CN112529923A - Control identification method and device - Google Patents
Control identification method and device Download PDFInfo
- Publication number
- CN112529923A CN112529923A CN202011477741.0A CN202011477741A CN112529923A CN 112529923 A CN112529923 A CN 112529923A CN 202011477741 A CN202011477741 A CN 202011477741A CN 112529923 A CN112529923 A CN 112529923A
- Authority
- CN
- China
- Prior art keywords
- determining
- pixel points
- area
- poster
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000012545 processing Methods 0.000 claims abstract description 24
- 238000004891 communication Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000012937 correction Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000003708 edge detection Methods 0.000 abstract description 10
- 238000001514 detection method Methods 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000013461 design Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000009792 diffusion process Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention provides a control identification method and device, and relates to the technical field of computers. The method comprises the steps of positioning the position of a target control in a poster area corresponding to a poster graph, and determining an expansion area of the target control according to a preset rule; determining a starting point in the expansion area, filling the poster area and the expansion area corresponding to the target control according to the starting point, and determining mask data; carrying out binarization processing on the mask data to generate a corresponding binarization image; intercepting a target image containing a vertex of the binary image; determining a plurality of pixel points corresponding to the fillet edge according to the target image; and determining the fillet radius corresponding to the fillet edge of the target control according to the plurality of pixel points. The method solves the technical problem that the control fillets and the radii corresponding to the poster graph cannot be identified or the identification error is large due to the fact that the fillets and the radii are determined in the edge detection or edge outline determination mode, and improves the fillet identification precision of the target control corresponding to the poster graph.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a control identification method and device.
Background
With the development of technology, the industry has started a research trend of directly converting design drawings into codes. Where control fillets are typically included in the design script, it becomes necessary to effectively identify fillet and fillet radii of the controls.
At present, in the prior art, Edge Detection (Edge-Detection) based on a Canny algorithm is usually adopted to obtain Edge information corresponding to a control to calculate a fillet radius of the control. In addition, there is also a round radius of the control obtained by determining the outline of the design and then fitting a circle. Canny edge detection, however, may introduce false edges, and its denoising may also introduce pixel errors. When a draft is designed to be a poster image, the content corresponding to the poster image also has a plurality of edges, and the edges of the poster image can be confused, wherein the outline of the poster image is determined and often faces the interference and noise brought by the poster image, so that the edge position of the poster cannot be determined. Therefore, the control round angle and the radius corresponding to the poster graph cannot be identified, or the identification error is large.
Disclosure of Invention
The embodiment of the invention aims to provide a control identification method and device, so as to improve the accuracy of identifying a control fillet corresponding to a poster graph. The specific technical scheme is as follows:
in a first aspect of the embodiments of the present invention, there is provided a control identification method, which is applied in a poster graph processing process, and the method includes:
positioning the position of a target control in a poster area corresponding to the poster graph, and determining an expansion area of the target control according to a preset rule, wherein the expansion area surrounds the poster area;
determining a starting point in the expansion area, filling the poster area and the expansion area according to the starting point, and determining mask data;
carrying out binarization processing on the mask data to generate a corresponding binarization image;
intercepting a target image containing the vertex of the binary image, wherein the target image at least comprises the rounded edge of the target control;
determining a plurality of pixel points corresponding to the rounded edge according to the target image;
and determining the fillet radius corresponding to the fillet edge of the target control according to the plurality of pixel points.
Optionally, the determining a starting point in the extension area, and filling the poster area and the extension area according to the starting point, and determining mask data includes:
taking the vertex of the expansion area as a starting point;
and determining interest pixel points of the starting point in the poster area and the expansion area, and determining mask data according to the interest pixel points.
Optionally, the determining of interest pixel points of the starting point in the poster area and the expansion area and determining mask data according to the interest pixel points includes:
determining adjacent pixel points of the reference point in the poster area and the expansion area by taking the starting point as the reference point, and judging whether the adjacent pixel points are interest pixel points of the reference point;
under the condition that the adjacent pixel points are the interest pixel points, continuously determining the interest pixel points of the reference points by taking the adjacent pixel points as the reference points;
and determining the interest pixel points as first mask values, and determining pixel points outside the interest pixel points in the poster area and the expansion area as second mask values to obtain the mask data.
Optionally, the determining whether the adjacent pixel point is the interest pixel point of the reference point includes:
determining the difference value between the pixel value of the reference point and the pixel value of the adjacent pixel point;
and if the difference value does not exceed a preset threshold value, determining the adjacent pixel points as the interest pixel points of the reference points.
Optionally, the determining, according to the target image, a plurality of pixel points corresponding to the rounded edge includes:
determining the position information of pixels except for interest pixels at the tail end of each line in the target image to form a first set;
acquiring position information of pixels, except for interest pixels, at the tail end of each column in the target image to form a second set;
and obtaining a plurality of interest pixel points corresponding to the rounded edge according to the intersection of the first set and the second set.
Optionally, the determining, according to the plurality of pixel points, a fillet radius corresponding to a fillet edge of the target control includes:
determining the number of a plurality of interest pixel points corresponding to the rounded edge;
if the number of the interest pixel points is not larger than a preset limit value, matching a fillet radius corresponding to the fillet edge of the target control through a mapping table;
and if the number of the pixel points is larger than the limit value, determining the fillet radius corresponding to the fillet edge of the target control according to a least square method.
Optionally, the method further includes:
and correcting the fillet radius, and updating the fillet radius after correction.
Optionally, the method further includes:
determining the number of pixel points outside the interest pixel points in the poster area and the expansion area in each row and each column according to the binary image;
and if the number of the pixel points except the interest pixel point is less than the preset number, replacing the pixel values of all the pixel points corresponding to the row or the column with the pixel values corresponding to the interest pixel point, and updating the binary image.
