WO2020038065A1

WO2020038065A1 - Image processing method, terminal, and computer storage medium

Info

Publication number: WO2020038065A1
Application number: PCT/CN2019/090079
Authority: WO
Inventors: 胡允侃; 纪德威
Original assignee: 中兴通讯股份有限公司
Priority date: 2018-08-21
Filing date: 2019-06-05
Publication date: 2020-02-27
Also published as: CN110855876A; CN110855876B

Abstract

Disclosed by the embodiments of the present invention is an image processing method, the method comprising: acquiring a first image to be processed, and performing recognition on the first image to obtain a plurality of image regions; determining a region to be processed from among the plurality of image regions, and blurring an object in the region to be processed to obtain a second image; and acquiring a target image on the basis of the first image and the second image. Further simultaneously disclosed by the embodiments of the present invention are a terminal and a computer storage medium.

Description

Image processing method, terminal and computer storage medium

This application claims priority from Chinese patent application CN201810955721.6 entitled "An Image Processing Method, Terminal, and Computer Storage Medium" filed on August 21, 2018, the entire contents of which are incorporated herein by reference.

Technical field

The present invention relates to, but is not limited to, the field of image processing technologies, and in particular, to an image processing method, a terminal, and a computer storage medium.

Background technique

With the rapid development of mobile phones, cameras and other terminals, more and more people will use the terminal's image processing function to process images, and the diversity and convenience of people's terminal image processing functions are getting higher and higher in order to obtain good results. Display effects such as color balance, saturation adjustment, and background blur.

In the related art, in order to highlight an object in an image, an object other than the object in the image is subjected to a blurring process so that an object that has not been blurred is highlighted. However, when the related technology performs a blurring process on a specific object in an image, a situation of excessive blurring may occur, causing the user to fail to recognize the blurred object.

Summary of the Invention

In view of this, embodiments of the present invention desire to provide an image processing method, a terminal, and a computer storage medium, so as to avoid blurring when a specific object in an image is subjected to blurring, which may cause users to fail to recognize the blurring process Of the object.

To achieve the above object, the technical solution of the present invention is implemented as follows:

An image processing method, the method includes:

Acquiring a first image to be processed, and identifying the first image to obtain multiple image regions;

Determining a region to be processed from the plurality of image regions, and performing a blurring process on an object at the region to be processed to obtain a second image;

A target image is acquired based on the first image and the second image.

A terminal includes: a processor, a memory, and a communication bus;

The communication bus is used to implement a communication connection between the processor and the memory;

The processor is configured to execute a program of an image processing method in a memory to implement the following steps:

A target image is acquired based on the first image and the second image.

A computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the image processing method described above.

The image processing method, the terminal, and the computer storage medium provided in the embodiments of the present invention obtain a first image to be processed and identify the first image to obtain multiple image regions; determine the region to be processed from the multiple image regions, and The object at the area to be processed is blurred to obtain a second image; the target image is obtained based on the first image and the second image; thus, since the embodiment of the present invention is to blur the area to be processed of the first image, the first After the second image, the second image and the first image after blurring the area to be processed are combined, so as to avoid the blurring of the specific object in the image, which will cause the user to fail to recognize the blurring process. Of the object.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic flowchart of an image processing method according to an embodiment of the present invention;

2 is a schematic structural diagram of a terminal according to an embodiment of the present invention;

3 is a schematic diagram of an image change process according to an embodiment of the present invention;

4 is a schematic flowchart of another image processing method according to an embodiment of the present invention;

5 is a schematic flowchart of another image processing method according to an embodiment of the present invention;

6 is a schematic flowchart of an image processing method according to another embodiment of the present invention;

7 is a schematic flowchart of another image processing method according to another embodiment of the present invention;

8 is a schematic flowchart of an implementation manner of an image processing method according to an embodiment of the present invention;

FIG. 9 is a schematic structural diagram of another terminal according to an embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

It should be understood that “an embodiment of the present invention” or “the foregoing embodiment” mentioned throughout the specification means that a particular feature, structure, or characteristic related to the embodiment is included in at least one embodiment of the present invention. Therefore, "in the embodiments of the present invention" or "in the foregoing embodiments" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In various embodiments of the present invention, the size of the sequence numbers of the above processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not deal with the implementation process of the embodiment of the present invention Constitute any limitation. The sequence numbers of the foregoing embodiments of the present invention are only for description, and do not represent the superiority or inferiority of the embodiments.

It should be noted that the image processing method of any embodiment of the present invention is applied to a terminal. The terminal may be a mobile phone, a computer, a camera, or a tablet computer. The present invention does not limit the terminal, as long as the terminal can implement The image processing function of any embodiment of the invention is sufficient.

In image processing, in order to make the image more hierarchical, it is often necessary to blur the background of the image. For example, when a portrait is included in an image, the background other than the portrait is blurred to make the image more prominent.

An embodiment of the present invention provides an image processing method, which is applied to a terminal. As shown in FIG. 1, the method includes the following steps:

Step 101: The terminal acquires a first image to be processed, and recognizes the first image to obtain multiple image regions.

As shown in FIG. 2, the terminal may include an image processing module, a camera module, and an image display module. The image processing module may further include an image preprocessing module and an image scene enhancement module. In this embodiment, the image processing module may be a processor, the camera module may be an image collector, such as a camera, and the image display module may be a display screen. The step of recognizing the first image to obtain multiple image regions and the execution subject of the

following steps

102 and 103 are image scene enhancement modules.

There are multiple methods for obtaining the first image. For example, the image collector collects the first image and sends the first image to the processor, and the processor obtains the first image sent by the image collector; or the processor can call and process The processor acquires the first image through the first image stored in the memory connected to the communication bus. Optionally, before the user uses the camera to collect the first image, the user may choose to enable the preset function to implement the image processing method in this embodiment.

The first image may include multiple objects, and each object corresponds to an image area. Objects can be anything in the image, such as portraits, human eyes, big trees, and so on.

Recognizing the first image to obtain multiple image regions may include: identifying edges of objects in the first image to obtain multiple image regions.

After the edge of the object in the first image is recognized, the recognition result may also be output on the display screen of the terminal. For example, the edge of the object may be output on the display screen in a dashed or solid line. By outputting the recognition result on the display screen, the user can clearly know the result of the image recognition, which is convenient for the user's subsequent operations. In another embodiment, after the edge of the object in the first image is identified, the same image as the first image is still displayed on the display screen, but the processor has identified multiple image regions. In yet another embodiment, the display screen may display a plurality of image regions with a preset distance between each two adjacent image regions.

The processor may recognize edges of each object in the first image to obtain multiple image regions, and output all recognition results on a display screen. In this way, each object region in the image can be identified to avoid missing objects in the first image and thus missing key information in the image. In another embodiment, the processor may recognize edges of each object in the first image to obtain multiple image regions, and obtain a ratio of an area of each image region to the first image area in the multiple image regions, and The recognition result of the image area whose ratio of the area of the image area to the first image area is greater than a preset value is displayed on the display screen. For example, an image with a portrait may only show the recognition result of the head of the portrait on the display screen, but not the recognition result of the eyes of the portrait. For another example, an image with a big tree may display the recognition of the big tree only on the display As a result, the recognition result of each leaf is not displayed. In this way, the recognition result of each object in the image by the processor can be prevented from being displayed on the display screen, which not only causes display confusion but also makes it difficult for the user to select an image area that is too small.

Recognizing the edges of objects in the first image to obtain multiple image regions has multiple implementations: for example, using edge detection, multi-gradient detection, or a combination of edge detection and multi-gradient detection The edges are identified to obtain multiple image regions.

The method of edge detection can be an edge detection method based on Roberts operator, an edge detection method based on Sobel operator, an edge detection method based on Prewitt operator, an edge detection method based on Laplace operator, a combination of Gaussian and Laplacian (Laplacian of Gaussian, LOG) any one of the edge detection method of the operator, the edge detection method based on the Canny operator, the wavelet analysis method, the fuzzy algorithm, and the artificial neural network method.

The specific steps of the multi-gradient detection method are: extract the luminance component Y, color component Cb (blue chrominance component), Cr (red chrominance component), and depth component D of each pixel in the first image, and calculate different components Down the gradient image, and fuse the calculated gradient image for different directions (θ can take 0, π / 8, π / 4, 3π / 8, ..., 7π / 8), and take different after fusion The maximum value of the gradient value in the direction is used as the final gradient of the pixel (luminance gradient G _y , color gradient G _cb , G _cr , depth gradient G _d ), and the four gradients are fused to obtain a fused gradient, and based on The fused gradients yield multiple image regions. You can use linear weighting to fuse the 4 gradients. The specific formula is

i = 1,2,3,4. Where G _mix (x, y, θ) is the gradient of pixel point (x, y) in direction θ after fusion, α _i is the weight corresponding to the i-th gradient, and G _i (x, y, θ) is Before linear fusion, the gradient of the pixel (x, y) in the direction θ. In other embodiments, multiple image regions may be obtained based on any two components of the luminance component Y, the color component Cb, Cr, the depth component D, and other components. The specific steps are similar to the above steps, and are not repeated here.

Step 102: The terminal determines a region to be processed from a plurality of image regions, and performs a blurring process on an object at the region to be processed to obtain a second image.

The region to be processed is specifically an image region that needs to be blurred out of the multiple image regions. The region to be processed may be one image region among a plurality of image regions, or may be at least two image regions. For example, when M image regions are identified, the region to be processed may be m image regions, where 1 ≦ m ≦ M.

There are multiple implementations for determining a region to be processed from multiple image regions. For example, the processor may identify an image region having a preset feature from a plurality of image regions, such as a portrait region, an animal region, or a plant region, and use the identified image region having the preset feature as a region to be processed. For another example, the processor may obtain an operation instruction, and use an image area corresponding to the operation instruction as the area to be processed, or use an image area other than the image area corresponding to the operation instruction as the area to be processed.

Obtaining the second image by subjecting the object at the processing area to blurring may be: using the morphological filtering method to subject the subject at the processor area to blurring to obtain the second image. The morphological filtering method may be processing the area to be processed by using at least one operation method among corrosion operation, expansion operation, open operation, and closed operation. It should be understood that the size of the second image is the same as the size of the first image.

Step 103: The terminal obtains a target image based on the first image and the second image.

The target image may be acquired by fusing the first image and the second image.

In this embodiment, acquiring the target image based on the first image and the second image may include: fusing the image of the region corresponding to the region to be processed of the invention in the first image of the invention and the second image of the invention to obtain the target image of the invention. Specifically, the processor may fuse the image region after the blurring processing in the second image and the region to be processed in the first image to obtain a fused image region, and combine the fused image region with the first image. The reference region other than the region to be processed or the image region in the second image that is not subjected to the blurring processing is combined to obtain a target image.

Among them, the image fusion method may be an image fusion method based on pixel grayscale, an image fusion method based on principal component analysis (PCA) transformation, and a brightness, hue, and saturation (HIS) One of the transform fusion method and the image fusion method based on multi-resolution analysis, or a combination of at least two methods, performs image fusion. Among them, the image grayscale-based image fusion method may select a large image fusion method for a pixel grayscale value, a small image fusion method for a pixel grayscale value, or a weighted average image fusion method.

After the processor obtains the target image, it can output the target image to the display screen of the terminal.

In order to more clearly illustrate the process of processing the first image to obtain the target image in the embodiment of the present invention, please refer to FIG. 3. The first image is recognized to obtain four image areas: area A1, area B1, area C1, and area D1, that is, the first image I includes area A1, area B1, area C1, and area D1. In the determined area A1 and area B1, After the region to be processed, the region C1 and the region D1 are reference regions other than the region to be processed in the first image, and the processor continues to blur the objects in the region A1 and the region B1 to be processed to obtain a second image II. The second image includes area A2, area B2, area C1, and area D1. Area A2 and area B2 are areas after blurring area A1 and area B1, respectively, and then area A1, area B1, and area A2, area B2 performs fusion to obtain a fused image region, and combines the fused image region with regions C1 and D1 to obtain a target image III.

Because the embodiment of the present invention blurs the area to be processed of the first image, and obtains the second image, combines the second image after blurring the area to be processed with the first image, thereby avoiding specific changes in the image. When the object is blurred, there may be situations where the user is unable to recognize the blurred object due to excessive blur.

Based on the foregoing embodiments, an embodiment of the present invention provides an image processing method, which is applied to a terminal. As shown in FIG. 4, the method includes the following steps:

Step 201: The terminal acquires a first image to be processed.

Step 202: The terminal uses a first detection method to recognize the edges of the objects in the first image, and obtains multiple first recognition areas.

The first detection method is used to identify edges of objects in the first image.

In this embodiment, the first detection method may be an edge detection method.

Step 203: The terminal uses a second detection method to recognize the edge of the object in the first image, and obtains a plurality of second recognition regions.

The second detection method is used to identify edges of objects in the first image. The first detection method and the second detection method are two different detection methods.

In this embodiment, the second detection method may be a multi-gradient detection method. For specific steps of the multi-gradient detection method, refer to related descriptions in the first embodiment, and details are not described herein again. In other embodiments, the second detection method may also be an edge detection method different from the first detection method.

This embodiment does not limit the sequence of

steps

202 and 203. The processor may execute step 202 and then step 203; or may execute step 203 and then step 202; or step 202 and step 203 may be performed simultaneously.

Step 204: The terminal determines a plurality of image regions based on the plurality of first identification regions and the plurality of second identification regions.

Obtaining a plurality of image regions based on the first recognition result and the second recognition result includes: using a Bayesian probability problem to fuse the first recognition result and the second recognition result to obtain a plurality of image regions. The Bayesian probability problem is used to fuse a plurality of first recognition areas obtained by using the first detection method and a plurality of second recognition areas obtained by using the second detection method, which can improve the accuracy of identifying and obtaining a plurality of image areas.

In this embodiment, multiple image regions can be determined by: determining an accuracy rate of each first recognition region based on a display parameter of a pixel point in each first recognition region; and based on a pixel point in each second recognition region The display parameters of, determine the accuracy rate of each second recognition area; based on the plurality of first recognition areas, the plurality of second recognition areas, the accuracy rate of each first recognition area, and the accuracy rate of each second recognition area, Identify multiple image areas.

The display parameter may be at least one parameter such as a brightness parameter, a depth parameter, and a color parameter. The specific method of determining multiple image regions will be described below using the display parameter as an example of the brightness parameter. It should be understood that when the display parameters are other parameters, the method is similar and will not be repeated here. The processor may obtain the brightness value of each pixel, and obtain a statistics table of pixel brightness values on the first image; based on the display parameters of the pixels in each first recognition area and the statistics table of pixel brightness values, determine each The accuracy rate of the second recognition area; based on the display parameters of the pixels in each second recognition area and the pixel brightness value statistics table, determining the accuracy rate of each second recognition area, based on multiple first recognition areas, multiple first The two recognition areas, the accuracy rate of each first recognition area, and the accuracy rate of each second recognition area determine a plurality of image areas. For example, when the accuracy rate of the area E in the plurality of first recognition areas is higher than the accuracy rate of the area F corresponding to the area E in the plurality of second recognition areas, the area E is used as the image area obtained by the recognition, and vice versa , Then use the area F as the image area obtained by the recognition.

Step 205: The terminal determines a region to be processed from a plurality of image regions, and performs a blurring process on an object at the region to be processed to obtain a second image.

Step 206: The terminal acquires a target image based on the first image and the second image.

This embodiment supplements the steps of recognizing the first image to obtain multiple image regions in the first embodiment. For descriptions of the same steps and the same contents in the embodiment as in the foregoing embodiment, reference may be made to the foregoing embodiment. The description is not repeated here.

Since the image processing method of this embodiment determines a plurality of image regions obtained based on the plurality of first recognition regions and the plurality of second recognition regions, it is possible to synthesize each first recognition region and correspond to the first recognition region The recognition accuracy rate of the second recognition region is used to obtain multiple image regions, so that the multiple obtained image regions are more accurate.

Based on the foregoing embodiments, an embodiment of the present invention provides another image processing method, which is applied to a terminal. As shown in FIG. 5, the method includes the following steps:

Step 301: The terminal acquires a first image to be processed, and recognizes the first image to obtain multiple image regions.

Step 302: The terminal receives a first operation on the first image.

Specifically, the terminal may be provided with a display screen, and the first operation may be a user performing a click operation or a slide operation on the first image on the display screen. Alternatively, the terminal may be provided with a voice receiving unit. The first operation may be a user's voice input, so that the voice receiving unit sends the voice signal to the processor after receiving the voice signal, and the processor receives the voice signal for the first image.

The first image has a plurality of image regions, and the user may perform a first operation on any one of the plurality of image regions. For example, referring to FIG. 2, when the user wants to highlight the region B in the first image, the region B of the first image can be displayed on the display screen; or when the user wants to highlight the region A and the region in the first image At B, you can click area A and area B of the first image on the display.

Step 303: The terminal responds to the first operation and determines an image area corresponding to the first operation from a plurality of image areas to obtain a reference area.

In this embodiment, the terminal responds to the first operation and determines an image area corresponding to the first operation from a plurality of image areas, and obtaining the reference area may include: if the first operation meets a first preset condition, responding to the first operation and An image region corresponding to the first operation is determined from a plurality of image regions to obtain a reference region.

The first preset condition may be an operation performed an odd number of times on the same image area. For example, referring to FIG. 2, when the user clicks on the area B in the first image an odd number of times, the terminal receives the user's first Operation, in response to the first operation and determining an image area corresponding to the first operation from a plurality of image areas, to obtain a reference area.

Optionally, after responding to the first operation, the processor may further control the display screen to highlight the image area corresponding to the first operation, and the highlighting may include: changing the color or brightness of the image area corresponding to the first operation, or One operation sets the shadow of the corresponding image area. For example, referring to FIG. 2, when the user performs an odd number of click operations on the region B of the first image, the display screen increases the brightness of the object in the region B.

Optionally, the display screen may also provide the user with a "OK" or "Cancel All" selection box, so that the user can confirm the selected image area or cancel all selected image areas by clicking the selection box.

In this embodiment, the image area corresponding to the first operation is a reference area. In other embodiments, the image region corresponding to the first operation may be a region to be processed. That is, the processor can determine whether the first operation meets the first preset condition; if the first operation meets the first preset condition, respond to the first operation and determine an image area corresponding to the first operation from a plurality of image areas, and obtain Processing area. That is, the processor uses the image region corresponding to the first operation as a region to be processed.

In this embodiment, the terminal responds to the first operation and determines an image area corresponding to the first operation from multiple image areas. After obtaining the reference area, the terminal may also receive a second operation for the first image; if the second operation The second preset condition is satisfied, and an image region corresponding to the second operation is determined from a plurality of image regions in response to the second operation, and the image region corresponding to the second operation is set as a region to be processed.

The second operation may make the same operation as the first operation, such as an odd number of click operations or an odd number of slide operations, and the second preset condition is that the image area corresponding to the second operation is the same as the image area corresponding to the first operation. For example, referring to FIG. 2, after the user clicks on area B in the first image, if he wants to cancel the selection of area B, he can click on area B again.

Similarly, in other embodiments, when the terminal determines that the second operation satisfies the second preset condition, the terminal may set the image region corresponding to the operation from the region to be processed as the reference region.

Step 304: The terminal determines, from a plurality of image regions, a region other than the reference region as a region to be processed.

In this embodiment, the region to be processed is determined based on the reference region. In other embodiments, the reference region may be determined based on the region to be processed, that is, from a plurality of image regions, a region other than the region to be processed is determined as the reference region.

Step 305: The terminal performs a blurring process on the object at the area to be processed to obtain a second image.

Obtaining the second image by subjecting the object at the processing area to blurring may be: using the morphological filtering method to subject the subject at the processor area to blurring to obtain the second image. The morphological filtering method may be processing the area to be processed by using at least one operation method among corrosion operation, expansion operation, open operation, and closed operation.

Step 306: The terminal obtains a target image based on the first image and the second image.

This embodiment supplements the step of determining a region to be processed from a plurality of image regions in the first embodiment. For descriptions of the same steps and the same contents in the foregoing embodiment as in the foregoing embodiment, reference may be made to the description in the foregoing embodiment, and details are not described herein again.

With the image processing method of this embodiment, since the terminal can receive the first operation for the first image, use the image area corresponding to the first operation as the reference area, and determine that the area other than the reference area is the area to be processed. Therefore, the terminal can determine the area to be processed of the image and blur the area to be processed according to the user's selection, so that the user can determine the area to be processed according to his actual needs.

Based on the foregoing embodiments, an embodiment of the present invention provides an image processing method, which is applied to a terminal. As shown in FIG. 6, the method includes the following steps:

Step 401: The terminal acquires a third image to be processed.

There are multiple methods for acquiring the third image. For example, the image collector collects the third image and sends the third image to the processor, and the processor acquires the third image sent by the image collector; or the processor can call and process The processor acquires the third image through the third image stored in the memory connected to the communication bus. Optionally, before a user uses a camera to collect a third image, a preset function may be selected to enable the image processing method in this embodiment.

Step 402: The terminal filters and denoises the third image to obtain a first image.

The execution subject of this step is an image preprocessing module. There are multiple ways to filter and denoise the third image. In this embodiment, filtering and denoising the third image may be: denoising the third image by using a median filtering method. The median filtering method is a non-linear smoothing technique. It sets the gray value of each pixel to the median of the gray values of all pixels in a neighborhood window at that point. In other embodiments, filtering and denoising the third image may be: using a mean filtering method to denoise the third image. Mean filtering is a typical linear filtering algorithm. It refers to giving a template to the target pixel on the image. The template includes neighboring pixels around it (8 pixels around the target pixel as the center, forming a filtering template, that is, removing The target pixel itself), and then replace the original pixel value with the average of all pixels in the template.

Step 403: The terminal acquires a first image to be processed, and recognizes the first image to obtain multiple image regions.

The first image to be processed is obtained by filtering and denoising the third image.

Step 404: The terminal determines a region to be processed from a plurality of image regions, and performs a blurring process on an object at the region to be processed to obtain a second image.

Step 405: The terminal acquires a target image based on the first image and the second image.

This embodiment further supplements the step of acquiring the first image to be processed in the first embodiment. For descriptions of the same steps and the same contents in the foregoing embodiment as in the foregoing embodiment, reference may be made to the description in the foregoing embodiment, and details are not described herein again.

Because the first image in the image processing method of this embodiment is obtained by filtering and denoising the third image, it is possible to avoid interference of image noise when identifying the first image, and make the recognition result more accurate. .

Based on the foregoing embodiments, an embodiment of the present invention provides another image processing method, which is applied to a terminal. As shown in FIG. 7, the method includes the following steps:

Step 501: The terminal acquires a third image to be processed.

Step 502: The terminal filters and denoises the third image to obtain a first image.

Step 503: The terminal acquires a first image to be processed.

Step 504: The terminal uses the first detection method to recognize the edges of the objects in the first image, and obtains multiple first recognition areas.

Step 505: The terminal uses a second detection method to recognize the edge of the object in the first image, and obtains a plurality of second recognition regions.

This embodiment does not limit the sequence of

steps

504 and 505. The processor may execute step 504 and then execute 505; or may execute step 505 and then execute step 504; or step 504 and step 505 may be performed simultaneously.

Step 506: The terminal determines a plurality of image regions based on the plurality of first identification regions and the plurality of second identification regions.

Step 507: The terminal receives a first operation on the first image.

Step 508: The terminal responds to the first operation and determines an image area corresponding to the first operation from a plurality of image areas to obtain a reference area.

Step 509: The terminal determines an area other than the reference area from a plurality of image areas to be processed.

Step 510: The terminal performs a blurring process on an object at the region to be processed to obtain a second image.

Step 511: The terminal acquires a target image based on the first image and the second image.

For descriptions of the same steps and the same contents in the foregoing embodiment as in the foregoing embodiment, reference may be made to the description in the foregoing embodiment, and details are not described herein again.

The image processing method in this embodiment is described below with a specific implementation manner. With reference to FIG. 8, in this embodiment, an image is captured through an image collector of a terminal, and the captured image is subjected to median filtering and denoising, and the filtered image is saved, and then the edge detection and multi-processing are performed on the filtered image. Gradient detection, and use the Bayesian method to fuse the two detection results to ensure the accuracy of the detection and to accurately distinguish the scene from the background. At this time, a preview screen can appear on the display screen, and the different scenes in the preview picture are already different from the background. Differentiate, there are multiple virtual frames containing the scene; then, the user can select the touch points according to the needs, and can select the touch points for one or more scenes. Click the odd frame of the same scene for an odd number of times to consider the scene to be enhanced. Even-numbered times are considered to cancel enhancement. The user clicks on the terminal to segment the background and the target scene in the image, and puts the obtained background into the next operation. Then, the morphological filtering method is used to smooth the background of the obtained image, and The median filtered and denoised image is fused with the image background obtained by the morphological filtering method. The background is weakened to achieve the enhancement and highlighting of scenes and portraits. Finally, the enhanced image is output and the enhanced image is displayed on the display screen.

The image processing method provided in this embodiment can avoid the situation that when a specific object in an image is blurred, the user may fail to recognize the blurred object due to excessive blurring; each first recognition can be integrated The recognition accuracy rate of the region and the second recognition region corresponding to the first recognition region is to obtain multiple image regions, so that the multiple image regions obtained are more accurate; the region to be processed and the region to be processed can be determined according to the user's selection Blur, so that users can determine the area to be processed according to their actual needs; and can avoid the interference of image noise, making the recognition results more accurate.

Based on the foregoing embodiments, an embodiment of the present invention provides a terminal 6. The terminal may be applied to an image processing method provided by the embodiments corresponding to FIGS. 1 and 4 to 7. Referring to FIG. 9, the terminal may include : Processor 61, memory 62, and communication bus 63, where:

The communication bus 63 is used to implement a communication connection between the processor 61 and the memory 62.

The processor 61 is configured to execute a program of an image processing method stored in the memory 62 to implement the following steps:

Determining a region to be processed from a plurality of image regions, and performing a blurring process on an object at the region to be processed to obtain a second image;

A target image is acquired based on the first image and the second image.

In other embodiments of the present invention, the processor 61 is configured to execute the identification of the first image stored in the memory 62 to obtain multiple image regions, so as to implement the following steps:

Recognize the edges of objects in the first image to obtain multiple image regions.

In other embodiments of the present invention, the processor 61 is configured to perform recognition of an edge of an object in the first image stored in the memory 62 to obtain a plurality of image regions to implement the following steps:

Adopting a first detection method to recognize the edges of objects in the first image to obtain a plurality of first recognition regions;

Adopting a second detection method to recognize the edges of the objects in the first image to obtain a plurality of second recognition areas; wherein the first detection method and the second detection method are both used to identify the edges of the objects in the first image;

Based on the plurality of first recognition areas and the plurality of second recognition areas, a plurality of image areas are determined.

In other embodiments of the present invention, the processor 61 is configured to execute a plurality of image regions based on the plurality of first identification regions and the plurality of second identification regions stored in the memory 62 to implement the following steps:

Determining an accuracy rate of each first recognition area based on display parameters of pixels in each first recognition area;

Determining an accuracy rate of each second recognition area based on display parameters of pixels in each second recognition area;

A plurality of image regions are determined based on a plurality of first recognition regions, a plurality of second recognition regions, an accuracy rate of each first recognition region, and an accuracy rate of each second recognition region.

In other embodiments of the present invention, the processor 61 is configured to execute the determination of a region to be processed from a plurality of image regions stored in the memory 62 to implement the following steps:

Receiving a first operation on a first image;

Responding to the first operation and determining an image area corresponding to the first operation from a plurality of image areas to obtain a reference area;

From the plurality of image regions, a region other than the reference region is determined as a region to be processed.

In other embodiments of the present invention, the processor 61 is configured to execute a response to the first operation stored in the memory 62 and determine an image region corresponding to the first operation from a plurality of image regions to obtain a reference region to implement the following steps:

If the first operation satisfies the first preset condition, in response to the first operation and determining an image region corresponding to the first operation from a plurality of image regions, a reference region is obtained.

In other embodiments of the present invention, the processor 61 is configured to execute a response to the first operation stored in the memory 62 and determine an image region corresponding to the first operation from a plurality of image regions. After obtaining the reference region, the following steps are implemented: :

Receiving a second operation for the first image;

If the second operation meets the second preset condition, respond to the second operation and determine an image region corresponding to the second operation from a plurality of image regions, and set the image region corresponding to the second operation as a region to be processed.

In other embodiments of the present invention, the processor 61 is configured to execute the acquisition of the target image based on the first image and the second image stored in the memory 62 to implement the following steps:

The target image is obtained by fusing the image of the region corresponding to the region to be processed with the second image.

In other embodiments of the present invention, the processor 61 is configured to execute acquiring the first image stored in the memory 62 to implement the following steps:

Obtaining a third image to be processed;

Filter and denoise the third image to obtain a first image.

It should be noted that, for the specific implementation process of the steps performed by the processor in this embodiment, reference may be made to the implementation process in the image processing method provided by the embodiment corresponding to FIG. 1 and FIG. 4 to FIG.

Based on the foregoing embodiments, an embodiment of the present invention provides a computer-readable storage medium. The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement The following steps:

A target image is acquired based on the first image and the second image.

In other embodiments of the present invention, the one or more programs may be executed by one or more processors to identify the first image to obtain multiple image regions, so as to implement the following steps:

In other embodiments of the present invention, the one or more programs may be executed by one or more processors to recognize edges of objects in the first image to obtain a plurality of image regions to implement the following steps:

Adopting a second detection method to recognize the edges of objects in the first image to obtain a plurality of second recognition areas; wherein the first detection method and the second detection method are both used to identify the edges of the objects in the first image;

In other embodiments of the present invention, the one or more programs may be executed by one or more processors to determine a plurality of image regions based on a plurality of first recognition regions and a plurality of second recognition regions to implement the following steps:

In other embodiments of the present invention, the one or more programs may be executed by one or more processors to determine a region to be processed from a plurality of image regions to implement the following steps:

Receiving a first operation on a first image;

In other embodiments of the present invention, the one or more programs may be executed by one or more processors in response to the first operation and determining an image region corresponding to the first operation from a plurality of image regions to obtain a reference region to Implement the following steps:

In other embodiments of the present invention, the one or more programs may be executed by one or more processors in response to the first operation and determining an image region corresponding to the first operation from a plurality of image regions. After obtaining the reference region, To achieve the following steps:

Receiving a second operation for the first image;

In other embodiments of the present invention, the one or more programs may be executed by one or more processors to obtain a target image based on the first image and the second image to implement the following steps:

In other embodiments of the present invention, the one or more programs may be executed by one or more processors to acquire the first image to implement the following steps:

Obtaining a third image to be processed;

Filter and denoise the third image to obtain a first image.

It should be noted that the above processor may be an application specific integrated circuit (ASIC, Application Specific Integrated Circuit), a digital signal processor (DSP, Digital Signal Processor), a digital signal processing device (DSPD, Digital Signal Processing Device), programmable At least one of a logic device (PLD, Programmable Logic Device), field programmable gate array (FPGA, Field Programmable Gate Array), central processing unit (CPU, Central Processing Unit), controller, microcontroller, and microprocessor . Understandably, the electronic device that implements the foregoing processor function may also be other, which is not specifically limited in the embodiment of the present application.

It should be noted that the computer storage medium / memory may be a read-only memory (ROM), a programmable read-only memory (PROM), and an erasable programmable read-only memory (PROM Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Ferromagnetic Random Access Memory (FRAM), Flash Memory (Flash Memory) , Magnetic surface memory, compact disc, or read-only memory (CD-ROM) and other memories; it can also include one or any combination of the above terminals, such as mobile phones, computers, tablet devices , Personal digital assistants, etc.

It should be noted that, in this article, the terms "including", "including" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, It also includes other elements not explicitly listed, or elements inherent to such a process, method, article, or device. Without more restrictions, an element limited from the sentence "including a ..." does not exclude that there are other identical elements in the process, method, article, or device that includes the element.

The above-mentioned serial numbers of the embodiments of the present application are merely for description, and do not represent the superiority or inferiority of the embodiments.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods in the above embodiments can be implemented by means of software plus a necessary universal hardware platform, and of course, also by hardware, but in many cases the former is better. Implementation. Based on such an understanding, the technical solution of this application that is essentially or contributes to the existing technology can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, The optical disc) includes several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the embodiments of the present application.

This application is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented from computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, so that the instructions generated by the processor of the computer or other programmable data processing device are used to generate instructions Means for implementing the functions specified in one or more flowcharts and / or one or more blocks of the block diagrams.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to work in a particular manner such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, the instructions The device implements the functions specified in one or more flowcharts and / or one or more blocks of the block diagram.

These computer program instructions can also be loaded on a computer or other programmable data processing device, so that a series of steps can be performed on the computer or other programmable device to produce a computer-implemented process, which can be executed on the computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more flowcharts and / or one or more blocks of the block diagrams.

The above are only preferred embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the contents of the specification and drawings of the present application, or directly or indirectly used in other related technical fields Are included in the scope of patent protection of this application.

Claims

An image processing method, wherein the method includes:

Acquiring a first image to be processed, and identifying the first image to obtain multiple image regions;

Determining a region to be processed from the plurality of image regions, and performing a blurring process on an object at the region to be processed to obtain a second image;

A target image is acquired based on the first image and the second image.
The method according to claim 1, wherein the identifying the first image to obtain a plurality of image regions comprises:

Identify the edges of the objects in the first image to obtain the plurality of image regions.
The method according to claim 2, wherein said recognizing an edge of an object in said first image to obtain said plurality of image regions comprises:

Adopting a first detection method to recognize the edges of objects in the first image to obtain a plurality of first recognition areas;

A second detection method is used to recognize the edges of the objects in the first image to obtain a plurality of second recognition areas; wherein the first detection method and the second detection method are both used to identify the first image Edge of object

The plurality of image regions are determined based on the plurality of first recognition regions and the plurality of second recognition regions.
The method according to claim 3, wherein the determining the plurality of image regions based on the plurality of first recognition regions and the plurality of second recognition regions comprises:

Determining an accuracy rate of each first recognition area based on display parameters of pixels in each first recognition area;

Determining an accuracy rate of each second recognition area based on display parameters of pixels in each second recognition area;

Determining the plurality of image regions based on the plurality of first recognition regions, the plurality of second recognition regions, the accuracy rate of each of the first recognition regions, and the accuracy rate of each of the second recognition regions .
The method according to claim 1, wherein said determining a region to be processed from said plurality of image regions comprises:

Receiving a first operation on the first image;

Responding to the first operation and determining an image area corresponding to the first operation from the plurality of image areas to obtain a reference area;

From the plurality of image regions, a region other than the reference region is determined to be the region to be processed.
The method according to claim 5, wherein the responding to the first operation and determining an image area corresponding to the first operation from the plurality of image areas to obtain a reference area comprises:

If the first operation satisfies a first preset condition, in response to the first operation and determining an image region corresponding to the first operation from the plurality of image regions, the reference region is obtained.
The method according to claim 6, wherein in response to the first operation and determining an image area corresponding to the first operation from the plurality of image areas, after obtaining the reference area, further comprising:

Receiving a second operation for the first image;

If the second operation satisfies a second preset condition, respond to the second operation and determine from the plurality of image regions that an image region corresponding to the second operation is the region to be processed.
The method according to claim 1, wherein the acquiring a target image based on the first image and the second image comprises:

The target image is obtained by fusing an image of a region corresponding to the region to be processed with the second image in the first image.
The method according to claim 1, wherein the acquiring the first image comprises:

Obtaining a third image to be processed;

Filtering and denoising the third image to obtain the first image.
A terminal, wherein the terminal includes: a processor, a memory, and a communication bus;

The communication bus is used to implement a communication connection between the processor and the memory;

The processor is configured to execute a program of an image processing method in a memory to implement the following steps:

Acquiring a first image to be processed, and identifying the first image to obtain multiple image regions;

Determining a region to be processed from the plurality of image regions, and performing a blurring process on an object at the region to be processed to obtain a second image;

A target image is acquired based on the first image and the second image.
The terminal according to claim 10, wherein when the processor executes the step of blurring the object at the region to be processed to obtain a second image, the following steps may be further implemented:

Adopting a first detection method to recognize the edges of objects in the first image to obtain a plurality of first recognition areas;

A second detection method is used to recognize the edges of the objects in the first image to obtain a plurality of second recognition areas; wherein the first detection method and the second detection method are both used to identify the first image Edge of object

The plurality of image regions are determined based on the plurality of first recognition regions and the plurality of second recognition regions.
The terminal according to claim 10, wherein when the processor executes the step of determining a region to be processed from the plurality of image regions, the following steps can be further implemented:

Receiving a first operation on the first image;

Responding to the first operation and determining an image area corresponding to the first operation from the plurality of image areas to obtain a reference area;

From the plurality of image regions, a region other than the reference region is determined to be the region to be processed.
A computer storage medium, wherein the computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement any one of claims 1 to 9. The steps of the image processing method.