An image screening method, device, system and storage medium

Abstract

The application relates to the technical field of image processing, and relates to an image screening method, device and system, a storage medium, effective matching data, and each row of to-be-processed row image data collected by an image extraction device, the effective matching data comprising a matching template, a matching template position and an effective edition cycle; based on the row number of the to-be-processed row image data in an image and the number of rows of the matching template, an initial matching area in the image is determined; in the initial matching area, based on a preset matching strategy, a matching value of at least one sub-area included in the initial matching area and the matching template is determined, and a target matching value is determined; if the target matching value meets a preset determination condition, based on the target matching value, the matching template position and the effective edition cycle, an effective area in the image is determined and sent to an image processing device, so that the extraction of the effective area of the image by the image collection device is realized, the capacity of data processed by the image processing device is reduced, and the efficiency of a visual detection system is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to an image screening method, device, system and storage medium. BACKGROUND

[0002] In a visual inspection system, a target object to be measured is first photographed by a machine vision product (i.e. an image capturing device such as a camera), and then converted into image data. The image data is then transmitted directly to a dedicated image processing device by an image acquisition device, and the image processing device processes the received image data.

[0003] Taking visual inspection of printed matter as an example, when soft packaging material is visually inspected, a line array camera is usually used to collect image data of the soft packaging to be measured. The image data is then output to the image processing device by the image acquisition device, and the image processing device processes the received image data to obtain the result of the visual inspection of the soft packaging material.

[0004] However, in some fields (such as the industrial field), the image data photographed by the image capturing device often has a large capacity. After the image acquisition device outputs the image data to the image processing device, the image processing device often needs to process a large amount of data, resulting in low efficiency of the visual inspection system. SUMMARY

[0005] In order to solve the problem that the image processing device needs to process a large amount of data after the image acquisition device directly transmits the image data to the image processing device, resulting in low efficiency of the visual inspection system, the present application provides an image screening method, device, system and storage medium.

[0006] Embodiments of the present application are implemented as follows:

[0007] A first aspect of an embodiment of the present application provides an image screening method applied to an image acquisition device, the image acquisition device being in communication connection with an image extraction device and an image processing device, and the method comprising:

[0008] obtaining effective matching data and obtaining each row of to-be-processed row image data included in an image collected by the image extraction device, the effective matching data including a matching template, a matching template position and an effective version cycle, the effective version cycle being the number of rows of an effective area in the image, the matching template including a target in the effective area, the matching template position being the position of the target in the effective area, and the effective area including at least one row of to-be-processed row image data;

[0009] determining an initial matching area in the image based on the row number of the to-be-processed row image data in the image and the number of rows of the matching template;

[0010] In the initial matching region, based on a preset matching strategy, a matching value of at least one sub-region included in the initial matching region and the matching template is determined;

[0011] If the target matching value meets a preset determination condition, based on the target matching value, the matching template position and the effective edition cycle, an effective region in the image is determined, and the effective region is sent to the image processing device, and the target matching value is the most matching value in the matching values.

[0012] A second aspect of the embodiment of the application provides an image screening device, which comprises:

[0013] The acquisition module is configured to acquire effective matching data and each row of to-be-processed row image data included in the image collected by the image extraction device, the effective matching data comprising a matching template, a matching template position and an effective edition cycle, the effective edition cycle being a number of rows corresponding to an effective region in the image, the matching template comprising a target in the effective region, the matching template position being a position of the target in the effective region, and the effective region comprising at least one row of to-be-processed row image data;

[0014] The matching template is configured to determine an initial matching region in the image based on a row number of the to-be-processed row image data in the image and a number of rows of the matching template.

[0015] The matching template is further configured to determine, in the initial matching region, a matching value of at least one sub-region included in the initial matching region and the matching template based on a preset matching strategy.

[0016] The execution module is configured to, if the target matching value meets a preset determination condition, determine an effective region in the image based on the target matching value, the matching template position and the effective edition cycle, and send the effective region to the image processing device, the target matching value being the most matching value in the matching values.

