CN111581419A

CN111581419A - Image processing method and device, electronic equipment and storage medium

Info

Publication number: CN111581419A
Application number: CN202010359303.8A
Authority: CN
Inventors: 苏湘鹏; 龚太祥; 王炳章
Original assignee: Beijing Kingsoft Cloud Network Technology Co Ltd
Current assignee: Beijing Kingsoft Cloud Network Technology Co Ltd
Priority date: 2020-04-29
Filing date: 2020-04-29
Publication date: 2020-08-25
Anticipated expiration: 2040-04-29
Also published as: CN111581419B

Abstract

The embodiment of the invention provides an image processing method, an image processing device, electronic equipment and a storage medium, wherein the method comprises the following steps: receiving a selection instruction aiming at an image to be analyzed, and acquiring the image to be analyzed; obtaining a target image corresponding to the image to be analyzed based on the retrieval of the image to be analyzed in a preset image database; synthesizing the image to be analyzed and the target image to obtain a synthesized image; the composite image comprises the image to be analyzed and the target image; and displaying the composite image. According to the embodiment of the invention, the image processing efficiency can be improved.

Description

Image processing method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of image processing technologies, and in particular, to an image processing method and apparatus, an electronic device, and a storage medium.

Background

Images are the subject of many fields of research as carriers of information. In the research process of the images, the images similar to or identical to the images to be analyzed are retrieved from the image library, so that a user can perform auxiliary analysis on the images to be analyzed according to the retrieval result, and the computing resources are saved. The image library may include the image subjected to the calculation processing and a processing result corresponding to the image subjected to the calculation processing.

In the conventional image retrieval service, after an image to be analyzed is received, the similarity between the image to be analyzed and each image in an image library is calculated, and an image with the similarity larger than a certain threshold is determined as a similar image of the image to be analyzed. However, the threshold for judging the similarity of the images is set manually, and when the threshold is set unreasonably, the accuracy of the retrieval is affected. The existing method for processing similar images obtained by image retrieval service is as follows: downloading the image to be analyzed and the similar image of the image to be analyzed obtained by searching to the local, manually comparing the image to be analyzed and the similar image of the image to be analyzed one by one, and then recording the comparison result in a document.

In practical applications, the number of images to be analyzed may be large, and then, the images to be analyzed and the similar images of the retrieved images to be analyzed are manually compared one by one, and frequent switching of comparison images may be required in the process of recording the comparison result, so that a phenomenon of comparison error is easily caused, and the efficiency of image processing is low.

Disclosure of Invention

An object of embodiments of the present invention is to provide an image processing method, an image processing apparatus, an electronic device, and a storage medium, so as to improve efficiency of image processing. The specific technical scheme is as follows:

in a first aspect, an embodiment of the present invention provides an image processing method, where the method includes:

receiving a selection instruction aiming at an image to be analyzed, and acquiring the image to be analyzed;

obtaining a target image corresponding to the image to be analyzed based on retrieval of the image to be analyzed in a preset image database, wherein the target image is used for representing an image similar to the image to be analyzed in the preset image database;

synthesizing the image to be analyzed and the target image to obtain a synthesized image; the composite image comprises the image to be analyzed and the target image;

and displaying the synthetic image for comparing and analyzing the image to be analyzed and the target image contained in the synthetic image.

Optionally, the method further includes:

receiving a first sort store instruction for the composite image;

storing the composite image to preset storage positions corresponding to different classification results according to the first classification storage instruction; the different classification results include: a first classification result and a second classification result, wherein the first classification result indicates that the image to be analyzed in the synthetic image is similar to the target image, and the second classification result indicates that the image to be analyzed in the synthetic image is not similar to the target image;

and recording the classification result corresponding to the synthetic image.

Optionally, the method further includes:

receiving a first sort store instruction for the composite image;

storing the synthetic image and the image to be analyzed and the target image corresponding to the synthetic image to preset storage positions corresponding to different classification results according to the first classification storage instruction; the different classification results include: a first classification result and a second classification result, wherein the first classification result indicates that the image to be analyzed in the synthetic image is similar to the target image, and the second classification result indicates that the image to be analyzed in the synthetic image is not similar to the target image;

and recording the classification result corresponding to the synthetic image.

Optionally, the step of obtaining the target image corresponding to the image to be analyzed based on the retrieval of the image to be analyzed in a preset image database includes:

obtaining a target image corresponding to the image to be analyzed and the similarity between the image to be analyzed and the target image based on the retrieval of the image to be analyzed in a preset image database;

the step of presenting the composite image comprises:

a composite image including the similarity is shown.

Optionally, the step of presenting the composite image comprises:

displaying the composite image to a user in a display interface, and storing operation options for the classification of the composite image; different ones of the classification storage operation options are used to store the composite image to a storage location corresponding to the classification result.

Optionally, the step of displaying the composite image includes:

displaying the composite image to a user in a display interface, and storing operation options for the classification of the composite image; and different classification storage operation options are used for storing the composite image, the image to be analyzed and the target image corresponding to the composite image to storage positions corresponding to different classification results.

Optionally, the step of obtaining a target image corresponding to the image to be analyzed and a similarity between the image to be analyzed and the target image based on the retrieval of the image to be analyzed in a preset image database includes:

sending an image retrieval request to the image database to obtain a target image corresponding to the image to be analyzed and the similarity between the image to be analyzed and the target image, wherein the image retrieval request carries information of the image to be analyzed, and the information of the image to be analyzed is used for identifying the image to be analyzed.

Optionally, the step of displaying the composite image includes:

displaying the current composite image and the first option and the second option to a user in a display interface;

the method further comprises the following steps:

under the condition that a selection instruction of a user for the first option is received, switching the current synthetic image to a new synthetic image so that the user classifies the new synthetic image, wherein the new synthetic image is as follows: a composite image to be classified;

and under the condition that a selection instruction of the user for the second option is received, switching the current synthetic image to a history synthetic image, wherein the history synthetic image is a synthetic image which is classified completely.

Optionally, after the current synthetic image is switched to the historical synthetic image in the case of receiving a selection instruction of the second option from the user, the method further includes:

receiving a second sort store instruction for the historical composite image;

when the second classification storage instruction is different from the classification result corresponding to the historical synthetic image, reclassifying the historical synthetic image;

storing the reclassified historical synthetic image to a storage position of a classification result corresponding to the second classification storage instruction, and removing the historical synthetic image from an original storage position;

and updating the record of the classification result corresponding to the historical synthetic image.

receiving a second sort store instruction for the historical composite image;

storing the reclassified historical synthetic image and the image to be analyzed and the target image corresponding to the historical synthetic image to a storage position of a classification result corresponding to the second classification storage instruction, and removing the historical synthetic image and the image to be analyzed and the target image corresponding to the historical synthetic image from an original storage position;

In a second aspect, an embodiment of the present invention provides an image processing apparatus, including:

the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for receiving a selection instruction aiming at an image to be analyzed and acquiring the image to be analyzed;

the second acquisition module is used for obtaining a target image corresponding to the image to be analyzed based on the retrieval of the image to be analyzed in a preset image database, wherein the target image is used for representing an image similar to the image to be analyzed in the preset image database;

the image synthesis module is used for carrying out synthesis processing on the image to be analyzed and the target image to obtain a synthesized image; the composite image comprises the image to be analyzed and the target image;

and the image display module is used for displaying the synthetic image and comparing and analyzing the image to be analyzed and the target image contained in the synthetic image.

Optionally, the apparatus further comprises:

a first receiving module for receiving a first classification storage instruction for the composite image;

the first classification storage module is used for storing the composite image to preset storage positions corresponding to different classification results according to the first classification storage instruction; the different classification results include: a first classification result and a second classification result, wherein the first classification result indicates that the image to be analyzed in the synthetic image is similar to the target image, and the second classification result indicates that the image to be analyzed in the synthetic image is not similar to the target image;

and the first result recording module is used for recording the classification result corresponding to the synthetic image.

Optionally, the apparatus further comprises:

a second receiving module for receiving a first sort store instruction for the composite image;

the second classification storage module is used for storing the synthetic image, the image to be analyzed and the target image corresponding to the synthetic image to preset storage positions corresponding to different classification results according to the first classification storage instruction; the different classification results include: a first classification result and a second classification result, wherein the first classification result indicates that the image to be analyzed in the synthetic image is similar to the target image, and the second classification result indicates that the image to be analyzed in the synthetic image is not similar to the target image;

and the second result recording module is used for recording the classification result corresponding to the synthetic image.

Optionally, the second obtaining module is specifically configured to:

the image display module is specifically configured to:

a composite image including the similarity is shown.

Optionally, the image display module is specifically configured to:

Optionally, the second obtaining module is specifically configured to:

Optionally, the image display module is specifically configured to:

the device further comprises:

a first switching module, configured to switch the current composite image to a new composite image to enable a user to classify the new composite image when receiving a selection instruction of the user for the first option, where the new composite image is: a composite image to be classified;

and the second switching module is used for switching the current synthetic image to a historical synthetic image under the condition of receiving a selection instruction of a user for the second option, wherein the historical synthetic image is a classified synthetic image.

Optionally, the apparatus further comprises:

a third receiving module, configured to receive a second classification storage instruction for the history synthetic image;

a first classification module, configured to, when the second classification storage instruction is different from the classification result corresponding to the historical synthetic image, reclassify the historical synthetic image;

the first storage module is used for storing the reclassified historical synthetic image to a storage position of a classification result corresponding to the second classification storage instruction and removing the historical synthetic image from an original storage position;

and the first record updating module is used for updating the record of the classification result corresponding to the historical synthetic image.

Optionally, the apparatus further comprises:

a fourth receiving module, configured to receive a second classification storage instruction for the history synthetic image;

a second classification module, configured to, when the second classification storage instruction is different from the classification result corresponding to the historical synthetic image, re-classify the historical synthetic image;

the second storage module is used for storing the reclassified historical synthetic image, the image to be analyzed and the target image which correspond to the historical synthetic image into a storage position of a classification result which corresponds to the second classification storage instruction, and removing the historical synthetic image, the image to be analyzed and the target image which correspond to the historical synthetic image from an original storage position;

and the second record updating module is used for updating the record of the classification result corresponding to the historical synthetic image.

In a third aspect, an embodiment of the present invention provides an electronic device, which includes a processor and a machine-readable storage medium, where the machine-readable storage medium stores machine-executable instructions capable of being executed by the processor, and the processor executes the machine-executable instructions to implement the method steps of the image processing method provided in the first aspect.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the method steps of the image processing method provided in the first aspect are implemented.

In a fifth aspect, embodiments of the present invention further provide a computer program product containing instructions, which when run on a computer, cause the computer to perform the method steps of the image processing method provided in the first aspect.

In a sixth aspect, embodiments of the present invention further provide a computer program, which, when run on a computer, causes the computer to perform the method steps of the image processing method provided in the first aspect.

According to the image processing method, the image processing device, the electronic equipment and the storage medium, the selection instruction for the image to be analyzed is received, the image to be analyzed is obtained, the target image corresponding to the image to be analyzed is obtained based on the retrieval of the image to be analyzed in the preset image database, the image to be analyzed and the target image are subjected to synthesis processing, a synthetic image is obtained, the synthetic image comprises the image to be analyzed and the target image, and the synthetic image is displayed. In the embodiment of the invention, after the image is obtained, the image to be analyzed and the target image are combined into one image and displayed, so that the comparison of the images is facilitated, compared with the separate comparison of the downloaded images, the comparison and the verification of the images are facilitated, and the processing efficiency of the images can be improved while the workload is reduced. Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above-described advantages at the same time.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

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

FIG. 2 is a flowchart illustrating a second image processing method according to an embodiment of the present invention;

FIG. 3 is a flowchart illustrating a third image processing method according to an embodiment of the present invention;

FIG. 4 is a flowchart illustrating a fourth image processing method according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of an image display interface according to an embodiment of the present invention;

fig. 6 is a flowchart illustrating a fifth image processing method according to an embodiment of the present invention;

fig. 7 is a flowchart illustrating a sixth image processing method according to an embodiment of the present invention;

fig. 8 is a flowchart illustrating a seventh image processing method according to an embodiment of the present invention;

fig. 9 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present invention;

FIG. 10 is a schematic structural diagram of another image processing apparatus according to an embodiment of the present invention;

FIG. 11 is a diagram illustrating a third exemplary embodiment of an image processing apparatus;

FIG. 12 is a diagram illustrating a fourth exemplary embodiment of an image processing apparatus;

fig. 13 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In practical application, in the existing image retrieval service, after receiving an image to be analyzed requested by a user, a similar image of the image to be analyzed requested by the user is returned, and because different application scenes have different requirements for image analysis, thresholds for determining image similarity may be different. When the threshold value is set unreasonably, the retrieval accuracy is affected, and similar images obtained by the image retrieval service need to be audited to test the accuracy of the image retrieval service.

In practice, the number of images to be analyzed may be large, and then, the images to be analyzed and the similar images of the retrieved images to be analyzed are manually compared one by one, and the comparison images may need to be frequently switched in the process of recording the comparison result, so that the phenomenon of comparison error is easily caused, and the efficiency of image processing is low. Further, when the accuracy of the image retrieval service is tested, the accuracy of the similar image obtained by the image retrieval service needs to be manually calculated according to the recorded comparison result, so that the efficiency of testing the accuracy of the image retrieval service is low, and the accuracy of the test is also influenced.

In view of this, an embodiment of the present invention first provides an image processing method, which may include:

obtaining a target image corresponding to the image to be analyzed based on the retrieval of the image to be analyzed in the preset image database, wherein the target image is used for representing an image similar to the image to be analyzed in the preset image database;

synthesizing the image to be analyzed and the target image to obtain a synthesized image; the synthetic image comprises an image to be analyzed and a target image;

and displaying the composite image for comparing and analyzing the image to be analyzed and the target image contained in the composite image.

According to the image processing method provided by the embodiment of the invention, after the image is obtained, the image to be analyzed and the target image are combined into one image and displayed, so that the comparison of the images is facilitated, compared with the separate comparison of the downloaded images, the comparison and verification of the images are facilitated, the workload is reduced, and the processing efficiency of the images is improved.

The following describes an image processing method provided by an embodiment of the present invention in detail:

method example 1

As shown in fig. 1, an embodiment of the present invention provides an image processing method, which may include the steps of:

s101, receiving a selection instruction aiming at an image to be analyzed, and acquiring the image to be analyzed.

The embodiment of the invention can be applied to electronic equipment, and the electronic equipment can be a terminal or a server and other equipment capable of acquiring and displaying images.

Illustratively, when retrieving an image to be analyzed, a target image pair corresponding to the image to be analyzed can be obtained through an image retrieval service, and the target image pair includes: the image to be analyzed and the target image corresponding to the image to be analyzed obtained through retrieval. The obtained target image pair is then stored in a preset storage location, which may be local, or another server communicatively connected to the local, or a cloud server, etc. When the target image pair obtained by the image retrieval service needs to be audited or otherwise processed, a selection instruction for the image to be analyzed can be received, the image to be analyzed is queried, and the image to be analyzed is obtained.

For example, the selection instruction may be a click selection operation instruction for directly selecting the image to be analyzed, or may be a selection operation instruction for selecting a function option associated with the image to be analyzed.

S102, obtaining a target image corresponding to the image to be analyzed based on the retrieval of the image to be analyzed in the preset image database.

When a selection instruction for an image to be analyzed is received and the image to be analyzed is acquired, a target image corresponding to the image to be analyzed can be obtained. The target image corresponding to the image to be analyzed may be obtained by retrieving the image to be analyzed in a preset image database through an image retrieval service, wherein the preset image database stores processed images, and the target image is used for representing an image similar to the image to be analyzed in the preset image database. For example, the image to be analyzed may be one image in road monitoring, and the preset image database stores processed images in the road monitoring, where the processed images correspond to the processing result, for example, information about whether the image includes a vehicle, a type of the included vehicle, a number plate of the vehicle, and the like.

And S103, synthesizing the image to be analyzed and the target image to obtain a synthesized image.

After the image to be analyzed and the target image corresponding to the image to be analyzed are obtained, the image to be analyzed and the target image are synthesized to obtain a synthesized image. The composite image comprises an image to be analyzed and a target image.

For example, after the image to be analyzed and the target image corresponding to the image to be analyzed are obtained, an image to be analyzed and the target image may be synthesized into one image by using a pass function of a PIL (Python Imaging Library) image processing module in a Python language, where the synthesized image includes the image to be analyzed and the target image. Of course, the embodiment of the present invention is described only by taking the pass function of the PIL image processing module in Python language as an example, and the implementation of the present invention may be implemented by using any other manner that can combine two images into one image.

And S104, displaying the composite image.

In the embodiment of the invention, after the image to be analyzed and the target image are combined into one image, the combined image can be directly displayed. The displayed composite image can be used for comparing and analyzing an image to be analyzed and a target image contained in the composite image. Illustratively, a person skilled in the art can use Python language to implement development of an image user interface, and display a composite image on the developed image user interface so as to compare, analyze or view the image to be analyzed and the target image.

According to the image processing method provided by the embodiment of the invention, after the image is obtained, the image to be analyzed and the target image are combined into one image and displayed, so that the comparison of the image is facilitated, compared with the separate comparison of the downloaded image, the comparison and verification of the image are facilitated, and the processing efficiency of the image can be improved while the workload is reduced.

Method example 2

On the basis of the above method embodiment 1, as shown in fig. 2, fig. 2 is a schematic flow chart of a second image processing method provided by an embodiment of the present invention, and the method may include the following steps:

s201, receiving a selection instruction aiming at the image to be analyzed, and acquiring the image to be analyzed.

The implementation of this step may refer to the implementation process of step S101 in method embodiment 1, which is not described herein again in this embodiment of the present invention.

S202, based on the retrieval of the image to be analyzed in the preset image database, a target image corresponding to the image to be analyzed and the similarity between the image to be analyzed and the target image are obtained.

When a selection instruction for an image to be analyzed is received and the image to be analyzed is acquired, a target image corresponding to the image to be analyzed and the similarity between the image to be analyzed and the target image can be obtained. The target image corresponding to the image to be analyzed may be obtained by retrieving the image to be analyzed in a preset image database through an image retrieval service, wherein the preset image database stores the image which has been subjected to the calculation processing. The similarity between the image to be analyzed and the target image may also be obtained when the image retrieval service retrieves the target image from the preset image database for the image to be analyzed. Illustratively, the similarity may be expressed in percentage or decimal.

In an optional implementation manner of the embodiment of the present invention, step S202 may include:

sending an image retrieval request to an image database to obtain a target image corresponding to the image to be analyzed and the similarity between the image to be analyzed and the target image, wherein the image retrieval request carries information of the image to be analyzed.

In the embodiment of the invention, the electronic equipment can send the image retrieval request carrying the information of the image to be analyzed to the image database, so as to obtain the target image corresponding to the image to be analyzed and the similarity between the image to be analyzed and the target image. The information of the image to be analyzed carried in the image retrieval request can be used for identifying the image to be analyzed. For example, the information for identifying the image to be analyzed may be a code performed on the image to be analyzed in advance, or a corresponding storage number of the image to be analyzed in a storage location thereof, and the information of the image to be analyzed may be used to uniquely identify the image to be analyzed.

For example, the elastic search is a distributed, highly-extended, and highly-real-time search and data analysis engine, and may use es (elastic search) query to query each image to be analyzed, the image subjected to computation processing in the image database, and the similarity between each image to be analyzed obtained through the image retrieval service and each image in the image database, so as to obtain each image to be analyzed, a target image corresponding to each image to be analyzed, and the similarity between each image to be analyzed and the corresponding target image. And further analyzing the obtained images to be analyzed, the target images corresponding to the images to be analyzed and the similarity between the images to be analyzed and the corresponding target images by using a JSON module in the Python language to obtain each image to be analyzed, the target image corresponding to each image to be analyzed and the similarity between each image to be analyzed and the target image.

And S203, synthesizing the image to be analyzed and the target image to obtain a synthesized image.

The implementation of this step may refer to the implementation process of step S103 in method embodiment 1, which is not described herein again in this embodiment of the present invention.

S204, displaying the composite image containing the similarity.

After the image to be analyzed and the target image are combined into one image, the similarity between the image to be analyzed and the target image can be added to the combined image, and the combined image containing the similarity is displayed. Specifically, the implementation manner of adding the similarity between the image to be analyzed and the target image to the synthesized image is as follows: the similarity may be watermarked to the composite image by adding a watermark, or may be added to the composite image by adding a label.

In the embodiment of the invention, after the image is obtained, the image to be analyzed and the target image are combined into one image, and the combined image containing the similarity is displayed, so that the comparison of the images is facilitated, compared with the separate comparison of the downloaded images, the comparison and verification of the images are more facilitated, and the similarity between the image to be analyzed and the target image is displayed, so that a reference basis can be provided for a verifier, the verification speed is further improved, and the processing efficiency of the image is improved while the workload is reduced.

Method example 3

On the basis of the above method embodiment 1, as shown in fig. 3, fig. 3 is a schematic flow chart of a third image processing method provided in the embodiment of the present invention, and the method may further include the following steps:

s301, a first classification storage instruction for the synthetic image is received.

In presenting the composite image, a first sort store instruction for the composite image may be received, which may be used to sort and store the composite image. Illustratively, the composite image may be presented on a graphical user interface that also includes a function option for processing the presented composite image.

And S302, storing the synthetic image to preset storage positions corresponding to different classification results according to the first classification storage instruction.

After receiving a first classification storage instruction for the composite image, the composite image may be classified and stored in a storage location corresponding to a preset different classification result. The different classification results may include: and the first classification result is used for indicating that the image to be analyzed in the synthetic image is similar to the target image, and the second classification result is used for indicating that the image to be analyzed in the synthetic image is not similar to the target image.

For example, the first sorting storage instruction may represent a similar instruction or a dissimilar instruction, and when the first sorting storage instruction represents a similar instruction, it indicates that the image to be analyzed in the displayed composite image is judged to be similar to the target image, and at this time, the composite image is stored in a similar corresponding storage location, and in particular, may be stored in a folder representing similarity, for example, the folder may be named as similar or a, and so on. When the first classification storage instruction indicates a dissimilarity instruction, it indicates that the image to be analyzed in the displayed composite image is judged to be dissimilar from the target image, and at this time, the composite image is stored in a dissimilar corresponding storage location, specifically, the composite image may be stored in a folder representing dissimilarity, for example, the folder may be named dissimilar or B, and the like. The composite image is stored to the storage positions corresponding to the preset different classification results, and the composite image can be conveniently used in subsequent checking or re-auditing, classifying and other operations.

And S303, recording the classification result corresponding to the composite image.

When the displayed composite images are classified and stored, the classification results corresponding to the composite images can be recorded, so that the accuracy of the image retrieval service can be calculated when needed.

In the embodiment of the invention, the displayed synthetic images can be classified and stored, only the synthetic images are stored, the space occupied by storage can be reduced, resources are saved, the classification result is automatically recorded, the workload of manual recording is reduced, and meanwhile, the phenomenon that errors are easy to occur in the manual recording process is avoided. The accuracy of testing the image retrieval service can be improved while the image processing efficiency is improved.

On the basis of the method embodiment 3, in an optional implementation manner of the embodiment of the present invention, the implementation manner of the step S104 may include:

and displaying the composite image to a user in a display interface, and storing operation options for the classification of the composite image. And different classification storage operation options are used for storing the composite image to storage positions corresponding to different classification results.

For example, as shown in fig. 5, fig. 5 is a schematic diagram of an image presentation interface provided by an embodiment of the present invention, a top column of the presentation interface may include a function option, which may be a classification storage operation option for a composite image, for example, similar and dissimilar, for a user to perform a selection operation, and the composite image may be presented to the user below the function option, where the composite image may include an image to be analyzed, a target image, and a similarity between the image to be analyzed and the target image. The image to be analyzed and the target image may be images with the same aspect ratio distributed up and down or left and right, or images with different aspect ratios distributed up and down or left and right, and the specific display size and proportion can be adjusted by those skilled in the art according to the angle convenient for observation. The display position of the similarity may be at any position on the synthesized image.

In the embodiment of the invention, the composite image can be displayed to the user in the display interface, and the classified storage operation options and other functional options aiming at the composite image can be displayed to the user, so that the user can observe and operate the composite image conveniently, and the image processing efficiency is improved.

Method example 4

On the basis of the foregoing method embodiment 1, as shown in fig. 4, fig. 4 is a schematic flow chart of a fourth image processing method according to an embodiment of the present invention, where the method may further include the following steps:

s401, a first classification storage instruction for the synthetic image is received.

The implementation of this step may refer to the implementation process of step S301 in method embodiment 3, which is not described herein again in this embodiment of the present invention.

S402, storing the synthetic image, the image to be analyzed and the target image corresponding to the synthetic image to preset storage positions corresponding to different classification results according to the first classification storage instruction.

After receiving a first classification storage instruction for the synthetic image, the synthetic image may be classified, and the synthetic image, the image to be analyzed and the target image corresponding to the synthetic image are stored in the storage locations corresponding to the preset different classification results. The different classification results may include: and the first classification result is used for indicating that the image to be analyzed in the synthetic image is similar to the target image, and the second classification result is used for indicating that the image to be analyzed in the synthetic image is not similar to the target image.

For example, the first classification storage instruction may represent a similar instruction or a dissimilar instruction, and when the first classification storage instruction represents a similar instruction, it indicates that the image to be analyzed and the target image in the displayed composite image are judged to be similar, at this time, the composite image and the image to be analyzed and the target image corresponding to the composite image are stored in a storage location corresponding to the similarity, and specifically, may be stored in a folder representing the similarity, for example, the folder may be named as similar or a, and so on. When the first classified storage instruction indicates a dissimilarity instruction, it indicates that the image to be analyzed and the target image in the displayed synthetic image are judged to be dissimilar, and at this time, the synthetic image and the image to be analyzed and the target image corresponding to the synthetic image are stored to a storage location corresponding to dissimilarity, and specifically, may be stored in a folder representing dissimilarity, for example, the folder may be named dissimilar or B, and so on. And storing the synthetic image, the image to be analyzed and the target image corresponding to the synthetic image to preset storage positions corresponding to different classification results, so that the synthetic image can be conveniently used in subsequent checking or re-auditing, classifying and other operations.

And S403, recording the classification result corresponding to the composite image.

The implementation of this step may refer to the implementation process of step S303 in method embodiment 3, which is not described herein again in this embodiment of the present invention.

In the embodiment of the invention, the displayed synthetic images can be classified and stored, and the synthetic images, the images to be analyzed and the target images corresponding to the synthetic images are stored, so that more bases are provided for the follow-up re-examination or re-classification of the synthetic images, and the classification result is automatically recorded, thereby reducing the workload of manual recording and avoiding the phenomenon of error easily occurring in the manual recording process. The accuracy of testing the image retrieval service can be improved while the image processing efficiency is improved.

On the basis of the method embodiment 4, in an optional implementation manner of the embodiment of the present invention, the implementation manner of the step S104 may include:

and displaying the composite image to a user in a display interface, and storing operation options for the classification of the composite image. And different classification storage operation options are used for storing the synthetic image, the image to be analyzed corresponding to the synthetic image and the target image to storage positions corresponding to different classification results.

Method example 5

On the basis of the above method embodiments 1 to 4, the step of presenting the composite image in the above step S104 or S204 may include:

the current composite image and the first and second options are presented to the user in a presentation interface.

For example, as shown in fig. 5, the function options included in the uppermost column of the presentation interface may also be a first option and a second option, where the first option may be represented as a forward option, the forward option may be used to process a next unprocessed image to be analyzed, the second option may be represented as a backward option, and the backward option may be used to view or reclassify a processing result of a composite image corresponding to a last processed image to be analyzed. Of course, the examples provided in the embodiments of the present invention are only for facilitating understanding of the embodiments of the present invention, and do not constitute specific limitations on the embodiments of the present invention.

On the basis of the above method embodiments 1-4, as shown in fig. 6, fig. 6 is a schematic flow chart of a fifth image processing method provided by the embodiment of the present invention, and after the above step S104 or S204, the method may further include the following steps:

and S505, under the condition that a selection instruction of the user for the first option is received, switching the current synthetic image to a new synthetic image so that the user classifies the new synthetic image.

When receiving a selection instruction of a user for a first option indicating forward progress, indicating that operations such as classified storage or viewing have been completed on a currently displayed composite image, processing a next unprocessed image to be analyzed, and switching the current composite image to a new composite image, so that the user performs classification processing on the new composite image, where the new composite image is: a composite image to be classified.

And S506, under the condition that a selection instruction of the user for the second option is received, switching the current synthetic image to the historical synthetic image.

And under the condition that a selection instruction of the user for a second option representing backward movement is received, indicating that the classified historical synthetic images need to be viewed or reviewed, classified and the like again, and at the moment, switching the current synthetic image into the historical synthetic image, wherein the historical synthetic image is the classified synthetic image.

In the embodiment of the present invention, operations such as viewing or modifying and classifying may be performed on a synthetic image corresponding to a processed image to be analyzed, where the synthetic image corresponding to the processed image to be analyzed, and/or the image to be analyzed corresponding to the synthetic image and a target image have been stored in storage locations corresponding to different classification results. For example, each image to be analyzed may be stored in any data structure, and the images to be analyzed are processed and sorted according to the storage sequence during the processing of the images to be analyzed. In the case of receiving a selection instruction of the user for the second option representing the backward movement, the current synthetic image may be switched to the historical synthetic image corresponding to the previous image to be analyzed adjacent to the current synthetic image in the order of classified storage of the images to be analyzed, so that the user can view the historical synthetic image again or modify the classification and the like.

In the embodiment of the invention, the processed composite image can be checked or modified and classified by directly using the functional options displayed on the display interface, and the processed composite image does not need to be selected one by one from a plurality of processed images and redisplayed for checking, so that the process of checking, checking or modifying the processed image is simplified, and the processing efficiency of the image is further improved.

Method example 6

On the basis of the foregoing method embodiment 5, as shown in fig. 7, fig. 7 is a schematic flowchart of a sixth image processing method according to an embodiment of the present invention, where the method may further include the following steps:

s601, receiving a second classification storage instruction aiming at the history synthetic image.

After the current composite image displayed on the display interface is switched to the historical composite image, operations such as viewing or modifying the classified storage corresponding to the historical composite image can be performed, when the classified storage corresponding to the historical composite image is modified, a second classified storage instruction aiming at the historical composite image can be received, and the second classified storage instruction can represent a similar instruction or a dissimilar instruction.

And S602, reclassifying the history synthetic images when the second classification storage command is different from the classification result corresponding to the history synthetic images.

When a second sort storage instruction for the history synthetic image is received, it may be determined whether the second sort storage instruction is the same as the sort result corresponding to the history synthetic image. If the historical synthetic images are the same, the classification storage result of the historical synthetic image does not need to be modified, and then no operation is performed; if not, indicating that the classification storage result of the history synthetic image needs to be modified, step S603 is performed.

Illustratively, the classification results corresponding to the historical synthetic images are similar, and when the second classification storage instruction indicates similarity, it indicates that the classification storage results of the historical synthetic images do not need to be modified; when the second classification storage instruction indicates that the historical synthetic images are not similar, the classification storage result of the historical synthetic images needs to be modified, namely, the historical synthetic images are classified and stored again.

S603, storing the reclassified historical synthetic image to a storage position of a classification result corresponding to the second classification storage instruction, and removing the historical synthetic image from the original storage position.

Illustratively, the classification results corresponding to the historical synthetic images are similar, and when the classification storage result of the historical synthetic images needs to be modified, the historical synthetic images after being reclassified can be stored in the storage positions of the classification results corresponding to the dissimilar synthetic images, and the historical synthetic images can be removed from the storage positions corresponding to the original similar classification results.

And S604, updating the record of the classification result corresponding to the historical synthetic image.

And updating the record of the classification result corresponding to the historical synthetic image while classifying and storing the historical synthetic image again so that the recorded classification result of the synthetic image is consistent with the actual classification and storage result of the synthetic image.

According to the embodiment of the invention, the current synthetic image displayed on the display interface can be directly switched into the historical synthetic image, so that the historical synthetic image can be conveniently checked, and further auditing and modifying can be carried out. When the historical synthetic images are modified, the stored positions of the historical synthetic images can be synchronously modified and the recorded results can be updated, manual modification is not needed, the operation process of modifying the classified and stored historical synthetic images is simplified, and the image processing efficiency is improved.

Method example 7

On the basis of the foregoing method embodiment 5, as shown in fig. 8, fig. 8 is a schematic flow chart of a seventh image processing method according to an embodiment of the present invention, where the method may further include the following steps:

s701, receiving a second classification storage instruction aiming at the history synthetic image.

And S702, reclassifying the historical synthetic images when the second classification storage command is different from the classification result corresponding to the historical synthetic images.

The implementation of steps S701 and S702 may refer to the implementation processes of steps S601 and S602 in the above method embodiment 6, and details of the embodiment of the present invention are not repeated herein.

And S703, storing the reclassified historical synthetic image and the image to be analyzed and the target image corresponding to the historical synthetic image to a storage position of a classification result corresponding to the second classification storage instruction, and removing the historical synthetic image and the image to be analyzed and the target image corresponding to the historical synthetic image from the original storage position.

Illustratively, the classification results corresponding to the historical synthetic images are similar, and when the classification storage results of the historical synthetic images need to be modified, the reclassified historical synthetic images, and the images to be analyzed and the target images corresponding to the historical synthetic images can be stored in the storage positions of the classification results which are not similar, and the historical synthetic images, and the images to be analyzed and the target images corresponding to the historical synthetic images can be removed from the storage positions corresponding to the original similar classification results.

S704, the record of the classification result corresponding to the history synthetic image is updated.

Corresponding to the above method embodiment, the embodiment of the present invention also provides a corresponding device embodiment.

Apparatus example 1

As shown in fig. 9, an embodiment of the present invention provides an image processing apparatus, which may include:

the first obtaining module 801 is configured to receive a selection instruction for an image to be analyzed, and obtain the image to be analyzed.

The second obtaining module 802 is configured to obtain a target image corresponding to an image to be analyzed based on the retrieval of the image to be analyzed in the preset image database, where the target image is used to represent an image similar to the image to be analyzed in the preset image database.

An image synthesis module 803, configured to perform synthesis processing on the image to be analyzed and the target image to obtain a synthesized image; the composite image includes an image to be analyzed and a target image.

The image displaying module 804 is configured to display the composite image, and compare and analyze an image to be analyzed and a target image included in the composite image.

According to the image processing device provided by the embodiment of the invention, after the image is obtained, the image to be analyzed and the target image are combined into one image and displayed, so that the comparison of the image is facilitated, compared with the case of separately comparing the downloaded image, the comparison and verification of the image are facilitated, and the processing efficiency of the image can be improved while the workload is reduced.

Optionally, the second obtaining module 802 is specifically configured to:

and obtaining a target image corresponding to the image to be analyzed and the similarity between the image to be analyzed and the target image based on the retrieval of the image to be analyzed in the preset image database.

The image display module 804 is specifically configured to:

a composite image including the similarity is shown.

Optionally, the second obtaining module 802 is specifically configured to:

sending an image retrieval request to an image database to obtain a target image corresponding to the image to be analyzed and the similarity between the image to be analyzed and the target image, wherein the image retrieval request carries information of the image to be analyzed, and the information of the image to be analyzed is used for identifying the image to be analyzed.

Apparatus example 2

As shown in fig. 10, on the basis of the above-mentioned apparatus embodiment 1, an embodiment of the present invention provides another image processing apparatus, which may further include:

a first receiving module 901, configured to receive a first classification storage instruction for a composite image.

A first classification storage module 902, configured to store the composite image to a storage location corresponding to a preset different classification result according to the first classification storage instruction; the different classification results include: and the first classification result and the second classification result, wherein the first classification result indicates that the image to be analyzed in the synthetic image is similar to the target image, and the second classification result indicates that the image to be analyzed in the synthetic image is not similar to the target image.

And a first result recording module 903, configured to record a classification result corresponding to the composite image.

Optionally, on the basis of the image processing apparatus shown in fig. 10, the image displaying module 804 is specifically configured to:

displaying the composite image to a user in a display interface, and storing operation options aiming at the classification of the composite image; and different classification storage operation options are used for storing the composite image to storage positions corresponding to different classification results.

Optionally, on the basis of the apparatus embodiment 1, an embodiment of the present invention provides another image processing apparatus, which may further include the following modules:

a second receiving module to receive a first sort store instruction for the composite image.

The second classification storage module is used for storing the synthetic image, the image to be analyzed and the target image corresponding to the synthetic image to preset storage positions corresponding to different classification results according to the first classification storage instruction; the different classification results include: and the first classification result and the second classification result, wherein the first classification result indicates that the image to be analyzed in the synthetic image is similar to the target image, and the second classification result indicates that the image to be analyzed in the synthetic image is not similar to the target image.

Optionally, the image displaying module 804 is specifically configured to:

displaying the composite image to a user in a display interface, and storing operation options aiming at the classification of the composite image; and different classification storage operation options are used for storing the composite image, the image to be analyzed corresponding to the composite image and the target image to storage positions corresponding to different classification results.

In the embodiment of the invention, the displayed synthetic images can be classified and stored, the classification result is automatically recorded, the manual recording workload is reduced, and meanwhile, the phenomenon that errors are easy to occur in the manual recording process is avoided. And the composite image can be displayed to the user in the display interface, and the classified storage operation options and other functional options aiming at the composite image can be displayed to the user, so that the user can observe and operate the composite image conveniently, and the accuracy of the image retrieval service test can be improved while the image processing efficiency is improved.

Apparatus example 3

On the basis of the foregoing device embodiment 2, the image display module 804 is specifically configured to:

As shown in fig. 11, the embodiment of the present invention provides a third image processing apparatus, which may further include:

a first switching module 110, configured to switch, when receiving a selection instruction of a user for a first option, the current composite image to a new composite image, so that the user classifies the new composite image, where the new composite image is: a composite image to be classified.

And a second switching module 111, configured to switch the current synthetic image to a history synthetic image when receiving a selection instruction of the user for the second option, where the history synthetic image is a classified synthetic image.

In the embodiment of the invention, the processed composite image can be checked by directly using the functional options displayed on the display interface, and the processed images do not need to be selected one by one and displayed again for checking, so that the process of checking, checking or modifying the processed images is simplified, and the processing efficiency of the images is further improved.

Apparatus example 4

As shown in fig. 12, on the basis of the above-mentioned apparatus embodiment 3, an embodiment of the present invention provides a fourth image processing apparatus, which may further include:

a third receiving module 120, configured to receive a second classification storage instruction for the history composite image.

And the first classification module 121 is configured to reclassify the historical synthetic images when the second classification storage instruction is different from the classification result corresponding to the historical synthetic images.

And the first storage module 122 is configured to store the reclassified historical composite image in a storage location of a classification result corresponding to the second classification storage instruction, and remove the historical composite image from the original storage location.

And the first record updating module 123 is configured to update a record of the classification result corresponding to the history synthetic image.

Optionally, on the basis of the apparatus embodiment 3, an embodiment of the present invention provides another image processing apparatus, which may further include the following modules:

and the fourth receiving module is used for receiving a second classification storage instruction aiming at the historical synthetic image.

And the second classification module is used for reclassifying the historical synthetic images when the second classification storage instruction is different from the classification result corresponding to the historical synthetic images.

And the second storage module is used for storing the reclassified historical synthetic images, the images to be analyzed and the target images corresponding to the historical synthetic images to the storage positions of the classification results corresponding to the second classification storage instructions, and removing the historical synthetic images, the images to be analyzed and the target images corresponding to the historical synthetic images from the original storage positions.

As shown in fig. 13, the device 130 includes a processor 131 and a machine-readable storage medium 132, where the machine-readable storage medium stores machine-executable instructions capable of being executed by the processor, and the processor executes the machine-executable instructions to implement the steps of the image processing method provided by the embodiment of the present invention.

The machine-readable storage medium may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.

According to the electronic equipment provided by the embodiment of the invention, after the image is obtained, the image to be analyzed and the target image are combined into one image and displayed, so that the comparison of the images is facilitated, compared with the separate comparison of the downloaded images, the comparison and verification of the images are facilitated, and the processing efficiency of the images can be improved while the workload is reduced.

The embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the computer program is used to execute the steps of the image processing method provided by the embodiment of the present invention.

According to the computer-readable storage medium provided by the embodiment of the invention, after the image is obtained, the image to be analyzed and the target image are combined into one image and displayed, so that the comparison of the image is facilitated, compared with the case of separately comparing the downloaded image, the comparison and verification of the image are facilitated, and the processing efficiency of the image can be improved while the workload is reduced.

Embodiments of the present invention further provide a computer program product containing instructions, which when run on a computer, cause the computer to perform the steps of an image processing method provided by an embodiment of the present invention.

According to the computer program product containing the instructions, after the image is obtained, the image to be analyzed and the target image are combined into one image and displayed, so that the comparison of the image is facilitated, compared with the case that the downloaded image is separately compared, the comparison and verification of the image are facilitated, the workload is reduced, and meanwhile, the processing efficiency of the image is improved.

Embodiments of the present invention further provide a computer program, which, when running on a computer, causes the computer to execute the steps of an image processing method provided by an embodiment of the present invention.

According to the computer program containing the instructions, after the images are obtained, the images to be analyzed and the target images are combined into one image and displayed, so that comparison of the images is facilitated, comparison and verification of the images are facilitated compared with the comparison of the downloaded images separately, and the processing efficiency of the images can be improved while the workload is reduced.

For the apparatus/electronic device/storage medium embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to part of the description of the method embodiment.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the device/electronic apparatus embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and for the relevant points, reference may be made to some descriptions of the method embodiments.

The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims

1. An image processing method, characterized in that the method comprises:

2. The method of claim 1, further comprising:

receiving a first sort store instruction for the composite image;

and recording the classification result corresponding to the synthetic image.

3. The method of claim 1, further comprising:

receiving a first sort store instruction for the composite image;

and recording the classification result corresponding to the synthetic image.

4. The method according to claim 1, wherein the step of obtaining the target image corresponding to the image to be analyzed based on the retrieval of the image to be analyzed in a preset image database comprises:

the step of presenting the composite image comprises:

a composite image including the similarity is shown.

5. The method of claim 2, wherein said step of presenting said composite image comprises:

6. The method of claim 3, wherein said step of presenting said composite image comprises:

displaying the composite image to a user in a display interface, and storing operation options for the classification of the composite image; and different classification storage operation options are used for storing the composite image, the image to be analyzed and the target image corresponding to the composite image to storage positions corresponding to the classification results.

7. The method according to claim 4, wherein the step of obtaining the target image corresponding to the image to be analyzed and the similarity between the image to be analyzed and the target image based on the retrieval of the image to be analyzed in a preset image database comprises:

8. The method of any one of claims 2, 3, 5 and 6, wherein said step of presenting said composite image comprises:

the method further comprises the following steps:

9. The method according to claim 8, wherein after switching the current synthesized image to a history synthesized image upon receiving a selection instruction of the second option from a user, the method further comprises:

receiving a second sort store instruction for the historical composite image;

10. The method according to claim 8, wherein after switching the current synthesized image to a history synthesized image upon receiving a selection instruction of the second option from a user, the method further comprises:

receiving a second sort store instruction for the historical composite image;

11. An image processing apparatus, characterized in that the apparatus comprises:

12. An electronic device comprising a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor to perform method steps of an image processing method as claimed in any one of claims 1 to 10.

13. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method steps of an image processing method according to any one of claims 1 to 10.