CN114494058A - Image processing method, image processing device, electronic equipment and storage medium - Google Patents
Image processing method, image processing device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114494058A CN114494058A CN202210078688.XA CN202210078688A CN114494058A CN 114494058 A CN114494058 A CN 114494058A CN 202210078688 A CN202210078688 A CN 202210078688A CN 114494058 A CN114494058 A CN 114494058A
- Authority
- CN
- China
- Prior art keywords
- image
- straight line
- edge
- mask
- pixel point
- 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.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 35
- 238000003672 processing method Methods 0.000 title claims abstract description 10
- 238000000034 method Methods 0.000 claims abstract description 25
- 230000001788 irregular Effects 0.000 claims description 8
- 230000000694 effects Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000010339 dilation Effects 0.000 description 4
- 230000003628 erosive effect Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/543—Depth or shape recovery from line drawings
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the application discloses an image processing method, an image processing device, electronic equipment and a storage medium, which can effectively eliminate the protrusion on each edge of a target object in an image to be processed, so that each edge is relatively smooth, and the image processing effect is improved. The method in the embodiment of the application comprises the following steps: generating a mask corresponding to an image to be processed, wherein the mask is used for marking an image position corresponding to a target object in the image to be processed; performing straight line fitting on each edge of the target object in the mask to obtain a slope corresponding to each fitted straight line, and acquiring a gradient value corresponding to each pixel point on each edge of the target object in the image to be processed; correcting each edge of the target object in the mask by using the slope corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask; and obtaining a target image according to the new mask and the image to be processed.
Description
Technical Field
The present application relates to the field of imaging technologies, and in particular, to an image processing method and apparatus, an electronic device, and a storage medium.
Background
In order to improve the recognition accuracy of the image, the object to be recognized in the image is processed, such as eliminating a protrusion generated on an edge of the object to be recognized. Currently, morphological algorithms of the image are generally used to eliminate the protrusion generated on the edge of the object to be recognized in the image, such as an opening operation or a closing operation. Specifically, the open operation refers to performing erosion operation and then performing dilation operation on the image, and the close operation refers to performing dilation operation and then erosion operation on the image. The erosion operation refers to expanding a highlight area or a white part of an image, a brightness area of an obtained erosion graph is larger than that of the image, and the dilation operation refers to reducing and thinning the highlight area or the white part of the image, and a brightness area of an obtained dilation graph is smaller than that of the image.
Whether the operation is an opening operation or a closing operation, the protrusion generated on the edge of the object to be recognized cannot be accurately and effectively eliminated to a certain extent, so that the edge of the object to be recognized is not smooth enough.
Disclosure of Invention
The embodiment of the application provides an image processing method, an image processing device, electronic equipment and a storage medium, which can effectively eliminate the protrusion on each edge of a target object in an image to be processed, so that each edge of the target object is relatively smooth, and the image processing effect is improved.
A first aspect of an embodiment of the present application provides an image processing method, which may include:
generating a mask corresponding to an image to be processed, wherein the mask is used for marking an image position corresponding to a target object in the image to be processed;
performing straight line fitting on each edge of the target object in the mask to obtain a slope corresponding to each fitted straight line, and acquiring a gradient value corresponding to each pixel point on each edge of the target object in the image to be processed;
correcting each edge of the target object in the mask by using the slope corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask;
and obtaining a target image according to the new mask and the image to be processed.
Optionally, the correcting each edge of the target object in the mask by using the slope corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask includes: if the slope corresponding to the first straight line is determined to be not infinite, determining the slope range corresponding to the first straight line according to the slope corresponding to the first straight line and a preset threshold, wherein the first straight line is any one of the straight lines; and correcting each edge of the target object in the mask by utilizing the slope range corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask.
Optionally, the correcting each edge of the target object in the mask by using the slope range corresponding to each straight line and the gradient value corresponding to each pixel point on each edge includes: if the first gradient value corresponding to the first pixel point is determined not to be located in the slope range corresponding to the first straight line, setting the pixel value corresponding to the first pixel point in the mask as a preset pixel value; the first pixel point is any one of the pixel points on the first edge corresponding to the first straight line, and the preset pixel value is used for indicating that the pixel point belongs to the background image area.
Optionally, the correcting each edge of the target object in the mask by using the slope corresponding to each straight line and the gradient value corresponding to each pixel point on each edge includes: if the slope corresponding to the first straight line is determined to be infinite, judging whether a first gradient direction corresponding to a first pixel point in the image to be processed is the vertical direction of the first straight line, wherein the first straight line is any straight line in each straight line, and the first pixel point is any pixel point in each pixel point on a first edge corresponding to the first straight line; if the first gradient direction is the vertical direction of the first straight line, setting a pixel value corresponding to the first pixel point in the mask as a preset pixel value, wherein the preset pixel value is used for indicating that the pixel point belongs to a background image area.
Optionally, obtaining a target image according to the new mask and the image to be processed includes: and multiplying the pixel value of each pixel point in the new mask with the pixel value of the pixel point at the same image position in the image to be processed to obtain a target image.
Optionally, the generating a mask corresponding to the image to be processed includes: extracting color features of an image to be processed and/or various shape features contained in an object in the image to be processed; and identifying the target object included in the image to be processed according to the color feature and/or the shape feature, and generating a mask corresponding to the image to be processed.
Optionally, the target object is a regular polygonal object, or an irregular polygonal object.
A second aspect of the embodiments of the present application provides an image processing apparatus, which may include:
the processing module is used for generating a mask corresponding to the image to be processed, and the mask is used for marking the image position corresponding to the target object in the image to be processed;
the acquisition module is used for performing straight line fitting on each edge of the target object in the mask to obtain a slope corresponding to each fitted straight line and acquiring a gradient value corresponding to each pixel point on each edge of the target object in the image to be processed;
the processing module is further configured to correct each edge of the target object in the mask by using a slope corresponding to each straight line and a gradient value corresponding to each pixel point on each edge, so as to obtain a new mask; and obtaining a target image according to the new mask and the image to be processed.
Optionally, the processing module is specifically configured to determine a slope range corresponding to a first straight line according to a slope corresponding to the first straight line and a preset threshold if it is determined that the slope corresponding to the first straight line is not infinite, where the first straight line is any one of the straight lines; and correcting each edge of the target object in the mask by utilizing the slope range corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask.
Optionally, the processing module is specifically configured to set a pixel value corresponding to the first pixel point in the mask as a preset pixel value if it is determined that the first gradient value corresponding to the first pixel point is not within the slope range corresponding to the first straight line; the first pixel point is any one of the pixel points on the first edge corresponding to the first straight line, and the preset pixel value is used for indicating that the pixel point belongs to the background image area.
Optionally, the processing module is specifically configured to determine whether a first gradient direction corresponding to a first pixel point in the image to be processed is a vertical direction of the first straight line if it is determined that a slope corresponding to the first straight line is infinite, where the first straight line is any one of the straight lines, and the first pixel point is any one of the pixel points on a first edge corresponding to the first straight line; if the first gradient direction is the vertical direction of the first straight line, setting a pixel value corresponding to the first pixel point in the mask as a preset pixel value, wherein the preset pixel value is used for indicating that the pixel point belongs to a background image area.
Optionally, the processing module is specifically configured to multiply a pixel value of each pixel in the new mask by a pixel value of a pixel at the same image position in the image to be processed, so as to obtain the target image.
Optionally, the processing module is specifically configured to extract color features of the image to be processed and/or shape features included in an object in the image to be processed; and identifying the target object included in the image to be processed according to the color feature and/or the shape feature, and generating a mask corresponding to the image to be processed.
Optionally, the target object is a regular polygon object, or an irregular polygon object.
A third aspect of embodiments of the present application provides an electronic device, which may include:
a memory storing executable program code;
and a processor coupled to the memory;
the processor calls the executable program code stored in the memory, and when executed by the processor, the executable program code causes the processor to implement the method according to the first aspect of the embodiments of the present application.
Yet another aspect of the embodiments of the present application provides a computer-readable storage medium, on which an executable program code is stored, and when the executable program code is executed by a processor, the method according to the first aspect of the embodiments of the present application is implemented.
In another aspect, an embodiment of the present application discloses a computer program product, which, when run on a computer, causes the computer to perform any one of the methods disclosed in the first aspect of the embodiment of the present application.
In another aspect, an application publishing platform is disclosed, which is configured to publish a computer program product, where when the computer program product runs on a computer, the computer is caused to perform any one of the methods disclosed in the first aspect of the embodiments of the present application.
According to the technical scheme, the embodiment of the application has the following advantages:
in the embodiment of the application, a mask corresponding to an image to be processed is generated, and the mask can accurately mark the image position corresponding to a target object in the image to be processed; performing straight line fitting on each edge of the target object in the mask to obtain a slope corresponding to each edge, and acquiring a gradient value corresponding to each pixel point on each edge of the target object in the image to be processed; then, correcting each edge of the target object in the mask by utilizing the slope corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask; and finally, obtaining a target image according to the new mask and the image to be processed, and effectively eliminating the bulge on each edge of the target object in the image to be processed, so that each edge of the target object in the target image is relatively smooth, and the image processing effect is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments and the prior art will be briefly described below, and it is obvious that the drawings in the description below are only some embodiments of the present application, and other drawings can be obtained according to the drawings.
FIG. 1 is a schematic diagram of an embodiment of an image processing method in an embodiment of the present application;
FIG. 2a is a schematic diagram of an embodiment of an image to be processed in an embodiment of the present application;
FIG. 2b is a schematic diagram of an embodiment of a mask in an embodiment of the present application;
FIG. 2c is a schematic diagram of an embodiment of the new mask in the present embodiment;
FIG. 2d is a schematic diagram of an embodiment of a target image in an embodiment of the present application;
FIG. 3 is a schematic diagram of an embodiment of an image processing apparatus according to the embodiment of the present application;
fig. 4 is a schematic diagram of an embodiment of an electronic device in an embodiment of the present application.
Detailed Description
The embodiment of the application provides an image processing method, an image processing device, electronic equipment and a storage medium, which can effectively eliminate the protrusion on each edge of a target object in an image to be processed, so that each edge of the target object is relatively smooth, and the image processing effect is improved.
For a person skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. The embodiments in the present application shall fall within the protection scope of the present application.
As shown in fig. 1, which is a schematic diagram of an embodiment of an image processing method in an embodiment of the present application, the method may include:
101. and generating a mask corresponding to the image to be processed.
Wherein the image to be processed refers to an image including a target object.
The target object refers to an object of interest in the image to be processed, and may be a foreground object in the image to be processed, or a specified object (e.g., a person, a specific object, etc.) in the image to be processed. Further, the target object may be a polygonal object. Optionally, the target object may be a regular polygon object or an irregular polygon object, which is not limited herein.
