangular coordinate system. The deviation between the coordinate value of the actual edge and the coordinate value of the preset standard position can be determined by comparing the coordinate value of the actual edge with the coordinate value of the preset standard position. The deviation value is then used as the offset to more accurately determine the offset.

[0074] Furthermore, identifying and calculating the offset of the region relative to the preset standard position also includes:

[0075] S304, calculating the size between the actual edge and the edge of the product packaging image as a comparison size value, which may be specifically the distance between the four sides of the actual edge and the four sides of the edge of the product packaging image. If the distances meet the requirements, it means that the position of the actual edge is accurate.

[0076] S305: Compare the comparison dimension value with the standard dimension value corresponding to the preset standard position, and use the deviation value between the two as the comparison offset.

[0077] By calculating the size between the actual edge and the edge of the product packaging image as the reference size value, and then comparing it with the standard size value, the deviation between the two is used as the reference offset, thereby providing further offset comparison and improving the accuracy of comparison judgment.

[0078] Comparing the offset with a preset threshold value specifically includes:

[0079] S306, comparing the offset with a preset threshold to form a first comparison result;

[0080] S307, comparing the control offset with a preset threshold to form a second comparison result;

[0081] S308: If any one of the first comparison result and the second comparison result exceeds the preset threshold, it is determined that the offset exceeds the preset threshold.

[0082] When any one of the offset and the control offset exceeds the preset threshold, it means that the deviation of the position of the area carrying the product identification code is too large and it can be judged as unqualified.

[0083] S400. If the offset exceeds a preset threshold, the product packaging is determined to be unqualified, and the robotic arm is triggered and controlled to remove the product from the production line. Specifically, when the intelligent camera device captures the product packaging image, since the position of the intelligent camera device is determined, the position of the product on the production line can be determined based on the position of the intelligent camera device. At this time, the robotic arm can be controlled to accurately grasp the product based on the position information and remove it from the production line.

[0084] S500: If the offset does not exceed the preset threshold, the product packaging is determined to be qualified, and a quality inspection pass information is sent to the MES system. After receiving the quality inspection pass information, the MES system can control the production line to perform subsequent processing operations on the quality inspection passed products.

[0085] The packaging of the product to be tested is photographed by an intelligent camera device. At the same time, the position of the product can be determined during the shooting. The area carrying the product identification code in the product packaging image is then identified and located. The actual position of the area is then calculated, and the actual position is compared with the preset standard position. The offset between the two is calculated, and the offset is compared with the preset threshold. If the offset exceeds the preset threshold, the product packaging is judged to be unqualified. At this time, the robot arm on the production line is controlled to discharge the product for repackaging or further manual quality inspection. Otherwise, the product packaging is judged to be qualified, that is, the quality inspection pass information is sent to the MES system, and subsequent processing or shipment can be carried out. The intelligent camera device is used for shooting and judging instead of manual quality inspection, so there is no need to invest a large amount of manpower for quality inspection, which reduces the quality inspection cost, and the evaluation standards are consistent, so that the quality of product packaging after quality inspection is consistent, which improves the intelligence of product quality inspection.

[0086] The second aspect of the embodiment of the present invention further provides an automated product quality assessment system based on online recognition technology, such as Figure 3As shown, it includes: an image acquisition unit 601, which is used to control the intelligent camera device to acquire the product packaging image to locate the position of the product, and the product packaging image includes the image of the area carrying the product identification code; a positioning and identification unit 602, which is used to identify and locate the area carrying the product identification code in the product packaging image according to a preset comparison strategy; a calculation and comparison unit 603, which is used to identify and calculate the offset of the area relative to the preset standard position, and compare the offset with the preset threshold; a judgment execution unit 604, which is used to determine that the product packaging is unqualified when the offset exceeds the preset threshold, trigger and control the robot arm to remove the product from the production line; and, when the offset does not exceed the preset threshold, determine that the product packaging is qualified and send quality inspection pass information to the MES system.

[0087] The image acquisition unit 601 controls the intelligent camera device to shoot the packaging of the product to be tested. At the same time, the position of the product can be determined during the shooting. The positioning and identification unit 602 then identifies and locates the area carrying the product identification code in the product packaging image. The calculation and comparison unit 603 then calculates the actual position of the area, compares the actual position with the preset standard position, and calculates the offset between the two. The offset is then compared with the preset threshold. If the offset exceeds the preset threshold, the product packaging is determined to be unqualified. At this time, the judgment execution unit 604 controls the robot arm on the production line to discharge the product for repackaging or further manual quality inspection. Otherwise, the product packaging is determined to be qualified. The judgment execution unit 604 sends the quality inspection pass information to the MES system, and the subsequent processing process or shipment can be carried out. The intelligent camera device is used to shoot and judge instead of manual quality inspection, so there is no need to invest a lot of manpower in quality inspection, which reduces the quality inspection cost. The evaluation standards are consistent, so that the quality of the product packaging after quality inspection is consistent, and the intelligence of product quality inspection is improved.

[0088] A third aspect of the present invention provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0089] like Figure 4As shown, a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a non-volatile storage medium, a memory, and a network interface connected via a system bus. Among them, the non-volatile storage medium of the computer device stores an operating system, a database, and computer-readable instructions. The database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor can implement an automated product quality assessment method based on online identification technology. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor can execute an automated product quality assessment method based on online identification technology. The network interface of the computer device is used to connect and communicate with a terminal. Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0090] In this embodiment, the processor is used to execute Figure 3 The memory stores the program codes and various data required to execute the above modules. The network interface is used to transmit data between user terminals or servers. The server of the present invention can call the program codes and data of the server to execute the functions of all submodules.

[0091] When the computer equipment is conducting product quality inspection, it controls the intelligent camera device to shoot the packaging of the product to be tested. At the same time, it can determine the position of the product during shooting, and then identify and locate the area carrying the product identification code in the product packaging image, and then calculate the actual position of the area, compare the actual position with the preset standard position, and calculate the offset between the two, and then compare the offset with the preset threshold value. If the offset exceeds the preset threshold value, the product packaging is judged to be unqualified. At this time, the robot arm on the production line is controlled to discharge the product for repackaging or further manual quality inspection. Otherwise, the product packaging is judged to be qualified, that is, the quality inspection pass information is sent to the MES system, and the subsequent processing process or shipment can be carried out. By shooting and judging with the intelligent camera device instead of manual quality inspection, there is no need to invest a large amount of manpower for quality inspection, which reduces the quality inspection cost, and the evaluation standards are consistent, so that the quality of product packaging after quality inspection is consistent, which improves the intelligence of product quality inspection.

[0092] The present invention also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the automated product quality assessment method based on online identification technology in any of the above-mentioned embodiments.

[0093] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0094] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

Claims

1. An automated product quality assessment method based on online recognition technology, characterized in that: include: Using an intelligent camera device to acquire a product packaging image to locate the position of the product, the product packaging image including an image of an area carrying a product identification code; Identifying and locating the area carrying the product identification code in the product packaging image according to a preset comparison strategy; Identifying and calculating the offset of the area relative to a preset standard position, and comparing the offset with a preset threshold; If the offset exceeds the preset threshold, the product packaging is determined to be unqualified, and the robot arm is triggered and controlled to remove the product from the production line; If the offset does not exceed the preset threshold, the product packaging is determined to be qualified and a quality inspection pass information is sent to the MES system.

2. The automated product quality assessment method based on online identification technology according to claim 1, characterized in that: The method of using the intelligent camera device to obtain the product packaging image to locate the position of the product specifically includes: The intelligent camera device photographs the product packaging to generate a plurality of product packaging images; Scan and identify each of the product packaging images and use the product packaging image with the product identification code scanned as the main processing object; An area of ​​a predetermined size around the scanned product identification code is used as an initial area for carrying the product identification code.

3. The automated product quality assessment method based on online identification technology according to claim 2 is characterized in that: The step of identifying and locating the area carrying the product identification code in the product packaging image according to the preset comparison strategy specifically includes: Identify the area with the same color around the product identification code in the initial area and obtain the initial outer edge of the area; Aligning an outer edge frame of a predetermined shape and a predetermined size with the initial outer edge to modify the initial outer edge; The corrected initial outer edge is used as the actual edge of the area carrying the product identification code to locate the position of the area on the product packaging image.

4. The automated product quality assessment method based on online identification technology according to claim 3 is characterized in that: The identifying and calculating the offset of the area relative to the preset standard position specifically includes: Establishing a three-dimensional rectangular coordinate system according to the posture and imaging plane of the intelligent camera device; Locating the coordinate value of the actual edge on the three-dimensional rectangular coordinate system in pixels; The coordinate value of the actual edge is compared with the coordinate value corresponding to the preset standard position, and the deviation value between the two is used as the offset.

5. The automated product quality assessment method based on online identification technology according to claim 4 is characterized in that: The identifying and calculating the offset of the area relative to the preset standard position also includes: Calculate the size between the actual edge and the edge of the product packaging image as a reference size value; The comparison dimension value is compared with the standard dimension value corresponding to the preset standard position, and the deviation value between the two is used as the comparison offset.

6. The automated product quality assessment method based on online identification technology according to claim 5 is characterized in that: The comparing the offset with a preset threshold specifically includes: Comparing the offset with the preset threshold to form a first comparison result; Comparing the control offset with the preset threshold to form a second comparison result; If any one of the first comparison result and the second comparison result exceeds the preset threshold, it is determined that the offset exceeds the preset threshold.

7. The automated product quality assessment method based on online identification technology according to claim 1, characterized in that: The product identification code includes one or more of a barcode, a two-dimensional code, a logo text or a logo graphic.

8. An automated product quality assessment system based on online recognition technology, characterized in that: include: An image acquisition unit, used to control the intelligent camera device to acquire a product packaging image to locate the position of the product, wherein the product packaging image includes an image of an area carrying a product identification code; A positioning and identifying unit, used to identify and locate the area carrying the product identification code in the product packaging image according to a preset comparison strategy; a calculation and comparison unit, used for identifying and calculating the offset of the area relative to a preset standard position, and comparing the offset with a preset threshold; The determination execution unit is used to determine that the product packaging is unqualified when the offset exceeds the preset threshold, trigger and control the robot arm to remove the product from the production line; and to determine that the product packaging is qualified when the offset does not exceed the preset threshold, and send quality inspection pass information to the MES system.

9. A computer device comprising a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the automated product quality assessment method based on online identification technology as described in any one of claims 1 to 7.

10. A storage medium storing computer-readable instructions, which, when executed by one or more processors, enables the one or more processors to perform the steps of the automated product quality assessment method based on online identification technology as claimed in any one of claims 1 to 7.

Images