[0017] A third aspect of the embodiment of the application provides an image screening system, which comprises an image extraction device, an image processing device and an image collection device, the image collection device and the image processing device being communicatively connected, and the image collection device being configured to:

[0018] The image collection device is configured to acquire effective matching data and each row of to-be-processed row image data included in the image collected by the image extraction device, the effective matching data comprising a matching template, a matching template position and an effective edition cycle, the effective edition cycle being a number of rows corresponding to an effective region in the image, the matching template comprising a target in the effective region, the matching template position being a position of the target in the effective region, and the effective region comprising at least one row of to-be-processed row image data.

[0019] The image collection device is configured to determine an initial matching region in the image based on a row number of the to-be-processed row image data in the image and a number of rows of the matching template.

[0020] In the initial matching region, based on a preset matching strategy, a matching value of at least one sub-region included in the initial matching region and the matching template is determined;

[0021] If the target matching value meets a preset determination condition, an effective region in the image is determined based on the target matching value, the matching template position and the effective edition cycle, and the effective region is sent to the image processing device, and the target matching value is the most matching value in the matching values.

[0022] A fourth aspect of the embodiment of the application provides a computer storage medium, a computer program is stored on the computer readable storage medium, and the computer program is executed by a processor to make the processor execute the steps of the image screening method in the first aspect of the summary.

[0023] The image screening method is applied to an image acquisition device, the image acquisition device is in communication connection with an image extraction device and an image processing device respectively, effective matching data is acquired, each row of to-be-processed image data included in an image acquired by the image extraction device is acquired, the effective matching data includes a matching template, a matching template position and an effective edition cycle, an initial matching region in the image can be determined based on the row number of the to-be-processed image data in the image and the number of rows of the matching template, in the initial matching region, based on a preset matching strategy, a matching value of at least one sub-region included in the initial matching region and the matching template can be determined, and a target matching value can be determined, if the target matching value meets a preset determination condition, an effective region in the image is determined based on the target matching value, the matching template position and the effective edition cycle, and the effective region is sent to the image processing device, the extraction of the effective region of the image by the image acquisition device is realized, the capacity of the data processed by the image processing device is reduced, and the efficiency of the visual detection system is improved. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or the prior art description. Obviously, the drawings in the following description are some embodiments of the application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0025] Figure 1 Part of the schematic diagram of the soft packaging material is shown, and the packaging pattern on the material is exemplary;

[0026] Figure 2 The flowchart of the image screening method provided by the embodiment of the application is shown;

[0027] Figure 3A schematic diagram showing the matching of a sub-region in an initial matching region with a matching template is shown;

[0028] Figure 4 A flowchart of another image screening method provided by the embodiments of the present application is shown;

[0029] Figure 5 A flowchart of another image screening method provided by the embodiments of the present application is shown;

[0030] Figure 6 A schematic diagram showing the matching of a sub-region in an initial matching region with a matching template is shown;

[0031] Figure 7 A structural schematic diagram of an image screening device provided by the embodiments of the present application is shown;

[0032] Wherein, 110-soft packaging material; 121-valid region; 122-inactive region; 130-initial matching region; 131, 132, 138-sub-region; 140-matching template; 150-target matching region; 151, 152, 153-sub-region; 150-matching template. DETAILED DESCRIPTION

[0033] In order to make the purpose, implementation and advantages of the present application more clear, the following will combine the drawings in the exemplary embodiments of the present application to clearly and completely describe the exemplary embodiments of the present application. Obviously, the described exemplary embodiments are only a part of the embodiments of the present application, but not all the embodiments.

[0034] It should be noted that the brief description of the terms in the present application is only for the convenience of understanding the following described embodiments, and is not intended to limit the embodiments of the present application. Unless otherwise specified, these terms should be understood according to their ordinary and general meanings.

[0035] The terms "first", "second", "third" and the like in the specification and claims of the present application and the above drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit the specific order or sequence, unless otherwise specified. It should be understood that the terms used in this way can be interchanged under appropriate circumstances.

[0036] The terms "include" and "have" and any variations thereof are intended to cover but not exclusive inclusion, for example, a product or device including a series of components does not necessarily limit to all the components clearly listed, but can include other components not clearly listed or inherent to these products or devices.

[0037] In the visual inspection system, the image acquisition and processing are generally completed by a machine vision product, an image acquisition device and an image processing device. The process is that the machine vision product (i.e. image acquisition device, such as a camera) first photographs the target object to be detected, and then converts the photographed optical data into image data. The image data is directly transmitted to a dedicated image processing device by the image acquisition device. The image processing device processes the received image data to realize the detection of the target object.

[0038] The machine vision product is the image acquisition device, such as a camera. The image acquisition device can be an image acquisition card, which is used to realize the conversion of the image data transmission protocol. The image processing device is generally a terminal device with image processing function, such as a computer.

[0039] Taking the visual inspection of printed matter as an example, when the soft packaging roll is visually inspected, the image acquisition device is generally used to collect the image data of the soft packaging to be detected. Then the image data is transmitted to the image processing device by the image acquisition card. The image processing device processes the received image data to obtain the result of the visual inspection of the soft packaging roll.

[0040] The image acquisition card does not identify the image, and provides all the image data from the camera to the image processing device without distinction. The image data photographed by the image acquisition device often has a large capacity. After the image acquisition device transmits the image data to the image processing device, the image processing device often needs to process a large amount of data, which leads to low efficiency of the visual inspection system.

[0041] In order to solve the problem that after the image acquisition device directly transmits the image data to the image processing device, the image processing device needs to process a large amount of data, which leads to low efficiency of the visual inspection system, the present application provides an image screening method, device and system and storage medium, which are applied to the image acquisition device. The image acquisition device is in communication connection with the image acquisition device and the image processing device. The effective matching data is obtained, and each row of to-be-processed image data included in the image collected by the image acquisition device is obtained. The effective matching data includes a matching template, a matching template position and an effective edition cycle. Further, based on the row number of the to-be-processed image data in the image and the number of rows of the matching template, the initial matching area in the image can be determined. In the initial matching area, based on the preset matching strategy, the matching value of at least one sub-area included in the initial matching area and the matching template can be determined, and the target matching value can be determined. If the target matching value meets the preset determination condition, the effective area in the image is determined based on the target matching value, the matching template position and the effective edition cycle, and the effective area is sent to the image processing device. The extraction of the effective area of the image in the image acquisition device is realized, the capacity of the data processed by the image processing device is reduced, and the efficiency of the visual inspection system is improved.

[0042] The image screening method, device, system and storage medium of the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0043] The scheme of the present application can be applied to the scene of visual detection of various target objects. For example, one of the scenes can be the scene of soft packaging roll feeding. FIG. 1 shows a partial schematic view of a soft packaging roll. The packaging pattern on the roll is exemplary, as shown in the figure. Figure 1 The roll 110 has continuous and identical packaging images. During the process of soft packaging roll feeding, the image extraction device periodically captures the soft packaging roll to obtain image data of each row of the soft packaging roll. The collection of the packaging images on the soft packaging roll includes the effective area 121 and the invalid area 122. In order to reduce the data processing capacity of the image processing device, an image screening method can be provided and applied to the image collection device, which is in communication connection with the image extraction device and the image processing device respectively.

[0044] It should be understood that the image collection device has a chip or unit capable of processing data, such as FPGA (Field Programmable Gate Array), ARM (Advanced RISC Machines) and the like.

[0045] Figure 2 A flowchart of an image screening method provided by an embodiment of the present application is shown. The method is applied to an image collection device, which is in communication connection with an image extraction device and an image processing device respectively. As shown in the figure, Figure 2 the present application provides an image screening method.

[0046] The image screening method includes the following steps:

[0047] S210, obtaining effective matching data and obtaining each row of to-be-processed row image data included in the image collected by the image extraction device. The effective matching data includes a matching template, a matching template position and an effective version number.

[0048] The effective matching data is related data for screening the effective area in the packaging image in the soft packaging roll. It can be sent to the image collection device by the image processing device, or it can be obtained by setting on the image collection device. If the packaging image in the soft packaging roll needs to be detected, the effective area can be the area including the packaging image in the soft packaging roll, and the invalid area can be the area including the adjacent packaging images in the soft packaging roll.

[0049] For different soft packaging and packaging images, the corresponding effective matching data is different.

[0050] For example,Figure 1 The effective area, wherein the selection of the target (i.e. the matching template) for determining the effective area is different for different soft packages, and even for the same packaging material, the matching template can be set to be different.

[0051] It should be understood that the effective matching data includes the matching template, the matching template position, and the effective version number. The effective version number is the number of rows in the image corresponding to the effective area, the matching template includes the target in the effective area, the matching template position is the position of the target in the effective area, and the effective area includes at least one row of the to-be-processed row image data. Wherein, if the effective area is an area in the soft package roll including the packaging image, the target in the effective area is the packaging image, and the matching template includes the packaging image.

[0052] The size of the matching template can be M rows * N columns, and is smaller than the size of the effective area; the matching template position S is the position of the matching template in the effective area, which can be the row number corresponding to the first row of the matching template in the effective image, the row number corresponding to the Mth row of the matching template in the effective image, or the row number corresponding to a certain row in the matching template in the effective image; and the effective version number L is the total number of rows corresponding to an effective area.

[0053] Each row of the to-be-processed row image data is obtained by the image extraction device collecting the packaging image row by row, so whether the corresponding image contains an effective area needs to be determined according to the to-be-processed row image collected row by row.

[0054] In some embodiments, each row of the to-be-processed row image data is obtained by a line array camera collecting the packaging image row by row.

[0055] S220, determining an initial matching area in the image based on the row number of the to-be-processed row image data in the image and the number of rows of the matching template.

[0056] With the to-be-processed row image data continuously collected by the image extraction device, the relationship between the row number of the to-be-processed row image data and the number of rows of the matching template is analyzed, and the to-be-processed row image data corresponding to the number of rows of the matching template is determined as the initial matching area in the image.

[0057] For example, the initial matching area can be from the to-be-processed row image data of the first row to the to-be-processed row image data of the Mth row, or from the to-be-processed row image data of the Oth row to the to-be-processed row image data of the M+Oth row.

[0058] S230, in the initial matching area, determining a matching number value that at least one sub-area included in the initial matching area matches the matching template based on a preset matching strategy, and a target matching number value.

[0059] Among them, the matching value between the sub-region and the matching template can be used to characterize the degree of matching between the sub-region and the matching template. The target matching value is the most matching value among all the matching data. Then, the sub-region corresponding to the target matching value is the sub-region that best matches the matching template.

[0060] The number of rows in the initial matching region is the same as the number of rows in the matching template. In the initial matching region, there is at least one sub-region with the same size as the matching template. Through a preset matching strategy, the matching value of each sub-region that matches the matching template is determined.

[0061] The preset matching strategies can be Sum of Absolute Differences (SAD), Mean Absolute Differences (MAD), Sum of Squared Differences (SSD), Mean Square Differences (MSD), etc.

[0062] Figure 3 This diagram illustrates the matching of sub-regions within an initial matching region with a matching template, as shown below. Figure 3 As shown, the size of the matching template 140 is 3*3, the initial matching area 130 is 3*10, and there are 8 sub-regions in the initial matching area 130 that can be matched with the matching template, namely sub-region 131, sub-region 132, ..., sub-region 138.

[0063] For each sub-region in the initial matching region, a matching template is used to perform matching according to the preset matching strategy, and the corresponding matching values ​​are determined.

[0064] The most matching value is selected from all the matching values, which is the target matching value.

[0065] In some embodiments, the minimum value among all matching values ​​is the target matching value, and the minimum value corresponding to the best match depends on the prediction matching strategy. For example, if the preset matching strategy is SAD, the target matching value is the minimum value among all matching values.

[0066] S240. If the target matching value meets the preset judgment conditions, the effective area in the image is determined based on the target matching value, the matching template position and the effective area, and the effective area is sent to the image processing device.

[0067] The target matching value is the most matching matching value for each corresponding to-be-processed row image data available for matching; but for the to-be-processed row image data before the current to-be-processed row image data and the to-be-processed row image data after the current to-be-processed row image data, further determination is needed to determine whether the corresponding region is the most matching region to the matching template, so that the accuracy of the determination is improved by the preset determination condition.

[0068] If the target matching value meets the preset determination condition, the effective region in the image can be determined, and the effective region is sent to the image processing device, so that the image acquisition device extracts the effective region of the image, and the data capacity of the image acquisition device sent to the image processing device is reduced.

[0069] In some embodiments, the starting row number of the effective region is determined by the row number of the to-be-processed row image data corresponding to the target matching value and the matching template position; the ending row number of the effective region is determined by the row number of the to-be-processed row image data corresponding to the target matching value, the matching template position and the effective version cycle; and the effective region is determined from the starting row number to the ending row number.

[0070] For example, the row number of the to-be-processed row image data corresponding to the target matching value is Q, the matching template position is S, and the effective version cycle range is T, then the starting row number of the effective region is Q-S, and the ending row number of the effective region is Q-S+T-1.

[0071] If the target matching value does not meet the preset determination condition, the acquisition of the next to-be-processed row image data and the determination by steps 220 to 240 are continued.

[0072] In some embodiments, the effective matching data further includes a matching criterion, the matching criterion is a threshold preset for determining whether the target matching value meets the matching requirement, the target matching value meeting the preset determination condition includes that the target matching value is less than the matching criterion; the target matching value is greater than the target matching value corresponding to the previous to-be-processed row image data and less than the target matching value corresponding to the next to-be-processed row image data.

[0073] Figure 4 A flowchart of another image screening method provided by an embodiment of the present application is shown in FIG. 6. Figure 4 As shown in FIG. 6, step 220 can include the following steps.

[0074] 221, if the row number of the current to-be-processed row image data in the image is less than the row number of the matching template, the current to-be-processed row image data is stored.

[0075] 222、if the row number of the current to-be-processed row image data in the image is greater than or equal to the row number M of the matching template, determining an initial matching region in the image based on the to-be-processed row image data of the M-1 rows before the current to-be-processed row image data and the current to-be-processed row image data.

[0076] It should be understood that the current to-be-processed row image data corresponding to the case that the row number of the current to-be-processed row image data in the image is greater than or equal to the row number M of the matching template also needs to be stored, and the current to-be-processed row image data needs to be used in the process of determining the next row to-be-processed row image data.

[0077] The row number of the initial matching region is the same as the row number of the matching template, and there is at least one sub-region with the same size as the matching template in the initial matching region. The matching number of each sub-region matched with the matching template is determined through a preset matching strategy.

[0078] The effective matching data can also include a pre-judgment region, which is a column number range preset according to the matching template. The capacity of data storage in step 221 can be reduced, and the number of times of determination according to the preset matching strategy in step 222 can also be reduced. Figure 5 A flowchart of another image screening method provided by an embodiment of the present application is shown in FIG. 6. Figure 5 As shown in FIG. 6, step 220 can include the following steps:

[0079] S223、if the row number of the current to-be-processed row image data in the image is less than the row number of the matching template, storing the pre-judgment data in the pre-judgment region in the current to-be-processed row image data.

[0080] At this time, the stored data is the pre-judgment data in the pre-judgment region in the current to-be-processed row image data, and the pre-judgment data is less than the current to-be-processed row image data.

[0081] For example, if the pre-judgment region is the Xth column to the X+Yth column, where X is greater than 1 and X+Y is less than the maximum column number of the to-be-processed row image data.

[0082] S224、if the row number of the current to-be-processed row image data in the image is greater than or equal to the row number M of the matching template, determining a target matching region based on the pre-judgment data of the M-1 rows before the current to-be-processed row image data and the current pre-judgment data, and the target matching region is contained in the initial matching region.

[0083] It should be understood that the pre-judgment data corresponding to the case that the row number of the current to-be-processed row image data in the image is greater than or equal to the row number M of the matching template also needs to be stored.

[0084] The number of rows of the target matching region is the same as the number of rows of the matching template, and there is at least one sub-region of the same size as the matching template in the target matching region. The matching number value of each sub-region matched with the matching template is determined by the preset matching strategy.

[0085] Figure 6 Another schematic diagram of the matching of the sub-region in the initial matching region with the matching template is shown as follows. Figure 6 As shown in the figure, the size of the matching template 160 is 3*3, the target matching region 150 is a part of the initial matching region (3*10), and the size of the target matching region 150 is 3*5. In the target matching region 150, there are three sub-regions that can be matched with the matching template, which are sub-region 151, sub-region 152, and sub-region 153.

[0086] As shown in the figure, Figure 5 Figure 2 The step 230 can further include the following step S231: in the target matching region, the matching number value of at least one sub-region included in the target matching region matched with the matching template is determined based on the preset matching strategy, and the target matching number value.