The mask may be used to label an image position corresponding to a target object in the image to be processed. In this mask, since the target object is a foreground object, the region image other than the target object is a background image region.
It is understood that the mask may be a grayscale image or a binary image. The mask according to the embodiment of the present application is a binarized image which is an image composed of a pixel value of 0 and a pixel value of 1, where a pixel value of 0 indicates black and a pixel value of 1 indicates white. Optionally, in the mask, when a pixel value corresponding to a pixel point of the target object is 0, a pixel value corresponding to a pixel point of the background image area is 1; when the pixel value corresponding to the pixel point of the background image area is 1, the pixel value corresponding to the pixel point of the target object is 0, which is not specifically limited herein.
Exemplarily, as shown in fig. 2a, the embodiment is a schematic diagram of an embodiment of an image to be processed in an embodiment of the present application. In fig. 2a, the image to be processed 200a comprises a target object 201a and a background image area 202 a. The target object 201a is composed of an irregular multi-pentagonal object and a regular quadrilateral object. The pentagonal object comprises five vertexes, namely a point A, a point B, a point C, a point D and a point E, and comprises five edges, namely an edge AB, an edge BC, an edge CD, an edge DE and an edge EA. Furthermore, the edge DE is provided with a projection F. The quadrilateral object comprises four vertexes, namely a point G, a point H, a point I and a point J, and comprises four edges, namely an edge GH, an edge HI, an edge IJ and an edge JG.
Fig. 2b is a schematic diagram of an embodiment of a mask in the embodiment of the present application. The mask 200b shown in fig. 2b corresponds to the image to be processed 200a shown in fig. 2 a. In the mask 200b, the pixel value corresponding to the pixel point of the target object 201b is 1, and the pixel value corresponding to the pixel point of the background image area 202b is 0.
Optionally, the generating, by the electronic device, a mask corresponding to the image to be processed may include: the electronic equipment extracts color features of an image to be processed and/or various shape features contained in an object in the image to be processed; the electronic equipment identifies the target object included in the image to be processed according to the color feature and/or the shape feature, and generates a mask corresponding to the image to be processed.
It should be noted that the electronic device has an image recognition function, and may recognize and obtain a target object corresponding to each shape feature included in the color feature and/or the object according to a color distribution condition in the extracted image to be processed, that is, according to each shape feature (for example, an irregular quadrangle or a regular hexagon) included in the color feature and/or the object; the electronic device extracts the target object to generate a mask corresponding to the image to be processed, so that each edge of the target object can be corrected by the electronic device in the following process, and the protrusion of the target object on the corresponding edge of the image to be processed can be effectively eliminated.
Optionally, the generating, by the electronic device, a mask corresponding to the image to be processed may include: the electronic equipment inputs the image to be processed to the image recognition model so as to obtain a mask corresponding to the image to be processed and output by the image recognition model.
The image recognition model is obtained by training a historical image set to be processed and a historical mask set.
It can be understood that, because the image recognition model is obtained by training a large number of historical images to be processed and a large number of historical masks, when the electronic device inputs the images to be processed into the image recognition model, the image recognition model can quickly output the masks corresponding to the images to be processed, so that the electronic device can quickly acquire the masks, and the use power consumption of the electronic device can be effectively saved while the mask acquisition efficiency is improved.
102. And performing straight line fitting on each edge of the target object in the mask to obtain a slope corresponding to each fitted straight line, and acquiring a gradient value corresponding to each pixel point on each edge of the target object in the image to be processed.
Optionally, the performing, by the electronic device, straight line fitting on each edge of the target object in the mask to obtain a slope corresponding to each fitted straight line may include: the electronic device performs straight line fitting on each edge of the target object in the mask through a Random Sample Consensus (RANSAC) algorithm to obtain a slope corresponding to each straight line that is fitted.
The slope may be infinite or infinite, and is not particularly limited herein.
It should be noted that the RANSAC algorithm estimates parameters of the linear model from a group of pixels including outliers in a mask in an iterative manner.
Take the first edge as an example. Among a group of outlier-containing pixels, some pixels belong to the pixels on the first edge, and some pixels do not belong to the pixels on the first edge. If the electronic device determines the first straight line corresponding to the first edge according to the group of outlier-containing pixels, it needs to determine the first straight line corresponding to the first edge according to the pixels belonging to the first edge. Because one straight line model needs two data to uniquely determine a straight line equation, namely one straight line model needs two pixel points to uniquely determine a straight line, the electronic equipment randomly selects two pixel points from all the pixel points belonging to the first edge, and can calculate a first straight line model equation Y expressed by the two pixel points as aX + b by using the pixel coordinates of the two pixel points, wherein a represents the slope of the first edge corresponding to the first straight line, and b represents a constant; then, the pixel coordinates of the pixel points on the first edge are all applied by a first straight line model equation Y which is aX + b, the distance value between each pixel point and the first straight line is calculated, the distance value between each pixel point and the first straight line is compared with a preset distance threshold, and the pixel point with the distance value smaller than the preset distance threshold is determined as a target pixel point. And after the steps are repeatedly executed to reach the preset iteration times, selecting the first straight line model equation with the most target pixel points, and accurately obtaining the slope of the first straight line corresponding to the first edge.