Optionally, the intercepting a target image including a vertex of the binarized image includes:
detecting the number of pixel points corresponding to rows and columns of the binary image, and determining the shape information of the binary image;
determining a truncated area containing a vertex in the binary image according to the shape information;
and intercepting the binary image according to the intercepted area to obtain a corresponding target image.
In a second aspect of the present invention, there is also provided a control identifying apparatus, including:
the control positioning module is used for positioning the position of a target control in a poster area corresponding to the poster graph and determining an expansion area of the target control according to a preset rule, wherein the expansion area surrounds the poster area;
the mask determining module is used for determining a starting point in the expansion area, filling the poster area and the expansion area according to the starting point and determining mask data;
the binarization processing module is used for carrying out binarization processing on the mask data to generate a corresponding binarization image;
the image intercepting module is used for intercepting a target image containing the vertex of the binaryzation image, wherein the target image at least comprises the rounded edge of the target control;
the pixel point determining module is used for determining a plurality of pixel points corresponding to the fillet edge according to the target image;
and the data calculation module is used for determining the fillet radius corresponding to the fillet edge of the target control according to the plurality of pixel points.
Optionally, the mask determining module includes:
a starting point determining submodule for taking the vertex of the expansion area as a starting point;
and the mask data generation submodule is used for determining interest pixel points of the starting point in the poster area and the expansion area and determining mask data according to the interest pixel points.
Optionally, the mask data generation sub-module includes:
an interest pixel point determining unit, configured to determine, in the poster area and the extension area, an adjacent pixel point of the reference point by using the starting point as the reference point, and determine whether the adjacent pixel point is an interest pixel point of the reference point;
under the condition that the adjacent pixel points are the interest pixel points, continuously determining the interest pixel points of the reference points by taking the adjacent pixel points as the reference points;
and the mask data generating unit is used for determining the interest pixel points as first mask values, and determining pixel points except the interest pixel points in the poster area and the expansion area as second mask values to obtain the mask data.
Optionally, the interest pixel point determining unit is further configured to:
determining the difference value between the pixel value of the reference point and the pixel value of the adjacent pixel point;
and if the difference value does not exceed a preset threshold value, determining the adjacent pixel points as the interest pixel points of the reference points.
Optionally, the pixel point determining module includes:
the first position submodule is used for determining the position information of pixel points, except for interest pixel points, of each line at the tail end in the target image to form a first set;
the second position submodule is used for acquiring position information of pixels, except for interest pixels, at the tail end of each row in the target image to form a second set;
and the pixel point obtaining submodule is used for obtaining a plurality of interest pixel points corresponding to the fillet edge according to the intersection of the first set and the second set.
Optionally, the data calculation module includes:
the number calculation module is used for determining the number of a plurality of interest pixel points corresponding to the rounded edge;
the radius calculation module is used for matching the fillet radius corresponding to the fillet edge of the target control through a mapping table if the number of the interest pixel points is not greater than a preset limit value;
and if the number of the pixel points is larger than the limit value, determining the fillet radius corresponding to the fillet edge of the target control according to a least square method.
Optionally, the apparatus further comprises:
and the radius correction module is used for correcting the fillet radius and updating the fillet radius after correction.
Optionally, the apparatus further comprises:
the first calculation module is used for determining the number of pixel points outside the interest pixel points in the poster area and the expansion area in each row and each column according to the binary image;
and the second calculation module is used for replacing the pixel values of all the pixel points corresponding to the row or the column with the pixel values corresponding to the interest pixel points and updating the binary image if the number of the pixel points except the interest pixel points is less than the preset number.
Optionally, the image capturing module includes:
the image detection submodule is used for detecting the number of pixel points corresponding to the rows and the columns of the binary image and determining the shape information of the binary image;
the intercepted area determining submodule is used for determining an intercepted area containing a vertex in the binary image according to the shape information;
and the target image acquisition submodule is used for intercepting the binary image according to the intercepted area to obtain a corresponding target image.
In yet another aspect of the present invention, there is also provided a computer-readable storage medium having stored therein instructions, which when run on a computer, cause the computer to execute any of the above-described control identification methods.
In yet another aspect of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform any of the control identification methods described above.
According to the control identification method and device provided by the invention, the expansion area is added outside the poster area corresponding to the target control by positioning the target control, an initial point can be selected in the expansion area by utilizing the high color consistency of the expansion area, and the poster area and the expansion area are filled according to the initial point to form mask data representing the edge structure characteristics corresponding to the target control. Subsequently, the mask data are converted into a binary image, the edge contour of the target control can be highlighted, the target image comprising the rounded corner edge of the target control is intercepted at the vertex of the binary image, the target image is utilized, a plurality of pixel points corresponding to the rounded corner edge can be determined by detecting the pixel point coordinates and the pixel values in the target image, and then the rounded corner radius corresponding to the rounded corner edge is determined according to the relevant information of the pixel points. The method and the device can solve the technical problem that the control fillet and the radius corresponding to the poster graph cannot be identified or the identification error is large due to the fact that the fillet edge and the radius are determined in an edge detection or edge outline determination mode, and therefore the accuracy of identifying the control fillet corresponding to the poster graph can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.
Fig. 1 is a flowchart illustrating steps of a control identification method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of another method for identifying a control according to an embodiment of the present invention;
FIG. 3 is a flowchart of method steps for determining mask data according to an embodiment of the present invention;
FIG. 4 is a flowchart of method steps for determining a fillet radius provided in an embodiment of the present invention;
fig. 5 is a block diagram of a control identification apparatus provided in an embodiment of the present invention;
fig. 6 is an architecture diagram of an electronic device provided in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.
Referring to fig. 1, a control identification method is shown, and is applied to poster graph processing, and the method may include:
Wherein the expansion area forms an enclosure for the poster area.