[0087] For example, if the pre-judgment region is the Xth column to the X+Yth column, and Y is greater than the number N of columns of the matching template, in the step of determining the target matching number value in the target matching region based on the preset matching strategy, the following steps are included:

[0088] In the target matching region, Y-N times of matching are performed based on the preset matching strategy to determine the matching number value of each sub-region in the target matching region matched with the matching template.

[0089] The target matching number value is selected from the initial matching number values, and the target matching number value is the minimum data in the matching number values.

[0090] The embodiment of the present application provides an image screening method, effective matching data and each row of to-be-processed row image data included in an image collected by an image extraction device are obtained, the effective matching data includes a matching template, a matching template position, and an effective version cycle, an initial matching region in the image is determined based on the row number of the to-be-processed row image data in the image and the number of rows of the matching template, in the initial matching region, the matching number value of at least one sub-region included in the initial matching region matched with the matching template is determined based on a preset matching strategy, and a target matching number value is determined. If the target matching number value meets a preset judgment condition, the effective region in the image is determined based on the target matching number value, the matching template position, and the effective version cycle, and is sent to an image processing device, so that the extraction of the effective region of the image by the image collection device is realized, the capacity of the data processed by the image processing device is reduced, and the efficiency of the visual detection system is improved.

[0091] Figure 7 ​A structural schematic diagram of an image screening device provided by an embodiment of the present application is shown in FIG. 7. As shown in FIG. 7, the image screening device 700 includes an acquisition module 710, a matching module 720, and an execution module 730. Figure 7

[0092] The acquisition module is configured to acquire effective matching data and acquire each row of to-be-processed row image data included in an image collected by an image extraction device. The effective matching data includes a matching template, a matching template position, and an effective version cycle. The effective version cycle is a number of rows corresponding to an effective region in the image. The matching template includes a target in the effective region. The matching template position is a position of the target in the effective region. The effective region includes at least one row of to-be-processed row image data.

[0093] The matching module is configured to determine an initial matching region in the image based on a row number of the to-be-processed row image data in the image and a number of rows of the matching module. The matching module is also configured to determine a matching value of at least one sub-region included in the initial matching region and the matching template based on a preset matching strategy in the initial matching region.

[0094] The execution module is configured to determine an effective region in the image based on the target matching value, the matching template position, and the effective version cycle if the target matching value satisfies a preset determination condition, and send the effective region to an image processing device.

[0095] In some embodiments, the matching module further includes a first matching unit. The first matching unit is configured to determine an initial matching region in the image based on to-be-processed row image data of M-1 rows before the current to-be-processed row image data and the current to-be-processed row image data if a row number of the current to-be-processed row image data in the image is greater than or equal to a number of rows M of the matching template.

[0096] In some embodiments, the effective matching data further includes a pre-judgment region. The matching module further includes a second matching unit. The second matching unit is configured to store pre-judgment data in the pre-judgment region in the current to-be-processed row image data if a row number of the current to-be-processed row image data in the image is less than the number of rows of the matching template, and determine a target matching region based on the pre-judgment data of the M-1 rows before the current to-be-processed row image data and the current pre-judgment data. The target matching region is contained in the initial matching region.

[0097] The matching module can further include a second matching unit. The execution module is further configured to determine a matching value of at least one sub-region included in the target matching region and the matching template based on a preset matching strategy in the target matching region.

[0098] ​In some embodiments, the execution module comprises an effective determination unit configured to determine a starting row number of the effective area by matching the row number of the to-be-processed row image data corresponding to the target matching value and the matching template position; determine a terminating row number of the effective area by matching the row number of the to-be-processed row image data corresponding to the target matching value, the matching template position and the effective edition cycle; and determine the effective area from the starting row number to the terminating row number.

[0099] The effective matching data further comprises a matching criterion, and the execution module further comprises a judgment unit configured to determine that the target matching value is less than the matching criterion; and the target matching value is greater than the target matching value corresponding to the to-be-processed row image data of the previous row and less than the target matching value corresponding to the to-be-processed row image data of the next row.

[0100] The embodiments of the present application provide an image screening device, which comprises an acquisition module, a matching module and an execution module; effective matching data is acquired, and each row of to-be-processed row image data included in an image collected by an image extraction device is acquired; the effective matching data comprises a matching template, a matching template position and an effective edition cycle; based on the row number of the to-be-processed row image data in the image and the number of rows of the matching template, an initial matching area in the image is determined; in the initial matching area, based on a preset matching strategy, a matching value that at least one sub-area included in the initial matching area matches the matching template and a target matching value are determined; if the target matching value satisfies a preset judgment condition, based on the target matching value, the matching template position and the effective edition cycle, an effective area in the image is determined and sent to an image processing device, so that the extraction of the effective area of the image by the image collection device is realized, the capacity of the data processed by the image processing device is reduced, and the efficiency of the visual detection system is improved.

[0101] The embodiments of the present application further provide an image screening system, which comprises an image extraction device, an image processing device and an image collection device, and the image collection device and the image processing device are in communication connection.

[0102] The image collection device is configured to acquire effective matching data, and acquire each row of to-be-processed row image data included in an image collected by an image extraction device; the effective matching data comprises a matching template, a matching template position and an effective edition cycle; the effective edition cycle is the number of rows of an effective area in the image; the matching template comprises a target in the effective area; the matching template position is the position of the target in the effective area; and the effective area comprises at least one row of to-be-processed row image data; based on the row number of the to-be-processed row image data in the image and the number of rows of the matching template, an initial matching area in the image is determined; in the initial matching area, based on a preset matching strategy, a matching value that at least one sub-area included in the initial matching area matches the matching template and a target matching value are determined; if the target matching value satisfies a preset judgment condition, based on the target matching value, the matching template position and the effective edition cycle, an effective area in the image is determined and sent to an image processing device.

[0103] The implementation principle and technical effects of the image acquisition device are similar to those of the method embodiments, and thus will not be described herein.

[0104] The embodiments of the present application further provide a computer storage medium, and a computer program is stored on the computer readable storage medium. When the computer program is executed by a processor, the processor executes the image screening method, and the implementation principle and technical effects are similar to those of the method embodiments, and thus will not be described herein.

[0105] The following paragraphs will compare and list the Chinese terms involved in the present application and their corresponding English terms, so as to facilitate reading and understanding.

[0106] The above description has been made in conjunction with specific embodiments for the convenience of explanation. However, the above description in some embodiments is not intended to be exhaustive or to limit the embodiments to the specific form disclosed. Various modifications and variations can be derived from the above teachings. The selection and description of the above embodiments are for better explanation of the principles and practical applications, so that those skilled in the art can better use the embodiments and various different modified embodiments suitable for specific use considerations.

Claims

1. An image screening method characterized by, The application is applied to an image acquisition device, which is respectively connected with an image extraction device and an image processing device, and comprises: acquiring effective matching data and acquiring each row of to-be-processed row image data included in an image acquired by the image extraction device, the effective matching data comprising a matching template, a matching template position and an effective edition week, the effective edition week being the number of rows of an effective area in the image, the matching template comprising a target in the effective area, the matching template position being the position of the target in the effective area, and the effective area comprising at least one row of to-be-processed row image data; the effective area being an area including a packaging image in a soft packaging roll material; determining an initial matching area in the image based on the row number of the to-be-processed row image data in the image and the number of rows of the matching template; in the initial matching area, determining a matching value of at least one sub-area included in the initial matching area and a target matching value based on a preset matching strategy, the target matching value being the minimum value of each matching value; if the target matching value meets a preset determination condition, determining the effective area in the image based on the target matching value, the matching template position and the effective edition week, and sending the effective area to the image processing device.

2. The image screening method according to claim 1, characterized by, The number of rows of the initial matching area is the same as the number of rows of the matching template; the determination of the initial matching area in the image based on the row number of the to-be-processed row image data in the image and the number of rows of the matching template comprises: if the current row number of the to-be-processed row image data in the image is greater than or equal to the number of rows M of the matching template, determining the initial matching area in the image based on the to-be-processed row image data of M-1 rows before the current to-be-processed row image data and the current to-be-processed row image data.

3. The image screening method according to claim 2, characterized by, The effective matching data further comprises a pre-judgment area, the pre-judgment area being a column number range preset according to the matching template; the determination of the initial matching area in the image based on the row number of the to-be-processed row image data in the image and the number of rows of the matching template comprises: if the current row number of the to-be-processed row image data in the image is less than the number of rows of the matching template, storing pre-judgment data in the pre-judgment area in the current to-be-processed row image data; continuously increasing the row number of the current to-be-processed row image data in the image and storing the pre-judgment data in the pre-judgment area in the current to-be-processed row image data; until the row number of the current to-be-processed row image data in the image is equal to the number of rows M of the matching template, determining a target matching area based on the pre-judgment data of M-1 rows before the current to-be-processed row image data and the current pre-judgment data, the target matching area being in the initial matching area.

4. The image screening method according to claim 3, characterized by, In the initial matching area, the preset matching strategy is that if the target matching area is X+Y columns and the matching template is X columns, the matching template is moved downwards successively until it stops at X+Y columns. In the step of determining the matching values of at least one sub-region included in the initial matching region matching the matching template, the step comprises: In the target matching region, based on a preset matching strategy, determine the matching values of at least one sub-region included in the target matching region matching the matching template.

5. The image screening method according to claim 4, characterized by, If the pre-judgment region is the Xth column to the X+Yth column, and Y is greater than the column number N of the matching template, in the step of determining the matching values of at least one sub-region included in the target matching region matching the matching template based on a preset matching strategy in the target matching region, the step comprises: In the target matching region, perform Y-N+2 times of matching through a preset matching strategy to determine the initial matching values of each sub-region in the target matching region matching the matching template; From each of the initial matching values, filter out the target matching value, which is the minimum value of each of the initial matching values.

6. The image screening method of claim 1, wherein, The determination of the effective region based on the target matching value, the matching template position, and the effective version cycle comprises: Determine the starting row number of the effective region through the row number of the to-be-processed row image data corresponding to the target matching value and the matching template position; Determine the terminal row number of the effective region through the row number of the to-be-processed row image data corresponding to the target matching value, the matching template position, and the effective version cycle; Determine the effective region from the starting row number to the terminal row number.

7. The image screening method of claim 1, wherein, The effective matching data further comprises a matching criterion, and the target matching value satisfies a preset determination condition, which comprises: The target matching value is less than the matching criterion; The target matching value is greater than the target matching value corresponding to the to-be-processed row image data of the previous row and less than the target matching value corresponding to the to-be-processed row image data of the next row.

8. An image screening apparatus characterized by comprising: The method comprises: An acquisition module is configured to acquire effective matching data and to-be-processed row image data included in an image collected by an image extraction device, wherein the effective matching data comprises a matching template, a matching template position, and an effective version cycle, the effective version cycle is the row number of an effective region in the image, the matching template comprises a target in the effective region, the matching template position is the position of the target in the effective region, and the effective region comprises at least one to-be-processed row image data; the effective region is a region including a packaging image in a soft packaging roll material; A matching module is configured to determine an initial matching region in the image based on the row number of the to-be-processed row image data in the image and the row number of the matching template. The matching module is further configured to determine, in the initial matching region, matching values of at least one sub-region included in the initial matching region matching the matching template and a target matching value based on a preset matching strategy, wherein the target matching value is the minimum value of each matching value. The execution module is configured to, if the target matching value meets a preset determination condition, determine an effective area in the image based on the target matching value, the matching template position, and the effective number of turns, and send the effective area to the image processing device.

9. An image screening system characterized by, The image extraction device comprises: The image processing device; The image acquisition device is in communication connection with the image processing device, and is configured to: acquire effective matching data and acquire each row of to-be-processed row image data included in the image acquired by the image extraction device, the effective matching data comprising a matching template, a matching template position, and an effective number of turns, the effective number of turns being the number of rows of an effective area in the image, the matching template comprising a target in the effective area, the matching template position being the position of the target in the effective area, and the effective area comprising at least one row of to-be-processed row image data; the effective area being an area including a packaging image in a soft packaging roll; determine an initial matching area in the image based on the row number of the to-be-processed row image data in the image and the number of rows of the matching template; in the initial matching area, determine a matching value and a target matching value of at least one sub-area included in the initial matching area and the matching template based on a preset matching strategy, the target matching value being the minimum value of each matching value; if the target matching value meets a preset determination condition, determine an effective area in the image based on the target matching value, the matching template position, and the effective number of turns, and send the effective area to the image processing device. The computer readable storage medium stores a computer program, and the computer program is executed by the processor to make the processor execute the steps of the image screening method in any one of claims 1 to 7.

10. A computer storage medium, characterized in that ​

Images