WO2021078276A1

WO2021078276A1 - Method for obtaining continuously photographed photos, smart terminal, and storage medium

Info

Publication number: WO2021078276A1
Application number: PCT/CN2020/123355
Authority: WO
Inventors: 蒋佳; 阮志峰
Original assignee: Tcl科技集团股份有限公司
Priority date: 2019-10-25
Filing date: 2020-10-23
Publication date: 2021-04-29
Also published as: CN112714246A

Abstract

The present application is applicable to the technical field of computers, and provides a method for obtaining continuously photographed photos. The method comprises: obtaining continuously photographed first photos; blurring each first photo separately to obtain a blurred photo respectively corresponding to each first photo; calculating a difference value between each first photo and the respectively corresponding blurred photo; determining the definition of each first photo on the basis of the difference value, and obtaining a second photo from the first photos on the basis of the definition. Because after each of the continuously photographed first photos is blurred, the difference value between each first photo and the respectively corresponding blurred photo is calculated, and the definition of each first photo is determined on the basis of the difference value and the second photo is obtained from the first photos on the basis of the definition. The second photo is quickly and accurately obtained from the continuously photographed first photos on the basis of the definition, so as to improve the efficiency of selecting a clear photo from multiple continuously photographed photos.

Description

Continuous photo acquisition method, intelligent terminal and storage medium

This application claims the priority of the Chinese patent application filed at the Chinese Patent Office on October 25, 2019, with the application number 201911025549.5, and the title of the invention "Methods for obtaining continuous shots, smart terminals and storage media", all of which are approved The reference is incorporated in this application.

Technical field

This application belongs to the field of computer technology, and in particular relates to a method for obtaining continuous photographs, an intelligent terminal and a storage medium.

Background technique

Today, as the camera function of mobile phones is becoming more and more powerful, many people choose to use mobile phones instead of cameras to take pictures. This puts forward higher and higher demands for the stability and intelligence of the camera function of mobile phones. Usually, in the capture scene, there will be a certain blur effect. Therefore, users are used to taking multiple photos in succession to select relatively clear photos. This process takes a lot of time and is inefficient.

technical problem

One of the objectives of the embodiments of the present application is to provide a method for acquiring continuous photographs, an intelligent terminal, and a storage medium, so as to solve the problem of inefficient and inefficient selection of continuous photographs.

Technical solutions

The first aspect of the embodiments of the present application provides a method for acquiring continuous photographs, including:

Get the first photo of the continuous shooting;

Performing blurring processing on each of the first photos, respectively, to obtain a blurry photo corresponding to each of the first photos;

Calculate the difference value between each of the first photos and the corresponding blurred photos; determine the sharpness of each of the first photos based on the difference value, and determine the sharpness of each of the first photos based on the sharpness from the first photos To get the second photo.

Optionally, the respectively performing blurring processing on each of the first photos to obtain a respective blurred photo corresponding to each of the first photos includes:

The target area of each of the first photos is detected separately, and the target area includes a face image and /2 or an object image; the respective target areas corresponding to each of the first photos are subjected to fuzzy filtering processing to obtain each Fuzzy photos corresponding to each of the first photos.

Optionally, the separately detecting the target area of each of the first photos includes:

A trained image detection model is used to detect the target area of each photo, and the trained image detection model is a neural network model.

Optionally, the determining the sharpness of each of the first photos based on the difference value, and obtaining a second photo from the first photos based on the sharpness includes:

The sharpness of each of the first photos is determined based on the difference value, and a second photo with the highest sharpness is obtained from all the first photos.

Optionally, the determining the sharpness of each of the first photos based on the difference value, and obtaining the second photo with the highest sharpness from all the first photos includes:

Calculate the peak signal-to-noise ratio of the difference value; determine the sharpness of each of the first photos according to the peak signal-to-noise ratio; obtain the second photo with the highest sharpness from all the first photos.

Optionally, the calculating the peak signal-to-noise ratio of the image difference value includes:

The peak signal-to-noise ratio of the differential value is calculated based on a preset peak signal-to-noise ratio calculation formula, and the preset peak signal-to-noise ratio calculation formula is:

Among them, a _ij represents the distance between the first pixel with the pixel coordinate (i, j) corresponding to the grayscale image of the first photo and the second pixel with the pixel coordinate (i, j) of the corresponding blurred photo The difference value of i represents the abscissa of the pixel, j represents the ordinate of the pixel, n represents the width of the current photo, and m represents the length of the current photo.

Gaussian filtering processing is performed on each of the first photos respectively to obtain respective blurred photos corresponding to each of the first photos.

Optionally, the calculating the difference value between each of the first photos and the respective corresponding blurred photos includes:

Perform grayscale processing on each of the first photos to obtain a grayscale image corresponding to each of the first photos; respectively calculate the grayscale image and each grayscale image corresponding to each first photo. The difference value between the blurred photos corresponding to each of the first photos.

A second aspect of the embodiments of the present application provides a device for acquiring continuous photographs, including:

The first obtaining module 501 is configured to obtain the first photo continuously shot;

The processing module 502 is configured to perform blurring processing on each of the first photos to obtain respective blurred photos corresponding to each of the first photos;

The calculation module 503 is configured to calculate the difference value between each of the first photos and the corresponding blurred photos;

The second acquisition module 504 is configured to determine the sharpness of each of the first photos based on the difference value, and obtain a second photo from the first photos based on the sharpness.

Preferably, the processing module 502 includes:

A detection unit, configured to separately detect a target area of each of the first photos, where the target area includes a face image and/or an object image;

The first processing unit is configured to perform blur filtering processing on the respective target regions corresponding to each of the first photos to obtain respective blurred photos corresponding to each of the first photos.

Preferably, the detection unit is specifically used for:

Preferably, the second acquiring module 504 is specifically configured to:

Preferably, the second acquisition module 504 includes:

The first calculation unit is configured to calculate the peak signal-to-noise ratio of the difference value;

A determining unit, configured to determine the sharpness of each of the first photos according to the peak signal-to-noise ratio;

The obtaining unit is configured to obtain the second photo with the highest definition from all the first photos.

Preferably, the calculation unit is specifically used for:

Preferably, the processing module 502 is specifically configured to: respectively perform Gaussian filtering processing on each of the first photos to obtain respective fuzzy photos corresponding to each of the first photos.

Preferably, the calculation module 503 includes:

The second processing unit is configured to perform grayscale processing on each of the first photos to obtain a grayscale image corresponding to each of the first photos;

The second calculation unit is configured to calculate the difference value between the grayscale image corresponding to each first photo and the blurred photo corresponding to each first photo.

The third aspect of the embodiments of the present application provides an intelligent terminal, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, The steps of the method for obtaining continuous shots as described in the first aspect are implemented.

A fourth aspect of the embodiments of the present application provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the continuous shooting of photos as described in the first aspect is achieved. Method steps.

Compared with the prior art, the method for acquiring continuous shots provided by the first aspect of the application has the following beneficial effects: by acquiring the first continuous shot; blurring each of the first photos to obtain each The fuzzy photos corresponding to each of the first photos; calculate the difference value between each of the first photos and the corresponding fuzzy photos; determine the sharpness of each of the first photos based on the difference value, based on The sharpness derives a second photo from the first photo. After the blurring process is performed on each of the first photos in the continuous shooting, the difference value between each of the first photos and the corresponding blurred photos is calculated, and each of the first photos is determined based on the difference value. The sharpness of the first photo, and the second photo is obtained from the first photo based on the sharpness. It is realized that the second photo based on the sharpness is obtained from the first photos of the continuous shooting quickly and accurately, and the efficiency of selecting a clear photo from the multiple continuous photos is improved.

Compared with the prior art, the terminal provided in the second aspect of the present application and the computer-readable storage medium provided in the fourth aspect have beneficial effects. Compared with the prior art, the method for acquiring continuous photographs provided in the first aspect of the present application has The beneficial effects are the same and will not be repeated here.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only of the present application. For some embodiments, those of ordinary skill in the art can obtain other drawings based on these drawings without creative labor.

FIG. 1 is an implementation process of a method for acquiring continuous shots provided by an embodiment of the present application;

Figure 2 is a flow chart of the specific implementation of S102 in Figure 1;

Figure 3 is a flow chart of the specific implementation of S103 in Figure 1;

Figure 4 is a flow chart of the specific implementation of S104 in Figure 1;

FIG. 5 is a schematic diagram of the device for acquiring continuous photographs provided by the present application;

Fig. 6 is a schematic diagram of a terminal provided by the present application.

Detailed ways

In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are proposed for a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from obstructing the description of this application.

It should be noted that today, as the camera functions of terminals, such as mobile phones and PADs, are becoming more and more powerful, many people choose to use terminals instead of cameras to take pictures. This puts increasing demands on the stability and intelligence of the camera function of the terminal. At present, in terminal shooting, different degrees of blur will occur due to some shooting problems, for example, the blur caused by the shaking of the terminal during shooting, the motion blur caused by the movement of the shooting target, or the out-of-focus blur caused by the lack of focus, etc. . In order to be able to take satisfactory photos, users usually choose to take multiple photos continuously to reduce the probability of blurring and increase the range of clear photos. However, there are usually about 7-20 photos in continuous shooting, which requires the user to select one by one, which wastes a lot of time and is inefficient in film selection.

In view of the above problems, if the terminal can automatically and quickly determine the best photo from multiple continuous photos and store it, it can save a lot of time for users to select photos. At present, some methods for automatically identifying the image definition have been proposed. The common traditional algorithm is the edge detection algorithm, which is based on the assumption that the image is blurry, then the edge information will be blurred, and the corresponding detected edge information will be less. After the edge detection of the picture, the variance calculation method is used to calculate the variance of the edge picture. A picture with a relatively small variance is regarded as a blurred picture, and a picture with a relatively large variance is regarded as a clear picture. However, in real-life photography, moiré effects, changes in light sensitivity, or changes in photo content often occur, leading to the problem of low accuracy when the edge detection algorithm is used to judge the mood of the picture. In view of the above-mentioned problems, the present invention provides a new method for blurring photos.

In order to illustrate the technical solution described in the present application, specific embodiments are used for description below. As shown in FIG. 1, it is a flow chart of the method for acquiring continuous shots provided by the first embodiment of the present application, and the execution subject of this embodiment is a terminal. The details are as follows:

S101: Acquire the first photo continuously shot.

Understandably, when the user sees his favorite scenery or captures some specific actions for his family and friends, he will quickly press the shooting button to start the shooting function to shoot. At this time, the shooting will be detected. In this embodiment, when it is detected that the photo is taken, the first photo continuously taken can be obtained.

S102: Perform blurring processing on each of the first photos, respectively, to obtain a blurry photo corresponding to each of the first photos.

Understandably, in the process of taking photos, people are most concerned about the clarity of the shooting target, such as the clarity of the face in the photo of a person, including whether the facial expression is natural, such as whether there are actions that affect the beauty of the photo, such as blinking and opening the mouth. , Or whether the framing of the object is clear, etc. Therefore, in this example, further, the sharpness of each first photo can be determined by detecting the target area included in each first photo, and by the sharpness of the target area. Specifically, the first photo includes a human face image and/or an object image, and in this embodiment, the target area is the human face image and/or an object image.

Specifically, FIG. 2 is a flowchart of specific implementation of S102 in FIG. 1. As can be seen from Figure 2, S102 includes:

S1021: Detect a target area of each of the first photos, where the target area includes a face image and/or an object image.

It should be noted that there are many common face image and/or object image detection methods. For example, face detection and/or object image detection are performed through machine learning models. Specifically, in this embodiment, The trained image detection model detects the target area of each photo, and the trained image detection model is a neural network model.

Specifically, the detecting the target area of each of the first photos separately includes: inputting each of the first photos into the neural network model to perform target area detection, and obtaining each output of the neural network model The target area of the first photo.

The training process of the trained image detection model includes: obtaining a first preset number of target photos, where the target photos are the first photos marked with the target area, and the first photos include human face images and /Or an object image, and the target area is a human face image and/or an object image.

Understandably, in the training process of the image detection model, the pre-established model structure is usually selected, for example, the structure of the neural network model in this embodiment, and then the training samples are input into the pre-established model structure for training. In an embodiment, the training samples are the first preset number of target photos. Specifically, in order to improve the efficiency and accuracy of image detection model training, the first preset number of target photos are all the target photos marked with the target area. Narrate the first photo.

Specifically, the training process of the neural network model includes: obtaining a first preset target photo; inputting the first preset number of target photos into a pre-established neural network model for training, and obtaining the neural network model after training. Network model; acquiring a second preset number of target photos, and sequentially inputting the second preset number of target photos into the neural network model after training for analysis, and obtaining the annotations output by the neural network model after training The target photo of the target area; if the target photo marked with the target area is compared with the preset target photo marked with the target area, the probability that the target area overlaps is greater than the preset probability threshold, then determine The neural network model after training is a trained neural network model; if the target photo with the target area is compared with the preset target photo with the target area, the probability that the target area overlaps is less than Or equal to the preset probability threshold, then increase the first preset number of target photos, and perform training by inputting the first preset number of target photos into a pre-established neural network model to obtain the training Neural network model.

Generally, after the training of the model is completed, the first photo of the unlabeled target area is input into the trained neural network model for target area labeling, and the output of the trained neural network model with the target area marked will be obtained. The first photo.

S1022: Perform fuzzy filtering processing on the target area corresponding to each of the first photos respectively, to obtain respective blurred photos corresponding to each of the first photos.

Generally, when there is a blur in the image, the image is further subjected to blur filtering processing, corresponding to the loss of sharpness of the image with blurring.

In this example, using this characteristic of blur filtering, the respective target regions corresponding to each of the first photos are respectively subjected to blur filtering processing to obtain respective blurred photos corresponding to each of the first photos. Specifically, Gaussian filtering processing is performed on the target area corresponding to each of the first photos to obtain the fuzzy photos corresponding to each of the first photos.

S103: Calculate the difference value between each of the first photos and the corresponding blurred photos.

It should be noted that since the original blurry image is subjected to blur filter processing, the loss of its sharpness is small, and the original clear image is subjected to blur filter processing, and its sharpness loss is greater, so the blurred picture is blurred After the filtering process, the difference value between it and the original image is smaller. Correspondingly, the clearer the image, after the fuzzy filtering process is performed on it, the difference value between it and the original image is larger.

In this embodiment, the characteristics of different loss of images of different definitions by blur filtering are used, and the definition of the original image is determined by calculating the difference value between each of the first photos and the corresponding blurred photos. Specifically, the difference value of the image corresponds to the pixel difference value obtained by subtracting the corresponding pixel values of the two images.

Specifically, as shown in FIG. 3, it is a flowchart of the specific implementation of S103 in FIG. It can be seen from Figure 3 that S103 includes:

S1031: Perform grayscale processing on each of the first photos to obtain a grayscale image corresponding to each of the first photos.

It should be noted that the first photo is an image of three primary colors (RGB, where R represents the red channel, G represents the green channel, and B represents the blue channel) image, and the blurred photo corresponding to each of the first photos is gray When calculating the image difference, it is required that the input images have the same type and size. Therefore, it is necessary to perform grayscale processing on each of the first photos first. Specifically, the specific method of gray-scale processing for each of the first photos is not limited here. As an example and not a limitation, a preset gray-scale formula can be used, for example, Gray=R*0.299+G* 0.587+B*0.114, grayscale processing is performed on each of the first photos, where in the grayscale processing process, R represents the pixel value of the red channel, G represents the pixel value of the green channel, and B represents The pixel value of the blue channel, Gray represents the single-channel pixel value after grayscale processing.

S1032: Calculate the difference value between the grayscale image corresponding to each first photo and the blurred photo corresponding to each first photo.

Specifically, since the grayscale image corresponding to each of the first photos has the same type and size as the fuzzy photos corresponding to each of the first photos, each of the first photos can be directly The grayscale image corresponding to each first photo is subtracted from the fuzzy photo corresponding to each first photo to obtain a difference image, and the pixel value corresponding to each pixel of the difference image is the difference value.

Further, in an achievable embodiment, the grayscale image and the blurred photo corresponding to each of the first photos may be normalized separately, and then the normalized image may be calculated after the normalization process. The difference value between the grayscale image of and the blurred photo after normalization processing. Specifically, the process of normalization processing is not specifically limited. Specifically, the purpose of the normalization processing is to make the value of each pixel of the grayscale image and each pixel of the blurred photo They are between [0,1].

S104: Determine the sharpness of each of the first photos based on the difference value, and obtain a second photo from the first photos based on the sharpness.

Specifically, according to the previous analysis, it can be known that the more blurry image is subjected to blur filter processing, the less the loss of sharpness of the original image is, therefore, the calculated difference value is smaller. Generally, the difference value is each of the difference images. The pixel value of the pixel is often not clear to determine the sharpness of the image by comparing the size of the pixel value of each pixel of the image. Therefore, in this embodiment, the peak signal-to-noise ratio corresponding to the difference value is further calculated. , To determine the sharpness of each of the first photos.

It is understandable that users usually have high-definition photos. Therefore, in an optional implementation manner, the S104 specifically includes: determining the sharpness of each first photo based on the difference value, from all The second photo with the highest definition is obtained among the first photos.

Specifically, as shown in FIG. 4, it is a flowchart of the specific implementation of S104 in FIG. It can be seen from Figure 4 that S104 includes:

S1041: Calculate the peak signal-to-noise ratio of the difference value.

Specifically, the peak signal-to-noise ratio is often used to indicate the measurement of pixel reconstruction quality in the fields of image compression and the like. In this embodiment, the peak signal-to-noise ratio of the differential value is calculated to determine the value of each first photo. Clarity.

Specifically, the peak signal-to-noise ratio of the differential value is calculated based on a preset peak signal-to-noise ratio calculation formula. Further, the preset peak signal-to-noise ratio calculation formula is:

It should be noted that the common peak signal-to-noise ratio is a negative number. In this example, in order to more conveniently determine the sharpness of each of the first photos, the preset peak signal-to-noise ratio formula is based on the traditional peak signal-to-noise ratio. The noise ratio formula evolved, and its value is positive.

S1042: Determine the sharpness of each first photo according to the peak signal-to-noise ratio.

Specifically, in this example, when the peak signal-to-noise ratio is larger, the corresponding first photo is blurred, and the peak signal-to-noise ratio is smaller, which means the corresponding first photo is clearer.

S1043: Obtain a second photo with the highest definition from all the first photos.

Optionally, after the second photo with the highest definition is obtained from all the first photos for storage, the remaining first photos are deleted to release cache space.

It should be understood that the size of the sequence number of each step in the foregoing embodiment does not mean the order of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

From the above analysis, it can be seen that the method for acquiring continuous photographs proposed in this application obtains the first photograph of the continuous photograph; and blurs each of the first photographs to obtain the corresponding blurred photograph of each of the first photographs. Calculate the difference between each of the first photos and the respective corresponding blurred photos; determine the sharpness of each of the first photos based on the difference value, and determine the sharpness of each of the first photos based on the sharpness from the first Get the second photo in the photo. After the blurring process is performed on each of the first photos in the continuous shooting, the difference value between each of the first photos and the corresponding blurred photos is calculated, and each of the first photos is determined based on the difference value. The sharpness of the first photo, and the second photo is obtained from the first photo based on the sharpness. It is realized that the second photo based on the sharpness is obtained from the first photos continuously shot quickly and accurately, and the efficiency of selecting clear photos from the multiple consecutive photos is improved.

Fig. 5 is a schematic diagram of the device for acquiring continuous photographs provided by the present application. As shown in FIG. 5, the continuous-photograph acquisition device 5 of this embodiment includes: a first acquisition module 501, a processing module 502, a calculation module 503, and a second acquisition module 504. among them,

Preferably, the processing module 502 includes:

Preferably, the detection unit is specifically configured to: use a trained image detection model to detect the target area of each photo, and the trained image detection model is a neural network model.

Preferably, the second obtaining module 504 is specifically configured to: determine the sharpness of each of the first photos based on the difference value, and obtain the second photo with the highest sharpness from all the first photos.

Preferably, the second acquisition module 504 includes:

Preferably, the calculation unit is specifically configured to: calculate the peak signal-to-noise ratio of the differential value based on a preset peak signal-to-noise ratio calculation formula, and the preset peak signal-to-noise ratio calculation formula is:

Preferably, the calculation module 503 includes:

Fig. 6 is a schematic diagram of a terminal provided by the present application. As shown in FIG. 6, the terminal 6 of this embodiment includes a processor 60, a memory 61, and a computer program 62 stored in the memory 61 and running on the processor 60, such as a continuous photo acquisition program. When the processor 60 executes the computer program 62, the steps in the foregoing embodiments of the method for acquiring continuous photographs are implemented, for example, steps 101 to 104 shown in FIG. 1. Alternatively, when the processor 60 executes the computer program 62, the functions of the modules/units in the embodiment of the apparatus for acquiring continuous photographs are realized, for example, the functions of the modules 501 to 504 shown in FIG. 5.

Exemplarily, the computer program 62 may be divided into one or more modules/units, and the one or more modules/units are stored in the memory 61 and executed by the processor 60 to complete This application. The one or more modules/units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 62 in the terminal 6. For example, the computer program 62 may be divided into a first acquisition module, a processing module, a calculation module, and a second acquisition module (a module in a virtual device), and the specific functions of each module are as follows:

The first acquisition module is used to acquire the first photo continuously shot;

A processing module, which is configured to perform blur processing on each of the first photos to obtain a blurry photo corresponding to each of the first photos;

A calculation module, configured to calculate the difference between each of the first photos and the corresponding blurred photos;

The second acquisition module is configured to determine the sharpness of each of the first photos based on the pixel difference value, and acquire and store the second photo with the highest sharpness from all the first photos.

Preferably, the terminal further includes a photographing module, and the photographing module is used to photograph the first photo.

Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the division of the above functional units and modules is used as an example. In practical applications, the above functions can be allocated to different functional units and modules as needed. Module completion, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist alone physically, or two or more units can be integrated into one unit. The above-mentioned integrated units can be hardware-based Formal realization can also be realized in the form of software functional units. In addition, the specific names of the functional units and blocks are only used to facilitate distinguishing each other, and are not used to limit the protection scope of the present application. For the specific working process of the units and modules in the foregoing system, reference may be made to the corresponding process in the foregoing method embodiment, which will not be repeated here. In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail or recorded in an embodiment, reference may be made to related descriptions of other embodiments.

A person of ordinary skill in the art may realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of this application.

In the embodiments provided in this application, it should be understood that the disclosed device/terminal device and method may be implemented in other ways. For example, the device/terminal device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units. Or components can be combined or integrated into another system, or some features can be omitted or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple communication units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit. If the integrated module/unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, this application implements all or part of the processes in the above-mentioned embodiments and methods, and can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the program is executed by the processor, it can implement the steps of the foregoing method embodiments. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file, or some intermediate forms. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electrical carrier signal, telecommunications signal, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately added or deleted according to the requirements of the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to the legislation and patent practice, the computer-readable medium Does not include electrical carrier signals and telecommunication signals.

The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, a person of ordinary skill in the art should understand that it can still implement the foregoing The technical solutions recorded in the examples are modified, or some of the technical features are equivalently replaced; these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the application, and should be included in Within the scope of protection of this application.

Claims

A method for obtaining continuous photographs, which is characterized in that it comprises:

Get the first photo of the continuous shooting;

Performing blurring processing on each of the first photos, respectively, to obtain a blurry photo corresponding to each of the first photos;

Calculating a difference value between each of the first photos and the corresponding blurred photos;

The sharpness of each of the first photos is determined based on the difference value, and a second photo is obtained from the first photos based on the sharpness.
8. The method for acquiring continuous shot photos according to claim 1, wherein said respectively performing blur processing on each of said first photos to obtain respective blurred photos corresponding to each of said first photos comprises:

Respectively detecting a target area of each of the first photos, where the target area includes a face image and/or an object image;

A fuzzy filtering process is performed on the target area corresponding to each of the first photos, respectively, to obtain a fuzzy photo corresponding to each of the first photos.
3. The method for acquiring continuous shooting photos according to claim 2, wherein said detecting the target area of each of said first photos respectively comprises:

A trained image detection model is used to detect the target area of each photo, and the trained image detection model is a neural network model.
The method for acquiring continuous shooting photos according to claim 1, wherein the sharpness of each of the first photos is determined based on the difference value, and the first photo is obtained from the first photos based on the sharpness. Two photos, including:

The sharpness of each of the first photos is determined based on the difference value, and a second photo with the highest sharpness is obtained from all the first photos.
The method for obtaining continuous shooting photos according to claim 4, wherein the definition of each of the first photos is determined based on the difference value, and the first photo with the highest definition is obtained from all the first photos. Two photos, including:

Calculating the peak signal-to-noise ratio of the difference value;

Determining the sharpness of each of the first photos according to the peak signal-to-noise ratio;

Obtain the second picture with the highest definition from all the first pictures.
8. The method for acquiring continuous shooting photos according to claim 5, wherein the calculating the peak signal-to-noise ratio of the difference value comprises:

The peak signal-to-noise ratio of the differential value is calculated based on a preset peak signal-to-noise ratio calculation formula, and the preset peak signal-to-noise ratio calculation formula is:
8. The method for acquiring continuous shot photos according to claim 1, wherein said respectively performing blur processing on each of said first photos to obtain respective blurred photos corresponding to each of said first photos comprises:

Gaussian filtering processing is performed on each of the first photos respectively to obtain respective blurred photos corresponding to each of the first photos.
3. The method for acquiring continuous shooting photos according to claim 2, wherein said respectively performing blur processing on each of said first photos to obtain respective blurred photos corresponding to each of said first photos comprises:

Gaussian filtering processing is performed on each of the first photos respectively to obtain respective blurred photos corresponding to each of the first photos.
8. The method for acquiring continuous shot photos according to claim 7, wherein said calculating the difference value between each of said first photos and said corresponding blurred photos comprises:

Performing grayscale processing on each of the first photos to obtain a grayscale image corresponding to each of the first photos;

The difference value between the grayscale image corresponding to each of the first photos and the fuzzy photo corresponding to each of the first photos is calculated respectively.
An intelligent terminal includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the following steps when the processor executes the computer program:

Get the first photo of the continuous shooting;

Performing blurring processing on each of the first photos, respectively, to obtain a blurry photo corresponding to each of the first photos;

Calculating a difference value between each of the first photos and the corresponding blurred photos;

The sharpness of each of the first photos is determined based on the difference value, and a second photo is obtained from the first photos based on the sharpness.
The smart terminal according to claim 10, wherein said respectively performing blur processing on each of said first photos to obtain respective fuzzy photos corresponding to each of said first photos comprises:

Respectively detecting a target area of each of the first photos, where the target area includes a face image and/or an object image;

A fuzzy filtering process is performed on the target area corresponding to each of the first photos, respectively, to obtain a fuzzy photo corresponding to each of the first photos.
The smart terminal of claim 11, wherein the detecting the target area of each of the first photos respectively comprises:

A trained image detection model is used to detect the target area of each photo, and the trained image detection model is a neural network model.
The smart terminal according to claim 10, wherein said determining the sharpness of each of said first photos based on said difference value, and obtaining a second photo from said first photos based on said sharpness, include:

The sharpness of each of the first photos is determined based on the difference value, and a second photo with the highest sharpness is obtained from all the first photos.
The smart terminal according to claim 13, wherein said determining the sharpness of each of the first photos based on the difference value, and obtaining the second photo with the highest sharpness from all the first photos, include:

Calculating the peak signal-to-noise ratio of the difference value;

Determining the sharpness of each of the first photos according to the peak signal-to-noise ratio;

Obtain the second picture with the highest definition from all the first pictures.
The smart terminal of claim 14, wherein the calculating the peak signal-to-noise ratio of the difference value comprises:

The peak signal-to-noise ratio of the differential value is calculated based on a preset peak signal-to-noise ratio calculation formula, and the preset peak signal-to-noise ratio calculation formula is:
The smart terminal according to claim 10, wherein said respectively performing blur processing on each of said first photos to obtain respective fuzzy photos corresponding to each of said first photos comprises:

Gaussian filtering processing is performed on each of the first photos respectively to obtain respective blurred photos corresponding to each of the first photos.
The smart terminal according to claim 16, wherein said calculating the difference value between each of said first photos and the respective corresponding blurred photos comprises:

Performing grayscale processing on each of the first photos to obtain a grayscale image corresponding to each of the first photos;

The difference value between the grayscale image corresponding to each of the first photos and the fuzzy photo corresponding to each of the first photos is calculated respectively.
A computer-readable storage medium that stores a computer program, and is characterized in that, when the computer program is executed by a processor, the following steps are implemented:

Get the first photo of the continuous shooting;

Performing blurring processing on each of the first photos, respectively, to obtain a blurry photo corresponding to each of the first photos;

Calculating a difference value between each of the first photos and the corresponding blurred photos;

The sharpness of each of the first photos is determined based on the difference value, and a second photo is obtained from the first photos based on the sharpness.
18. The computer-readable storage medium according to claim 18, wherein said respectively performing blur processing on each of said first photos to obtain respective blurred photos corresponding to each of said first photos comprises:

Respectively detecting a target area of each of the first photos, where the target area includes a face image and/or an object image;

A fuzzy filtering process is performed on the target area corresponding to each of the first photos, respectively, to obtain a fuzzy photo corresponding to each of the first photos.
19. The computer-readable storage medium of claim 19, wherein said detecting the target area of each of the first photos respectively comprises:

A trained image detection model is used to detect the target area of each photo, and the trained image detection model is a neural network model.