In the embodiment of the invention, the design of the vertex of the poster graph as the round corner is already a standard match, so the target control can be understood as an operable unit which makes the vertex of the poster graph form the round corner when the poster graph is designed to be drawn. For example, the target control may be a rectangular box with rounded corners, etc. And in the process of drawing the poster graph, a frame corresponding to the poster graph can be formed by inserting the target control. The area contained by the target control corresponding to the poster graph can be determined as the poster area. In a subsequent poster graph processing procedure, an expanded area can be determined by locating the position of a target control, thereby forming an enclosure for the poster area.
Specifically, the characteristic that the background color of the poster image is stable and consistent can be utilized, and the background area of the poster image is selected to assist in round angle identification of the target control. For example, after the target control is located at the position according to an edge detection method and the like, an expansion area may be added outside the poster area corresponding to the target control according to a preset rule, where the expansion area surrounds the poster area.
In an example, the determining, according to the preset rule, the extended area of the target control may specifically include: after the edge position corresponding to the target control is detected, N pixel points, for example, 5 pixel points, may be respectively expanded outwards by the edge position, so as to determine the extended area corresponding to the target control.
Specifically, because the background color consistency of the expansion area is high, the target control is prevented from being directly identified by edge detection or contour detection on the poster image, and the identification precision of the fillet corresponding to the target control is favorably improved.
In the embodiment of the invention, the position information and the pixel value corresponding to any pixel point in the poster area and the expansion area corresponding to the target control can be acquired. Because the background of the poster image is all pure color, the consistency of the color in the expansion area is high, and a pixel point can be selected in the expansion area as a starting point. And detecting pixel points in the control area and the expansion area by adopting a preset detection algorithm according to the starting point, so that the edge corresponding to the target control is drawn through the detected pixel points. For example, the preset detection algorithm may be understood as determining a pixel point with the same pixel value as the initial point based on the diffusion of the initial point to the adjacent pixel point.
In addition, in order to be able to extract the edge structure feature of the poster area, a mask image of the same specification as that of the poster area and the extension area may be generated. Therefore, according to the position information of the detected pixel points, the corresponding pixel points in the mask image can be sequentially filled with the first mask value, and the pixel points except the detected pixel points are filled with the second mask value. Specifically, the first mask value may be 1, and the second mask value may be 0. Therefore, a data set composed of the first mask value and the second mask value may be determined as the mask data, and according to the mask data, an edge structure feature corresponding to the target control may be determined in the mask image.
And 103, performing binarization processing on the mask data to generate a corresponding binarized image.
In the embodiment of the invention, the binarization processing refers to setting the pixel value corresponding to the pixel point on the image to be 0 or 255, and the image after the binarization processing can show obvious black and white effect, so that the mask image can be converted into the binarization image by performing the binarization processing on the mask data, thereby highlighting the edge contour of the target control. For example, the pixel value of the pixel corresponding to the first mask value may be set to a first gray scale value, e.g., 0, and the pixel value of the pixel corresponding to the second mask value may be set to a second gray scale value, e.g., 255.
And 104, intercepting a target image containing the vertex of the binarized image, wherein the target image at least comprises the rounded edge of the target control.
In the embodiment of the invention, the edge contour of the target control can be clearly highlighted by the binary image, and in order to further identify the fillet corresponding to the target control, the image including the fillet edge of the target control needs to be intercepted. Illustratively, according to the shape information of the binarized image, the region containing the vertex of the binarized image can be selectively intercepted, and the corresponding intercepted image only needs to include the rounded edge corresponding to the target control. Therefore, the captured image is used as a target image to facilitate subsequent correlation operations.
And 105, determining a plurality of pixel points corresponding to the rounded edge according to the target image.
In the embodiment of the present invention, the target image includes a rounded edge corresponding to the target control, and may also include a linear edge corresponding to the target control. The chromatic aberration of the target image is clear, so that the pixel value of the pixel point coordinate corresponding to the target image can be detected according to the target image, and a plurality of pixel points corresponding to the edge of the target control are determined through the pixel value. The method comprises the steps of obtaining a target image, obtaining coordinates of a plurality of pixel points corresponding to the edge of a target control, and determining a plurality of pixel points corresponding to the edge of a fillet.
In one example, when the target image is captured from the top left corner of the binarized image, the coordinates of the pixel points with the first pixel value being the second gray value may be determined by scanning the rows of the target image from left to right, so as to form a first set; and scanning the columns of the target image from top to bottom, determining the coordinates of the pixel points of which the first pixel values are the second gray values to form a second set, taking the intersection of the first set and the second set, and determining a plurality of pixel points corresponding to the fillet edge.
In another example, when the target image is captured from the upper right corner of the binarized image, the coordinates of the pixel point with the last pixel value being the second gray scale value are determined by scanning the rows of the target image from left to right, and a first set is formed; and scanning the columns of the target image from top to bottom, determining the coordinates of the pixel points of which the first pixel values are the second gray values to form a second set, taking the intersection of the first set and the second set, and determining a plurality of pixel points corresponding to the fillet edge.
In another example, when the target image is captured from the lower left corner of the binarized image, the coordinates of the pixel points of which the first pixel values are the second gray values are determined by scanning the rows of the target image from left to right, so as to form a first set; and scanning the columns of the target image from top to bottom, determining the coordinates of the pixel point with the last pixel value as the second gray value to form a second set, taking the intersection of the first set and the second set, and determining a plurality of pixel points corresponding to the fillet edge.
In another example, when the target image is captured from the lower right corner of the binarized image, the coordinates of the pixel point with the last pixel value being the second gray scale value are determined by scanning the rows of the target image from left to right, and a first set is formed; and scanning the columns of the target image from top to bottom, determining the coordinates of the pixel point with the last pixel value as the second gray value to form a second set, taking the intersection of the first set and the second set, and determining a plurality of pixel points corresponding to the fillet edge.
And 106, determining the fillet radius corresponding to the fillet edge of the target control according to the plurality of pixel points.
According to the embodiment of the invention, the fillet radius corresponding to the fillet edge of the target control can be determined according to the obtained coordinates of the plurality of pixel points on the fillet edge. Illustratively, the fillet radius is derived by fitting a circle to the coordinates of the plurality of pixel points. In another example, when the number of the plurality of pixel points is small, the fillet radius may be determined by directly querying a preset mapping table.
In summary, by positioning the target control, an extended area is added outside the poster area corresponding to the target control, and by using the high color consistency of the extended area, an initial point can be selected in the extended area, and the poster area and the extended area are filled according to the initial point, so as to form mask data representing edge structure features corresponding to the target control. Subsequently, the mask data are converted into a binary image, the edge contour of the target control can be highlighted, the target image comprising the rounded corner edge of the target control is intercepted at the vertex of the binary image, the target image is utilized, a plurality of pixel points corresponding to the rounded corner edge can be determined by detecting the pixel point coordinates and the pixel values in the target image, and then the rounded corner radius corresponding to the rounded corner edge is determined according to the relevant information of the pixel points. The method and the device can solve the technical problem that the control fillets and the radii corresponding to the poster graph cannot be identified or the identification error is large due to the fact that the fillets and the radii are determined in the edge detection or edge outline determination mode, and therefore the fillet identification precision of the target control corresponding to the poster graph can be improved.
Referring to fig. 2, another control identification method is shown, which is applied to poster graph processing, and the method may include:
Wherein the expansion area forms an enclosure for the poster area.
In the embodiment of the present invention, reference may be made to the description of step 101 for the description of step 201.
Determining a starting point in the expansion area, filling the poster area and the expansion area according to the starting point, and determining mask data; the method comprises the following steps: step 202-step 203.
And step 202, taking the vertex of the expansion area as a starting point.
In the embodiment of the invention, the position information and the pixel value corresponding to any pixel point in the poster area and the expansion area corresponding to the target control can be acquired. Because the color consistency in the expansion area is higher, a pixel point can be selected in the expansion area as a starting point. For example, to facilitate performing the operation, a vertex of the extended region may be used as a starting point, for example, a vertex in the upper left corner of the extended region is determined as the starting point.
According to the starting point, the pixels in the control area and the expansion area can be detected according to a preset detection algorithm, and the detected pixels are used as interest pixels of the starting point, so that the edge corresponding to the target control is drawn through the interest pixels. For example, the preset detection algorithm may be understood as determining a plurality of detected pixel points having the same pixel value as the initial point as the interest pixel points based on the diffusion of the initial point to the adjacent pixel points.
In addition, in order to be able to extract the edge structure feature of the poster area, a mask image of the same specification as that of the poster area and the extension area may be generated. Therefore, according to the position information of the interest pixel points, the corresponding pixel points in the mask image can be sequentially filled with the first mask value, and the pixel points except the interest pixel points are filled with the second mask value. Specifically, the first mask value may be 1, and the second mask value may be 0. Therefore, a data set composed of the first mask value and the second mask value may be determined as the mask data, and according to the mask data, an edge structure feature corresponding to the target control may be determined in the mask image.
An alternative embodiment, referring to fig. 3, step 203 may comprise the following sub-steps: substeps S31-substep S37.
And a substep S31, using the starting point as a reference point.
Substep S32, determining adjacent pixel points of the reference point in the poster area and the extension area.
And a substep S33 of judging whether the adjacent pixel point is the interest pixel point of the reference point.
Wherein, the judging whether the adjacent pixel point is the interest pixel point of the reference point includes:
and determining the difference value between the pixel value of the reference point and the pixel value of the adjacent pixel point.
And if the difference value does not exceed a preset threshold value, determining the adjacent pixel points as the interest pixel points of the reference points.
In the embodiment of the invention, the initial point is used as the reference point, and the adjacent pixel points of the reference point are determined in the poster area and the expansion area. Illustratively, the coordinate information corresponding to the reference point is used to find the adjacent pixel point of the reference point. And then judging whether the adjacent pixel points are the interest pixel points of the reference points, wherein the interest pixel points can be understood as pixel points with the same pixel values as the reference points.
For example, the adjacent pixel point of the reference point can be determined through the coordinate information corresponding to the reference point, and then whether the adjacent pixel point is an interest pixel point of the reference point is further determined. Meanwhile, in order to optimize the robustness performance, a difference threshold value is preset when an interested pixel point is determined. Such as 20, etc.
Therefore, after the adjacent pixel point is determined, the pixel value of the adjacent pixel point and the pixel value of the reference point are obtained, so that the difference value between the pixel value of the reference point and the pixel value of the adjacent pixel point can be determined. And under the condition that the difference value does not exceed a preset threshold value, determining that the pixel value of the adjacent pixel point is the same as the pixel value of the reference point. Thereby, the adjacent pixel point can be determined as the interest pixel point.
And executing a substep S34 if the adjacent pixel point is the interest pixel point, otherwise executing a substep S36.
And a substep S34, using the adjacent pixel point as a reference point.
After the sub-step S34 is completed, the sub-steps S35 and S32 may be performed simultaneously, so as to continue to determine the interested pixel points of the reference point.
And a substep S35, determining the interest pixel point as a first mask value.
And a substep S36, determining pixel points outside the interest pixel points in the poster area and the expansion area as second mask values.
And a substep S37, obtaining the mask data according to the first mask value and the second mask value.
Optionally, the method steps from substep S31 to substep S37 may be used as the predetermined detection algorithm.
In the embodiment of the present invention, after determining the neighboring pixel point as the interest pixel point, the neighboring pixel point may be used as a new reference point, and the substep S32 is executed to continue to determine the interest pixel point corresponding to the reference point.
In addition, in order to be able to extract the edge structure feature of the poster area, a mask image of the same specification as that of the poster area and the extension area may be generated. Therefore, according to the position information of the interest pixel points, the corresponding pixel points in the mask image can be filled by adopting the first mask value.