Specifically, the preset number of iterations is two. The electronic equipment is used for processing the pixel coordinates of the first pixel point and the pixel coordinates of the second pixel pointDetermining a first linear model equation Y1＝a1X1+b1(ii) a The electronic equipment calculates a distance value between each pixel point on the first edge and the first straight line, compares each distance value with a first preset distance threshold, determines the pixel points with the distance values smaller than the first preset distance threshold as first target pixel points, and then acquires a first number of the first target pixel points;
the electronic equipment determines a second linear model equation Y according to the pixel coordinates of the third pixel point and the fourth pixel point2＝a2X2+b2(ii) a The electronic equipment calculates a distance value between each pixel point on the first edge and the second straight line, compares each distance value with a second preset distance threshold, determines the pixel points with the distance values smaller than the second preset distance threshold as second target pixel points, and then obtains a second number of the second target pixel points;
finally, the electronic device compares the first number with the second number, and if the first number is larger than the second number, a1Determining the slope of the first straight line corresponding to the first edge; if the second number is larger than the first number, a2Determining the slope of the first straight line corresponding to the first edge; if the first number is equal to the second number, a1Or a2The slope of the first straight line corresponding to the first edge is determined.
It should be noted that the preset distance threshold and the preset iteration number may be set before the electronic device leaves the factory, or may be customized by the user according to the requirement of the target object, and are not specifically limited herein.
Illustratively, the electronic device performs a straight line fitting on the edge of the pentagonal object in the mask 200b shown in fig. 2b by using the RANSAC algorithm, so as to obtain that the slope of the straight line corresponding to the edge CD is 1/2.
Optionally, the obtaining, by the electronic device, a gradient value corresponding to each pixel point on each edge of the target object in the image to be processed may include: the electronic equipment acquires pixel coordinates corresponding to each pixel point on each edge of the target object in the image to be processed; and the electronic equipment determines the gradient value corresponding to each pixel point according to the pixel coordinate of each pixel point.
It should be noted that the gradient refers to a vector, and the vector is a vector. The gradient value corresponding to the gradient may represent a maximum value obtained by a directional derivative of a pixel point of the electronic device in the image to be processed along the gradient direction, that is, a value in which the change rate of the pixel point is the maximum and the change speed of the pixel point is the fastest along the gradient direction. I.e. the gradient value corresponding to the gradient is the mode of the gradient.
Take the first pixel point as an example. The process of determining the gradient value G (x, y) corresponding to the first pixel point by the electronic device according to the pixel coordinate I (I, j) of the first pixel point is as follows: the electronic equipment obtains a derivative dx (i, j) of the first pixel point in the first direction and a derivative dy (i, j) of the first pixel point in the second direction according to the pixel coordinate (i, j) of the first pixel point; and obtaining the gradient value G (x, y) corresponding to the first pixel point according to dx (i, j) and dy (i, j).
Specifically, the electronic device calculates a derivative dx (i, j) of the first pixel point in the first direction according to a first derivative formula; the electronic equipment calculates a derivative dy (i, j) of the first pixel point in the second direction according to a second derivative formula; and the electronic equipment calculates to obtain a gradient value G (x, y) corresponding to the first pixel point according to a gradient value formula.
Wherein the first derivation formula is dx (I, j) ═ I (I + p, j) -I (I, j) ]/p;
the second derivation formula is dy (I, j) ═ I (I, j + p) -I (I, j) ]/p;
the gradient value formula is G (x, y) ═ dx (i, j) + dy (i, j).
Wherein, (i, j) is the pixel coordinate of the first pixel point; i (I, j) is the first pixel value corresponding to the first pixel point. Alternatively, p is taken to be 1.
103. And correcting each edge of the target object in the mask by utilizing the slope corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask.
It should be noted that, because there may be a protrusion at an edge of a target object in an image to be processed, the edge may not be smooth enough, and if the electronic device does not process the protrusion on the edge, subsequent image processing may be affected, therefore, after the electronic device obtains the image to be processed and a mask corresponding to the image to be processed, the electronic device may correct each edge of the target object in the mask by using a slope of a corresponding straight line of each edge of the target object in the mask and a gradient value of each pixel point on each edge of the target object in the image to be processed, so as to effectively eliminate the protrusion carried by the edge of the target object, so that each edge of the target object is smooth, and a new mask may be obtained.
Optionally, the electronic device corrects each edge of the target object in the mask by using the slope corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask, which may include but is not limited to the following implementation manners:
implementation mode 1: if the electronic equipment determines that the slope corresponding to the first straight line is not infinite, determining a slope range corresponding to the first straight line according to the slope corresponding to the first straight line and a preset threshold; and the electronic equipment corrects each edge of the target object in the mask by utilizing the slope range corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask.
The first straight line is any one of straight lines obtained by the electronic equipment performing straight line fitting on each edge of the target object in the mask.
It can be understood that, since the target object may include a plurality of edges, each edge corresponds to one straight line, that is, the target object may include a plurality of straight lines, and the first straight line is any one of the plurality of straight lines, the electronic device only needs to fit the straight line corresponding to each edge according to the method of the foregoing implementation mode 1 to obtain the slope corresponding to each straight line.
The preset threshold may be set before the electronic device leaves a factory, or may be user-defined according to actual needs, and is not specifically limited here.
The electronic device may determine whether a slope corresponding to the first straight line is infinite, that is, may determine whether the first straight line is a straight line perpendicular to the horizontal line. If the slope corresponding to the first straight line is determined not to be infinite, determining that the first straight line is not a straight line vertical to the horizontal; and if the slope corresponding to the first straight line is determined to be infinite, determining that the first straight line is a straight line vertical to the horizontal.
Optionally, the determining, by the electronic device, the slope range corresponding to the first straight line according to the slope corresponding to the first straight line and a preset threshold may include: the electronic equipment subtracts a preset threshold value from the slope corresponding to the first straight line to obtain a first slope threshold value corresponding to the first straight line; the electronic equipment adds the preset threshold to the slope corresponding to the first straight line to obtain a second slope threshold corresponding to the first straight line; the electronic device uses the first slope threshold as a lower limit value of a slope range corresponding to the first straight line, and uses the second slope threshold as an upper limit value of the slope range, so as to obtain the slope range corresponding to the first straight line.
It should be noted that the timing for the electronic device to obtain the first slope threshold and the second slope threshold is not limited.
Further, the electronic device determines a first slope threshold corresponding to the first straight line according to a first formula; the electronic equipment determines a second slope threshold corresponding to the first straight line according to a second formula; the electronic device uses the first slope threshold as a lower limit value of a slope range corresponding to the first straight line, and uses the second slope threshold as an upper limit value of the slope range, so as to obtain the slope range corresponding to the first straight line.
Wherein, the first formula is m ═ a-th, and the second formula is n ═ a + th; m represents the first slope threshold, n represents the second slope threshold, a represents the slope corresponding to the first line, and th represents a preset threshold. Further, the slope range may be represented as (m, n).
Optionally, the electronic device corrects each edge of the target object in the mask by using the slope range corresponding to each straight line and the gradient value corresponding to each pixel point on each edge, and the correcting may include: if the first gradient value corresponding to the first pixel point is determined not to be within the slope range corresponding to the first straight line, the electronic device sets the pixel value corresponding to the first pixel point in the mask as a preset pixel value.
The first pixel point is any one of the pixel points on the first edge corresponding to the first straight line, and the preset pixel value is used for indicating that the pixel point belongs to the background image area.
It should be noted that, when the electronic device determines that the slope corresponding to the first straight line is not infinite, the slope range corresponding to the first straight line exists. The electronic equipment can acquire the pixel points of which the gradient values correspond to the pixel points on the first edge, are located in the slope range corresponding to the first straight line, and the pixel points in the slope range corresponding to the first straight line are also the pixel points in the target object, so that the electronic equipment does not need to adjust the pixel values corresponding to the pixel points in the target object, and the pixel values of the pixel points in the slope range corresponding to the first straight line can be reserved by the electronic equipment. Meanwhile, under the condition that the electronic device determines that the first gradient value corresponding to the first pixel point is not located in the slope range corresponding to the first straight line, it may be determined that the first pixel point is a pixel point in the protrusion on the first edge, and in order to eliminate the first pixel point in the protrusion, the electronic device may set the pixel value corresponding to the first pixel point in the mask as a preset pixel value, where the preset pixel value may be 0 or 1, so that the pixel value corresponding to the first pixel point is the same as the pixel value corresponding to the pixel point in the background image area.
It can be understood that, since each edge of the target object corresponds to a plurality of pixel points, the electronic device only needs to calculate each pixel point according to the above method to obtain the gradient value corresponding to each pixel point.
Implementation mode 2: if the electronic equipment determines that the slope corresponding to the first straight line is infinite, whether a first gradient direction corresponding to the first pixel point in the image to be processed is the vertical direction of the first straight line is judged; if the first gradient direction is the vertical direction of the first straight line, the electronic device sets the pixel value of the first pixel point in the mask as a preset pixel value.
It should be noted that, when the electronic device determines that the slope corresponding to the first straight line is infinite, the electronic device cannot acquire the slope range corresponding to the first straight line, that is, the slope range corresponding to the first straight line does not exist. When the electronic device determines that the slope corresponding to the first straight line is infinite, the first straight line is a straight line perpendicular to the horizontal direction, so that if the first gradient direction corresponding to the first pixel point is the horizontal direction of the first straight line, that is, the first gradient direction is parallel to the horizontal direction, the electronic device can determine that the first pixel point is a pixel point on the corresponding edge of the first straight line, that is, the first pixel point can be determined to be a pixel point in the target object, and the electronic device does not need to adjust the pixel value corresponding to the pixel point in the target object, so that the electronic device can reserve the pixel value of the first pixel point; if the first gradient direction corresponding to the first pixel point is the vertical direction of the first straight line, it may be determined that the first pixel point is a pixel point in the protrusion on the first edge, and in order to eliminate the first pixel point in the protrusion, the electronic device may set a pixel value corresponding to the first pixel point in the mask as a preset pixel value, so that the pixel value corresponding to the first pixel point is the same as the pixel value corresponding to the pixel point in the background image area.
Exemplarily, as shown in fig. 2c, it is a schematic diagram of an embodiment of the new mask in the embodiment of the present application. In fig. 2c, the new mask 200c comprises a target object 201c and a background image area 202 c. In the new mask 200c, there is no protrusion on each edge of the target object 201 c.
It can be understood that, in both the above implementation 1 and the above implementation 2, in order to determine the pixel points in the mask more accurately, which pixel points are pixel points on the edge of the target object and which pixel points are pixel points in the protrusion generated by the edge, so that the electronic equipment can accurately adjust the pixel values corresponding to the pixel points in the mask, the electronic device may retain pixel values corresponding to pixel points on the edge of the target object, and adjusting the pixel values corresponding to the pixel points in the protrusions to preset pixel values so that the pixel values corresponding to the pixel points in the protrusions can be the same as the pixel values corresponding to the pixel points in the background image area, so as to effectively eliminate the pixel points in the protrusion generated by the upper edge of the target object, thereby ensuring that each edge of the target object in the mask is smoother.
104. And obtaining a target image according to the new mask and the image to be processed.
The new mask accurately defines the position of the image of the target object without the edge protrusion, so that the electronic equipment can adjust the pixel points of the target object of the image to be processed according to the new mask to obtain the target image, and the pixel points of the edge protrusion belonging to the target object in the image to be processed are adjusted to be the pixel points close to the background area.
Optionally, the obtaining, by the electronic device, the target image according to the new mask and the image to be processed may include: and the electronic equipment multiplies the pixel value of each pixel point in the new mask by the pixel value of the pixel point at the same image position in the image to be processed to obtain a target image.
It should be noted that, in the new mask, if the pixel value corresponding to the pixel point of the target object is 1 and the pixel value corresponding to the pixel point of the background image region is 0, the electronic device multiplies the pixel value of each pixel point in the new mask by the pixel value of the pixel point at the same image position in the image to be processed, and then obtains a target image in which the pixel value corresponding to the pixel point actually belonging to the target object is retained, and the pixel value corresponding to the pixel point generating the protrusion on the edge of the target object is adjusted to the pixel value corresponding to the pixel point of the background image region, so that the protrusion generated on the edge is effectively eliminated, and each edge of the target object in the target image is relatively smooth.
Exemplarily, as shown in fig. 2d, the embodiment is a schematic view of an embodiment of a target image in the embodiment of the present application. In fig. 2d, the target image 200d comprises a target object 201d and a background image area 202 d. The pixel value corresponding to the pixel point of the target object 201d is retained, and the pixel value corresponding to the pixel point of the background image area 202d is 0. In the target image 200d, there is no protrusion on each edge of the target object 201 d.
In the embodiment of the application, a mask corresponding to an image to be processed is generated, and the mask can accurately mark the image position corresponding to a target object in the image to be processed; performing straight line fitting on each edge of the target object in the mask to obtain a slope corresponding to each edge, and acquiring a gradient value corresponding to each pixel point on each edge of the target object in the image to be processed; then, each edge of the target object in the mask is corrected by utilizing the slope corresponding to each straight line and the gradient value corresponding to each pixel point on each edge, so that the bulge on each edge of the target object in the image to be processed can be effectively eliminated, each edge of the target object in the target image is relatively smooth, and the image processing effect is improved.
As shown in fig. 3, which is a schematic diagram of an embodiment of an image processing apparatus in an embodiment of the present application, the image processing apparatus may include:
the processing module 301 is configured to generate a mask corresponding to an image to be processed, where the mask is used to mark an image position corresponding to a target object in the image to be processed;
an obtaining module 302, configured to perform linear fitting on each edge of the target object in the mask to obtain a slope corresponding to each linear line that is fitted, and obtain a gradient value corresponding to each pixel point on each edge of the target object in the image to be processed;
the processing module 301 is further configured to modify each edge of the target object in the mask by using a slope corresponding to each straight line and a gradient value corresponding to each pixel point on each edge, so as to obtain a new mask; and obtaining a target image according to the new mask and the image to be processed.
Alternatively, in some embodiments of the present application,
the processing module 301 is specifically configured to determine a slope range corresponding to a first straight line according to a slope corresponding to the first straight line and a preset threshold if it is determined that the slope corresponding to the first straight line is not infinite, where the first straight line is any one of the straight lines; and correcting each edge of the target object in the mask by utilizing the slope range corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask.
Alternatively, in some embodiments of the present application,
the processing module 301 is specifically configured to set a pixel value corresponding to the first pixel point in the mask as a preset pixel value if it is determined that the first gradient value corresponding to the first pixel point is not within the slope range corresponding to the first straight line; the first pixel point is any one of the pixel points on the first edge corresponding to the first straight line, and the preset pixel value is used for indicating that the pixel point belongs to the background image area.
Alternatively, in some embodiments of the present application,
the processing module 301 is specifically configured to determine, if it is determined that the slope corresponding to a first straight line is infinite, whether a first gradient direction corresponding to a first pixel point in the image to be processed is a vertical direction of the first straight line, where the first straight line is any one of the straight lines, and the first pixel point is any one of the pixel points on a first edge corresponding to the first straight line; if the first gradient direction is the vertical direction of the first straight line, setting a pixel value corresponding to the first pixel point in the mask as a preset pixel value, wherein the preset pixel value is used for indicating that the pixel point belongs to a background image area.
Alternatively, in some embodiments of the present application,
the processing module 301 is specifically configured to multiply the pixel value of each pixel in the new mask by the pixel value of a pixel in the same image position in the image to be processed, so as to obtain a target image.
Alternatively, in some embodiments of the present application,
a processing module 301, specifically configured to extract color features of an image to be processed and/or shape features included in an object in the image to be processed; and identifying the target object included in the image to be processed according to the color feature and/or the shape feature, and generating a mask corresponding to the image to be processed.
Optionally, the target object is a regular polygon object, or an irregular polygon object.
As shown in fig. 4, a schematic diagram of an embodiment of an electronic device in an embodiment of the present application may include: a memory 402 and a processor 401, the processor 401 and the memory 402 are coupled, and the processor 401 can call an executable program code stored in the processor 401;
the processor 401 included in the image processing apparatus has the following functions:
generating a mask corresponding to an image to be processed, wherein the mask is used for marking an image position corresponding to a target object in the image to be processed;
performing straight line fitting on each edge of the target object in the mask to obtain a slope corresponding to each fitted straight line, and acquiring a gradient value corresponding to each pixel point on each edge of the target object in the image to be processed;
correcting each edge of the target object in the mask by using the slope corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask;
and obtaining a target image according to the new mask and the image to be processed.
