WO2020206912A1

WO2020206912A1 - Image definition recognition method, image definition recognition apparatus, and terminal device

Info

Publication number: WO2020206912A1
Application number: PCT/CN2019/103283
Authority: WO
Inventors: 惠慧; 严明洋
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-04-11
Filing date: 2019-08-29
Publication date: 2020-10-15
Also published as: CN110175980A

Abstract

An image definition recognition method, an image definition recognition apparatus, and a terminal device. The method comprises: obtaining an image to be recognized that comprises one or more target objects, and the position of each target object in the image to be recognized (S101); according to the position of each target object in the image to be recognized, clipping one or more sub images comprising the target object from the image to be recognized (S102); and recognizing the image definition of each sub image, and according to the recognized image definition of each sub image, determining the image definition of the image to be recognized (S103). The method can make the image definition recognition result of the image to be recognized be closer to the image definition sensed by human eyes.

Description

Image definition recognition method, image definition recognition device and terminal equipment

This application requires that the application number submitted on April 11, 2019 is CN 201910288549.8, the priority of the Chinese patent application with the title of "Image Clarity Recognition Method, Image Clarity Recognition Device and Terminal Equipment", the entire content of the Chinese patent application is incorporated into this application by reference.

Technical field

This application belongs to the field of image processing technology, and in particular relates to an image definition recognition method, image definition recognition device, terminal equipment, and computer non-volatile readable storage medium.

Background technique

At present, there are many ways to recognize image definition, such as Tenengrad gradient method, Laplacian gradient method, and variance method. The current image definition recognition method usually determines the image definition based on all the pixels in the entire image.

However, the human eye's perception of image sharpness is often affected by some areas in the image, and therefore, the sharpness recognition result obtained by the current image sharpness recognition method may be different from the sharpness perceived by the human eye.

technical problem

In view of this, this application provides an image definition recognition method, image definition recognition device, terminal equipment and computer non-volatile readable storage medium, which can make the recognized image definition closer to human to a certain extent. The sharpness of the image perceived by the eyes.

Technical solutions

The first aspect of this application provides an image definition recognition method, including:

Acquiring an image to be recognized containing one or more target objects and the position of each target object in the image to be recognized;

According to the position of each target object in the image to be recognized, one or more sub-images containing the target object are intercepted in the image to be recognized;

The image definition of each sub-image is recognized, and the image definition of the image to be recognized is determined according to the recognized image definition of each sub-image.

The second aspect of the present application provides an image definition recognition device, including:

The target acquisition module is used to acquire the image to be recognized containing one or more target objects and the position of each target object in the image to be recognized;

The target interception module is configured to intercept one or more sub-images containing the target object in the image to be recognized according to the position of each target object in the image to be recognized;

The definition recognition module is used to recognize the image definition of each sub-image, and determine the image definition of the image to be recognized according to the recognized image definition of each sub-image.

The third aspect of the present application provides a terminal device, including a memory, a processor, and computer-readable instructions stored in the memory and capable of running on the processor. When the processor executes the computer-readable instructions, the implementation is as described above. The steps of the first aspect of the method.

A fourth aspect of the present application provides a computer non-volatile readable storage medium. The computer non-volatile readable storage medium stores computer readable instructions. When the computer readable instructions are executed by a processor, the above-mentioned On the one hand the steps of the method.

The fifth aspect of the present application provides a computer-readable instruction product. The computer-readable instruction product includes computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the steps of the method in the first aspect are implemented. .

Beneficial effect

It can be seen from the above that this application provides a method for recognizing image clarity. First, obtain an image to be recognized that contains one or more target objects, and obtain the position of each target object in the image to be recognized. For example, if the above target object is a dog, then an image to be recognized containing a dog can be obtained X and the position of the dog in the image X to be recognized; secondly, according to the position of each target object in the image to be recognized, one or more sub-images containing the target object are intercepted in the image to be recognized, that is Yes, after obtaining the position of the dog in the image X to be recognized, the sub-image Y containing the dog can be intercepted in the image X to be recognized; finally, the image definition of each sub-image is recognized, and the For each image definition, determine the image definition of the image to be recognized, that is, identify the image definition of the sub-image Y, and determine the image definition of the image X to be recognized according to the image definition of the sub-image Y ( For example, the image definition of the sub-image Y can be directly determined as the image definition of the image X to be recognized). It can be seen that, in the technical solution provided by this application, the image clarity of the image to be recognized is based on the image clarity of the image area where the target object is located. Normally, when the human eye observes the image, it is often Attracted by a specific object, therefore, the human eye’s perception of image clarity is largely determined by the image area where the target object is located. Therefore, the recognition result of image clarity in this application will be closer to the human eye’s perception Image clarity.

Description of the drawings

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

FIG. 1 is a schematic diagram of the implementation process of an image definition recognition method provided by Embodiment 1 of the present application;

FIG. 2 is a schematic diagram of a method for capturing sub-images according to Embodiment 1 of the present application;

FIG. 3 is a schematic diagram of the implementation process of another image definition recognition method provided by Embodiment 2 of the present application;

FIG. 4 is a schematic structural diagram of an image definition recognition device provided by Embodiment 3 of the present application;

Fig. 5 is a schematic structural diagram of a terminal device provided in Embodiment 4 of the present application.

Embodiments of the invention

In the following description, for the purpose of explanation rather than limitation, specific details such as specific are proposed. 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.

The image definition recognition method provided by the embodiments of the present application is applicable to terminal devices. Illustratively, the terminal devices include, but are not limited to, smart phones, tablet computers, notebooks, smart wearable devices, desktop computers, and cloud servers.

It should be understood that when used in this specification and appended claims, the term "comprising" indicates the existence of the described features, wholes, steps, operations, elements and/or components, but does not exclude one or more other features Existence or addition of, whole, step, operation, element, component and/or its collection.

It should also be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in the specification of this application and the appended claims, unless the context clearly indicates other circumstances, the singular forms "a", "an" and "the" are intended to include plural forms.

It should be further understood that the term "and/or" used in the specification and appended claims of this application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations .

In addition, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

In order to illustrate the technical solutions described in the present application, specific embodiments are used for description below.

The following describes the image definition recognition method provided in the first embodiment of the application. The image definition recognition method is applied to terminal devices (such as smart phones). Please refer to attached drawing 1. The image definition recognition method of the first embodiment of the application include:

In step S101, an image to be recognized containing one or more target objects and the position of each target object in the image to be recognized are obtained;

In the embodiments of the present application, the aforementioned target objects are objects that are easily captured by human eyes, such as portraits, dogs, cats, flowers, and so on.

In the embodiment of the present application, the specific implementation process of step S101 may include the following steps:

Step A: Obtain the image to be processed;

Step B: Perform target detection on the image to be processed to obtain a detection result, which is used to indicate whether the target object is detected in the image to be processed, and if the target object is detected in the image to be processed, the detection The result is used to indicate the position of each target object in the image to be processed;

Step C. If the detection result indicates that the target object is detected in the image to be processed, the image to be processed is determined as the image to be recognized, and based on the detection result, the position of each target object in the image to be recognized is determined position.

Wherein, the method for acquiring the image to be processed in the foregoing step A may be: when it is detected that the user takes an image through the camera, the image captured by the camera is determined as the image to be processed.

Those skilled in the art should note that the above-mentioned step A-step C is only a specific implementation method of step S101, and this step S101 can also have other specific implementation methods, for example, the terminal device can output the prompt message "Dear user, please You enter an image containing the target object (person, dog, or cat)", and then the user can select an image containing a person, dog, or cat from the images stored locally according to the prompt information, and the terminal device obtains the image selected by the user, And the image is determined as the above-mentioned image to be recognized. In addition, the user can also inform the terminal device of the location of the target object in the image to be recognized. For example, the user informs the terminal device that the target object is in the image to be recognized by selecting the target object. s position.

In the above step B, the method of performing target detection on the image to be processed to obtain the detection result may be: performing target detection on the image to be processed using the trained target detection model, and obtaining the detection result output by the target detection model (specifically, The method of using the target detection model to perform target detection on an image is an existing technology, and will not be repeated here). In addition, those skilled in the art should note that this application does not limit the target detection method specifically used in step B.

In addition, in this embodiment of the present application, the "image to be recognized" in step S101 may be an image taken by the user through the camera APP of the terminal device; or it may be the camera APP in the terminal device or the preview image collected by the camera APP It can also be a frame of preview image in the terminal; alternatively, it can also be an image saved locally on the terminal device; or, it can also be a certain frame of an image in a video watched online or locally saved. This application does not limit the source of the aforementioned image to be identified.

In step S102, according to the position of each target object in the image to be recognized, one or more sub-images containing the target object are intercepted in the image to be recognized;

In this embodiment of the present application, the number of sub-images obtained through this step S102 may be one or multiple, and the number of target objects contained in each sub-image may be one or multiple. This application does not limit the number of captured sub-images and the number of target objects contained in each sub-image.

In order to describe the specific implementation process of step S102 more clearly, the following uses FIG. 2 to describe in detail how to capture the sub-image.

As shown in Figure 2(a), assume that the image to be recognized obtained in step S101 is an image 201, which contains a target object 202 (ie a portrait), and the target object 202 obtained in step S101 is in the image 201 The position of is {A(x _a , y _a ), B(x _b , y _b )} (that is, the position of the target object 202 is: the rectangular area composed of point A and point B, as shown in Figure 2(a) Box). Then in the above step S102, the sub-image containing the target object 202 can be intercepted according to the coordinates of point A and point B. In this application, the rectangular area composed of point A and point B can be directly used as the sub-image, or The rectangular area formed by point A and point B is subjected to dilation operation, and the image area after dilation operation is used as the sub-image containing the target object 202 (please note that the method of obtaining the sub-image is not limited in this application).

As shown in Figure 2(b), assume that the image to be recognized obtained in step S101 is image 203, which contains two target objects, target object 204 and target object 205, respectively. The target obtained in step S101 is The position of the object 204 in the image 203 is {A(x _a , y _a ), B(x _b , y _b )}, and the position of the target object 205 in the image 203 obtained by the above step S101 is {C(x _c ,y _c ),D(x _d ,y _d )}. Then in the above step S102, according to the coordinates of point A, point B, point C, and point D, the screenshot may contain the sub-images of the target object 204 and the target object 205, or two sub-images may be intercepted, each of which contains only the target The sub-image of the image 204 and the sub-image only containing the target object 205. That is, when the image to be recognized contains multiple target objects, the number of sub-images obtained in step S102 may be one or multiple.

In step S103, the image clarity of each sub-image is identified, and the image clarity of the image to be identified is determined according to the identified image clarity of each sub-image;

In the embodiment of the present application, the image definition of each sub-image acquired in step S102 is recognized (the image definition of each sub-image can be recognized through the trained neural network model, or the Tenengrad gradient method, Laplacian gradient method, and Variance method, etc. to identify the image clarity of each sub-image, this application does not limit the image clarity identification method of each sub-image), and then the acquired image clarity of each sub-image can be averaged or weighted to obtain the The image clarity of the image.

The following specifically discusses a method of weighted average of the image definition of each sub-image to obtain the definition of the image to be recognized: according to the category of the target object contained in each sub-image, each sub-image is in the image to be recognized The position of each sub-image and/or the proportion of the area occupied by each sub-image of the image to be recognized to determine the weight value corresponding to the image clarity of each sub-image. For example, when a sub-image is located in the middle area of the image to be recognized, it occupies the image to be recognized When the area ratio of the sub-image is larger and the category of the target object included is a portrait (usually, the human eye is more interested in a portrait), the image clarity of the sub-image can correspond to a larger weight value; then, according to The weight value of the image sharpness of each sub-image is weighted and averaged on the image sharpness of all the sub-images to obtain the image sharpness of the image to be identified.

In addition, in the first embodiment of the present application, in addition to relying on the image clarity of each sub-image, the image clarity of the image area other than each sub-image in the image to be recognized can also be relied on to determine the image clarity of the image to be recognized. degree. As shown in Figure 2(b), when determining the image clarity of the image 203, in addition to relying on the image clarity of the sub-image 204 and the sub-image 205, you can also rely on the image 203 in addition to the sub-image 204 and the sub-image 205. The image clarity of the outer image area. At this time, when the final image clarity of the image 203 is determined, the image clarity of the sub-image 204 and the sub-image 205 can be assigned a larger weight value to remove the sub-image 204 and The image clarity of the image area outside the sub-image 205 is assigned a smaller weight value, so that the final image clarity of the image 203 is obtained.

In addition, after this step S103, the method further includes the following steps: judging whether the image clarity of the image to be recognized is less than a preset threshold; if it is less than the preset threshold, super-resolution reconstruction is performed on the image to be recognized.

In the first embodiment of the present application, the image clarity of the image to be recognized is based on the image clarity of the image area where the target object is located. Normally, when the human eye observes the image, it is often attracted by the specific object in the image. Therefore, the human eye’s perception of image clarity is largely determined by the image area where the target object is located. Therefore, the recognition result of a pair of image clarity in the embodiment of this application will be closer to the human eye’s perception of image clarity. degree.

The following describes another image definition recognition method provided in the second embodiment of the present application. Please refer to FIG. 3. The image definition recognition method of the second embodiment of the present application includes:

In step S301, an image to be recognized containing one or more target objects and the position of each target object in the image to be recognized are obtained;

The specific implementation manner of this step S301 is completely the same as that of step S101 in the first embodiment. For details, please refer to the description of the first embodiment, which will not be repeated here.

In step S302, according to the position of each target object in the image to be recognized, the union of the image regions indicated by each position is determined;

In the second embodiment of the present application, the union of the image area occupied by each target object in the image to be recognized needs to be obtained.

In the example shown in Fig. 2(a), it can be determined that the union of the image areas indicated by each position is: a rectangular area composed of point A and point B.

In the example shown in Figure 2(b), it can be determined that the union of the image areas indicated by each position is: a rectangular area composed of point A and point B + a rectangular area composed of point C and point D.

In step S303, calculate the proportion of the first area of the image to be recognized that the image area indicated by the union occupies;

In the example shown in FIG. 2(a), the above-mentioned first area ratio is: the area of the rectangular area composed of point A and point B/the area of image 201.

In the example shown in FIG. 2( b ), the above-mentioned first area ratio is: (area of a rectangular area composed of points A and B+area of a rectangular area composed of points C and D)/area of image 203.

In step S304, it is determined whether the first area ratio is less than the first preset ratio, and if it is less than the first preset ratio, one or more sub-images containing the target object are intercepted in the image to be recognized;

Those skilled in the art can easily understand that if the first area ratio is large (for example, greater than or equal to the first preset ratio), it means that most of the image areas in the image to be recognized are the target objects. In this case, it is completely There is no need to cut out the image area where the target object is located, and the traditional image definition recognition method can be used directly to recognize the image definition of the image to be recognized.

If the above-mentioned first area ratio is less than the above-mentioned first preset ratio, it means that besides the target object in the image to be recognized, there are also some images that are not easy to capture by the human eye. In this case, you can set the target object The image area is cut out, and the cut out sub-image is used to determine the image clarity of the image to be recognized.

In addition, the specific manner of “cutting one or more sub-images containing the target object in the image to be recognized” described in step S304 can refer to the first embodiment. In addition, in the second embodiment of the present application, a specific implementation manner of "intercepting one or more sub-images containing the target object in the image to be recognized" is provided:

Step D: According to the position of each target object in the image to be recognized, the ratio of the image area indicated by each position to the second area of the image to be recognized is calculated;

Step E: Determine whether there is an image area with a second area ratio greater than a second preset ratio based on the second area ratio, where the second preset ratio is less than the first preset ratio;

Step F: If it exists, perform an expansion operation on each image area larger than the second preset ratio to obtain each corrected image area;

Step G: Determine each corrected image area as each sub-image;

In order to enable those skilled in the art to more clearly understand the technical solutions described in the above step D-step G, the above technical solutions are described in detail below using FIG. 2(b).

In the example shown in Figure 2(b), it is first necessary to calculate the second area ratio of the rectangular area composed of point A and point B to the image 203 (for the convenience of subsequent description, this second area ratio is called area ratio 1), And, the rectangular area composed of point C and point D occupies the second area ratio of the image 203 (for the convenience of subsequent description, the second area ratio is called area ratio 2); secondly, it is judged whether the area ratio 1 is greater than the second preset ratio , And, determine whether the area ratio 2 is greater than the second preset ratio, if the area ratio 1 is greater than the second preset ratio, and the area ratio 2 is less than the second preset ratio, the judgment result of the above step E is that there is a The area ratio of is greater than the image area of the second preset ratio (that is, the image area composed of point A and point B); then, the above step F and step G are performed to perform the expansion operation on the image area composed of point A and point B, The corrected image area obtained by the dilation operation is determined as a sub-image.

The technical solution defined in the above step D-step F can ignore the influence of the target object occupying a small proportion of the area of the image to be recognized on the definition of the image to be recognized.

In step S305, the image clarity of each sub-image is identified, and the image clarity of the image to be identified is determined according to the identified image clarity of each sub-image;

The specific implementation manner of step S305 is completely the same as step S103 in Embodiment 1. For details, please refer to the description of Embodiment 1, which will not be repeated here.

Compared with the first embodiment, the technical solution defined in the second embodiment of the present application performs the interception operation only when the proportion of the area occupied by the target object in the image to be recognized is less than a certain value. Therefore, the technology defined in the second embodiment of the present application Compared with the first embodiment, the solution can reduce the processing burden of the terminal device to a certain extent. In addition, the technical solution provided in the above step D-step F in the second embodiment of the present application can reduce the number of sub-images to a certain extent. Therefore, the processing burden on the terminal device can be further reduced. In addition, the second embodiment of the present application is the same as the first embodiment, which can also make the image definition recognition result of the image to be recognized more close to the image definition perceived by the human eye.

It should be understood that the size of the sequence number of each step in the above method embodiment does not mean the sequence of execution. The execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiment of the application. .

The third embodiment of the present application provides an image clarity recognition device. For ease of description, only the parts related to the present application are shown. As shown in FIG. 4, the image clarity recognition device 400 includes:

The target acquisition module 401 is configured to acquire an image to be recognized containing one or more target objects and the position of each target object in the image to be recognized;

The target capturing module 402 is configured to capture one or more sub-images containing the target object in the image to be recognized according to the position of each target object in the image to be recognized;

The definition recognition module 403 is configured to recognize the image definition of each sub-image, and determine the image definition of the image to be recognized according to the recognized image definition of each sub-image.

Optionally, the foregoing target interception module 402 includes:

A union determining unit, configured to determine the union of the image regions indicated by each position according to the position of each target object in the image to be recognized;

The first ratio unit is used to calculate the ratio of the first area of the image to be recognized by the image area indicated by the union;

A judging unit for judging whether the first area ratio is smaller than a first preset ratio;

The target capture unit is configured to capture one or more sub-images containing the target object in the image to be recognized if the ratio is smaller than the first preset ratio.

Optionally, the foregoing target interception unit includes:

The second ratio sub-unit is used to calculate the image area indicated by the previous position to occupy the second proportion of the image to be identified according to the position of each target object in the image to be identified if it is less than the first preset ratio. Area ratio

A judging subunit for judging whether there is an image area with a second area ratio greater than a second preset ratio based on the second area ratio, where the second preset ratio is less than the first preset ratio;

An expansion operation subunit, if it exists, perform expansion operation on each image area larger than the second preset ratio to obtain each corrected image area;

A sub-image determining sub-unit for determining each corrected image area as each sub-image;

Optionally, the aforementioned clarity recognition module 403 includes:

The weight determination unit is used to determine the size of each sub-image according to the category of the target object contained in each sub-image, the position of each sub-image in the image to be recognized, and/or the area ratio of each sub-image to the image to be recognized. The weight value corresponding to the image clarity;

The weighted average unit is used for weighting and averaging all the image definitions according to the weight value of each image definition to obtain the image definition of the image to be recognized.

Optionally, the aforementioned image definition recognition device 400 further includes:

A judging module for judging whether the image clarity of the image to be recognized is less than a preset threshold;

The reconstruction module is configured to perform super-resolution reconstruction on the image to be recognized if it is less than the preset threshold.

Optionally, the foregoing target acquisition module 401 includes:

An image acquisition unit for acquiring an image to be processed;

The target detection unit is used to perform target detection on the image to be processed and obtain a detection result, which is used to indicate whether the target object is detected in the image to be processed, and if the target object is detected in the image to be processed , The detection result is used to indicate the position of each target object in the image to be processed;

The target acquisition unit is configured to, if the detection result indicates that the target object is detected in the image to be processed, determine the image to be processed as the image to be recognized, and determine that each target object is in the image to be recognized based on the detection result. The position in the image.

Optionally, the aforementioned image acquisition unit is specifically configured to: when it is detected that the user takes an image through a camera, the image taken by the camera is determined as the aforementioned image to be processed.

It should be noted that the information interaction and execution process between the above-mentioned devices/units are based on the same concept as the method embodiments of this application, and their specific functions and technical effects can be found in the method embodiments. I won't repeat it here.

FIG. 5 is a schematic diagram of a terminal device provided in Embodiment 4 of the present application. As shown in FIG. 5, the terminal device 500 of this embodiment includes: a processor 501, a memory 502, and computer-readable instructions 503 stored in the foregoing memory 502 and running on the foregoing processor 501. When the processor 501 executes the computer-readable instruction 503, the steps in the foregoing method embodiments are implemented, for example, steps S101 to S103 shown in FIG. 1. Alternatively, when the processor 501 executes the computer readable instruction 503, the functions of the modules/units in the foregoing device embodiments, such as the functions of the modules 401 to 403 shown in FIG. 4, are implemented.

Exemplarily, the foregoing computer-readable instruction 503 may be divided into one or more modules/units, and the foregoing one or more modules/units are stored in the foregoing memory 502 and executed by the foregoing processor 501 to complete the application . The foregoing one or more modules/units may be a series of computer-readable instruction instruction segments capable of completing specific functions, and the instruction segment is used to describe the execution process of the foregoing computer-readable instructions 503 in the foregoing terminal device 500. For example, the above-mentioned computer-readable instruction 503 can be divided into a target acquisition module, a target interception module, and a definition recognition module, and the specific functions of each module are as follows:

Identify the image definition of each sub-image, and determine the image definition of the image to be identified according to the identified definition of each image.

The foregoing terminal device may include, but is not limited to, a processor 501 and a memory 502. Those skilled in the art can understand that FIG. 5 is only an example of the terminal device 500, and does not constitute a limitation on the terminal device 500. It may include more or less components than shown in the figure, or a combination of certain components, or different components. For example, the aforementioned terminal device may also include input and output devices, network access devices, buses, and so on.

The so-called processor 501 may be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.

The foregoing memory 502 may be an internal storage unit of the foregoing terminal device 500, such as a hard disk or memory of the terminal device 500. The memory 502 may also be an external storage device of the terminal device 500, for example, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a Secure Digital (SD) card, and a flash memory equipped on the terminal device 500. Card (Flash Card) etc. Further, the aforementioned memory 502 may also include both an internal storage unit of the aforementioned terminal device 500 and an external storage device. The aforementioned memory 502 is used to store the aforementioned computer-readable instructions and other programs and data required by the aforementioned terminal device. The aforementioned memory 502 may also be used to temporarily store data that has been output or will be output.

Those skilled in the art can clearly understand that for the convenience and conciseness of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned functions can be allocated to different functional units and modules as required. Module completion, that is, divide the internal structure of the above device 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 modules 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 is not 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 be aware 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 executed 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 apparatus/terminal device and method may be implemented in other ways. For example, the device/terminal device embodiments described above are merely illustrative. For example, the division of the above-mentioned modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or Components can be combined or integrated into another system, or some features can be omitted or not implemented.

The units described above as separate components may or may not be physically separate, 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 network 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 each embodiment 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 above integrated modules/units are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the present 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 computer-readable instructions. The above-mentioned computer-readable instructions can be stored in a nonvolatile computer. In the read storage medium, when the computer-readable instructions are executed by the processor, the steps of the foregoing method embodiments can be implemented.

The above-mentioned computer-readable instruction includes computer-readable instruction code, and the above-mentioned computer-readable instruction code may be in the form of source code, object code, executable file, or some intermediate forms. Wherein, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and/or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not a limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc. 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, those of ordinary skill in the art should understand that they can still compare the foregoing embodiments. The recorded technical solutions 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 this Within the scope of protection applied for.

Claims

An image definition recognition method, characterized in that it comprises:

Acquiring an image to be recognized containing one or more target objects and the position of each target object in the image to be recognized;

According to the position of each target object in the image to be recognized, one or more sub-images containing the target object are intercepted in the image to be recognized;

The image definition of each sub-image is recognized, and the image definition of the image to be recognized is determined according to the recognized image definition of each sub-image.
The image definition recognition method according to claim 1, characterized in that, according to the position of each target object in the image to be recognized, one or more sub-elements containing the target object are intercepted in the image to be recognized. Images, including:

According to the position of each target object in the image to be recognized, determine the union of the image regions indicated by each position;

Calculating the proportion of the image area indicated by the union occupying the first area of the image to be recognized;

Determine whether the first area ratio is less than a first preset ratio;

If it is less than the first preset ratio, one or more sub-images containing the target object are captured in the image to be recognized.
3. The image definition recognition method according to claim 2, wherein if the ratio is smaller than the first preset ratio, intercepting one or more sub-images containing the target object in the image to be recognized includes:

If less than the first preset ratio, then

According to the position of each target object in the image to be recognized, calculating the ratio of the image area indicated by each position to the second area of the image to be recognized;

Judging whether there is an image area with a second area ratio greater than a second preset ratio according to the second area ratio, where the second preset ratio is less than the first preset ratio;

If it exists, performing an expansion operation on each image area larger than the second preset ratio to obtain each corrected image area;

Each corrected image area is determined as each sub-image.
The image definition identification method according to any one of claims 1 to 3, wherein the image definition of the image to be identified is determined according to the identified image definition of each of the sub-images ,include:

According to the category of the target object contained in each sub-image, the position of each sub-image in the image to be recognized, and/or the proportion of the area occupied by each sub-image of the image to be recognized, the image definition of each sub-image is determined. The corresponding weight value;

According to the weight value of the image sharpness of each sub-image, the image sharpness of all the sub-images is weighted and averaged to obtain the image sharpness of the image to be recognized.
The image definition recognition method according to any one of claims 1 to 3, characterized in that, after the step of determining the image definition of the image to be recognized, the method further comprises:

Determine whether the image clarity of the image to be recognized is less than a preset threshold;

If it is less than the preset threshold, super-resolution reconstruction is performed on the image to be recognized.
The image definition recognition method according to any one of claims 1 to 3, wherein said acquiring the image to be recognized containing one or more target objects and the position of each target object in the image to be recognized Location, including:

Obtain the image to be processed;

Perform target detection on the image to be processed to obtain a detection result, the detection result is used to indicate whether a target object is detected in the image to be processed, and if the target object is detected in the image to be processed, the The detection result is used to indicate the position of each target object in the image to be processed;

If the detection result indicates that a target object is detected in the image to be processed, then:

The image to be processed is determined as the image to be recognized, and the position of each target object in the image to be recognized is determined according to the detection result.
8. The image definition recognition method according to claim 6, wherein said acquiring the image to be processed comprises:

When it is detected that the user has taken an image through the camera, the image taken by the camera is determined as the image to be processed.
An image definition recognition device, characterized in that it comprises:

The target acquisition module is used to acquire an image to be recognized containing one or more target objects and the position of each target object in the image to be recognized;

The target interception module is used to intercept one or more sub-images containing the target object in the image to be recognized according to the position of each target object in the image to be recognized;

The definition recognition module is configured to recognize the image definition of each sub-image, and determine the image definition of the image to be recognized according to the recognized image definition of each sub-image.
8. The image definition recognition device according to claim 8, wherein the target interception module comprises:

A union determining unit, configured to determine the union of the image regions indicated by each position according to the position of each target object in the image to be recognized;

The first proportion unit is used to calculate the proportion of the image area indicated by the union occupying the first area of the image to be recognized;

A judging unit, configured to judge whether the first area ratio is less than a first preset ratio;

The target capture unit is configured to capture one or more sub-images containing the target object in the image to be recognized if the ratio is smaller than the first preset ratio.
9. The image definition recognition device according to claim 9, wherein the target interception unit comprises:

The second ratio subunit is used to calculate the image area indicated by the previous position to occupy the image to be identified according to the position of each target object in the image to be identified if it is less than the first preset ratio The second area ratio;

A judging subunit for judging whether there is an image area with a second area ratio greater than a second preset ratio based on the second area ratio, wherein the second preset ratio is less than the first preset ratio;

An expansion operation subunit, if it exists, perform expansion operation on each image area larger than the second preset ratio to obtain each corrected image area;

The sub-image determination sub-unit is used to determine each corrected image area as each sub-image.
A terminal device, comprising a memory, a processor, and computer-readable instructions stored in the memory and capable of running on the processor, wherein the processor executes the computer-readable instructions as follows step:

Acquiring an image to be recognized containing one or more target objects and the position of each target object in the image to be recognized;

According to the position of each target object in the image to be recognized, one or more sub-images containing the target object are intercepted in the image to be recognized;

The image definition of each sub-image is recognized, and the image definition of the image to be recognized is determined according to the recognized image definition of each sub-image.
The terminal device according to claim 11, wherein the intercepting one or more sub-images containing the target object in the image to be recognized according to the position of each target object in the image to be recognized includes :

According to the position of each target object in the image to be recognized, determine the union of the image regions indicated by each position;

Calculating the proportion of the image area indicated by the union occupying the first area of the image to be recognized;

Determine whether the first area ratio is less than a first preset ratio;

If it is less than the first preset ratio, one or more sub-images containing the target object are captured in the image to be recognized.
The terminal device according to claim 12, wherein, if the ratio is smaller than the first preset ratio, intercepting one or more sub-images containing the target object in the image to be recognized includes:

If less than the first preset ratio, then

According to the position of each target object in the image to be recognized, calculating the ratio of the image area indicated by each position to the second area of the image to be recognized;

Judging whether there is an image area with a second area ratio greater than a second preset ratio according to the second area ratio, where the second preset ratio is less than the first preset ratio;

If it exists, performing an expansion operation on each image area larger than the second preset ratio to obtain each corrected image area;

Each corrected image area is determined as each sub-image.
The terminal device according to any one of claims 11 to 13, wherein the determining the image clarity of the image to be identified according to the identified image clarity of each of the sub-images comprises:

According to the category of the target object contained in each sub-image, the position of each sub-image in the image to be recognized, and/or the proportion of the area occupied by each sub-image of the image to be recognized, the image definition of each sub-image is determined. The corresponding weight value;

According to the weight value of the image sharpness of each sub-image, the image sharpness of all the sub-images is weighted and averaged to obtain the image sharpness of the image to be recognized.
The terminal device according to any one of claims 11 to 13, wherein the processor further implements the following steps when executing the computer-readable instruction:

Determine whether the image clarity of the image to be recognized is less than a preset threshold;

If it is less than the preset threshold, super-resolution reconstruction is performed on the image to be recognized.
The terminal device according to any one of claims 11 to 13, wherein the acquiring the image to be recognized containing one or more target objects and the position of each target object in the image to be recognized includes :

Obtain the image to be processed;

Perform target detection on the image to be processed to obtain a detection result, the detection result is used to indicate whether a target object is detected in the image to be processed, and if the target object is detected in the image to be processed, the The detection result is used to indicate the position of each target object in the image to be processed;

If the detection result indicates that a target object is detected in the image to be processed, then:

The image to be processed is determined as the image to be recognized, and the position of each target object in the image to be recognized is determined according to the detection result.
The terminal device according to claim 16, wherein said acquiring the image to be processed comprises:

When it is detected that the user has taken an image through the camera, the image taken by the camera is determined as the image to be processed.
A computer non-volatile readable storage medium, the computer non-volatile readable storage medium storing computer readable instructions, wherein the computer readable instructions are executed by a processor to implement the following steps:

Acquiring an image to be recognized containing one or more target objects and the position of each target object in the image to be recognized;

According to the position of each target object in the image to be recognized, one or more sub-images containing the target object are intercepted in the image to be recognized;

The image definition of each sub-image is recognized, and the image definition of the image to be recognized is determined according to the recognized image definition of each sub-image.
The computer non-volatile readable storage medium according to claim 18, wherein, according to the position of each target object in the image to be recognized, the image containing the target object is intercepted in the image to be recognized One or more sub-images, including:

According to the position of each target object in the image to be recognized, determine the union of the image regions indicated by each position;

Calculating the proportion of the image area indicated by the union occupying the first area of the image to be recognized;

Determine whether the first area ratio is less than a first preset ratio;

If it is less than the first preset ratio, one or more sub-images containing the target object are captured in the image to be recognized.
The computer non-volatile readable storage medium according to claim 19, wherein if the ratio is smaller than the first preset ratio, one or more sub-groups containing the target object are intercepted in the image to be recognized Images, including:

If less than the first preset ratio, then

According to the position of each target object in the image to be recognized, calculating the ratio of the image area indicated by each position to the second area of the image to be recognized;

Judging whether there is an image area with a second area ratio greater than a second preset ratio according to the second area ratio, where the second preset ratio is less than the first preset ratio;

If it exists, performing an expansion operation on each image area larger than the second preset ratio to obtain each corrected image area;

Each corrected image area is determined as each sub-image.