After determining that the adjacent pixel points are not the interest pixel points, filling the pixel points except the interest pixel points in the corresponding poster area and the expansion area with a second mask value, and determining a data set generated according to the first mask value and the second mask value as mask data. For example, the first mask value may be 1, and the second mask value may be 0, so that the edge structure feature corresponding to the target control is determined in the mask image through the mask data.
And 204, performing binarization processing on the mask data to generate a corresponding binarized image.
In the embodiment of the invention, the binarization processing refers to setting the pixel value corresponding to the pixel point on the image to be 0 or 255, and the image after the binarization processing can show obvious black and white effect, so that the mask image can be converted into the binarization image by performing the binarization processing on the mask data, thereby highlighting the edge contour of the target control. For example, the pixel value of the pixel corresponding to the first mask value may be set to a first gray scale value, e.g., 0, and the pixel value of the pixel corresponding to the second mask value may be set to a second gray scale value, e.g., 255.
And step 205, determining the number of pixel points outside the interest pixel points in the poster area and the expansion area in each row and each column according to the binary image.
And step 206, if the number of the pixel points except the interest pixel point is less than the preset number, replacing the pixel values of all the pixel points corresponding to the row or the column with the pixel values corresponding to the interest pixel point, and updating the binary image.
In the embodiment of the invention, whether noise pollution exists in the corresponding row or column can be judged by determining the number of the pixel points except the interest pixel points in the poster area and the expansion area in each row and each column. For example, the number of pixels having the second gray value in each row or each column may be counted according to the projections of the binarized image in the vertical direction and the horizontal direction. If the number of the pixels of which the pixel value of a certain row or a certain column is the second gray scale value is smaller than the preset number set according to the total pixels of the row or the column, for example, the preset number is 1/4 of the number of the total pixels of the row or the column, it can be determined that the row or the column has noise pollution, and then the pixel values of the corresponding row or the column are all charged to the first gray scale value, so as to eliminate the influence of the noise pollution and improve the anti-interference performance of the invention.
And step 207, intercepting a target image containing the vertex of the binarized image, wherein the target image at least comprises the rounded edge of the target control.
In an alternative embodiment, step 207 may further include the steps of:
and detecting the number of pixel points corresponding to the rows and the columns of the binary image, and determining the shape information of the binary image.
And determining a truncated area containing a vertex in the binary image according to the shape information.
And intercepting the binary image according to the intercepted area to obtain a corresponding target image.
In the embodiment of the invention, the edge contour of the target control can be clearly highlighted by the binary image, and in order to further identify the fillet corresponding to the target control, the image including the fillet edge of the target control needs to be intercepted. Illustratively, according to the shape information of the binarized image, the region containing the vertex of the binarized image can be selectively intercepted, and the corresponding intercepted image only needs to include the rounded edge corresponding to the target control.
Illustratively, the shape information of the binarized image may be determined by detecting the number of row pixels and the number of column pixels corresponding to the binarized image, wherein the shape information may include a square and a rectangle. According to the shape information, a cut-out area of the target image on the binary image can be determined. For example, when the binarized image is square, an image of an 1/4 image area including the vertex of the binarized image in the lower right in the binarized image may be clipped as the target image. When the binarized image is rectangular, an image of an 1/16 image area including the apex of the binarized image in the lower right of the binarized image may be clipped as a target image. The target image may be a square.
And 208, determining a plurality of pixel points corresponding to the rounded edge according to the target image.
In an alternative embodiment, step 208 may further include the steps of:
and determining the position information of the pixels except the interest pixels at the tail end of each line in the target image to form a first set.
And acquiring the position information of pixels except the interest pixel at the tail end of each column in the target image to form a second set.
And obtaining a plurality of interest pixel points corresponding to the rounded edge according to the intersection of the first set and the second set.
In the embodiment of the present invention, the target image includes a rounded edge corresponding to the target control, and may also include a linear edge corresponding to the target control. The chromatic aberration of the target image is clear, so that the pixel value of the pixel point coordinate corresponding to the target image can be detected according to the target image, and a plurality of pixel points corresponding to the edge of the target control are determined through the pixel value. The method comprises the steps of obtaining a target image, obtaining coordinates of a plurality of pixel points corresponding to the edge of a target control, and determining a plurality of pixel points corresponding to the edge of a fillet.
In order to facilitate the execution of the steps, it can be determined that the intercepted target image is intercepted from the lower right corner of the binary image every time. Therefore, the coordinates of the pixel points at the tail end except the interest pixel point can be determined by scanning the rows of the target image from left to right to form a first set; the coordinates of the pixel points at the tail end except the interest pixel points are determined by scanning the columns of the target image from top to bottom to form a second set, and the intersection of the first set and the second set is taken, so that the coordinates of a plurality of pixel points corresponding to the fillet edge can be determined.
And 209, determining the fillet radius corresponding to the fillet edge of the target control according to the plurality of pixel points.
An alternative embodiment, referring to fig. 4, step 209 may further include the following steps: substeps S41-substep S44.
And a substep S41 of determining the number of a plurality of interest pixel points corresponding to the rounded edge.
And a substep S42 of judging whether the number of the interest pixel points is larger than a preset limit value.
If the number of the interest pixels is not greater than the predetermined limit value, the sub-step S43 is executed.
If the number of the pixel points is larger than the limit value, the sub-step S44 is executed.
And a substep S43, matching the fillet radius corresponding to the fillet edge of the target control through a mapping table.
And a substep S44, determining the fillet radius corresponding to the fillet edge of the target control according to a least square method.
In the embodiment of the invention, the number of the interest pixel points can be determined according to the plurality of interest pixel points corresponding to the obtained fillet edge, and the number of the interest pixel points can be judged firstly for facilitating the execution of the steps and simplifying the operation. Illustratively, when the number of the interest pixel points is greater than a preset limit value, for example, the number of the interest pixel points is greater than 5, the corresponding fillet radius may be obtained by fitting according to the coordinates of the plurality of interest pixel points by using a method such as a least square method. When the number of the interested pixel points is not larger than the preset limit value, because the number of the pixel points is less, a mapping table with the corresponding determination of the fillet radius can be formed in advance according to the coordinates of a plurality of pixel points. Therefore, under the condition that the interest pixel points are few, the fillet radius corresponding to the fillet edge of the target control can be matched quickly by inquiring the mapping table.
In an alternative embodiment, the method further comprises:
step 210, correcting the fillet radius, and updating the fillet radius after correction.
In the embodiment of the invention, in order to reduce the calculation error of the fillet radius of the fillet edge of the target control, for example, the fillet radius is larger, and the calculated fillet radius causes the edge of the target control to be semicircular. The width that poster area corresponds can be determined through the pixel number of the row and the column of detecting poster area, according to the width, detects fillet radius.
The fillet radius detection according to the length and the width may include the following steps: substeps S45-substep S46.
And a substep S45 of determining whether the fillet radius is close to half the width.
If yes, go to substep S46; if not, go to substep S47.
And a substep S46, taking the width to be a small half as the radius of the fillet.
And a substep S47 of keeping the radius of the fillet consistent with the radius of the fillet before the correction.
Specifically, when the poster area is the square, its width that corresponds is the length of side, when the poster area is the rectangle, its width that corresponds is the length of a shorter limit in the rectangle, if the difference of fillet radius and half of width is less than the pixel threshold value, for example, the pixel threshold value is 4 pixels, can judge that the fillet radius is close to half of width this moment, then in order to avoid causing the edge of target control to present semi-circular, can reduce the width according to actual conditions, take half of its width again to determine for the fillet radius, revise and update fillet radius's value. Otherwise, the updated fillet radius is consistent with the fillet radius before correction.
In summary, by positioning the target control, an extended area is added outside the poster area corresponding to the target control, and by using the high color consistency of the extended area, an initial point can be selected in the extended area, and the poster area and the extended area are filled according to the initial point, so as to form mask data representing edge structure features corresponding to the target control. Subsequently, the mask data are converted into a binary image, the edge contour of the target control can be highlighted, the target image comprising the rounded corner edge of the target control is intercepted at the vertex of the binary image, the target image is utilized, a plurality of pixel points corresponding to the rounded corner edge can be determined by detecting the pixel point coordinates and the pixel values in the target image, and then the rounded corner radius corresponding to the rounded corner edge is determined according to the relevant information of the pixel points. The method and the device can solve the technical problem that the control fillets and the radii corresponding to the poster graph cannot be identified or the identification error is large due to the fact that the fillets and the radii are determined in the edge detection or edge outline determination mode, and therefore the method and the device can improve the fillet identification accuracy of the target control corresponding to the poster graph and have good universality.
Referring to fig. 5, there is shown a control recognition apparatus, which may include:
and a control positioning module 501, configured to position a position of a target control in a poster area corresponding to the poster diagram, and determine an extended area of the target control according to a preset rule, where the extended area surrounds the poster area.
A mask determining module 502, configured to determine a starting point in the extension area, and fill the poster area and the extension area according to the starting point to determine mask data.
A binarization processing module 503, configured to perform binarization processing on the mask data to generate a corresponding binarized image.
An image clipping module 504, configured to clip a target image including vertices of the binarized image, where the target image at least includes rounded edges of the target control.
A pixel point determining module 505, configured to determine, according to the target image, a plurality of pixel points corresponding to the rounded edge.
And a data calculating module 506, configured to determine, according to the plurality of pixel points, a fillet radius corresponding to the fillet edge of the target control.
In an alternative embodiment, the mask determining module may include:
and the starting point determining submodule is used for taking the vertex of the expansion area as a starting point.
And the mask data generation submodule is used for determining interest pixel points of the starting point in the poster area and the expansion area and determining mask data according to the interest pixel points.
In an alternative embodiment, the mask data generation sub-module may include:
and the interest pixel point determining unit is used for determining adjacent pixel points of the reference point in the poster area and the expansion area by taking the starting point as the reference point, and judging whether the adjacent pixel points are the interest pixel points of the reference point.
And under the condition that the adjacent pixel points are the interest pixel points, continuously determining the interest pixel points of the reference points by taking the adjacent pixel points as the reference points.
And the mask data generating unit is used for determining the interest pixel points as first mask values, and determining pixel points except the interest pixel points in the poster area and the expansion area as second mask values to obtain the mask data.
In an alternative embodiment, the interest pixel point determining unit is further configured to:
and determining the difference value between the pixel value of the reference point and the pixel value of the adjacent pixel point.
And if the difference value does not exceed a preset threshold value, determining the adjacent pixel points as the interest pixel points of the reference points.
In an alternative embodiment, the pixel point determining module may include:
and the first position submodule is used for determining the position information of the pixel points, except the interest pixel point, of each line at the tail end in the target image to form a first set.
And the second position submodule is used for acquiring the position information of pixels, except the interest pixel, at the tail end of each row in the target image to form a second set.
And the pixel point obtaining submodule is used for obtaining a plurality of interest pixel points corresponding to the fillet edge according to the intersection of the first set and the second set.
In an alternative embodiment, the data calculation module may include:
and the number calculation module is used for determining the number of the interest pixel points corresponding to the rounded edge.
And the radius calculation module is used for matching the fillet radius corresponding to the fillet edge of the target control through the mapping table if the number of the interest pixel points is not greater than a preset limit value.
And if the number of the pixel points is larger than the limit value, determining the fillet radius corresponding to the fillet edge of the target control according to a least square method.
In an alternative embodiment, the apparatus may further comprise:
and the radius correction module is used for correcting the fillet radius and updating the fillet radius after correction.
In an alternative embodiment, the apparatus may further comprise:
and the first calculation module is used for determining the number of pixel points outside the interest pixel points in the poster area and the expansion area in each row and each column according to the binary image.
And the second calculation module is used for replacing the pixel values of all the pixel points corresponding to the row or the column with the pixel values corresponding to the interest pixel points and updating the binary image if the number of the pixel points except the interest pixel points is less than the preset number.
In an alternative embodiment, the image capture module may include:
and the image detection submodule is used for detecting the number of pixel points corresponding to the rows and the columns of the binary image and determining the shape information of the binary image.
And the intercepted area determining submodule is used for determining the intercepted area containing the vertex in the binary image according to the shape information.
And the target image acquisition submodule is used for intercepting the binary image according to the intercepted area to obtain a corresponding target image.
In summary, by positioning the target control, an extended area is added outside the poster area corresponding to the target control, and by using the high color consistency of the extended area, an initial point can be selected in the extended area, and the poster area and the extended area are filled according to the initial point, so as to form mask data representing edge structure features corresponding to the target control. Subsequently, the mask data are converted into a binary image, the edge contour of the target control can be highlighted, the target image comprising the rounded corner edge of the target control is intercepted at the vertex of the binary image, the target image is utilized, a plurality of pixel points corresponding to the rounded corner edge can be determined by detecting the pixel point coordinates and the pixel values in the target image, and then the rounded corner radius corresponding to the rounded corner edge is determined according to the relevant information of the pixel points. The method and the device can solve the technical problem that the control fillet and the radius corresponding to the poster graph cannot be identified or the identification error is large due to the fact that the fillet edge and the radius are determined in an edge detection or edge outline determination mode, and therefore the method and the device can improve the fillet identification accuracy of the target control corresponding to the poster graph and have good universality.
An embodiment of the present invention further provides an electronic device, as shown in fig. 6, including a processor 601, a communication interface 602, a memory 603, and a communication bus 604, where the processor 601, the communication interface 602, and the memory 603 complete mutual communication through the communication bus 604,
a memory 603 for storing a computer program;
the processor 601 is configured to implement the following steps when executing the program stored in the memory 603:
and positioning the position of a target control in a poster area corresponding to the poster graph, and determining an expansion area of the target control according to a preset rule, wherein the expansion area surrounds the poster area.
And determining a starting point in the expansion area, filling the poster area and the expansion area according to the starting point, and determining mask data.
And carrying out binarization processing on the mask data to generate a corresponding binarization image.
And intercepting a target image containing the vertex of the binary image, wherein the target image at least comprises the rounded edge of the target control.
And determining a plurality of pixel points corresponding to the rounded edge according to the target image.
And determining the fillet radius corresponding to the fillet edge of the target control according to the plurality of pixel points.
The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the terminal and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In another embodiment of the present invention, a computer-readable storage medium is further provided, which has instructions stored therein, and when the computer-readable storage medium runs on a computer, the computer is caused to execute the control identification method in any one of the above embodiments.
In yet another embodiment, a computer program product containing instructions is provided, which when run on a computer causes the computer to perform the control identification method of any of the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (12)
1. A control identification method is applied to poster graph processing, and comprises the following steps:
positioning the position of a target control in a poster area corresponding to the poster graph, and determining an expansion area of the target control according to a preset rule, wherein the expansion area surrounds the poster area;
determining a starting point in the expansion area, filling the poster area and the expansion area according to the starting point, and determining mask data;
carrying out binarization processing on the mask data to generate a corresponding binarization image;
intercepting a target image containing the vertex of the binary image, wherein the target image at least comprises the rounded edge of the target control;
determining a plurality of pixel points corresponding to the rounded edge according to the target image;
and determining the fillet radius corresponding to the fillet edge of the target control according to the plurality of pixel points.
2. The method of claim 1, wherein determining a starting point in the expanded area and populating the poster area and the expanded area in accordance with the starting point, determining mask data, comprises:
taking the vertex of the expansion area as a starting point;
and determining interest pixel points of the starting point in the poster area and the expansion area, and determining mask data according to the interest pixel points.
3. The method of claim 2, wherein determining pixel points of interest of the starting point in the poster area and the expansion area and determining mask data from the pixel points of interest comprises:
determining adjacent pixel points of the reference point in the poster area and the expansion area by taking the starting point as the reference point, and judging whether the adjacent pixel points are interest pixel points of the reference point;
under the condition that the adjacent pixel points are the interest pixel points, continuously determining the interest pixel points of the reference points by taking the adjacent pixel points as the reference points;
and determining the interest pixel points as first mask values, and determining pixel points outside the interest pixel points in the poster area and the expansion area as second mask values to obtain the mask data.
4. The method of claim 3, wherein the determining whether the neighboring pixel is the pixel of interest of the reference point comprises:
determining the difference value between the pixel value of the reference point and the pixel value of the adjacent pixel point;
and if the difference value does not exceed a preset threshold value, determining the adjacent pixel points as the interest pixel points of the reference points.
5. The method of claim 2, wherein the determining a plurality of pixel points corresponding to the rounded edge according to the target image comprises:
determining the position information of pixels except for interest pixels at the tail end of each line in the target image to form a first set;
acquiring position information of pixels, except for interest pixels, at the tail end of each column in the target image to form a second set;
and obtaining a plurality of interest pixel points corresponding to the rounded edge according to the intersection of the first set and the second set.
6. The method of claim 5, wherein the determining, according to the plurality of pixel points, a fillet radius corresponding to a fillet edge of the target control comprises:
determining the number of a plurality of interest pixel points corresponding to the rounded edge;
if the number of the interest pixel points is not larger than a preset limit value, matching a fillet radius corresponding to the fillet edge of the target control through a mapping table;
and if the number of the pixel points is larger than the limit value, determining the fillet radius corresponding to the fillet edge of the target control according to a least square method.
7. The method of claim 6, further comprising:
and correcting the fillet radius, and updating the fillet radius after correction.
8. The method of claim 1, further comprising:
determining the number of pixel points outside the interest pixel points in the poster area and the expansion area in each row and each column according to the binary image;
and if the number of the pixel points except the interest pixel point is less than the preset number, replacing the pixel values of all the pixel points corresponding to the row or the column with the pixel values corresponding to the interest pixel point, and updating the binary image.
9. The method according to claim 1, wherein said intercepting a target image containing vertices of said binarized image comprises:
detecting the number of pixel points corresponding to rows and columns of the binary image, and determining the shape information of the binary image;
determining a truncated area containing a vertex in the binary image according to the shape information;
and intercepting the binary image according to the intercepted area to obtain a corresponding target image.
10. An apparatus for identifying controls, the apparatus comprising:
the control positioning module is used for positioning the position of a target control in a poster area corresponding to the poster graph and determining an expansion area of the target control according to a preset rule, wherein the expansion area surrounds the poster area;
the mask determining module is used for determining a starting point in the expansion area, filling the poster area and the expansion area according to the starting point and determining mask data;
the binarization processing module is used for carrying out binarization processing on the mask data to generate a corresponding binarization image;
the image intercepting module is used for intercepting a target image containing the vertex of the binaryzation image, wherein the target image at least comprises the rounded edge of the target control;
the pixel point determining module is used for determining a plurality of pixel points corresponding to the fillet edge according to the target image;
and the data calculation module is used for determining the fillet radius corresponding to the fillet edge of the target control according to the plurality of pixel points.
11. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1-9 when executing a program stored in the memory.
12. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011477741.0A CN112529923A (en) | 2020-12-15 | 2020-12-15 | Control identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011477741.0A CN112529923A (en) | 2020-12-15 | 2020-12-15 | Control identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112529923A true CN112529923A (en) | 2021-03-19 |
Family
ID=75000066
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011477741.0A Pending CN112529923A (en) | 2020-12-15 | 2020-12-15 | Control identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112529923A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114331951A (en) * | 2021-09-30 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Image detection method, image detection device, computer, readable storage medium, and program product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004272885A (en) * | 2003-02-21 | 2004-09-30 | Shinko Electric Ind Co Ltd | Device and method for edge extraction |
| CN108038891A (en) * | 2017-12-28 | 2018-05-15 | 福建中金在线信息科技有限公司 | A kind of graphic processing method and device |
| CN108765364A (en) * | 2018-04-02 | 2018-11-06 | 青岛海信医疗设备股份有限公司 | Vessel radius determines method, apparatus, terminal and storage medium |
| CN109360236A (en) * | 2018-10-26 | 2019-02-19 | 郑州轻工业学院 | A kind of floral disc of sunflower dimension measurement method |
| CN112017232A (en) * | 2020-08-31 | 2020-12-01 | 浙江水晶光电科技股份有限公司 | Method, device and equipment for positioning circular pattern in image |
-
2020
- 2020-12-15 CN CN202011477741.0A patent/CN112529923A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004272885A (en) * | 2003-02-21 | 2004-09-30 | Shinko Electric Ind Co Ltd | Device and method for edge extraction |
| CN108038891A (en) * | 2017-12-28 | 2018-05-15 | 福建中金在线信息科技有限公司 | A kind of graphic processing method and device |
| CN108765364A (en) * | 2018-04-02 | 2018-11-06 | 青岛海信医疗设备股份有限公司 | Vessel radius determines method, apparatus, terminal and storage medium |
| CN109360236A (en) * | 2018-10-26 | 2019-02-19 | 郑州轻工业学院 | A kind of floral disc of sunflower dimension measurement method |
| CN112017232A (en) * | 2020-08-31 | 2020-12-01 | 浙江水晶光电科技股份有限公司 | Method, device and equipment for positioning circular pattern in image |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114331951A (en) * | 2021-09-30 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Image detection method, image detection device, computer, readable storage medium, and program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110046529B (en) | Two-dimensional code identification method, device and equipment | |
| CN112001406B (en) | Text region detection method and device | |
| CN112199268B (en) | Software compatibility testing method and electronic equipment | |
| CN110708568B (en) | Video content mutation detection method and device | |
| CN111079730A (en) | Method for determining area of sample image in interface image and electronic equipment | |
| CN112686919A (en) | Object boundary line determining method and device, electronic equipment and storage medium | |
| CN112419207A (en) | Image correction method, device and system | |
| CN113557520A (en) | Character processing and character recognition method, storage medium and terminal device | |
| CN110751156A (en) | Method, system, device and medium for table line bulk interference removal | |
| CN113129298B (en) | Method for identifying definition of text image | |
| CN112529923A (en) | Control identification method and device | |
| CN113392455A (en) | House type graph scale detection method and device based on deep learning and electronic equipment | |
| CN111340788B (en) | Hardware Trojan horse layout detection method and device, electronic equipment and readable storage medium | |
| CN116993654B (en) | Camera module defect detection method, device, equipment, storage medium and product | |
| CN114140336B (en) | Infrared image-based dead pixel processing method and device | |
| CN112668578B (en) | Pointer type instrument reading method, pointer type instrument reading device, computer equipment and storage medium | |
| CN112511725A (en) | Automatic identification method and device for endoscope ring, storage medium and terminal | |
| CN112465931A (en) | Image text erasing method, related equipment and readable storage medium | |
| CN111428707A (en) | Method and device for identifying pattern identification code, storage medium and electronic equipment | |
| CN111695557A (en) | Image processing method and device | |
| CN112507910B (en) | Image recognition method and system based on pixel deformation, electronic device and storage medium | |
| CN110543624B (en) | Method and device for identifying check boxes in PDF document and electronic equipment | |
| CN111290676B (en) | Method, device and equipment for intercepting picture of designated area in client | |
| US11989908B2 (en) | Visual positioning method, mobile machine using the same, and computer readable storage medium | |
| CN113378595B (en) | Two-dimensional code positioning method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |