Connected Region Acquisition Method, Storage Medium, and Electronic Device

Abstract

The present disclosure provides a method for obtaining a connected region, a storage medium, and an electronic device. The method includes: taking a target pixel point in a target image as a current pixel point and configuring a label for the current pixel point; if there is an unused label value and the current pixel point is not the last target pixel point of the target image, taking the next target pixel point of the current pixel point as a new current pixel point and configuring a label for the current pixel point; if there is no unused label value and the current pixel point is not the last target pixel point of the target image, configuring the label value of the target pixel point that meets the reconfiguration condition as unused, taking the next target pixel point of the current pixel point as a new current pixel point, and configuring a label for the current pixel point; and obtaining a connected region according to the label values of the target pixel points in the target image. The method can obtain the connected region in the target image.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing, and particularly to a method for obtaining connected components, a storage medium, and an electronic device. Background Art

[0002] A connected component usually refers to an image area composed of foreground pixel points with the same pixel value and adjacent positions in an image. Connected component analysis or acquisition refers to the process of finding and labeling each connected component in an image. Currently, connected component analysis or acquisition has been widely applied to scenarios such as OCR (Optical Character Recognition), visual tracking, and medical image processing. Summary of the Invention

[0003] The purpose of the present disclosure is to provide a method for obtaining connected components, a storage medium, and an electronic device, which are used to label the connected components in a target image.

[0004] In a first aspect of the present disclosure, a method for obtaining connected components is provided. The method includes: taking a target pixel point in the target image as the current pixel point, and configuring a label for the current pixel point; if there is an unused label value and the current pixel point is not the last target pixel point of the target image, taking the next target pixel point of the current pixel point as the new current pixel point, and configuring a label for the current pixel point; if there is no unused label value and the current pixel point is not the last target pixel point of the target image, configuring the label value of the target pixel point that meets the reconfiguration condition as unused, taking the next target pixel point of the current pixel point as the new current pixel point, and configuring a label for the current pixel point; and obtaining connected components according to the label values of the target pixel points in the target image.

[0005] In an embodiment of the first aspect, configuring a label for the current pixel point includes: if the neighborhood of the current pixel point contains a configured pixel point, configuring the label of the current pixel point according to the label value of the configured pixel point in the neighborhood of the current pixel point; and if the neighborhood of the current pixel point does not contain a configured pixel point, configuring the label of the current pixel point as an unused label value.

[0006] In an embodiment of the first aspect, configuring the label of the current pixel point according to the label value of the configured pixel point in the neighborhood of the current pixel point includes: obtaining the minimum label value of the configured pixel points in the neighborhood of the current pixel point; and configuring the label of the current pixel point as the minimum label value.

[0007] In an embodiment of the first aspect, configuring the tag value of a target pixel point that meets the reconfiguration condition to unused includes: obtaining the scanned connected region according to the tag value of the target pixel point in the target image; and configuring the tag value of the target pixel point that meets the reconfiguration condition to unused according to the scanned connected region.

[0008] In an embodiment of the first aspect, configuring the tag value of a target pixel point that meets the reconfiguration condition to unused according to the scanned connected region includes: obtaining the tag value of the scanned connected region according to the tag value of the target pixel point in the scanned connected region; and if the tag value of the target pixel point is different from the tag value of its affiliated connected region, configuring the tag value of the target pixel point to unused and configuring the tag of the target pixel point to the tag value of its affiliated connected region, where the affiliated connected region of the target pixel point refers to the scanned connected region containing the target pixel point.

[0009] In an embodiment of the first aspect, configuring the tag value of a target pixel point that meets the reconfiguration condition to unused according to the scanned connected region further includes: if the current row and the row above it contain all used tag values, configuring the tag values of the target pixel points in the scanned connected regions with an area smaller than the area threshold to unused and configuring the tags of the target pixel points in these scanned connected regions to non-connected region tag values; and if the current row and the row above it do not contain all used tag values, configuring the tag values of the target pixel points in the scanned connected regions with an area smaller than the area threshold and not intersecting with the current row and the row above it to unused and configuring the tags of the target pixel points in these scanned connected regions to non-connected region tag values.

[0010] In an embodiment of the first aspect, the method further includes: adjusting the area threshold according to the tag values contained in the current row and the row above it and the area of the scanned connected region.

[0011] In an embodiment of the first aspect, adjusting the area threshold according to the tag values contained in the current row and the row above it and the area of the scanned connected region includes: if the current row and the row above it contain all used tag values, adjusting the area threshold to be greater than or equal to the minimum area of each of the scanned connected regions; and if the current row and the row above it do not contain all used tag values, adjusting the area threshold to be greater than or equal to the minimum area of each of the scanned connected regions that does not intersect with the current row and the row above it.

[0012] In an embodiment of the first aspect, obtaining the scanned connected region according to the label value of the target pixel point in the target image includes: obtaining a first alternative connected region according to the label value of the target pixel point in the target image; and merging the first alternative connected regions according to the connection relationship to obtain the scanned connected region.

[0013] In an embodiment of the first aspect, obtaining the connected region according to the label value of the target pixel point in the target image includes: obtaining a second alternative scanning region according to the label value of the target pixel point in the target image; and screening the second alternative scanning region to obtain the connected region.

[0014] The second aspect of the present disclosure provides a computer-readable storage medium, on which a computer program is stored. The computer program is executed by a processor to implement the connected region obtaining method according to any one of the first aspects of the present disclosure.

[0015] The third aspect of the present disclosure further provides an electronic device. The electronic device includes: a memory configured to store a computer program; and a processor configured to call the computer program to execute the connected region obtaining method according to any one of the first aspects of the present disclosure.

[0016] According to one or more embodiments of the present disclosure, the connected region obtaining method can use limited label values to label larger connected regions in the target image. For example, if 8-bit label values are used, the number of connected regions obtained by the connected region obtaining method is less than 255. Therefore, the connected region obtaining method described in the embodiments of the present disclosure has a high annotation efficiency and can reduce resource overhead. Description of the Drawings

[0017] Figure 1 It shows a flowchart of the connected region obtaining method in an embodiment of the present disclosure.

[0018] Figure 2 It shows an example diagram of a partial region of the target image in an embodiment of the present disclosure.

[0019] Figure 3A It shows a flowchart of reconfiguring the label value of the target pixel point in an embodiment of the present disclosure.

[0020] Figure 3B It shows a detailed flowchart of the steps of obtaining the scanned connected region in an embodiment of the present disclosure.

[0021] Figure 3C It shows a detailed flowchart of the steps of configuring the label value as unused in an embodiment of the present disclosure.

[0022] Figure 4It shows a flowchart of obtaining connected regions in an embodiment of the present disclosure.

[0023] Figure 5 It shows a schematic structural diagram of an electronic device in an embodiment of the present disclosure. Detailed implementation manners

[0024] The following uses specific specific examples to illustrate the implementation manners of the present disclosure. Those skilled in the art can easily understand other advantages and effects of the present disclosure from the content disclosed in this specification. The present disclosure can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0025] It should be noted that the diagrams provided in the following embodiments only schematically illustrate the basic concept of the present disclosure. The diagrams only show the components related to the present disclosure, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in actual implementation can be an arbitrary change, and the component layout type may also be more complex. In addition, in this article, relational terms such as "first", "second", etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0026] In practical applications, an image often contains a large number of connected regions. Especially for relatively complex images, it may contain hundreds of thousands or even millions of connected regions. In the related art, when analyzing the connected regions in an image, all the connected regions are marked and stored. However, for users, usually only the connected regions with larger areas need to be concerned, and the connected regions with smaller areas do not need to be marked. Therefore, the related art has problems of low efficiency and excessive resource consumption. For example, for an image of 1920×1080, in extreme cases (such as a black-and-white checkerboard image), 4,147,200 connected regions may be marked and stored.

[0027] At least for the above problems, according to an embodiment of the present disclosure, a method for processing connected regions in an image is provided. In some embodiments, the image is scanned from the upper left corner to the lower right corner. When encountering an isolated point that cannot be connected to other pixels, a new label is given to the mark. During the downward scan, the mutually connected regions are merged into one region, and the labels are merged. The area of each id in the marked image is statistically counted, and the ids that have appeared in the last two rows are statistically counted. The statistically counted regions are merged to determine the threshold and the connected regions. According to the embodiment of the present disclosure, the number of results of the connected regions can be limited and the hardware resource consumption can be reduced.

[0028] In the following, specific embodiments of the present disclosure will be described with reference to the accompanying drawings through exemplary embodiments.

[0029] Figure 1 is a flowchart showing a method for obtaining a connected region according to an embodiment of the present disclosure. In the embodiments of the present disclosure, the method for obtaining the connected region is introduced by taking the scanning order from the upper left corner to the lower right corner as an example, but the present disclosure is not limited thereto. As Figure 1 shown, the method for obtaining the connected region in the embodiments of the present disclosure includes the following steps S102 to S108.

[0030] In step S102, a target pixel point in the target image is used as the current pixel point, and a label of the current pixel point is configured. In some embodiments, the target pixel point is, for example, a foreground pixel point of the target image, and the target pixel point may be the first target pixel point. The first target pixel point is, for example, the first foreground pixel point in the upper left corner of the target image, but the present disclosure is not limited thereto. In some embodiments, the label of the current pixel point may be configured as an unused label value, or the label of the current pixel point may be configured as a used label value

[0031] In step S104, if there is an unused label value and the current pixel point is not the last target pixel point of the target image, then the next target pixel point of the current pixel point is used as the new current pixel point, and the label of the current pixel point is configured.

[0032] In step S106, if there is no unused label value and the current pixel point is not the last target pixel point of the target image, then the label value of the target pixel point that satisfies the reconfiguration condition is configured as unused, and the next target pixel point of the current pixel point is used as the new current pixel point and the label of the current pixel point is configured.

[0033] In step S108, a connected region is obtained according to the label values of the target pixel points in the target image.

[0034] In the embodiments of the present disclosure, after step S102 is executed, if the condition of "there is an unused label value and the current pixel point is not the last target pixel point of the target image" is satisfied, then step S104 can be continued. If the condition of "there is no unused label value and the current pixel point is not the last target pixel point of the target image" is satisfied, then step S106 can be continued. If neither of the above two conditions is satisfied, then step S108 can be executed.

[0035] It should be noted that the above labels S102 to S108 are only used to identify different steps, rather than to limit the execution order between these steps. In specific applications, the execution order of the above steps can be adjusted according to actual needs.

[0036] Optionally, in step S102, the unused tag values can be configured for each target pixel point in ascending order, that is, the smallest tag value is preferentially selected from the unused tag values and configured for the current pixel point.

[0037] Optionally, in the embodiments of the present disclosure, the tag values of each target pixel point can be recorded through an array P. The element serial numbers in the array P can be the serial numbers of each target pixel point, and the element values in the array P can be the tag values of each target pixel point.

[0038] According to an embodiment of the present disclosure, configuring the tag of the current pixel point includes: if the neighborhood of the current pixel point contains a configured pixel point, then configuring the tag of the current pixel point according to the tag values of the configured pixel points in the neighborhood of the current pixel point; otherwise, configuring the tag of the current pixel point as an unused tag value. The neighborhood of the current pixel point can be, for example, the eight-neighborhood or four-neighborhood of the current pixel point, and the configured pixel point refers to a pixel point for which the tag has been configured.

[0039] Figure 2 FIG. is a schematic diagram of a partial region of the target image according to an embodiment of the present disclosure, where p1 to p5 are foreground pixel points, and bg1 to bg4 are background pixel points. For the pixel point p3, its four-neighborhood includes bg1, bg2, bg3, and p5, and does not contain a configured pixel point. At this time, in the embodiments of the present disclosure, the tag of p3 can be configured as an unused tag value. For the pixel point p3, its eight-neighborhood includes p1, bg1, p2, bg2, bg3, p4, p5, and bg4. When scanning in the order from the upper left corner to the lower right corner, the neighborhood of p3 contains the configured pixel points p1 and p2. At this time, in the embodiments of the present disclosure, the tag value of p1 or p2 can be configured as the tag of p3.

[0040] Preferably, configuring the tag of the current pixel point according to the tag values of the configured pixel points in the neighborhood of the current pixel point includes: obtaining the minimum tag value of the configured pixel points in the neighborhood of the current pixel point and configuring the tag of the current pixel point as the minimum tag value. For example, in Figure 2 in the eight-neighborhood of the pixel point p3 shown, if the tag value of p1 is A1 and the tag value of p2 is A2, and A1 < A2, then in the embodiments of the present disclosure, it is preferred to configure the tag of p3 as A1.

[0041] Figure 3AIt is a flowchart showing that the label value of a target pixel point that meets the reconfiguration condition is configured as unused according to an embodiment of the present disclosure. As Figure 3A shown, the process of configuring the label value of a target pixel point that meets the reconfiguration condition as unused in the embodiment of the present disclosure includes the following steps S32 and S34.

[0042] In step S32, a scanned connected region is obtained according to the label value of the target pixel point in the target image.

[0043] In step S34, according to the scanned connected region, the label value of the target pixel point that meets the reconfiguration condition is configured as unused. Thereafter, these label values configured as unused can be used to label other target pixel points and / or connected regions.

[0044] Figure 3B It is a detailed flowchart showing the steps of obtaining a scanned connected region according to an embodiment of the present disclosure. As Figure 3B shown, step S32 in the embodiment of the present disclosure includes the following steps S322 and S324.

[0045] In step S322, a first alternative connected region is obtained according to the label value of the target pixel point in the target image. For example, each target pixel point with the same label value can be merged into a first alternative connected region.

[0046] In step S324, the first alternative connected regions are merged according to the connectivity relationship to obtain the scanned connected region. Specifically, if there are adjacent target pixel points in the first alternative connected region A and the first alternative connected region B, then there is a connectivity relationship between the first alternative regions A and B, and in step S324, the first alternative regions A and B can be merged. By this way, all the first alternative regions with a connectivity relationship can be merged to obtain the scanned connected region.

[0047] Optionally, step S32 in the embodiment of the present disclosure may further include: obtaining the statistical information of each of the first alternative connected regions, and merging the statistical information of each of the first alternative connected regions into the scanned connected region. For example, if the first alternative connected regions B1, B2, and B3 are merged into the scanned connected region B in step S324, then in the embodiment of the present disclosure, the statistical information of the first alternative connected regions B1, B2, and B3 can be merged into the scanned region B. The statistical information includes the area of the connected region, the circumscribed rectangle, whether the scanned region intersects with the current row and the row above it, etc.

[0048] Figure 3C It is a detailed flowchart showing the steps of configuring the label value as unused according to an embodiment of the present disclosure. As Figure 3CAs shown, step S34 in the embodiments of the present disclosure includes the following steps S342 and S344.

[0049] In step S342, the label value of the scanned connected region is obtained according to the label value of the target pixel points in the scanned connected region. Preferably, the label value of the scanned connected region may be the minimum label value of the target pixel points included therein, but the present disclosure is not limited thereto.

[0050] In step S344, if the label value of the target pixel point is different from the label value of its belonging connected region, the label value of the target pixel point is configured as unused, and the label of the target pixel point is configured as the label value of its belonging connected region, where the belonging connected region of the target pixel point refers to the scanned connected region containing the target pixel point.

[0051] For example, for Figure 2 the connected region CC shown, which includes target pixel points p1 to p5, if the label values of p1, p3, p4, p5 are A1 and the label value of p2 is A2, and A1 < A2, then, in step S342, the label value of the connected region CC can be configured as A1, and, in step S344, the label of p2 can be configured as A1, and the label value A2 can be configured as unused.

[0052] Optionally, in the embodiments of the present disclosure, configuring the label values of the target pixel points that meet the reconfiguration condition as unused according to the scanned connected region further includes: if the current row and the row above it contain all the used label values, then configure the label values of the target pixel points in the scanned connected regions with an area smaller than the area threshold as unused, and configure the labels of the target pixel points in these scanned connected regions as non-connected region label values, and the non-connected region label value is, for example, 0; otherwise, configure the label values of the target pixel points in the scanned connected regions with an area smaller than the area threshold and not intersecting with the current row and the row above it as unused, and configure the labels of the target pixel points in these scanned connected regions as non-connected region label values. Where the scanned connected region not intersecting with the current row and the row above it means that all the pixel points in the scanned connected region are not included in the current row and the row above it.

[0053] Optionally, in the embodiments of the present disclosure, the connected region obtaining method further includes: adjusting the area threshold according to the label values included in the current row and the row above it and the area of the scanned connected region.

[0054] Optionally, adjusting the area threshold according to the tag values included in the current row and the row above it and the area of the scanned connected regions includes: if the current row and the row above it include all the used tag values, adjusting the area threshold to be greater than or equal to the minimum area of each of the scanned connected regions; otherwise, adjusting the area threshold to be greater than or equal to the minimum area of each of the scanned connected regions that do not intersect with the current row and the row above it.

[0055] Optionally, during the process of adjusting the area threshold, a fixed step size can be used to adjust the area threshold, where the step size can be set according to actual requirements.

[0056] Figure 4 is a detailed flowchart showing the steps of obtaining connected regions according to an embodiment of the present disclosure. As Figure 4 shown, the specific implementation process of step S110 in the embodiment of the present disclosure includes step S42 and step S44.

[0057] In step S42, a second alternative scanning region is obtained according to the tag values of the target pixel points in the target image. For example, target pixel points with equivalent tag values and / or the same tag values can be merged into a second alternative scanning region, and in this way, all the second alternative scanning regions in the target image can be obtained. The equivalence of tag values can be defined in the following way: if in a round of scanning, connected regions Q_1,..., Q_N are configured with different tag values L_1,..., L_N, and in the next round of scanning, connected regions Q_1,..., Q_N are determined to have a connectivity relationship, then tag values L_1,..., L_N are equivalent to each other, and N is a positive integer greater than 1.

[0058] In step S44, the second alternative scanning regions are screened to obtain the connected regions. For example, the second alternative scanning regions with an area smaller than the area threshold can be deleted to achieve the screening and thus obtain the connected regions.

[0059] According to another aspect of the present disclosure, there is also provided a computer-readable storage medium, on which a computer program is stored. The computer program is executed by a processor to implement the connected region obtaining method in the embodiment of the present disclosure.

[0060] According to another aspect of the present disclosure, there is also provided an electronic device. Figure 5 is a block diagram showing an electronic device 500 according to an embodiment of the present disclosure. As Figure 5As shown, the electronic device 500 includes a memory 520 and a processor 540. The memory 520 is configured to store a computer program, and the processor 540 is communicatively connected to the memory 520 and configured to call the computer program to execute the image processing method described in the embodiments of the present disclosure.

[0061] Optionally, the electronic device 500 may further include a display 560. The display 560 is communicatively connected to the memory 520 and the processor 540 and is used to display the relevant GUI interaction interface of the connected region acquisition method described in the embodiments of the present disclosure.

[0062] The protection scope of the connected region acquisition method described in the present disclosure is not limited to the execution order of the steps listed in this embodiment. Any solution achieved by adding or subtracting steps of the prior art and replacing steps according to the principles of the present disclosure is included in the protection scope of the present disclosure.

[0063] In summary, in one or more embodiments of the present disclosure, a connected region acquisition method is provided. The connected region acquisition method can use limited tag values to mark the connected regions with larger areas in the target image. For example, if 8-bit tag values are used, the number of connected regions obtained by the connected region acquisition method is less than 255. Therefore, the connected region acquisition method described in the embodiments of the present disclosure has a high annotation efficiency and can reduce resource overhead. Thus, the present disclosure effectively overcomes various drawbacks in the prior art and has high industrial utilization value.

[0064] The above embodiments are only illustrative of the principles and effects of the present disclosure and are not used to limit the present disclosure. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present disclosure. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed by the present disclosure should still be covered by the claims of the present disclosure.

Claims

1. A method for obtaining a connected region, characterized in that, Including: Taking the target pixel points in the target image as the current pixel points, and configuring the labels of the current pixel points; If there are unused label values and the current pixel point is not the last target pixel point of the target image, taking the next target pixel point of the current pixel point as the new current pixel point, and configuring the label of the current pixel point; If there are no unused label values and the current pixel point is not the last target pixel point of the target image, configuring the label value of the target pixel point that meets the reconfiguration condition as unused, taking the next target pixel point of the current pixel point as the new current pixel point, and configuring the label of the current pixel point; And Obtaining connected regions according to the label values of the target pixel points in the target image, where configuring the label value of the target pixel point that meets the reconfiguration condition as unused includes: obtaining the scanned connected regions according to the label values of the target pixel points in the target image, and configuring the label value of the target pixel point that meets the reconfiguration condition as unused according to the scanned connected regions; where configuring the label value of the target pixel point that meets the reconfiguration condition as unused according to the scanned connected regions includes: obtaining the label value of the scanned connected region according to the label values of the target pixel points in the scanned connected region, if the label value of the target pixel point is different from the label value of its affiliated connected region, configuring the label value of the target pixel point as unused, and configuring the label of the target pixel point as the label value of its affiliated connected region, and the affiliated connected region of the target pixel point refers to the scanned connected region containing the target pixel point.

2. The method for obtaining a connected region according to claim 1, wherein Configuring the label of the current pixel point includes: If the neighborhood of the current pixel point contains configured pixel points, configuring the label of the current pixel point according to the label values of the configured pixel points in the neighborhood of the current pixel point; and If the neighborhood of the current pixel point does not contain configured pixel points, configuring the label of the current pixel point as an unused label value.

3. The method for obtaining a connected region according to claim 2, wherein Configuring the label of the current pixel point according to the label values of the configured pixel points in the neighborhood of the current pixel point includes: Obtaining the minimum label value of the configured pixel points in the neighborhood of the current pixel point; and Configuring the label of the current pixel point as the minimum label value.

4. The method for obtaining a connected region according to claim 1, wherein Configuring the label value of the target pixel point that meets the reconfiguration condition as unused according to the scanned connected regions further includes: If the current row and the row above it contain all the used label values, configuring the label values of the target pixel points in the scanned connected regions with an area smaller than the area threshold as unused, and configuring the labels of the target pixel points in these scanned connected regions as non-connected region label values; and If the current row and the row above it do not contain all the used label values, configuring the label values of the target pixel points in the scanned connected regions with an area smaller than the area threshold and not intersecting with the current row and the row above it as unused, and configuring the labels of the target pixel points in these scanned connected regions as non-connected region label values.

5. The method for obtaining a connected region according to claim 4, wherein Also including: Adjust the area threshold according to the label values included in the current row and the row above it and the area of the scanned connected region.

6. The method for obtaining a connected region according to claim 5, wherein Adjusting the area threshold according to the label values included in the current row and the row above it and the area of the scanned connected region includes: If the current row and the row above it include all used label values, adjust the area threshold to be greater than or equal to the minimum area of each of the scanned connected regions; and If the current row and the row above it do not include all used label values, adjust the area threshold to be greater than or equal to the minimum area of each of the scanned connected regions that do not intersect with the current row and the row above it.

7. The method for obtaining a connected region according to claim 1, wherein Obtaining the scanned connected region according to the label value of the target pixel point in the target image includes: Obtaining a first alternative connected region according to the label value of the target pixel point in the target image; and Merging the first alternative connected regions according to the connectivity relationship to obtain the scanned connected region.

8. The method for obtaining a connected region according to claim 1, wherein Obtaining the connected region according to the label value of the target pixel point in the target image includes: Obtaining a second alternative scanned region according to the label value of the target pixel point in the target image; and Filtering the second alternative scanned region to obtain the connected region.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program is executed by a processor to implement the connected region obtaining method according to any one of claims 1 to 8.

10. An electronic device, characterized in that, Including: A memory configured to store a computer program; And A processor configured to call the computer program to execute the connected region obtaining method according to any one of claims 1 to 8.

Images