Optionally, the processor 401 further has the following functions:
if the slope corresponding to the first straight line is determined to be not infinite, determining the slope range corresponding to the first straight line according to the slope corresponding to the first straight line and a preset threshold, wherein the first straight line is any one of the straight lines; and correcting each edge of the target object in the mask by utilizing the slope range corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask.
Optionally, the processor 401 further has the following functions:
if the first gradient value corresponding to the first pixel point is determined not to be located in the slope range corresponding to the first straight line, setting the pixel value corresponding to the first pixel point in the mask as a preset pixel value; the first pixel point is any one of the pixel points on the first edge corresponding to the first straight line, and the preset pixel value is used for indicating that the pixel point belongs to the background image area.
Optionally, the processor 401 further has the following functions:
if the slope corresponding to the first straight line is determined to be infinite, judging whether a first gradient direction corresponding to a first pixel point in the image to be processed is the vertical direction of the first straight line, wherein the first straight line is any straight line in each straight line, and the first pixel point is any pixel point in each pixel point on a first edge corresponding to the first straight line; if the first gradient direction is the vertical direction of the first straight line, setting a pixel value corresponding to the first pixel point in the mask as a preset pixel value, wherein the preset pixel value is used for indicating that the pixel point belongs to a background image area.
Optionally, the processor 401 further has the following functions:
and multiplying the pixel value of each pixel point in the new mask with the pixel value of the pixel point at the same image position in the image to be processed to obtain a target image.
Optionally, the processor 401 further has the following functions:
extracting color features of an image to be processed and/or various shape features contained in an object in the image to be processed; and identifying the target object included in the image to be processed according to the color feature and/or the shape feature, and generating a mask corresponding to the image to be processed.
Optionally, the target object is a regular polygon object, or an irregular polygon object.
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. The procedures or functions described in accordance with the embodiments of the application are all or partially generated when the computer program instructions are loaded and executed on a computer. 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 a computer can store or a data storage device, such as a server, a data center, etc., that is integrated with one or more 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 clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, which are essential or part of the technical solutions contributing to the prior art, or all or part of the technical solutions, may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present application.
Claims (10)
1. An image processing method, comprising:
generating a mask corresponding to an image to be processed, wherein the mask is used for marking an image position corresponding to a target object in the image to be processed;
performing straight line fitting on each edge of the target object in the mask to obtain a slope corresponding to each fitted straight line, and acquiring a gradient value corresponding to each pixel point on each edge of the target object in the image to be processed;
correcting each edge of the target object in the mask by using the slope corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask;
and obtaining a target image according to the new mask and the image to be processed.
2. The method according to claim 1, wherein the correcting each edge of the target object in the mask by using the slope corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask comprises:
if the slope corresponding to a first straight line is determined not to be infinite, determining a slope range corresponding to the first straight line according to the slope corresponding to the first straight line and a preset threshold, wherein the first straight line is any straight line in each straight line;
and correcting each edge of the target object in the mask by using the slope range corresponding to each straight line and the gradient value corresponding to each pixel point on each edge to obtain a new mask.
3. The method according to claim 2, wherein the correcting each edge of the target object in the mask by using the slope range corresponding to each straight line and the gradient value corresponding to each pixel point on each edge comprises:
if the first gradient value corresponding to the first pixel point is determined not to be located in the slope range corresponding to the first straight line, setting the pixel value corresponding to the first pixel point in the mask as a preset pixel value;
the first pixel point is any one of pixel points on a first edge corresponding to the first straight line, and the preset pixel value is used for indicating that the pixel point belongs to a background image area.
4. The method according to claim 1, wherein the correcting each edge of the target object in the mask by using the slope corresponding to each straight line and the gradient value corresponding to each pixel point on each edge comprises:
if the slope corresponding to a first straight line is determined to be infinite, judging whether a first gradient direction corresponding to a first pixel point in the image to be processed is the vertical direction of the first straight line, wherein the first straight line is any straight line in each straight line, and the first pixel point is any pixel point in each pixel point on a first edge corresponding to the first straight line;
and if the first gradient direction is the vertical direction of the first straight line, setting a pixel value corresponding to the first pixel point in the mask as a preset pixel value, wherein the preset pixel value is used for indicating that the pixel point belongs to a background image area.
5. The method according to any one of claims 1-4, wherein said deriving a target image from the new mask and the image to be processed comprises:
and multiplying the pixel value of each pixel point in the new mask with the pixel value of the pixel point at the same image position in the image to be processed to obtain a target image.
6. The method according to any one of claims 1-4, wherein the generating a mask corresponding to the image to be processed comprises:
extracting color features of an image to be processed and/or shape features of each object contained in the image to be processed;
and identifying a target object included in the image to be processed according to the color feature and/or the shape feature, and generating a mask corresponding to the image to be processed.
7. The method according to any of claims 1-4, wherein the target object is a regular polygonal object, or an irregular polygonal object.
8. An image processing apparatus characterized by comprising:
the processing module is used for generating a mask corresponding to an image to be processed, and the mask is used for marking an image position corresponding to a target object in the image to be processed;
the obtaining module is used for performing straight line fitting on each edge of the target object in the mask to obtain a slope corresponding to each fitted straight line, and obtaining a gradient value corresponding to each pixel point on each edge of the target object in the image to be processed;
the processing module is further configured to correct each edge of the target object in the mask by using a slope corresponding to each straight line and a gradient value corresponding to each pixel point on each edge, so as to obtain a new mask; and obtaining a target image according to the new mask and the image to be processed.
9. An electronic device, comprising:
a memory storing executable program code;
and a processor coupled to the memory;
the processor calls the executable program code stored in the memory, which when executed by the processor causes the processor to implement the method of any one of claims 1-7.
10. A computer-readable storage medium having executable program code stored thereon, wherein the executable program code, when executed by a processor, implements the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210078688.XA CN114494058B (en) | 2022-01-24 | 2022-01-24 | Image processing method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210078688.XA CN114494058B (en) | 2022-01-24 | 2022-01-24 | Image processing method, device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114494058A true CN114494058A (en) | 2022-05-13 |
| CN114494058B CN114494058B (en) | 2024-09-24 |
Family
ID=81473874
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210078688.XA Active CN114494058B (en) | 2022-01-24 | 2022-01-24 | Image processing method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114494058B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115049735A (en) * | 2022-08-12 | 2022-09-13 | 季华实验室 | Mask optimization processing method and device, electronic equipment and storage medium |
| CN116958137A (en) * | 2023-09-19 | 2023-10-27 | 易启科技(吉林省)有限公司 | New energy battery surface defect detection method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056619A (en) * | 2016-06-13 | 2016-10-26 | 长安大学 | Unmanned aerial vehicle vision wire patrol method based on gradient constraint Radon transform |
| US20200410710A1 (en) * | 2018-11-06 | 2020-12-31 | Wuyi University | Method for measuring antenna downtilt based on linear regression fitting |
| CN112686812A (en) * | 2020-12-10 | 2021-04-20 | 广州广电运通金融电子股份有限公司 | Bank card inclination correction detection method and device, readable storage medium and terminal |
-
2022
- 2022-01-24 CN CN202210078688.XA patent/CN114494058B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056619A (en) * | 2016-06-13 | 2016-10-26 | 长安大学 | Unmanned aerial vehicle vision wire patrol method based on gradient constraint Radon transform |
| US20200410710A1 (en) * | 2018-11-06 | 2020-12-31 | Wuyi University | Method for measuring antenna downtilt based on linear regression fitting |
| CN112686812A (en) * | 2020-12-10 | 2021-04-20 | 广州广电运通金融电子股份有限公司 | Bank card inclination correction detection method and device, readable storage medium and terminal |
Non-Patent Citations (2)
| Title |
|---|
| GUODONG CHEN等: "Efficient optical proximity correction based on virtual edge and mask pixelation with two-phase sampling", 《OPTICS EXPRESS》, vol. 29, no. 11, 21 May 2021 (2021-05-21), pages 17440 - 17463 * |
| 匡平等: "基于尺度乘积的X射线焊缝区域提取算法研究", 《电子科技大学学报》, no. 05, 30 September 2015 (2015-09-30), pages 737 - 742 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115049735A (en) * | 2022-08-12 | 2022-09-13 | 季华实验室 | Mask optimization processing method and device, electronic equipment and storage medium |
| CN116958137A (en) * | 2023-09-19 | 2023-10-27 | 易启科技(吉林省)有限公司 | New energy battery surface defect detection method and device |
| CN116958137B (en) * | 2023-09-19 | 2023-12-12 | 易启科技(吉林省)有限公司 | New energy battery surface defect detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114494058B (en) | 2024-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106846336B (en) | Method and device for extracting foreground image and replacing image background | |
| CN114494058B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN108961175B (en) | Face brightness adjusting method and device, computer equipment and storage medium | |
| CN111383232B (en) | Matting method, matting device, terminal equipment and computer readable storage medium | |
| CN104636118B (en) | QR Quick Response Code self-adaption binaryzation treating method and apparatus based on photo-equilibrium | |
| AU2016225841B2 (en) | Predicting accuracy of object recognition in a stitched image | |
| CN108198185B (en) | Segmentation method and device for fundus focus image, storage medium and processor | |
| CN110969046B (en) | Face recognition method, face recognition device and computer-readable storage medium | |
| CN108961260B (en) | Image binarization method and device and computer storage medium | |
| CN109598744A (en) | A kind of method, apparatus of video tracking, equipment and storage medium | |
| US10740907B2 (en) | Moving body tracking method, moving body tracking device, and program | |
| JP2010205067A (en) | Device, method and program for extracting area | |
| CN114862897B (en) | Image background processing method and device and electronic equipment | |
| CN114694141A (en) | Follicular point identification method, system, device and storage medium | |
| CN104346774A (en) | Method and device for enhancing image | |
| CN111476735B (en) | Face image processing method and device, computer equipment and readable storage medium | |
| CN111583280B (en) | Image processing method, device, equipment and computer readable storage medium | |
| CN111209908B (en) | Method, device, storage medium and computer equipment for updating annotation frame | |
| CN108805873A (en) | Image processing method and device | |
| JP2003303346A (en) | Method, device and program for tracing target, and recording medium recording the program | |
| CN111445411A (en) | Image denoising method and device, computer equipment and storage medium | |
| CN107103321B (en) | The generation method and generation system of road binary image | |
| JP2010097341A (en) | Image processor for detecting image as object of detection from input image | |
| US9785856B2 (en) | Repairing holes in images | |
| CN113724129B (en) | Image blurring method, storage medium and terminal equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |