CN108564541B - Image processing method and device - Google Patents
Image processing method and device Download PDFInfo
- Publication number
- CN108564541B CN108564541B CN201810266817.1A CN201810266817A CN108564541B CN 108564541 B CN108564541 B CN 108564541B CN 201810266817 A CN201810266817 A CN 201810266817A CN 108564541 B CN108564541 B CN 108564541B
- Authority
- CN
- China
- Prior art keywords
- image
- fuzzy
- target
- pixel point
- target pixel
- 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 196
- 238000000034 method Methods 0.000 claims abstract description 39
- 238000009499 grossing Methods 0.000 claims description 28
- 239000011159 matrix material Substances 0.000 claims description 25
- 238000000926 separation method Methods 0.000 claims description 10
- 238000005192 partition Methods 0.000 abstract description 12
- 230000000875 corresponding effect Effects 0.000 description 64
- 238000012549 training Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003796 beauty Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Abstract
The embodiment of the application provides an image processing method and device, wherein the method comprises the following steps: after receiving an image blurring processing request, acquiring a target image to be subjected to image blurring processing; carrying out region division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing; respectively determining fuzzy radiuses corresponding to the divided image subblocks; and for each image sub-block, respectively carrying out image blurring processing on the image sub-block according to the blurring radius of the image sub-block to obtain a target image after blurring processing. In the embodiment of the application, the target image is subjected to partition fuzzy processing, and meanwhile, corresponding fuzzy radiuses are adopted for different image sub-blocks to perform fuzzy processing, so that the image fuzzy has higher pertinence, the layering sense of the blurred target image is improved, the diversified image fuzzy processing requirements of users are met, and the user experience is improved.
Description
Technical Field
The present application relates to the field of information processing, and in particular, to an image processing method and apparatus.
Background
At present, with the continuous development of image processing technology, for different application scenes, a target image is subjected to corresponding image processing to obtain a required target image, for example, in order to improve the aesthetic degree of the image, the target image needs to be subjected to beauty processing, and for example, in order to protect privacy content included in the image, the target image needs to be subjected to blurring processing, and as the degree of emphasis of a user on the privacy of the user is continuously increased, the image needs to be subjected to blurring processing more and more.
Currently, an image blur processing method is provided in the prior art, and the method mainly includes: the method comprises the steps of obtaining a target image to be subjected to image blurring, determining a blurring radius used when the target image is subjected to image blurring, and integrally blurring the target image based on the blurring radius by using a preset blurring algorithm.
Therefore, the image blurring processing method in the prior art directly performs blurring processing on the whole target image, has the problems of single image blurring processing mode and poor flexibility, and cannot meet the diversified image blurring processing requirements of users.
Disclosure of Invention
The embodiment of the application aims to provide an image processing method and device, a partition fuzzy processing mode is adopted for a target image, meanwhile, corresponding fuzzy radiuses are adopted for different image sub-blocks for fuzzy processing, so that image blurring is more targeted, the layering sense of the blurred target image is improved, diversified image blurring processing requirements of users are met, and the user experience is improved.
In order to solve the above technical problem, the embodiment of the present application is implemented as follows:
the embodiment of the application provides an image processing method, which comprises the following steps:
after receiving an image blurring processing request, acquiring a target image to be subjected to image blurring processing;
carrying out region division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing;
respectively determining fuzzy radiuses corresponding to the divided image subblocks, wherein the fuzzy radiuses are determined according to user setting information and/or related information of the image subblocks and are used for representing fuzzy degrees corresponding to the image subblocks;
and for each image subblock, respectively carrying out image blurring processing on the image subblock according to the blurring radius of the image subblock to obtain a target image after blurring processing.
An embodiment of the present application provides an image processing apparatus, including:
the image acquisition module is used for acquiring a target image to be subjected to image blurring processing after receiving an image blurring processing request;
the image dividing module is used for carrying out region division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing;
the fuzzy radius determining module is used for respectively determining fuzzy radii corresponding to the image subblocks obtained by dividing, wherein the fuzzy radii are determined according to user setting information and/or related information of the image subblocks and are used for representing fuzzy degrees corresponding to the image subblocks;
and the image blurring module is used for respectively carrying out image blurring processing on the image subblocks according to the blurring radius of the image subblock to obtain a target image after blurring processing.
An embodiment of the present application provides an image processing apparatus, including: a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to implement the following:
after receiving an image blurring processing request, acquiring a target image to be subjected to image blurring processing;
carrying out region division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing;
respectively determining fuzzy radiuses corresponding to the divided image subblocks, wherein the fuzzy radiuses are determined according to user setting information and/or related information of the image subblocks and are used for representing fuzzy degrees corresponding to the image subblocks;
and for each image subblock, respectively carrying out image blurring processing on the image subblock according to the blurring radius of the image subblock to obtain a target image after blurring processing.
Embodiments of the present application provide a storage medium for storing computer-executable instructions, which when executed implement the following processes:
after receiving an image blurring processing request, acquiring a target image to be subjected to image blurring processing;
carrying out region division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing;
respectively determining fuzzy radiuses corresponding to the divided image subblocks, wherein the fuzzy radiuses are determined according to user setting information and/or related information of the image subblocks and are used for representing fuzzy degrees corresponding to the image subblocks;
and for each image subblock, respectively carrying out image blurring processing on the image subblock according to the blurring radius of the image subblock to obtain a target image after blurring processing.
According to the image processing method and device in the embodiment of the application, after an image blurring request is received, a target image to be subjected to image blurring processing is obtained; carrying out region division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing; respectively determining fuzzy radiuses corresponding to the divided image subblocks; and for each image sub-block, respectively carrying out image blurring processing on the image sub-block according to the blurring radius of the image sub-block to obtain a target image after blurring processing. In the embodiment of the application, the target image is subjected to partition fuzzy processing, and meanwhile, corresponding fuzzy radiuses are adopted for different image sub-blocks to perform fuzzy processing, so that the image fuzzy has higher pertinence, the layering sense of the blurred target image is improved, the diversified image fuzzy processing requirements of users are met, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.
Fig. 1 is a first flowchart of an image processing method according to an embodiment of the present application;
fig. 2 is a schematic diagram illustrating an implementation principle of blurring a target image according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram illustrating an implementation principle of establishing a coordinate system of a target image according to an embodiment of the present disclosure;
fig. 4 is a second flowchart of an image processing method according to an embodiment of the present application;
fig. 5 is a third flowchart illustrating an image processing method according to an embodiment of the present application;
fig. 6 is a schematic diagram illustrating an implementation principle of performing region division on a target image in an image processing method according to an embodiment of the present application;
fig. 7 is a fourth flowchart illustrating an image processing method according to an embodiment of the present application;
fig. 8 is a schematic block diagram of an image processing apparatus according to an embodiment of the present disclosure;
fig. 9 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The embodiment of the application provides an image processing method and device, a partition fuzzy processing mode is adopted for a target image, meanwhile, corresponding fuzzy radiuses are adopted for different image sub-blocks for fuzzy processing, so that image blurring is more targeted, the layering of the blurred target image is improved, diversified image blurring processing requirements of users are met, and the user experience is improved.
Fig. 1 is a first flowchart schematic diagram of an image processing method according to an embodiment of the present application, where an execution subject of the method in fig. 1 may be a computer device or a mobile terminal device, as shown in fig. 1, the method at least includes the following steps:
s101, after receiving an image blurring processing request, acquiring a target image to be subjected to image blurring processing; specifically, the image blurring processing request may be generated based on a user selecting a target image and clicking an image blurring control, or may be generated based on voice information input by the user.
S102, carrying out region division processing on the obtained target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing; specifically, in the process of performing the area division on the target image, the division mode may be determined based on a manual area division operation of a user, the division mode may be automatically determined based on image information of the target image, or the division mode may be determined by combining two modes of system automatic determination and user manual selection, that is, a plurality of partition options are given according to the image information of the target image, and the division mode is determined according to a designated option selected by the user for the partition option.
S103, determining respective corresponding fuzzy radiuses of the divided image subblocks respectively, wherein the fuzzy radiuses are determined according to user setting information and/or related information of the image subblocks and are used for representing respective corresponding fuzzy degrees of the image subblocks; specifically, after the target image is subjected to partition processing, a matched blur radius needs to be determined for each image sub-block, wherein in the process of determining the blur radius of each image sub-block, the blur radius of the corresponding image sub-block can be determined based on a numerical value selected by a user, the blur radius of the image sub-block can be automatically determined based on the related information of the image sub-block, or the blur radius of the image sub-block can be determined by combining the automatic determination of the system and the manual selection of the user, that is, a plurality of blur radius options are provided according to the related information of each image sub-block, and the blur radius of each image sub-block is determined according to a designated option selected by the user for the blur radius option.
S104, respectively carrying out image blurring processing on each image sub-block according to a blurring radius corresponding to the image sub-block to obtain a target image after blurring processing; specifically, after determining the respective blur radius for each image sub-block, the blur radius is used to perform blur processing on the corresponding image sub-block, so as to generate the required blurred image.
In the embodiment of the application, the mode of carrying out partition fuzzy processing on the target image is adopted, and meanwhile, corresponding fuzzy radiuses are adopted for carrying out fuzzy processing on different image sub-blocks, so that the image blurring is more targeted, the layering sense of the blurred target image is improved, the effect of adjusting the depth of field is achieved, the diversified image fuzzy processing requirements of users are met, and the user experience is improved.
Fig. 2 is a schematic diagram illustrating an implementation principle of blurring a target image according to an embodiment of the present application, specifically, as shown in fig. 2, first, a target image to be subjected to image blurring is obtained based on an image blurring request;
then, determining a region division mode for the target image, and performing region division on the target image based on the region division mode to obtain a plurality of image sub-blocks, wherein taking dividing the target image into 4 image sub-blocks as an example, in specific implementation, the division is performed according to actual requirements, and the graphic shape of each image sub-block can be a regular shape or an irregular shape;
thirdly, determining the respective corresponding fuzzy radiuses of the divided image subblocks, namely determining the respective corresponding fuzzy radiuses R of the image subblocks 1 to 41To R4；
And finally, carrying out fuzzy processing on each image sub-block in sequence based on the respective fuzzy radius of the image sub-blocks to obtain a target image after the fuzzy processing.
As shown in fig. 3, in order to facilitate marking of the positions of the image sub-blocks and marking of the pixels, a coordinate system is established for the target image according to a preset rule, coordinates (x, y) of the pixels in the target image are determined, each pixel corresponds to a coordinate, before blurring the image, each pixel corresponds to a RGB value before blurring, after blurring the image, each pixel corresponds to a RGB value after blurring, and therefore, a certain correspondence relationship exists between the coordinates and the RGB values;
the coordinates of the center pixel point at the center position of the target image may be defined as (0, 0), at this time, the coordinates of the previous pixel point of the center pixel point are (0, 1), the coordinates of the next pixel point of the center pixel point are (0, -1), the coordinates of the right pixel point of the center pixel point are (1, 0), and the coordinates of the left pixel point of the center pixel point are (-1, 0).
Further, considering that when the target image is blurred, because the partition blurring method is adopted for the target image, and meanwhile, different blurring radiuses are adopted for blurring different image sub-blocks, a situation that a difference between blurring degrees of adjacent pixel points is large may exist at a junction of two image sub-blocks, at this time, a blurring naturalness of the blurred target image is greatly reduced, and a visual experience effect of a user is affected, as shown in fig. 4, in the above S104, for each image sub-block, the image blurring process is respectively performed on the image sub-block according to the blurring radius corresponding to the image sub-block, and after the blurred target image is obtained, the method further includes:
s105, determining the position information of the junction of the subblocks in the target image according to the position information of each image subblock; specifically, when the target image is divided into regions based on the coordinate system of the target image in fig. 3, the position information of each image sub-block in the coordinate system obtained by the division is recorded, and therefore, the position information of the boundary between the image sub-blocks in the target image can be obtained by combining the position information of each image sub-block.
S106, determining a target pixel point to be subjected to smoothing processing and a fuzzy RGB value of the target pixel point according to the determined position information of the junction of the subblocks; specifically, based on the coordinate system of the target image in fig. 3, after the position information of the junction of the sub-blocks in the target image is determined, the pixel points within the preset range of the intersection line of every two adjacent image sub-blocks are determined as target pixel points to be subjected to smoothing processing, the coordinates of each target pixel point are determined, and the blurred RGB values of each target pixel point are determined according to the corresponding relationship between the coordinates and the blurred RGB values.
S107, respectively determining the smooth RGB values of the target pixel points according to the fuzzy RGB values of the target pixel points; specifically, based on the fuzzy RGB values of the specified number of target pixel points on two sides of the intersection line of every two adjacent image subblocks, the smoothing coefficient of each target pixel point is determined, and the smooth RGB value of each target pixel point is determined by combining the smoothing coefficient, so that the effect of smoothing the fuzzy degrees of the specified number of target pixel points on two sides of the intersection line of every two adjacent image subblocks is achieved.
S108, adjusting the RGB value of each target pixel point from the blurred RGB value to the smoothed RGB value to obtain a blurred and boundary-smoothed target image; specifically, after the smoothed RGB values of the target pixel points to be smoothed are determined, the RGB values of the corresponding pixel points are adjusted based on the smoothed RGB values of the target pixel points, so as to obtain a blurred and boundary-smoothed target image.
Specifically, the step S107 of determining the smoothed RGB values of the target pixel points according to the blurred RGB values of the target pixel points includes:
dividing target pixel points into a plurality of target pixel point sets to be subjected to smoothing processing according to position information of each target pixel point; specifically, based on the intersection line of two adjacent image sub-blocks, according to the position information of each target pixel point, the target pixel points on the line segment perpendicular to the intersection line are drawn into the same target pixel point set, for example, the target image is divided into an upper image sub-block and a lower image sub-block, at this time, the abscissa of the pixel points belonging to the same target pixel point set is the same, and each target pixel point set includes a preset number of pixel points located in the first image sub-block closest to the intersection point and a preset number of pixel points located in the second image sub-block closest to the intersection point.
Step two, aiming at each target pixel point set, respectively determining a smoothing coefficient of each target pixel point according to the fuzzy RGB value of each target pixel point in the target pixel point set by utilizing a linear interpolation method, wherein the smoothing coefficient plays a role in adjusting the RGB value of every two adjacent target pixel points, so that the RGB value difference value between every two adjacent target pixel points is within a preset range;
and step three, respectively determining the smoothed RGB value of each target pixel point according to the blurred RGB value of each target pixel point and the smoothing coefficient of the target pixel point, specifically, multiplying the blurred RGB value of the target pixel point by the corresponding smoothing coefficient of the blurred RGB value of the target pixel point aiming at each target pixel point, and obtaining the smoothed RGB value of the target pixel point.
In the embodiment of the application, the mode of partitioning the target image is taken into consideration, meanwhile, different fuzzy radiuses are adopted for different image sub-blocks to perform fuzzy processing, so that the situation that the difference of the fuzzy degrees of adjacent pixel points is large possibly exists at the junction of the two image sub-blocks, the fuzzy naturalness of the blurred target image is greatly reduced at the moment, and the visual experience effect of a user is influenced.
As shown in fig. 5, for the target image partitioning process, in the step S102, performing region partitioning processing on the obtained target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing specifically includes:
s1021, performing image recognition processing on the target image, and extracting image information in the target image, specifically, extracting image information in the target image based on an image recognition algorithm;
s1022, determining location information of a plurality of image areas to be divided according to the area division information for the target image and the extracted image information, specifically, the area division information includes image separation information and a division manner of an image area that is not separated, for example, separation of human and object scenes, and the like, after determining the area division information for the target image, locating an image area that needs to be separated, and determining location information of at least one separated image area and location information of an image area that is not separated and divided into a plurality of image areas;
and S1023, performing area division processing on the target image according to the position information of the image areas to obtain a plurality of image sub-blocks to be subjected to image blurring processing.
The region division information for the target image is determined as follows:
the method comprises the steps that firstly, according to a region division request input by a user, region division information aiming at a target image is determined;
determining region division information for the target image according to a division rule corresponding to the target image;
determining the region division information aiming at the target image according to the selection operation of the user aiming at the automatically determined division option; specifically, a plurality of division options are determined and displayed according to the division rule corresponding to the target image, so that the requirement of the user for independent selection can be met, and the user can quickly select the required options.
Specifically, for a target image being a portrait image or a portrait image, it is necessary to perform blurring processing on a background image except for a portrait area or a portrait area, and since it is considered that a range of the background area is generally large, in order to improve a visual effect of a user and avoid a relatively abrupt blurring of a periphery of the portrait image or the portrait image, the background area may be divided into areas, and a division rule corresponding to the target image is determined in the following manner, specifically:
if an image area which does not need the blurring processing exists in the target image, determining a division rule corresponding to the target image according to the graph shape of the image area which does not need the blurring processing by taking the image area which does not need the blurring processing as a reference, wherein the division rule is to take the image area which does not need the blurring processing as one image sub-block and divide the image area which needs the blurring processing into a specified number of image sub-blocks.
For example, as shown in fig. 6, the target image is a photograph containing a soccer ball, and the soccer ball is required not to be blurred, and the blurring processing is performed on the areas other than the soccer ball, in this case, it is necessary to locate the position information of the soccer ball in the target image, and to divide a plurality of concentric circles outward with the soccer ball as the center of the circle, so that a plurality of image sub-blocks obtained by dividing the target image include: an image sub-block 1 including a soccer ball, and image sub-blocks 2 to 5 other than the soccer ball.
For the process of determining the blur radius of the image sub-blocks, the step S103 of determining the respective blur radius corresponding to each divided image sub-block specifically includes:
receiving a fuzzy radius setting request of a user for each image subblock, and determining the fuzzy radius of the image subblock according to the setting request;
in a second mode, the blur radius of each image sub-block is determined according to the relevant information of the image sub-block, wherein the relevant information includes: at least one of image content information, position information, and pre-blur RGB value distribution;
and thirdly, receiving the selection operation of the user for the plurality of automatically determined fuzzy radius options, and determining the fuzzy radius of each image sub-block according to the selection operation.
Specifically, after dividing the target image according to the graphic shape of the image region that does not need the blurring processing, if the relevant information is the position information, the blurring radius of each image sub-block is determined according to the relevant information of the image sub-block, specifically:
determining the blur radius of the image subblock needing the blur processing according to the spacing distance between the image subblock needing the blur processing and the image subblock not needing the blur processing, wherein the blur radius is positively correlated with the spacing distance, namely the larger the spacing distance is, the larger the blur radius of the corresponding image subblock is. For example, after the target image is divided according to the image area division rule in fig. 7, the farther from the soccer, the larger the blur radius, the gradually increased blur degree, so that the blurred image is more natural in connection and has more layering.
Specifically, considering that in the process of automatically determining the blur radius, the more reference factors are introduced, the more accurate the determined blur radius is, and in order to improve the accuracy of the determined blur radius and improve the satisfaction degree of the user on the final image blur effect, in the embodiment of the present application, the blur radius of each image sub-block is determined comprehensively in combination with a plurality of relevant factors influencing the blur effect and in combination with the image blur preference of the user, and based on this, for the case that the types of the relevant information of the introduced image sub-blocks are multiple, the above-described determination of the blur radius of each image sub-block according to the relevant information of each image sub-block is specifically performed by:
acquiring a fuzzy radius determination model corresponding to a target account requesting image fuzzy processing, wherein the fuzzy radius determination model is obtained by utilizing a deep learning method and training based on a model training sample corresponding to the target account;
for each image sub-block, inputting the relevant information of the image sub-block into the obtained fuzzy radius determination model;
and determining the numerical value output by the fuzzy radius determination model as the fuzzy radius of the image sub-block.
The method includes the steps of training each target account in advance to obtain a corresponding fuzzy radius determination model, specifically, training the fuzzy radius determination models corresponding to the target accounts in the following manner, specifically:
and judging whether the historical image fuzzy records under the target account meet preset conditions, wherein the historical image fuzzy records comprise the corresponding relation between image related information and fuzzy radiuses in a historical time period, and the preset conditions are that the number of the historical records is greater than a preset threshold value.
If so, taking the historical image fuzzy record under the target account as a model training sample of the target account;
and training to obtain a fuzzy radius determination model corresponding to the target account by utilizing a deep learning method based on the model training sample of the target account.
Specifically, when the historical image fuzzy record under the target account meets the preset condition, it is indicated that the information recorded in the historical image fuzzy record is sufficient, the more the information recorded in the historical image fuzzy record is, the better the image fuzzy preference of the user can be reflected, the record is used as a model training sample, and a fuzzy radius determination model corresponding to the target account is obtained through training, so that the higher the accuracy of the fuzzy radius determined by subsequently using the fuzzy radius determination model is.
If not, taking the first historical image fuzzy record under the target account and the second historical image fuzzy record under the reference account of the target account as model training samples of the target account, wherein the reference account of the target account and the target account have the same attribute information, and the attribute information comprises: at least one of age, occupation, hobby, gender, and identity of the user;
and training to obtain a fuzzy radius determination model corresponding to the target account by utilizing a deep learning method based on the model training sample of the target account.
Specifically, when the historical image fuzzy records under the target account do not meet the preset conditions, it is shown that the information recorded in the historical image fuzzy records is less, and at this time, the image fuzzy preference of the user cannot be determined comprehensively.
As shown in fig. 7, the step S104, for each image sub-block, of performing the image blurring process on the image sub-block according to the blurring radius corresponding to the image sub-block, to obtain the blurred target image specifically includes:
s1041, for each image sub-block, selecting a target pixel point of current blurring processing from a plurality of pixel points included in the image sub-block, specifically, selecting one pixel point from the plurality of pixel points included in the image sub-block as a target pixel point in sequence according to a preset rule;
s1042, determining a plurality of neighboring pixels of the target pixel according to the fuzzy radius corresponding to the image sub-block where the selected target pixel is located, specifically, the number of the neighboring pixels of the target pixel is R × R-1, where R is the fuzzy radius, for example, the fuzzy radius R is 3, at this time, the number of the neighboring pixels of the target pixel is 8, and taking the target pixel as a central pixel (0, 0) in the target image as an example, the neighboring pixels of the target pixel are: (0, 1), (0, -1), (1, 0), (-1, 0), (1, 1), (-1, -1), (-1, 1), (1, -1);
taking the fuzzy radius R as an example of 3, the number of the adjacent pixels of the target pixel is 8, and the pixel coordinate matrix of the central pixel (0, 0) is:
s1043, determining a blurred RGB value of the target pixel point according to the blurred front RGB value of the target pixel point and the blurred front RGB values of the adjacent pixel points of the target pixel point, specifically, after determining the coordinates of the adjacent pixel points of the target pixel point, obtaining the blurred front RGB value of each adjacent pixel point according to the corresponding relation between the coordinates and the blurred front RGB values, and obtaining the blurred rear RGB value of the target pixel point based on the blurred front RGB values;
s1044, judging whether the fuzzy RGB value of each pixel point in the image sub-block is determined;
if not, continuing to execute the step S1041;
if so, executing S1045, and adjusting the RGB value of each pixel point in the target image from the RGB value before blurring of the pixel point to the RGB value after blurring to obtain the target image after blurring.
Specifically, in S1043, determining the RGB value of the target pixel after the blurring according to the RGB value of the target pixel before the blurring and the RGB value of each adjacent pixel of the target pixel, specifically includes:
determining a pre-fuzzy RGB value matrix of a target pixel point according to the pre-fuzzy RGB value of the target pixel point and the pre-fuzzy RGB values of adjacent pixel points of the target pixel point;
after the coordinates of the adjacent pixel points of the target pixel point are determined, the RGB value before blurring of each adjacent pixel point can be obtained according to the corresponding relation between the coordinates and the RGB value before blurring, and a RGB value matrix before blurring of the target pixel point is obtained;
still taking the example that the blur radius R is 3, the number of the adjacent pixels of the target pixel is 8, and the RGB value matrix before the blur of the target pixel is:
wherein, a22The RGB values before blurring of the target pixel point are obtained, and the RGB values before blurring of 8 adjacent pixel points of the target pixel point are obtained.
Determining the weight coefficient of the target pixel point and the weight coefficient of each adjacent pixel point of the target pixel point according to the fuzzy radius of the image subblock where the target pixel point is located by using a specified fuzzy algorithm to obtain a fuzzy weight coefficient matrix of the target pixel point;
wherein specifying the fuzzy algorithm comprises: the image processing method comprises the following steps of Gaussian blur algorithm, mean value blur algorithm, radial blur, surface blur, shape blur and the like, which blur algorithm is selected by a user according to actual requirements, and the corresponding relation between the relevant information of the image and the blur algorithm can be stored in advance, so that the specified blur algorithm is determined based on the corresponding relation and the relevant information of the image sub-blocks.
Taking an appointed fuzzy algorithm as a gaussian fuzzy algorithm as an example, determining a fuzzy weight coefficient matrix of a target pixel point, specifically:
according to the formula
Calculating a weight coefficient of a target pixel point and a weight coefficient of each adjacent pixel point of the target pixel point, wherein gamma (x, y) represents the weight coefficient of the pixel point with coordinates (x, y), and R is a fuzzy radius;
still taking the example that the blur radius R is 3, the number of the adjacent pixels of the target pixel is 8, and the blur weight coefficient matrix of the target pixel is:
wherein, γ22The weight coefficients of the target pixel point and the weight coefficients of 8 adjacent pixel points of the target pixel point,
determining a fuzzy RGB value of the target pixel point according to the pre-fuzzy RGB value matrix and the fuzzy weight coefficient matrix of the target pixel point, and specifically, after determining the pre-fuzzy RGB value matrix and the fuzzy weight coefficient matrix of the target pixel point, calculating the sum of products of each pre-fuzzy RGB and the corresponding fuzzy weight coefficient to obtain the fuzzy RGB value of the target pixel point;
still taking the example that the blur radius R is 3, the number of the adjacent pixels of the target pixel is 8, and the RGB value of the target pixel after blurring is:
wherein, A is the fuzzy RGB value of the target pixel point, i is the row subscript of the matrix, and j is the column subscript of the matrix.
The image processing method in the embodiment of the application acquires a target image to be subjected to image blurring processing after receiving an image blurring processing request; carrying out region division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing; respectively determining fuzzy radiuses corresponding to the divided image subblocks; and for each image sub-block, respectively carrying out image blurring processing on the image sub-block according to the blurring radius of the image sub-block to obtain a target image after blurring processing. In the embodiment of the application, the target image is subjected to partition fuzzy processing, and meanwhile, corresponding fuzzy radiuses are adopted for different image sub-blocks to perform fuzzy processing, so that the image fuzzy has higher pertinence, the layering sense of the blurred target image is improved, the diversified image fuzzy processing requirements of users are met, and the user experience is improved.
On the basis of the same technical concept, corresponding to the image processing method described in fig. 1 to 7, an embodiment of the present application further provides an image processing apparatus, and fig. 8 is a schematic diagram of module composition of the image processing apparatus provided in the embodiment of the present application, the apparatus is configured to perform the image processing method described in fig. 1 to 7, and as shown in fig. 8, the apparatus includes:
an image obtaining module 801, configured to obtain a target image to be subjected to image blurring processing after receiving an image blurring processing request;
an image dividing module 802, configured to perform region division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing;
a blur radius determining module 803, configured to determine respective blur radii corresponding to the divided image sub-blocks, where the blur radii are determined according to user setting information and/or related information of the image sub-blocks, and are used to indicate respective corresponding blur degrees of the image sub-blocks;
and an image blurring module 804, configured to perform image blurring processing on each image sub-block according to the blurring radius of the image sub-block, so as to obtain a blurred target image.
Optionally, the apparatus further comprises: a sub-block boundary smoothing module 805, wherein the sub-block boundary smoothing module 805 is configured to:
determining the position information of the junction of the subblocks in the target image according to the position information of each image subblock;
determining a target pixel point to be subjected to smoothing processing and a fuzzy RGB value of the target pixel point according to the position information of the junction of the subblocks;
respectively determining the smooth RGB values of the target pixel points according to the fuzzy RGB values of the target pixel points;
and adjusting the RGB value of each target pixel point from the blurred RGB value to the smoothed RGB value to obtain a blurred and boundary-smoothed target image.
Optionally, the sub-block boundary smoothing module 805 is specifically configured to:
dividing the target pixel points into a plurality of target pixel point sets to be subjected to smoothing processing according to the position information of each target pixel point;
aiming at each target pixel point set, respectively determining a smooth coefficient of each target pixel point according to the fuzzy RGB value of each target pixel point in the target pixel point set by utilizing a linear interpolation method;
and respectively determining the smoothed RGB value of each target pixel point according to the blurred RGB value of each target pixel point and the smoothing coefficient of the target pixel point.
Optionally, the image dividing module 802 is specifically configured to:
carrying out image recognition processing on the target image, and extracting image information in the target image;
determining position information of a plurality of image areas to be divided according to area division information aiming at the target image and the extracted image information, wherein the area division information is determined according to an area division request input by a user, a division rule corresponding to the target image or a selection operation of the user aiming at an automatically determined division option;
and according to the position information of the image areas, carrying out area division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing.
Optionally, the blur radius determination module 803 is specifically configured to:
receiving a fuzzy radius setting request of a user for each image subblock, and determining the fuzzy radius of the image subblock according to the setting request;
alternatively, the first and second electrodes may be,
determining a blur radius of each image subblock according to related information of each image subblock, wherein the related information comprises: at least one of image content information, position information, and pre-blur RGB value distribution;
alternatively, the first and second electrodes may be,
and receiving selection operation of a user for a plurality of automatically determined fuzzy radius options, and determining the fuzzy radius of each image sub-block according to the selection operation.
Optionally, the image blurring module 804 is specifically configured to:
aiming at each image subblock, selecting a target pixel point of current fuzzy processing from a plurality of pixel points contained in the image subblock;
determining a plurality of adjacent pixel points of the target pixel point according to the fuzzy radius corresponding to the image subblock where the target pixel point is located;
determining a fuzzy RGB value of the target pixel point according to the RGB value before the target pixel point is fuzzy and the RGB value before the adjacent pixel points are fuzzy until the fuzzy RGB value of each pixel point in the image subblock is determined;
and adjusting the RGB value of each pixel point in the target image from the RGB value before blurring of the pixel point to the RGB value after blurring to obtain the target image after blurring processing.
Optionally, the image blurring module 804 is further specifically configured to:
determining a pre-fuzzy RGB value matrix of the target pixel point according to the pre-fuzzy RGB value of the target pixel point and the pre-fuzzy RGB values of the adjacent pixel points;
determining a weight coefficient of the target pixel point and a weight coefficient of each adjacent pixel point according to the fuzzy radius of the image subblock where the target pixel point is located by using a specified fuzzy algorithm to obtain a fuzzy weight coefficient matrix of the target pixel point;
and determining the fuzzy RGB value of the target pixel point according to the RGB value matrix before the fuzzy and the fuzzy weight coefficient matrix.
The image processing device in the embodiment of the application acquires a target image to be subjected to image blurring processing after receiving an image blurring processing request; carrying out region division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing; respectively determining fuzzy radiuses corresponding to the divided image subblocks; and for each image sub-block, respectively carrying out image blurring processing on the image sub-block according to the blurring radius of the image sub-block to obtain a target image after blurring processing. In the embodiment of the application, the target image is subjected to partition fuzzy processing, and meanwhile, corresponding fuzzy radiuses are adopted for different image sub-blocks to perform fuzzy processing, so that the image fuzzy has higher pertinence, the layering sense of the blurred target image is improved, the diversified image fuzzy processing requirements of users are met, and the user experience is improved.
It should be noted that the image processing apparatus provided in the embodiment of the present application and the image processing method provided in the embodiment of the present application are based on the same inventive concept, and therefore, for specific implementation of the embodiment, reference may be made to implementation of the foregoing image processing method, and repeated details are not described again.
Further, on the basis of the same technical concept, corresponding to the methods shown in fig. 1 to 7, an embodiment of the present application further provides an image processing apparatus for executing the image processing method, and fig. 9 is a schematic structural diagram of the image processing apparatus provided in the embodiment of the present application. .
As shown in fig. 9, the image processing apparatus may have a relatively large difference due to different configurations or performances, and may include one or more processors 901 and a memory 902, where one or more stored applications or data may be stored in the memory 902. Memory 902 may be, among other things, transient storage or persistent storage. The application stored in memory 902 may include one or more modules (not shown), each of which may include a series of computer-executable instructions for the image processing device. Still further, the processor 901 may be arranged in communication with the memory 902 for executing a series of computer executable instructions in the memory 902 on the image processing device. The image processing apparatus may also include one or more power supplies 903, one or more wired or wireless network interfaces 904, one or more input-output interfaces 905, one or more keyboards 906, and the like.
In one particular embodiment, an image processing apparatus includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the image processing apparatus, and the one or more programs configured to be executed by the one or more processors include computer-executable instructions for:
after receiving an image blurring processing request, acquiring a target image to be subjected to image blurring processing;
carrying out region division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing;
respectively determining fuzzy radiuses corresponding to the divided image subblocks, wherein the fuzzy radiuses are determined according to user setting information and/or related information of the image subblocks and are used for representing fuzzy degrees corresponding to the image subblocks;
and for each image subblock, respectively carrying out image blurring processing on the image subblock according to the blurring radius of the image subblock to obtain a target image after blurring processing.
Optionally, the computer executable instructions, when executed, further comprise computer executable instructions for:
after the image sub-blocks are respectively subjected to image blurring processing according to the blurring radius of the image sub-blocks to obtain a target image after the blurring processing, the method further comprises the following steps:
determining the position information of the junction of the subblocks in the target image according to the position information of each image subblock;
determining a target pixel point to be subjected to smoothing processing and a fuzzy RGB value of the target pixel point according to the position information of the junction of the subblocks;
respectively determining the smooth RGB values of the target pixel points according to the fuzzy RGB values of the target pixel points;
and adjusting the RGB value of each target pixel point from the blurred RGB value to the smoothed RGB value to obtain a blurred and boundary-smoothed target image.
Optionally, when executed, the determining, according to the blurred RGB values of the target pixel points, smoothed RGB values of the target pixel points respectively includes:
dividing the target pixel points into a plurality of target pixel point sets to be subjected to smoothing processing according to the position information of each target pixel point;
aiming at each target pixel point set, respectively determining a smooth coefficient of each target pixel point according to the fuzzy RGB value of each target pixel point in the target pixel point set by utilizing a linear interpolation method;
and respectively determining the smoothed RGB value of each target pixel point according to the blurred RGB value of each target pixel point and the smoothing coefficient of the target pixel point.
Optionally, when executed, the performing, by the computer-executable instructions, region division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing includes:
carrying out image recognition processing on the target image, and extracting image information in the target image;
determining position information of a plurality of image areas to be divided according to area division information aiming at the target image and the extracted image information, wherein the area division information is determined according to an area division request input by a user, a division rule corresponding to the target image or a selection operation of the user aiming at an automatically determined division option;
and according to the position information of the image areas, carrying out area division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing.
Optionally, when executed, the determining respective blur radii corresponding to the divided image sub-blocks includes:
receiving a fuzzy radius setting request of a user for each image subblock, and determining the fuzzy radius of the image subblock according to the setting request;
alternatively, the first and second electrodes may be,
determining a blur radius of each image subblock according to related information of each image subblock, wherein the related information comprises: at least one of image content information, position information, and pre-blur RGB value distribution;
alternatively, the first and second electrodes may be,
and receiving selection operation of a user for a plurality of automatically determined fuzzy radius options, and determining the fuzzy radius of each image sub-block according to the selection operation.
Optionally, when executed, the performing, by the computer executable instructions, image blurring on each image subblock according to the blur radius of the image subblock to obtain a blurred target image includes:
aiming at each image subblock, selecting a target pixel point of current fuzzy processing from a plurality of pixel points contained in the image subblock;
determining a plurality of adjacent pixel points of the target pixel point according to the fuzzy radius corresponding to the image subblock where the target pixel point is located;
determining a fuzzy RGB value of the target pixel point according to the RGB value before the target pixel point is fuzzy and the RGB value before the adjacent pixel points are fuzzy until the fuzzy RGB value of each pixel point in the image subblock is determined;
and adjusting the RGB value of each pixel point in the target image from the RGB value before blurring of the pixel point to the RGB value after blurring to obtain the target image after blurring processing.
Optionally, when executed, the determining, according to the RGB before blurring value of the target pixel and the RGB before blurring value of each of the adjacent pixels, a RGB after blurring value of the target pixel includes:
determining a pre-fuzzy RGB value matrix of the target pixel point according to the pre-fuzzy RGB value of the target pixel point and the pre-fuzzy RGB values of the adjacent pixel points;
determining a weight coefficient of the target pixel point and a weight coefficient of each adjacent pixel point according to the fuzzy radius of the image subblock where the target pixel point is located by using a specified fuzzy algorithm to obtain a fuzzy weight coefficient matrix of the target pixel point;
and determining the fuzzy RGB value of the target pixel point according to the RGB value matrix before the fuzzy and the fuzzy weight coefficient matrix.
The image processing device in the embodiment of the application acquires a target image to be subjected to image blurring processing after receiving an image blurring processing request; carrying out region division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing; respectively determining fuzzy radiuses corresponding to the divided image subblocks; and for each image sub-block, respectively carrying out image blurring processing on the image sub-block according to the blurring radius of the image sub-block to obtain a target image after blurring processing. Therefore, by means of the image processing device in the embodiment of the application, the target image is subjected to partition fuzzy processing, and meanwhile, corresponding fuzzy radiuses are adopted for different image sub-blocks to perform fuzzy processing, so that image blurring is more targeted, the layering sense of the blurred target image is improved, diversified image blurring processing requirements of users are met, and the user experience is improved.
Preferably, an embodiment of the present application further provides an image processing apparatus, which includes a processor 901, a memory 902, and a computer program stored in the memory 902 and capable of running on the processor 901, where the computer program, when executed by the processor 902, implements each process of the above-mentioned embodiment of the image processing method, and can achieve the same technical effect, and in order to avoid repetition, details are not described here again.
Further, corresponding to the methods shown in fig. 1 to fig. 7, based on the same technical concept, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the embodiment of the image processing method, and can achieve the same technical effect, and in order to avoid repetition, the description is omitted here. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are 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 an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (11)
1. An image processing method, comprising:
after receiving an image blurring processing request, acquiring a target image to be subjected to image blurring processing;
carrying out region division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing;
respectively determining fuzzy radiuses corresponding to the divided image subblocks, wherein the fuzzy radiuses are determined according to user setting information and/or related information of the image subblocks and are used for representing fuzzy degrees corresponding to the image subblocks;
for each image subblock, respectively carrying out image blurring processing on the image subblock according to the blurring radius of the image subblock to obtain a target image after blurring processing;
the region division processing is performed on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing, and the method comprises the following steps:
carrying out image recognition processing on the target image, and extracting image information in the target image;
determining position information of a plurality of image areas to be divided according to area division information aiming at the target image and the extracted image information, wherein the area division information is determined according to an area division request input by a user, a division rule corresponding to the target image or a selection operation of the user aiming at an automatically determined division option, the area division information comprises image separation information and a division mode of an unseparated image, and the image separation information comprises human scene separation or object scene separation;
and according to the position information of the image areas, carrying out area division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing.
2. The method according to claim 1, wherein after performing image blurring processing on each image sub-block according to the blur radius of the image sub-block to obtain a blurred target image, the method further comprises:
determining the position information of the junction of the subblocks in the target image according to the position information of each image subblock;
determining a target pixel point to be subjected to smoothing processing and a fuzzy RGB value of the target pixel point according to the position information of the junction of the subblocks;
respectively determining the smooth RGB values of the target pixel points according to the fuzzy RGB values of the target pixel points;
and adjusting the RGB value of each target pixel point from the blurred RGB value to the smoothed RGB value to obtain a blurred and boundary-smoothed target image.
3. The method of claim 2, wherein the determining the smoothed RGB values of the target pixels according to the blurred RGB values of the target pixels respectively comprises:
dividing the target pixel points into a plurality of target pixel point sets to be subjected to smoothing processing according to the position information of each target pixel point;
aiming at each target pixel point set, respectively determining a smooth coefficient of each target pixel point according to the fuzzy RGB value of each target pixel point in the target pixel point set by utilizing a linear interpolation method;
and respectively determining the smoothed RGB value of each target pixel point according to the blurred RGB value of each target pixel point and the smoothing coefficient of the target pixel point.
4. The method of claim 1, wherein the separately determining the respective blur radius corresponding to each of the divided image sub-blocks comprises:
receiving a fuzzy radius setting request of a user for each image subblock, and determining the fuzzy radius of the image subblock according to the setting request;
alternatively, the first and second electrodes may be,
determining a blur radius of each image subblock according to related information of each image subblock, wherein the related information comprises: at least one of image content information, position information, and pre-blur RGB value distribution;
alternatively, the first and second electrodes may be,
and receiving selection operation of a user for a plurality of automatically determined fuzzy radius options, and determining the fuzzy radius of each image sub-block according to the selection operation.
5. The method according to claim 1, wherein the step of, for each image sub-block, performing image blurring on the image sub-block according to the blur radius of the image sub-block to obtain a blurred target image comprises:
aiming at each image subblock, selecting a target pixel point of current fuzzy processing from a plurality of pixel points contained in the image subblock;
determining a plurality of adjacent pixel points of the target pixel point according to the fuzzy radius corresponding to the image subblock where the target pixel point is located;
determining a fuzzy RGB value of the target pixel point according to the RGB value before the target pixel point is fuzzy and the RGB value before the adjacent pixel points are fuzzy until the fuzzy RGB value of each pixel point in the image subblock is determined;
and adjusting the RGB value of each pixel point in the target image from the RGB value before blurring of the pixel point to the RGB value after blurring to obtain the target image after blurring processing.
6. The method of claim 5, wherein determining the post-blur RGB value for the target pixel based on the pre-blur RGB value for the target pixel and the pre-blur RGB values for each of the neighboring pixels comprises:
determining a pre-fuzzy RGB value matrix of the target pixel point according to the pre-fuzzy RGB value of the target pixel point and the pre-fuzzy RGB values of the adjacent pixel points;
determining a weight coefficient of the target pixel point and a weight coefficient of each adjacent pixel point according to the fuzzy radius of the image subblock where the target pixel point is located by using a specified fuzzy algorithm to obtain a fuzzy weight coefficient matrix of the target pixel point;
and determining the fuzzy RGB value of the target pixel point according to the RGB value matrix before the fuzzy and the fuzzy weight coefficient matrix.
7. An image processing apparatus characterized by comprising:
the image acquisition module is used for acquiring a target image to be subjected to image blurring processing after receiving an image blurring processing request;
the image dividing module is used for carrying out region division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing;
the fuzzy radius determining module is used for respectively determining fuzzy radii corresponding to the image subblocks obtained by dividing, wherein the fuzzy radii are determined according to user setting information and/or related information of the image subblocks and are used for representing fuzzy degrees corresponding to the image subblocks;
the image blurring module is used for respectively carrying out image blurring processing on the image subblocks according to the blurring radius of the image subblock to obtain a target image after blurring processing;
the image dividing module is specifically configured to:
carrying out image recognition processing on the target image, and extracting image information in the target image;
determining position information of a plurality of image areas to be divided according to area division information aiming at the target image and the extracted image information, wherein the area division information is determined according to an area division request input by a user, a division rule corresponding to the target image or a selection operation of the user aiming at an automatically determined division option, the area division information comprises image separation information and a division mode of an unseparated image, and the image separation information comprises human scene separation or object scene separation;
and according to the position information of the image areas, carrying out area division processing on the target image to obtain a plurality of image sub-blocks to be subjected to image blurring processing.
8. The apparatus of claim 7, further comprising: a sub-block junction smoothing module, wherein the sub-block junction smoothing module is configured to:
determining the position information of the junction of the subblocks in the target image according to the position information of each image subblock;
determining a target pixel point to be subjected to smoothing processing and a fuzzy RGB value of the target pixel point according to the position information of the junction of the subblocks;
respectively determining the smooth RGB values of the target pixel points according to the fuzzy RGB values of the target pixel points;
and adjusting the RGB value of each target pixel point from the blurred RGB value to the smoothed RGB value to obtain a blurred and boundary-smoothed target image.
9. The apparatus of claim 8, wherein the sub-block intersection smoothing module is specifically configured to:
dividing the target pixel points into a plurality of target pixel point sets to be subjected to smoothing processing according to the position information of each target pixel point;
aiming at each target pixel point set, respectively determining a smooth coefficient of each target pixel point according to the fuzzy RGB value of each target pixel point in the target pixel point set by utilizing a linear interpolation method;
and respectively determining the smoothed RGB value of each target pixel point according to the blurred RGB value of each target pixel point and the smoothing coefficient of the target pixel point.
10. The apparatus of claim 7, wherein the blur radius determination module is specifically configured to:
receiving a fuzzy radius setting request of a user for each image subblock, and determining the fuzzy radius of the image subblock according to the setting request;
alternatively, the first and second electrodes may be,
determining a blur radius of each image subblock according to related information of each image subblock, wherein the related information comprises: at least one of image content information, position information, and pre-blur RGB value distribution;
alternatively, the first and second electrodes may be,
and receiving selection operation of a user for a plurality of automatically determined fuzzy radius options, and determining the fuzzy radius of each image sub-block according to the selection operation.
11. The apparatus of claim 7, wherein the image blurring module is specifically configured to:
aiming at each image subblock, selecting a target pixel point of current fuzzy processing from a plurality of pixel points contained in the image subblock;
determining a plurality of adjacent pixel points of the target pixel point according to the fuzzy radius corresponding to the image subblock where the target pixel point is located;
determining a fuzzy RGB value of the target pixel point according to the RGB value before the target pixel point is fuzzy and the RGB value before the adjacent pixel points are fuzzy until the fuzzy RGB value of each pixel point in the image subblock is determined;
and adjusting the RGB value of each pixel point in the target image from the RGB value before blurring of the pixel point to the RGB value after blurring to obtain the target image after blurring processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810266817.1A CN108564541B (en) | 2018-03-28 | 2018-03-28 | Image processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810266817.1A CN108564541B (en) | 2018-03-28 | 2018-03-28 | Image processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108564541A CN108564541A (en) | 2018-09-21 |
| CN108564541B true CN108564541B (en) | 2022-04-15 |
Family
ID=63533202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810266817.1A Active CN108564541B (en) | 2018-03-28 | 2018-03-28 | Image processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108564541B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110728632B (en) * | 2019-09-04 | 2022-07-12 | 北京奇艺世纪科技有限公司 | Image blurring processing method, image blurring processing device, computer device and storage medium |
| CN111199514B (en) * | 2019-12-31 | 2022-11-18 | 无锡宇宁智能科技有限公司 | Image background blurring method, device and equipment and readable storage medium |
| CN112488964B (en) * | 2020-12-18 | 2024-04-16 | 深圳市镜玩科技有限公司 | Image processing method, related device, equipment and medium for sliding list |
| CN113225606B (en) * | 2021-04-30 | 2022-09-23 | 上海哔哩哔哩科技有限公司 | Video barrage processing method and device |
| CN114626978A (en) * | 2022-03-17 | 2022-06-14 | 北京字跳网络技术有限公司 | Image processing method and device, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101375588A (en) * | 2006-01-27 | 2009-02-25 | 微软公司 | Region-based image denoising |
| CN104375797A (en) * | 2014-11-17 | 2015-02-25 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN105787888A (en) * | 2014-12-23 | 2016-07-20 | 联芯科技有限公司 | Human face image beautifying method |
| CN107169920A (en) * | 2017-04-24 | 2017-09-15 | 深圳市金立通信设备有限公司 | A kind of intelligence repaiies drawing method and terminal |
| CN107454332A (en) * | 2017-08-28 | 2017-12-08 | 厦门美图之家科技有限公司 | Image processing method, device and electronic equipment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE112013004718B4 (en) * | 2012-09-26 | 2017-10-19 | Fujifilm Corporation | Image processing apparatus and method, and program, printer and display apparatus |
| CN103945118B (en) * | 2014-03-14 | 2017-06-20 | 华为技术有限公司 | Image weakening method, device and electronic equipment |
| JP6537083B2 (en) * | 2014-09-26 | 2019-07-03 | エスゼット ディージェイアイ テクノロジー カンパニー リミテッドＳｚ Ｄｊｉ Ｔｅｃｈｎｏｌｏｇｙ Ｃｏ．，Ｌｔｄ | Method and imager for automatic focusing |
| CN107578459A (en) * | 2017-08-31 | 2018-01-12 | 北京麒麟合盛网络技术有限公司 | Expression is embedded in the method and device of candidates of input method |
-
2018
- 2018-03-28 CN CN201810266817.1A patent/CN108564541B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101375588A (en) * | 2006-01-27 | 2009-02-25 | 微软公司 | Region-based image denoising |
| CN104375797A (en) * | 2014-11-17 | 2015-02-25 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN105787888A (en) * | 2014-12-23 | 2016-07-20 | 联芯科技有限公司 | Human face image beautifying method |
| CN107169920A (en) * | 2017-04-24 | 2017-09-15 | 深圳市金立通信设备有限公司 | A kind of intelligence repaiies drawing method and terminal |
| CN107454332A (en) * | 2017-08-28 | 2017-12-08 | 厦门美图之家科技有限公司 | Image processing method, device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108564541A (en) | 2018-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564541B (en) | Image processing method and device | |
| US9483835B2 (en) | Depth value restoration method and system | |
| CN111031346B (en) | Method and device for enhancing video image quality | |
| EP3077898B1 (en) | Editing options for image regions | |
| WO2019228167A1 (en) | Makeup-assisting method and device and intelligent mirror | |
| CN110264405B (en) | Image processing method, device, server and storage medium based on interpolation algorithm | |
| CN111104704B (en) | Cabinet internal layout design method, device and system and storage medium | |
| CN112541867A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| US8983188B1 (en) | Edge-aware smoothing in images | |
| CN108111911A (en) | Video data real-time processing method and device based on the segmentation of adaptive tracing frame | |
| CN114255187A (en) | Multi-level and multi-level image optimization method and system based on big data platform | |
| CN108038491B (en) | Image classification method and device | |
| CN111144215B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN114373444B (en) | Method, system and equipment for synthesizing voice based on montage | |
| CN110264505B (en) | Monocular depth estimation method and device, electronic equipment and storage medium | |
| CN113269280B (en) | Text detection method and device, electronic equipment and computer readable storage medium | |
| CN113709560B (en) | Video editing method, device, equipment and storage medium | |
| CN114168052A (en) | Multi-graph display method, device, equipment and storage medium | |
| CN113592714A (en) | Image amplification method, module and system | |
| CN106340024B (en) | A kind of image partition method, application and calculate equipment | |
| CN113344001A (en) | Organism weight estimation method, device, equipment and storage medium | |
| CN112085025B (en) | Object segmentation method, device and equipment | |
| CN113450282A (en) | Method and system for beautifying image | |
| JP4401475B2 (en) | A method for identifying image frames suitable for printing | |
| JP6375778B2 (en) | Image processing method and image processing apparatus |
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 |