CN115311147A - 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 PDF

Info

Publication number
CN115311147A
CN115311147A CN202110488365.3A CN202110488365A CN115311147A CN 115311147 A CN115311147 A CN 115311147A CN 202110488365 A CN202110488365 A CN 202110488365A CN 115311147 A CN115311147 A CN 115311147A
Authority
CN
China
Prior art keywords
filtering
preset
parameter
value
values
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110488365.3A
Other languages
Chinese (zh)
Inventor
门泽华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Insta360 Innovation Technology Co Ltd
Original Assignee
Insta360 Innovation Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Insta360 Innovation Technology Co Ltd filed Critical Insta360 Innovation Technology Co Ltd
Priority to CN202110488365.3A priority Critical patent/CN115311147A/en
Priority to PCT/CN2022/089154 priority patent/WO2022233251A1/en
Publication of CN115311147A publication Critical patent/CN115311147A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G06T5/70—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20024—Filtering details
    • G06T2207/20032—Median filtering

Landscapes

  • Facsimile Image Signal Circuits (AREA)
  • Image Processing (AREA)

Abstract

The application relates to an image processing method, an image processing device, electronic equipment and a storage medium, wherein the electronic equipment carries out filtering processing on an image to be processed according to a preset value of a first filtering parameter, and determines alternative values of a plurality of sampling points of the image to be processed, which correspond to the first filtering parameter, respectively; in a plurality of corresponding preset values when the filtering results of the sampling points meet preset constraint conditions of a preset filtering model, the noise of the filtering results corresponding to the alternative values is lower than the noise of the filtering results corresponding to other preset values; smoothing the alternative values of the plurality of sampling points corresponding to the first filtering parameter to obtain a plurality of sampling points corresponding to the target values of the first filtering parameter; and filtering the image to be processed according to the plurality of sampling points corresponding to the target value of the first parameter, and outputting a processing result of the image to be processed. By adopting the method, the filtering effect can be improved, the image processing result is smoother, and the filtering effect is better.

Description

Image processing method, image processing device, electronic equipment and storage medium
Technical Field
The present application relates to the field of image processing technologies, and in particular, to an image processing method and apparatus, an electronic device, and a storage medium.
Background
In the process of processing image data by the electronic device, filtering processing is usually required to be performed on the acquired image data, so as to reduce noise signals in the image data.
In the traditional method, a spatial domain filtering model or a time domain filtering model can be adopted to process image data, so that the processed image is smoother; for example, the filter model may be a gaussian filter model. In general, the filtering effect of the gaussian filter model varies with the variation of the model parameters, for example, when the sliding window in the gaussian filter model is larger, the filtering effect is better. In order to achieve a certain filtering effect, a preset constraint condition is usually set in the gaussian filtering model to constrain the filtered data. When a large sliding window is used to perform filtering processing on image data, filtering results corresponding to a part of time points or spatial points may not satisfy preset constraint conditions. In general, in order to enable the filtering results corresponding to all time points or spatial points to satisfy the preset constraint condition, the length of the sliding window of the gaussian filtering model needs to be reduced, resulting in poor filtering effect of the image data.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an image processing method, an apparatus, an electronic device, and a storage medium capable of improving a filtering effect.
An image processing method, the method comprising:
filtering the image to be processed according to the preset value of the first filtering parameter, and respectively determining the alternative values of the plurality of sampling points of the image to be processed, which correspond to the first filtering parameter; in a plurality of corresponding preset values when the filtering results of the sampling points meet preset constraint conditions of a preset filtering model, the noise of the filtering results corresponding to the alternative values is lower than that of the filtering results corresponding to other preset values;
smoothing the alternative values of the plurality of sampling points corresponding to the first filtering parameter to obtain target values of the plurality of sampling points corresponding to the first filtering parameter;
and filtering the image to be processed according to the target value of the first parameter corresponding to the plurality of sampling points, and outputting the processing result of the image to be processed.
In one embodiment, the noise corresponding to the filtering result obtained by presetting the filtering model changes monotonically with the change of the first filtering parameter.
In one embodiment, the filtering the image to be processed according to the preset value of the first filter parameter, and respectively determining that the plurality of sampling points of the image to be processed correspond to the alternative values of the first filter parameter includes:
determining a preset value corresponding to the lowest noise as an initial value of the first filtering parameter according to the monotone change relation between the noise of the filtering result and the first filtering parameter;
for each sampling point of the image to be processed, filtering data of the sampling point by adopting an initial value to obtain an initial processing result of the sampling point;
if the initial processing result meets the preset constraint condition, determining the initial value as an alternative value of the sampling point corresponding to the first filtering parameter;
if the initial processing result does not meet the preset constraint condition, searching an alternative value in the preset value; and the filtering result corresponding to the alternative value meets the preset constraint condition and is closest to the initial value.
In one embodiment, the searching for the alternative value from the preset values includes:
on the basis of the initial value, adjusting the initial value according to a preset gradient until a filtering result corresponding to the adjusted initial value meets a preset constraint condition;
and determining a preset value corresponding to the filtering result meeting the preset constraint condition as an alternative value of the sampling point corresponding to the first filtering parameter.
In one embodiment, the searching for the alternative value from the preset values includes:
and searching for an alternative value of the sampling point corresponding to the first filtering parameter by adopting a bisection method in the preset value by taking the initial value as a starting point.
In one embodiment, the filtering the image to be processed according to the preset value of the first filter parameter, and respectively determining that the plurality of sampling points of the image to be processed correspond to the alternative values of the first filter parameter includes:
traversing all preset values of the first filtering parameter for each sampling point of the image to be processed to obtain N preset values meeting preset constraint conditions;
and determining the noise of the filtering result corresponding to the N preset values, and selecting the preset value with the lowest noise as the alternative value of the sampling point corresponding to the first filtering parameter.
In one embodiment, the smoothing the alternative values of the plurality of sampling points corresponding to the first filter parameter to obtain the target values of the plurality of sampling points corresponding to the first filter parameter includes:
determining sampling points corresponding to alternative values different from the initial values as control points;
keeping the alternative values of the control points unchanged, and performing curve fitting processing on the alternative values of other sampling points to obtain a parameter fitting curve;
and determining the fitting value corresponding to each sampling point in the parameter fitting curve as the target value corresponding to the first filtering parameter of the sampling point.
In one embodiment, the predetermined filtering model is a gaussian filtering model, and the first filtering parameter is a sliding window or a standard deviation of the gaussian filtering model.
An image processing apparatus, the apparatus comprising:
the determining module is used for performing filtering processing on the image to be processed according to the preset value of the first filtering parameter and respectively determining the alternative values of the first filtering parameter corresponding to the plurality of sampling points of the image to be processed; in a plurality of corresponding preset values when the filtering results of the sampling points meet preset constraint conditions of a preset filtering model, the noise of the filtering results corresponding to the alternative values is lower than the noise of the filtering results corresponding to other preset values;
the processing module is used for smoothing the alternative values of the plurality of sampling points corresponding to the first filtering parameter to obtain target values of the plurality of sampling points corresponding to the first filtering parameter;
and the filtering module is used for performing filtering processing on the image to be processed according to the plurality of sampling points corresponding to the target value of the first parameter and outputting the processing result of the image to be processed.
An electronic device comprising a memory storing a computer program and a processor implementing the following steps when the computer program is executed:
filtering the image to be processed according to the preset value of the first filtering parameter, and respectively determining the alternative values of the plurality of sampling points of the image to be processed, which correspond to the first filtering parameter; in a plurality of corresponding preset values when the filtering results of the sampling points meet preset constraint conditions of a preset filtering model, the noise of the filtering results corresponding to the alternative values is lower than the noise of the filtering results corresponding to other preset values;
smoothing the alternative values of the plurality of sampling points corresponding to the first filtering parameter to obtain target values of the plurality of sampling points corresponding to the first filtering parameter;
and filtering the image to be processed according to the target value of the first parameter corresponding to the plurality of sampling points, and outputting the processing result of the image to be processed.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
filtering the image to be processed according to the preset value of the first filtering parameter, and respectively determining the alternative values of the plurality of sampling points of the image to be processed, which correspond to the first filtering parameter; in a plurality of corresponding preset values when the filtering results of the sampling points meet preset constraint conditions of a preset filtering model, the noise of the filtering results corresponding to the alternative values is lower than that of the filtering results corresponding to other preset values;
smoothing the alternative values of the plurality of sampling points corresponding to the first filtering parameter to obtain a plurality of sampling points corresponding to the target values of the first filtering parameter;
and filtering the image to be processed according to the plurality of sampling points corresponding to the target value of the first parameter, and outputting a processing result of the image to be processed.
According to the image processing method, the image processing device, the electronic equipment and the storage medium, the electronic equipment carries out filtering processing on the image to be processed according to the preset value of the first filtering parameter, and the candidate values of the first filtering parameter corresponding to the plurality of sampling points of the image to be processed are respectively determined; in a plurality of corresponding preset values when the filtering results of the sampling points meet preset constraint conditions of a preset filtering model, the noise of the filtering results corresponding to the alternative values is lower than the noise of the filtering results corresponding to other preset values; then, smoothing the alternative values of the plurality of sampling points corresponding to the first filtering parameter to obtain target values of the plurality of sampling points corresponding to the first filtering parameter; and finally, filtering the image to be processed according to the plurality of sampling points corresponding to the target value of the first parameter, and outputting a processing result of the image to be processed. The electronic equipment determines the alternative values of the first filtering parameters corresponding to the plurality of sampling points, so that the value of the first filtering parameter with the best filtering effect meeting the preset constraint condition can be determined for each sampling point, and the best filtering effect is obtained under the condition that the filtering result of each sampling point meets the preset constraint condition; furthermore, as the electronic device performs smoothing processing on each alternative value to obtain the target value corresponding to each sampling point, after the data of each sampling point is processed through the target value, the obtained image processing result is smoother, and the filtering effect is better.
Drawings
FIG. 1 is a flow diagram illustrating a method for image processing in one embodiment;
FIG. 2 is a flow diagram that illustrates a method for image processing according to one embodiment;
FIG. 3 is a flow diagram illustrating a method for image processing according to one embodiment;
FIG. 4 is a flowchart illustrating an image processing method according to another embodiment;
FIG. 5 is a diagram illustrating an image processing method according to an embodiment;
FIG. 6 is a diagram illustrating a method of image processing according to one embodiment;
FIG. 7 is a block diagram showing a configuration of an image processing apparatus according to an embodiment;
FIG. 8 is a block diagram showing a configuration of an image processing apparatus according to an embodiment;
FIG. 9 is a block diagram showing the configuration of an image processing apparatus according to an embodiment;
FIG. 10 is a block diagram showing the configuration of an image processing apparatus according to an embodiment;
FIG. 11 is a diagram of the internal structure of an electronic device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The image processing method can be applied to electronic equipment, and the electronic equipment can perform data processing on image data to reduce noise in the image data. The electronic device may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The electronic device can also be a camera, a video camera and other imaging devices; the camera may be, but is not limited to, a general camera, a pocket camera, an anti-shake camera, a Virtual Reality (VR) panoramic camera, a motion camera, a consumer-grade or professional-grade panoramic camera, and the like.
In one embodiment, as shown in fig. 1, an image processing method is provided, which is described by taking the application of the method to the electronic device in fig. 1 as an example, and includes:
s101, filtering an image to be processed according to a preset value of a first filtering parameter, and respectively determining alternative values of a plurality of sampling points of the image to be processed, wherein the alternative values correspond to the first filtering parameter; and in a plurality of preset values corresponding to the condition that the filtering results of the sampling points meet the preset constraint conditions of the preset filtering model, the noise of the filtering results corresponding to the alternative values is lower than the noise of the filtering results corresponding to other preset values.
The image to be processed may be data acquired by the electronic device, or may be data sent by other devices and received by the electronic device, which is not limited herein. The image to be processed may be a single frame image or a video including a plurality of frames. The sampling points may be time sampling points in the image to be processed, or may also be spatial sampling points in the image to be processed, which is not limited herein. For example, the image lower than the single shot image may be data of a time sampling point corresponding to the shooting time; for video, the data of the spatial sampling points may be data acquired at different times for the same spatial position. The plurality of sampling points may be each sampling point in the image to be processed, or may be one sampling point in one of the sampling intervals in the image to be processed.
The preset filtering model can perform spatial domain filtering processing on the image to be processed, and also can perform time domain filtering processing on the image to be processed, so that noise in the image to be processed is reduced. The noise may be redundant interference information in the image to be processed, which affects the display effect of the image. The preset filtering model may be a gaussian filter, a median filter, an average filter, or the like, and the type of the preset filtering model is not limited herein. The gaussian filter may be a one-dimensional gaussian filter or a two-dimensional gaussian filter.
The first filtering parameter may be a model parameter in a preset filtering model, and is related to a filtering effect of the preset filtering model, for example, a sliding window in a median filter. The filtering effect may be noise in an image processing result obtained after the preset filtering model processes the image to be processed, may also be a noise reduction ratio of the preset filtering model to process the image to be processed, and may also be a signal-to-noise ratio of the image processing result, which is not limited herein; the better the filtering effect, the lower the noise in the image processing result after the characterization filtering. Optionally, noise corresponding to a filtering result obtained by presetting a filtering model changes monotonically with changes of the first filtering parameter. The noise of the filtering result obtained by the preset filtering model may change linearly with the change of the first filtering parameter, or may change nonlinearly and monotonically with the change of the first filtering parameter, which is not limited herein. The first filtering parameter may be positively correlated with the filtering effect of the preset filtering model, or negatively correlated with the filtering effect of the preset filtering model; and are not limited herein. Optionally, in a case that the preset filtering model is a gaussian filtering model, the first filtering parameter is a sliding window or a standard deviation of the gaussian filtering model.
The preset value of the first filtering parameter may be a preset range of the first filtering parameter, or may include a plurality of discrete values, which is not limited herein. For example, the preset value of the sliding window of the gaussian filter model may be a sliding window interval, e.g., [ A1, A2]; or sliding window values, such as A1, A2, A3 \8230 \ 8230; an, etc.; the specific form of the preset value is not limited herein.
The electronic equipment can respectively perform filtering processing on data of a plurality of sampling points in the image to be processed according to the preset value of the first filtering parameter to obtain a filtering result corresponding to the sampling point; further, the electronic device can determine an alternative value of the sampling point corresponding to the first filter parameter based on the filtering result. The purpose of the filtering process is to determine an alternative value corresponding to the sampling point. The alternative value is one of preset values of the first filtering parameter, and in a plurality of corresponding preset values under the condition that the filtering result of the sampling point meets the preset constraint condition of a preset filtering model, the noise of the filtering result corresponding to the alternative value is lower than the noise of the filtering results corresponding to other preset values; that is to say, after the data of the sampling point is filtered by the alternative value, the optimal filtering effect can be obtained when the filtering result meets the preset constraint condition.
The electronic device may select the candidate value according to the filtering result corresponding to each preset value in a traversal manner, or may search the candidate value in the preset value according to a preset search manner, which is not limited herein.
The preset constraint condition may be preset in the electronic device, or may be a condition obtained by adjusting with an image processing result of a previous image, and used for constraining an image processed by a preset filtering model; the preset constraint condition may be an upper limit of a filtering result corresponding to each sampling point, a lower limit of a filtering result corresponding to each sampling point, or a constraint of a variation range of data of the sampling point before and after being processed by the preset filtering model, so that after the data of the sampling point is processed by the preset filtering model, the difference between the data of the sampling point and the data before being processed cannot be too large.
S102, smoothing the alternative values of the plurality of sampling points corresponding to the first filtering parameter to obtain target values of the plurality of sampling points corresponding to the first filtering parameter.
After obtaining the alternative values corresponding to the first filter parameter at the plurality of sampling points, the alternative values may be discontinuous with the change of the sampling point positions, and the electronic device may smooth the alternative values. Specifically, the electronic device may connect the alternative values of each sampling point according to the position relationship of the sampling points, determine a discontinuous point in the connected curve, and make the curve smooth by adjusting the alternative values of the remaining sampling points around the discontinuous sampling point. The electronic device may sequentially adjust the candidate values of the other sampling points from near to far by using the discontinuous point as a starting point to obtain the target value of the first filtering parameter adjusted by each sampling point. It should be noted that, after the data of the sampling point is processed by using the target value, the obtained filtering result needs to satisfy the preset constraint condition.
S103, filtering the image to be processed according to the target value of the first parameter corresponding to the plurality of sampling points, and outputting the processing result of the image to be processed.
On the basis of the above steps, the electronic device may respectively adopt the target values corresponding to the sampling points to perform filtering processing on the data of the sampling points, obtain filtering results corresponding to the data of each sampling point, and output processing results corresponding to the image to be processed.
According to the image processing method, the electronic equipment carries out filtering processing on the image to be processed according to the preset value of the first filtering parameter, and the candidate values of the first filtering parameter corresponding to the plurality of sampling points of the image to be processed are respectively determined; in a plurality of corresponding preset values when the filtering results of the sampling points meet preset constraint conditions of a preset filtering model, the noise of the filtering results corresponding to the alternative values is lower than the noise of the filtering results corresponding to other preset values; then, smoothing the alternative values of the plurality of sampling points corresponding to the first filtering parameter to obtain target values of the plurality of sampling points corresponding to the first filtering parameter; and finally, filtering the image to be processed according to the target value of the first parameter corresponding to the plurality of sampling points, and outputting the processing result of the image to be processed. The electronic equipment determines the alternative values of the first filtering parameters corresponding to the plurality of sampling points, so that the value of the first filtering parameter with the best filtering effect meeting the preset constraint condition can be determined for each sampling point, and the best filtering effect is obtained under the condition that the filtering result of each sampling point meets the preset constraint condition; furthermore, as the electronic device performs smoothing processing on each alternative value to obtain the target value corresponding to each sampling point, after the data of each sampling point is processed through the target value, the obtained image processing result is smoother, and the filtering effect is better.
Fig. 2 is a schematic flowchart of an image processing method in an embodiment, where the embodiment relates to a manner of determining an alternative value by an electronic device, and on the basis of the embodiment, as shown in fig. 2, the step S101 includes:
s201, according to the monotone change relation between the noise of the filtering result and the first filtering parameter, determining a preset value corresponding to the lowest noise as an initial value of the first filtering parameter.
Under the condition that the noise corresponding to the filtering result changes monotonically with the change of the first filtering parameter, the electronic device may determine, according to preset values of the first filtering parameter of the preset filtering model, which preset value of the preset values corresponds to the filtering result with the lowest noise. Specifically, the electronic device may obtain a monotonic variation relationship between the noise of the filtering result and the first filtering parameter, for example, the monotonic variation relationship is that the larger the first filtering parameter is, the better the filtering effect is, the maximum value in the preset value may be determined by the electronic device as an initial value of the first filtering parameter, that is, the global optimal parameter; each sampling point in the image to be processed can obtain the best filtering effect by adopting the initial value, the obtained filtering result has the lowest noise, but the filtering results corresponding to part of the sampling points possibly do not meet the preset constraint condition. Accordingly, the above variation relationship is that the smaller the first filter parameter is, the better the filter effect is, the minimum value in the preset values may be determined by the electronic device as the initial value of the first filter parameter.
S202, aiming at each sampling point of the image to be processed, filtering data of the sampling point by adopting an initial value to obtain an initial processing result of the sampling point.
After obtaining the initial value of the first filtering parameter, the electronic device may set the first filtering parameter in the preset filtering model as the initial value, and then perform filtering processing on data corresponding to each sampling point in the multiple sampling points, so as to obtain an initial processing result of the sampling point.
And S203, if the initial processing result meets the preset constraint condition, determining the initial value as an alternative value of the sampling point corresponding to the first filtering parameter.
Further, for each sampling point, the electronic device may match the initial processing result of the sampling point with a preset constraint condition corresponding to the sampling point, and determine whether the initial processing result of the sampling point meets the preset constraint condition. If the initial processing result of the sampling point meets the preset constraint condition, the electronic device may determine the initial value as an alternative value of the first filtering parameter corresponding to the sampling point.
S204, if the initial processing result does not meet the preset constraint condition, searching an alternative value in the preset value; and the filtering result corresponding to the alternative value meets the preset constraint condition and is closest to the initial value.
If the initial processing result of the sampling point does not satisfy the preset constraint condition, the electronic device may search, according to the monotonic variation relationship of the noise of the filtering result along with the first filtering parameter, a preset value of which the corresponding filtering result satisfies the preset constraint condition from the preset values, and obtain an alternative value with the best filtering effect when the preset constraint condition is satisfied.
Because the noise of the filtering result obtained by presetting the filtering model changes monotonically with the change of the first filtering parameter, the electronic equipment can determine the searching direction of the alternative value according to the monotonic change relation of the noise of the filtering result with the first filtering parameter when searching the alternative value; for example, if the monotonic variation relationship is that the larger the first filtering parameter is, the lower the noise of the filtering result is, the electronic device may perform filtering processing on data of the sampling point by using a next preset value smaller than the initial value, and then determine whether the filtering result corresponding to the next preset value meets a preset constraint condition; if the monotonic variation relationship is that the smaller the first filter parameter is, the lower the noise of the filter result is, the data of the sampling point may be filtered by using the next preset value larger than the initial value, and then it is determined whether the filter result corresponding to the next preset value satisfies the preset constraint condition. Specifically, the electronic device adjusts the initial value according to a preset gradient on the basis of the initial value until a filtering result corresponding to the adjusted initial value meets a preset constraint condition; then, the preset value corresponding to the filtering result meeting the preset constraint condition is determined as the alternative value of the sampling point corresponding to the first filtering parameter.
For example, the first filtering parameter is a sliding window in a gaussian filtering model, and the preset value of the sliding window may include a plurality of window lengths arranged at equal intervals, which are A1, A2, and A3 \8230; a100; and, the larger the sliding window of the gaussian filter model is, the lower the noise of the filtering result is. The electronic device may set a100 as an initial value, if a filtering result does not satisfy a preset constraint condition of one of the sampling points when a100 is adopted by the sampling point, the electronic device may perform filtering processing on data of the sampling point by using a99, and if a filtering result corresponding to a99 satisfies the preset constraint condition, the electronic device may determine a99 as an alternative value of the sampling point corresponding to the first filtering parameter.
Optionally, when searching for the candidate value, the electronic device may further search for the candidate value corresponding to the first filtering parameter at the sampling point by using a bisection method in the preset value, with the initial value as a starting point. Continuing to take the gaussian filtering model as an example, when a filtering result of one of the sampling points adopts a100, and does not satisfy the preset constraint condition of the sampling point, the electronic device may adopt a80 to perform filtering processing on the data of the sampling point, and if the filtering result corresponding to the a80 satisfies the preset constraint condition, further adopt the a80 to perform filtering processing on the data of the sampling point; if the filtering result corresponding to the a90 does not satisfy the preset constraint condition, the electronic device may further search for a preset value satisfying the preset constraint condition between the a80 and the a90, and if the filtering result corresponding to the a90 satisfies the preset constraint condition, the electronic device may search for a preset value satisfying the preset constraint condition between the a90 and the a100 until a preset value with lower noise of the result satisfying the preset constraint condition is obtained, and determine the preset value as the alternative value of the sampling point corresponding to the first filtering parameter.
According to the image processing method, the electronic equipment can quickly obtain the alternative value of each sampling point corresponding to the first filtering parameter according to the monotone change relation between the first filtering parameter and the noise of the filtering result on the basis of determining the initial value, so that the optimal filtering effect is obtained under the condition that the filtering result of each sampling point meets the preset constraint condition.
Fig. 3 is a schematic flowchart of an image processing method in an embodiment, where the embodiment relates to a manner of determining an alternative value by an electronic device, and on the basis of the embodiment, as shown in fig. 3, the step S101 includes:
s301, traversing all preset values of the first filtering parameter aiming at each sampling point of the image to be processed to obtain N preset values meeting preset constraint conditions.
In another way of determining the candidate value, the electronic device may screen, for each sampling point, a plurality of preset values, in the preset values of the first filtering parameter, for which the filtering result corresponding to the sampling point meets the preset constraint condition. Specifically, when the preset value of the first filtering parameter is a plurality of discrete values, the electronic device may traverse all the preset values of the first filtering parameter for each sampling point of the image to be processed, to obtain N preset values that satisfy the preset constraint condition. Under the condition that the preset value of the first filtering parameter is a preset value interval, the electronic device may select a plurality of preset values in the preset value interval at preset intervals, and then traverse the plurality of preset values for each sampling point of the image to be processed to obtain N preset values meeting preset constraint conditions.
S302, determining the noise of the filtering result corresponding to the N preset values, and selecting the preset value with the lowest noise as the candidate value of the sampling point corresponding to the first filtering parameter.
On the basis of the above steps, the electronic device may further determine noise of the filtering result corresponding to the N preset values, and select a preset value with the lowest noise as an alternative value of the sampling point corresponding to the first filtering parameter.
According to the image processing method, under the condition that the filtering effect of the preset filtering model changes along with the first filtering parameter in a monotonous mode or in a non-monotonous mode, the electronic equipment can obtain the value of the first filtering parameter which meets the best filtering effect under the preset constraint condition by traversing all the preset values and screening out the N preset values of which the filtering results meet the preset constraint condition, and further through quantitative comparison of the filtering effect, the better image processing effect can be obtained.
Fig. 4 is a schematic flowchart of an image processing method in an embodiment, where the embodiment relates to a manner of determining an alternative value by an electronic device, and on the basis of the embodiment, as shown in fig. 4, the step S103 includes:
s401, determining sampling points corresponding to alternative values different from the initial values as control points.
On the basis of obtaining the alternative values corresponding to the sampling points, the electronic device may determine, as the control point, the sampling point corresponding to the alternative value different from the initial value according to a relationship between the alternative value and the initial value. If the larger the first filter parameter of the preset filter model is, the better the filter effect is, the alternative value different from the initial value is the alternative value smaller than the initial value; the smaller the first filter parameter of the preset filter model is, the better the filter effect is, and the alternative value different from the initial value is the alternative value larger than the initial value.
S402, keeping the alternative values of the control points unchanged, and performing curve fitting processing on the alternative values of other sampling points to obtain a parameter fitting curve.
In order to enable the alternative values of the sampling points to be continuously changed and enable the filtering results of the sampling points to meet the preset constraint condition, the electronic equipment can keep the alternative values of the control points unchanged, and curve fitting processing is carried out on the alternative values of other sampling points to obtain a parameter fitting curve. The curve fitting process may be a linear fitting process or a quadratic curve fitting process, and is not limited herein. Alternative values for each sampling point may be as shown in fig. 5, with the abscissa representing the sampling point and the ordinate representing the value of the first filtering parameter; the discontinuous points in the graph are control points, and after curve fitting processing is performed on the alternative values in fig. 5, a parameter fitting curve shown in fig. 6 can be obtained.
In a parameter fitting curve obtained by the electronic equipment, the fitting value of each sampling point is within the range of the preset value of the first filtering parameter. That is, if the first filter parameter of the preset filter model is larger, the filtering effect is better, in the fitting values of the sampling points, the fitting value of the control point is the same as the alternative value, and the fitting values of the other sampling points may be smaller than or equal to the initial value; if the smaller the first filter parameter of the preset filter model is, the better the filter effect is, in the fitting values of the sampling points, the fitting values of the control points are the same as the alternative values, and the fitting values of the other sampling points may be larger than or equal to the initial values.
And S403, determining the fitting value corresponding to each sampling point in the parameter fitting curve as the target value corresponding to the first filtering parameter of the sampling point.
On the basis of the steps, determining a fitting value corresponding to each sampling point in the parameter fitting curve as a target value corresponding to the first filtering parameter by using electrons; and then, filtering the image to be processed according to the plurality of sampling points corresponding to the target value of the first parameter, and outputting the processing result of the image to be processed. The electronic equipment can sequentially adopt the target values of all sampling points to filter the data of the sampling points according to the arrangement sequence of the sampling points, and output the processing result of the image to be processed.
According to the image processing method, the electronic equipment obtains the target value of each sampling point corresponding to the first filtering parameter by adopting the curve fitting mode, the noise of the filtering result of each sampling point is the lowest under the condition that the preset constraint condition is met, the image processing result of the image to be processed is smoother, the filtering effect is better, and the better image display effect is obtained.
It should be understood that although the various steps in the flow charts of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least some of the steps in fig. 2-4 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in fig. 7, there is provided an image processing apparatus including:
the determining module 10 is configured to perform filtering processing on the image to be processed according to the preset value of the first filtering parameter, and respectively determine candidate values of the first filtering parameter corresponding to the multiple sampling points of the image to be processed; in a plurality of corresponding preset values when the filtering results of the sampling points meet preset constraint conditions of a preset filtering model, the noise of the filtering results corresponding to the alternative values is lower than that of the filtering results corresponding to other preset values;
a processing module 20, configured to perform smoothing on the candidate values of the plurality of sampling points corresponding to the first filtering parameter to obtain target values of the plurality of sampling points corresponding to the first filtering parameter;
and the filtering module 30 is configured to perform filtering processing on the image to be processed according to the plurality of sampling points, where the plurality of sampling points correspond to the target value of the first parameter, and output a processing result of the image to be processed.
In an embodiment, on the basis of the above embodiment, the noise corresponding to the filtering result obtained by presetting the filtering model changes monotonically with the change of the first filtering parameter.
In an embodiment, on the basis of the above embodiment, as shown in fig. 8, the determining module 10 includes:
a first determining unit 101, configured to determine, according to a monotonic change relationship between noise of a filtering result and the first filtering parameter, a preset value corresponding to a lowest noise as an initial value of the first filtering parameter;
the processing unit 102 is configured to, for each sampling point of the image to be processed, perform filtering processing on data of the sampling point by using an initial value to obtain an initial processing result of the sampling point;
a second determining unit 103, configured to determine the initial value as an alternative value of the sampling point corresponding to the first filtering parameter when the initial processing result satisfies a preset constraint condition;
a searching unit 104, configured to search for an alternative value in the preset value when the initial processing result does not satisfy a preset constraint condition; and the filtering result corresponding to the alternative value meets a preset constraint condition and is closest to the initial value.
In an embodiment, on the basis of the foregoing embodiment, the search unit 104 is specifically configured to: on the basis of the initial value, adjusting the initial value according to a preset gradient until a filtering result corresponding to the adjusted initial value meets a preset constraint condition; and determining a preset value corresponding to the filtering result meeting the preset constraint condition as an alternative value of the sampling point corresponding to the first filtering parameter.
In an embodiment, on the basis of the foregoing embodiment, the search unit 104 is specifically configured to: and searching for an alternative value of the sampling point corresponding to the first filtering parameter by adopting a bisection method in the preset value by taking the initial value as a starting point.
In an embodiment, on the basis of the above embodiment, as shown in fig. 9, the determining module 10 includes:
a traversing unit 105, configured to traverse all preset values of the first filtering parameter for each sampling point of the image to be processed, to obtain N preset values that satisfy preset constraint conditions;
and the selecting unit 106 is configured to determine noise of the filtering result corresponding to the N preset values, and select a preset value with the lowest noise as an alternative value of the sampling point corresponding to the first filtering parameter.
In one embodiment, on the basis of the above embodiment, as shown in fig. 10, the processing module 20 includes:
a third determining unit 201 configured to determine a sampling point corresponding to an alternative value different from the initial value as a control point;
the fitting unit 202 is configured to keep the alternative values of the control points unchanged, and perform curve fitting processing on the alternative values of other sampling points to obtain a parameter fitting curve;
a fourth determining unit 203, configured to determine a fitting value corresponding to each sampling point in the parameter fitting curve as the sampling point corresponds to the target value for the first filtering parameter.
In one embodiment, based on the above embodiment, the preset filtering model is a gaussian filtering model, and the first filtering parameter is a sliding window or a standard deviation of the gaussian filtering model.
The image processing apparatus provided above may implement the above-mentioned embodiment of the image processing method, and the implementation principle and technical effects are similar, which are not described herein again.
For specific limitations of the image processing apparatus, reference may be made to the above limitations of the image processing method, which are not described in detail herein. The respective modules in the image processing apparatus described above may be wholly or partially implemented by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the electronic device, or can be stored in a memory in the electronic device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, an electronic device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 11. The electronic device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic equipment comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the electronic device is used for storing data processing data. The network interface of the electronic device is used for connecting and communicating with an external terminal through a network. The computer program is executed by a processor to implement an image processing method.
Those skilled in the art will appreciate that the architecture shown in fig. 11 is a block diagram of only a portion of the architecture associated with the subject application, and does not constitute a limitation on the electronic devices to which the subject application may be applied, and that a particular electronic device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, an electronic device is provided, comprising a memory having a computer program stored therein and a processor that when executing the computer program performs the steps of:
filtering the image to be processed according to the preset value of the first filtering parameter, and respectively determining the alternative values of the plurality of sampling points of the image to be processed, which correspond to the first filtering parameter; in a plurality of corresponding preset values when the filtering results of the sampling points meet preset constraint conditions of a preset filtering model, the noise of the filtering results corresponding to the alternative values is lower than that of the filtering results corresponding to other preset values;
smoothing the alternative values of the plurality of sampling points corresponding to the first filtering parameter to obtain target values of the plurality of sampling points corresponding to the first filtering parameter;
and filtering the image to be processed according to the target value of the first parameter corresponding to the plurality of sampling points, and outputting the processing result of the image to be processed.
In one embodiment, the noise corresponding to the filtering result obtained by presetting the filtering model changes monotonically with the change of the first filtering parameter.
In one embodiment, the processor, when executing the computer program, further performs the steps of: determining a preset value corresponding to the lowest noise as an initial value of the first filtering parameter according to the monotone change relation between the noise of the filtering result and the first filtering parameter; for each sampling point of the image to be processed, filtering data of the sampling point by adopting an initial value to obtain an initial processing result of the sampling point; if the initial processing result meets the preset constraint condition, determining the initial value as an alternative value of the sampling point corresponding to the first filtering parameter; if the initial processing result does not meet the preset constraint condition, searching a candidate value in the preset value; and the filtering result corresponding to the alternative value meets a preset constraint condition and is closest to the initial value.
In one embodiment, the processor, when executing the computer program, further performs the steps of: on the basis of the initial value, adjusting the initial value according to a preset gradient until a filtering result corresponding to the adjusted initial value meets a preset constraint condition; and determining a preset value corresponding to the filtering result meeting the preset constraint condition as an alternative value of the sampling point corresponding to the first filtering parameter.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and searching alternative values of the sampling points corresponding to the first filtering parameters by adopting a bisection method in the preset values by taking the initial values as starting points.
In one embodiment, the processor, when executing the computer program, further performs the steps of: traversing all preset values of the first filtering parameter for each sampling point of the image to be processed to obtain N preset values meeting preset constraint conditions; and determining the noise of the filtering result corresponding to the N preset values, and selecting the preset value with the lowest noise as the alternative value of the sampling point corresponding to the first filtering parameter.
In one embodiment, the processor, when executing the computer program, further performs the steps of: determining sampling points corresponding to alternative values different from the initial values as control points; keeping the alternative values of the control points unchanged, and performing curve fitting processing on the alternative values of other sampling points to obtain a parameter fitting curve; and determining the fitting value corresponding to each sampling point in the parameter fitting curve as the target value corresponding to the first filtering parameter of the sampling point.
In one embodiment, the predetermined filtering model is a gaussian filtering model, and the first filtering parameter is a sliding window or a standard deviation of the gaussian filtering model.
The implementation principle and technical effect of the electronic device provided by this embodiment are similar to those of the method embodiments described above, and are not described herein again.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, performs the steps of:
filtering the image to be processed according to the preset value of the first filtering parameter, and respectively determining the alternative values of the plurality of sampling points of the image to be processed, which correspond to the first filtering parameter; in a plurality of corresponding preset values when the filtering results of the sampling points meet preset constraint conditions of a preset filtering model, the noise of the filtering results corresponding to the alternative values is lower than that of the filtering results corresponding to other preset values;
smoothing the alternative values of the plurality of sampling points corresponding to the first filtering parameter to obtain target values of the plurality of sampling points corresponding to the first filtering parameter;
and filtering the image to be processed according to the target value of the first parameter corresponding to the plurality of sampling points, and outputting the processing result of the image to be processed.
In one embodiment, the noise corresponding to the filtering result obtained by presetting the filtering model changes monotonically with the change of the first filtering parameter.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining a preset value corresponding to the lowest noise as an initial value of the first filtering parameter according to the monotone change relation between the noise of the filtering result and the first filtering parameter; for each sampling point of the image to be processed, filtering data of the sampling point by adopting an initial value to obtain an initial processing result of the sampling point; if the initial processing result meets the preset constraint condition, determining the initial value as an alternative value of the sampling point corresponding to the first filtering parameter; if the initial processing result does not meet the preset constraint condition, searching a candidate value in the preset value; and the filtering result corresponding to the alternative value meets a preset constraint condition and is closest to the initial value.
In one embodiment, the computer program when executed by the processor further performs the steps of: on the basis of the initial value, adjusting the initial value according to a preset gradient until a filtering result corresponding to the adjusted initial value meets a preset constraint condition; and determining a preset value corresponding to the filtering result meeting the preset constraint condition as an alternative value of the sampling point corresponding to the first filtering parameter.
In one embodiment, the computer program when executed by the processor further performs the steps of: and searching for an alternative value of the sampling point corresponding to the first filtering parameter by adopting a bisection method in the preset value by taking the initial value as a starting point.
In one embodiment, the computer program when executed by the processor further performs the steps of: traversing all preset values of the first filtering parameter for each sampling point of the image to be processed to obtain N preset values meeting preset constraint conditions; and determining the noise of the filtering result corresponding to the N preset values, and selecting the preset value with the lowest noise as the alternative value of the sampling point corresponding to the first filtering parameter.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining sampling points corresponding to alternative values different from the initial values as control points; keeping the alternative values of the control points unchanged, and performing curve fitting processing on the alternative values of other sampling points to obtain a parameter fitting curve; and determining the fitting value corresponding to each sampling point in the parameter fitting curve as the target value corresponding to the first filtering parameter of the sampling point.
In one embodiment, the predetermined filtering model is a gaussian filtering model, and the first filtering parameter is a sliding window or a standard deviation of the gaussian filtering model.
The computer storage medium provided in this embodiment has similar implementation principles and technical effects to those of the above method embodiments, and is not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), for example.
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (11)

1. An image processing method, characterized in that the method comprises:
filtering an image to be processed according to a preset value of a first filtering parameter, and respectively determining a plurality of sampling points of the image to be processed corresponding to alternative values of the first filtering parameter; in a plurality of corresponding preset values when the filtering results of the sampling points meet preset constraint conditions of a preset filtering model, the noise of the filtering results corresponding to the alternative values is lower than that of the filtering results corresponding to other preset values;
smoothing the alternative values of the plurality of sampling points corresponding to the first filtering parameter to obtain target values of the plurality of sampling points corresponding to the first filtering parameter;
and filtering the image to be processed according to the target value of the first parameter corresponding to the plurality of sampling points, and outputting a processing result of the image to be processed.
2. The method according to claim 1, wherein the noise corresponding to the filtering result obtained by presetting the filtering model changes monotonically with the change of the first filtering parameter.
3. The method according to claim 2, wherein the filtering the image to be processed according to the preset value of the first filter parameter, and respectively determining that the plurality of sample points of the image to be processed correspond to the alternative values of the first filter parameter comprises:
determining a preset value corresponding to the lowest noise as an initial value of the first filtering parameter according to the monotone change relation between the noise of the filtering result and the first filtering parameter;
aiming at each sampling point of the image to be processed, filtering the data of the sampling point by adopting the initial value to obtain an initial processing result of the sampling point;
if the initial processing result meets a preset constraint condition, determining the initial value as an alternative value of the sampling point corresponding to the first filtering parameter;
if the initial processing result does not meet the preset constraint condition, searching for a candidate value in the preset value; and the filtering result corresponding to the alternative value meets a preset constraint condition and is closest to the initial value.
4. The method of claim 3, wherein searching for an alternative value among the preset values comprises:
on the basis of the initial value, adjusting the initial value according to a preset gradient until a filtering result corresponding to the adjusted initial value meets the preset constraint condition;
and determining a preset value corresponding to the filtering result meeting the preset constraint condition as an alternative value of the sampling point corresponding to the first filtering parameter.
5. The method of claim 3, wherein searching for an alternative value among the preset values comprises:
and searching the alternative value of the sampling point corresponding to the first filtering parameter by adopting a bisection method in the preset value by taking the initial value as a starting point.
6. The method according to claim 1, wherein the filtering the image to be processed according to the preset value of the first filter parameter, and respectively determining that the plurality of sample points of the image to be processed correspond to the alternative values of the first filter parameter comprises:
traversing all preset values of the first filtering parameter aiming at each sampling point of the image to be processed to obtain N preset values meeting preset constraint conditions;
and determining the noise of the filtering result corresponding to the N preset values, and selecting the preset value with the lowest noise as the alternative value of the sampling point corresponding to the first filtering parameter.
7. The method according to any one of claims 3 to 5, wherein said smoothing the alternative values of the plurality of samples corresponding to the first filtering parameter to obtain the target values of the plurality of samples corresponding to the first filtering parameter comprises:
determining sampling points corresponding to alternative values different from the initial values as control points;
keeping the alternative values of the control points unchanged, and performing curve fitting processing on the alternative values of other sampling points to obtain a parameter fitting curve;
and determining the fitting value corresponding to each sampling point in the parameter fitting curve as the target value corresponding to the first filtering parameter for the sampling point.
8. The method according to any one of claims 1 to 6, wherein the predetermined filter model is a Gaussian filter model, and the first filter parameter is a sliding window or a standard deviation of the Gaussian filter model.
9. An image processing apparatus, characterized in that the apparatus comprises:
the determining module is used for performing filtering processing on the image to be processed according to the preset value of the first filtering parameter and respectively determining the alternative values of a plurality of sampling points of the image to be processed corresponding to the first filtering parameter; in a plurality of corresponding preset values when the filtering results of the sampling points meet preset constraint conditions of a preset filtering model, the noise of the filtering results corresponding to the alternative values is lower than the noise of the filtering results corresponding to other preset values;
the processing module is used for smoothing the alternative values of the plurality of sampling points corresponding to the first filtering parameter to obtain target values of the plurality of sampling points corresponding to the first filtering parameter;
and the filtering module is used for filtering the image to be processed according to the target value of the first parameter corresponding to the plurality of sampling points and outputting the processing result of the image to be processed.
10. An electronic device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any of claims 1 to 8 when executing the computer program.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 8.
CN202110488365.3A 2021-05-06 2021-05-06 Image processing method, image processing device, electronic equipment and storage medium Pending CN115311147A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202110488365.3A CN115311147A (en) 2021-05-06 2021-05-06 Image processing method, image processing device, electronic equipment and storage medium
PCT/CN2022/089154 WO2022233251A1 (en) 2021-05-06 2022-04-26 Image processing method and apparatus, and electronic device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110488365.3A CN115311147A (en) 2021-05-06 2021-05-06 Image processing method, image processing device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN115311147A true CN115311147A (en) 2022-11-08

Family

ID=83853809

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110488365.3A Pending CN115311147A (en) 2021-05-06 2021-05-06 Image processing method, image processing device, electronic equipment and storage medium

Country Status (2)

Country Link
CN (1) CN115311147A (en)
WO (1) WO2022233251A1 (en)

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5960010B2 (en) * 2012-09-26 2016-08-02 日本電産サンキョー株式会社 Image processing apparatus, image processing method, and program
CN103823219B (en) * 2014-03-14 2016-03-02 中国科学院电子学研究所 The non local interfering synthetic aperture radar interferometric phase filtering method of adaptive iteration
CN110349080B (en) * 2019-06-10 2023-07-04 北京迈格威科技有限公司 Image processing method and device
CN110956594B (en) * 2019-11-27 2023-12-01 北京金山云网络技术有限公司 Image filtering method, device, electronic equipment and storage medium
CN111784733B (en) * 2020-07-06 2024-04-16 深圳市安健科技股份有限公司 Image processing method, device, terminal and computer readable storage medium
CN112651902A (en) * 2021-02-10 2021-04-13 江苏启阳半导体技术有限公司 Multi-frame filtering implementation method and system in image processing

Also Published As

Publication number Publication date
WO2022233251A1 (en) 2022-11-10

Similar Documents

Publication Publication Date Title
CN108154518B (en) Image processing method and device, storage medium and electronic equipment
CN110473137B (en) Image processing method and device
CN111522996B (en) Video clip retrieval method and device
US20150043826A1 (en) Image processing apparatus, image processing method, and program
CN110675404A (en) Image processing method, image processing apparatus, storage medium, and terminal device
WO2021115136A1 (en) Anti-shake method and apparatus for video image, electronic device, and storage medium
CN112749726B (en) Training method and device for target detection model, computer equipment and storage medium
CN110555526B (en) Neural network model training method, image recognition method and device
JP2014010621A (en) Image area dividing device by optimal image size, method and program
CN111988561A (en) Adaptive adjustment method and device for video analysis, computer equipment and medium
US10318816B2 (en) Method, system and apparatus for segmenting an image set to generate a plurality of event clusters
CN111754429A (en) Motion vector post-processing method and device, electronic device and storage medium
CN110689496B (en) Method and device for determining noise reduction model, electronic equipment and computer storage medium
CN115311147A (en) Image processing method, image processing device, electronic equipment and storage medium
CN110689565B (en) Depth map determination method and device and electronic equipment
CN110689478A (en) Image stylization processing method and device, electronic equipment and readable medium
CN115620017A (en) Image feature extraction method, device, equipment and storage medium
CN113723375B (en) Double-frame face tracking method and system based on feature extraction
CN115550558A (en) Automatic exposure method and device for shooting equipment, electronic equipment and storage medium
CN112565595B (en) Image jitter eliminating method, device, electronic equipment and storage medium
CN115514895B (en) Image anti-shake method, apparatus, electronic device, and computer-readable storage medium
CN117036490B (en) Method, device, computer equipment and medium for detecting preset bit offset of camera
WO2022213372A1 (en) Image dehazing method and apparatus, and electronic device and computer-readable medium
CN112884681B (en) Image shadow processing method and device, computer equipment and storage medium
CN114979608A (en) White balance adjustment method, white balance adjustment device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination