CN111897986A - An image selection method, device, storage medium and terminal - Google Patents

Abstract

The invention discloses an image selection method, device, storage medium and terminal. The method includes: comparing each second image in a second image library, the corresponding image category, and the relationship between each second image and the corresponding image category The mapping relationship is identified, and the corresponding identification information is obtained; in response to the user's first selection instruction for selecting an image of a designated category, at least one designated image is selected from the second image library according to the identification information as the designated image selected by the user, so , using the embodiment of the present application, since the identification information that can identify each second image in the second image library, the corresponding image category, and the mapping relationship between each second image and the corresponding image category is introduced, therefore, The selected designated image can be accurately indexed according to the above identification information, and at least one designated image can be quickly and intelligently selected from the second image library as the designated image selected by the user.

Description

An image selection method, device, storage medium and terminal

technical field

The present invention relates to the technical field of image processing, and in particular, to an image selection method, device, storage medium and terminal.

Background technique

A large amount of image data can be acquired based on the wide application of image acquisition devices such as image acquisition devices, such as cameras, in various places, for example, in homes, offices, shopping malls and other places.

At the same time, in the scenario where a large number of image acquisition devices such as cameras are deployed at multiple points, the user obtains a large amount of image data. If the user wants to select an image of a specified category from the above-mentioned large amount of image data, it needs to be manually selected manually. , the process of selecting images is too cumbersome, and often introduces the user's personal preferences, which is uncertain.

Alternatively, an image is randomly selected from the above-mentioned large amount of image data. In this way, the selected image is often not an image of the category specified by the user, so that the user cannot quickly and intelligently select any one of the specified category from the above-mentioned large amount of image data. image.

SUMMARY OF THE INVENTION

Embodiments of the present application provide an image selection method, device, storage medium, and terminal. In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended to be an extensive review, nor is it intended to identify key/critical elements or delineate the scope of protection of these embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the detailed description that follows.

In a first aspect, an embodiment of the present application provides an image selection method, the method comprising:

constructing a first image library from a plurality of first images collected by a plurality of image collection devices;

According to the preprocessing model, each first image in the first image library is preprocessed to obtain a corresponding second image, and a second image library is constructed from a plurality of second images;

Classify each second image in the second image library according to a preset neural network model for classifying images to obtain a corresponding image category;

Identifying each second image in the second image library, the corresponding image category, and the mapping relationship between each second image and the corresponding image category, to obtain corresponding identification information;

In response to the user's first selection instruction for selecting an image of a designated category, at least one designated image is selected from the second image library according to the identification information as the designated image selected by the user.

In a second aspect, an embodiment of the present application provides an image selection apparatus, and the apparatus includes:

a first image library building module, configured to construct a first image library from a plurality of first images collected by a plurality of image acquisition devices;

a preprocessing module, configured to preprocess each first image in the first image library according to the preprocessing model to obtain a corresponding second image;

A second image library building module, configured to form a second image library with a plurality of second images preprocessed by the preprocessing module;

an image classification module, configured to classify each second image in the second image library according to a preset neural network model for classifying images to obtain a corresponding image category;

an identification module, configured to identify each second image in the second image library, the corresponding image category, and the mapping relationship between each second image and the corresponding image category, to obtain corresponding identification information;

The image selection module is configured to select at least one designated image from the second image library according to the identification information as the designated image selected by the user in response to the user's first selection instruction for selecting an image of a designated category.

In a third aspect, an embodiment of the present application provides a computer storage medium, where the computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above method steps.

In a fourth aspect, an embodiment of the present application provides a terminal, which may include: a processor and a memory; wherein, the memory stores a computer program, and the computer program is adapted to be loaded by the processor and execute the above method steps.

The technical solutions provided by the embodiments of the present application may include the following beneficial effects:

In the embodiment of the present application, each second image in the second image library, the corresponding image category, and the mapping relationship between each second image and the corresponding image category are identified, and corresponding identification information is obtained; The first selection instruction for selecting an image of a designated category, selects at least one designated image from the second image library according to the identification information as the designated image selected by the user. Since the present application introduces identification information that can identify each second image in the second image library, the corresponding image category, and the mapping relationship between each second image and the corresponding image category, the identification information can be used according to the above identification information. The selected designated image is accurately indexed, and at least one designated image is quickly and intelligently selected from the second image library as the designated image selected by the user.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description serve to explain the principles of the invention.

1 is a schematic flowchart of an image selection method provided by an embodiment of the present application;

2 is a schematic structural diagram of an image selection device provided by an embodiment of the present application;

FIG. 3 is a schematic structural diagram of a terminal provided by an embodiment of the present application.

Detailed ways

The following description and drawings sufficiently illustrate specific embodiments of the invention to enable those skilled in the art to practice them.

It should be understood that the described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Where the following description refers to the drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with some aspects of the invention, as recited in the appended claims.

In the description of the present invention, it should be understood that the terms "first", "second" and the like are used for descriptive purposes only, and should not be construed as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood in specific situations. Furthermore, in the description of the present invention, unless otherwise specified, "a plurality" means two or more. "And/or", which describes the association relationship of the associated objects, means that there can be three kinds of relationships, for example, A and/or B, which can mean that A exists alone, A and B exist at the same time, and B exists alone. The character "/" generally indicates that the associated objects are an "or" relationship.

So far, the existing methods for selecting images of designated categories, if the images are not manually selected, the selection process of image selection is too cumbersome, time-consuming and labor-intensive; if the images are not randomly selected, the selected images are often not the user's For the specified types of images, the accuracy of image selection is low. To this end, the present application provides an image selection method, device, storage medium and terminal to solve the problems existing in the above-mentioned related technical problems. In the technical solution provided by the present application, each second image in the second image library, the corresponding image category, and the mapping relationship between each second image and the corresponding image category are identified, and corresponding identification information is obtained; The user's first selection instruction for selecting an image of a designated category selects at least one designated image from the second image library according to the identification information as the designated image selected by the user. Since the present application introduces identification information that can identify each second image in the second image library, the corresponding image category, and the mapping relationship between each second image and the corresponding image category, the identification information can be used according to the above identification information. The selected designated images are accurately indexed, and at least one designated image is quickly and intelligently selected from the second image library as the designated image selected by the user, which will be described in detail below using an exemplary embodiment.

The image selection method provided by the embodiment of the present application will be described in detail below with reference to FIG. 1 . The method can be implemented by means of a computer program, and can be run on an image selection device. The computer program can be integrated into an application or run as a stand-alone utility application. The image selection apparatus in this embodiment of the present application may be a user terminal, including but not limited to: a personal computer, a tablet computer, a handheld device, a vehicle-mounted device, a wearable device, a computing device, or other processing devices connected to a wireless modem. User terminals may be called by different names in different networks, for example: user equipment, access terminal, subscriber unit, subscriber station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication Equipment, user agent or user equipment, cellular phone, cordless phone, personal digital assistant (PDA), terminal equipment in 5G network or future evolution network, etc.

Referring to FIG. 1 , a schematic flowchart of an image selection method is provided in an embodiment of the present application. As shown in FIG. 1 , the image selection method in the embodiment of the present application may include the following steps:

S101, a first image library is constructed from a plurality of first images collected by a plurality of image collection devices.

In this step, a plurality of first images are acquired by a plurality of image acquisition devices respectively arranged in a preset area, and there is no overlapping acquisition area among the plurality of image acquisition devices.

In practical application scenarios, the image acquisition device may be a camera with a shooting function.

For example, in a specific application scenario, twenty cameras are arranged in a cell, so that the twenty cameras arranged in the cell can capture multiple first images, and there is no overlap between the twenty cameras. In this way, the phenomenon of repeated acquisition of images between any first image in the first image library and other first images is avoided.

In this step, each first image in the first image library is an original image collected by the image collection device, and an image that has not undergone any image processing.

S102: Perform preprocessing on each first image in the first image library according to the preprocessing model to obtain a corresponding second image, and construct a second image library from a plurality of second images.

In a possible implementation manner, the preprocessing model includes a first preprocessing model capable of highlighting at least one key information element in the set of key information elements, and according to the preprocessing model, each first image in the first image library is Performing preprocessing to obtain the corresponding second image includes the following steps:

According to the first preprocessing model, first preprocessing is performed on each first image in the first image library to obtain a corresponding second image highlighting at least one key information element, and the first preprocessing is used to highlight at least one item Preprocessing of key information elements.

In this step, at least one key information element includes at least one of the following:

Feature information elements of the main object in the first image, facial expression information elements of the main object in the first image, and accessory information elements of the main object in the first image.

In addition to the above key information elements, other key information elements may also be used, and the connotation of the key information elements is not specifically limited here.

In a specific scene, when the first image is a picture of a white Garfield, a key information element may be: highlighting the hair feature information element corresponding to the white hair of the white Garfield, then by using the information for highlighting the hair feature In the first preprocessing process of the information element, the background color of the picture is filtered to obtain the corresponding second image.

In the second image, the blue undertone of the background color contrasts sharply with Garfield's white fur in the picture, accentuating the cat's snow-white fur.

The above-mentioned first preprocessing process is only an example, and details are not repeated here. The first preprocessing process corresponding to the first preprocessing model may be adjusted according to the requirements of different specific application scenarios, which will not be repeated here.

It should be noted that the first preprocessing model is a model established according to a conventional model building method, and the method for building a model is not described here. The general method of building a model includes a training set and a test set. The initial training model is constructed according to the image data in the training set, and then the initial training model is tested according to the image data in the test set, and the revised training model is obtained.

In a possible implementation manner, before each first image in the first image library is preprocessed according to the first preprocessing model, the method further includes the following steps:

Read at least one key information element;

Among them, the key information elements include at least one of the following:

Feature information elements of the main object in the first image, facial expression information elements of the main object in the first image, and accessory information elements of the main object in the first image.

In addition to the above key information elements, other key information elements may also be used, and the connotation of the key information elements is not specifically limited here. For the description of the above-mentioned key information elements, please refer to the foregoing description, which will not be repeated here.

In another possible implementation manner, the preprocessing model includes a second preprocessing model capable of removing at least one unrelated background object and/or background person. According to the preprocessing model, each first image in the first image library is Performing preprocessing to obtain the corresponding second image further includes the following steps:

According to the second preprocessing model, a second preprocessing is performed on each of the first images in the first image library to obtain a corresponding second image with at least one background object and/or background person removed, and the second preprocessing is for removing Preprocessing of at least one unrelated background object and/or background person.

In a specific application scenario, when the current first image includes at least one unrelated background object and/or background person, for example, in the case that the current first image includes unrelated background objects and a water glass, according to the first image The second preprocessing model performs second preprocessing on the current first image, removes the water cup, and replaces it with a complete background image selected by the user, and finally obtains a second image with the unrelated background object (water cup) removed.

The above only exemplifies an application scenario in which the water cup is an unrelated background object. In other application scenarios, the unrelated background object may also be a flower, or a background object such as a fan that has no relationship with the main object in the first image, and details are not described herein again.

It should be noted that the second preprocessing model is a model established according to a conventional model building method, and the method for building the model is not described here. The general method of building a model includes a training set and a test set. The initial training model is constructed according to the image data in the training set, and then the initial training model is tested according to the image data in the test set, and the revised training model is obtained.

The above only enumerates two preprocessing processes. In addition to the two preprocessing processes listed above, other preprocessing processes may also be used, which will not be repeated here.

S103: Classify each second image in the second image library according to a preset neural network model for classifying images to obtain a corresponding image category.

In this step, the preset neural network model is a neural network model constructed based on the VGG model. The classification accuracy of this model is more accurate, and it can accurately classify images from the second image library, for example, which pictures belong to The pictures of cars, which pictures belong to the category of pet dogs.

Since the VGG model has more network layers and smaller convolution kernels, more image features can be extracted, thereby improving the accuracy of image classification. However, due to the high network complexity of the VGG model, the training process for building the model is also longer, and the requirements for computer hardware performance are also higher.

In a specific application scenario, different preset neural network models may be selected according to the number of second images in the second image library. For example, in the case that the number of second images in the second image library is not large, and the recognition accuracy of image classification is required to be high, the above-mentioned VGG model can be selected.

In practical applications, the VGG model has the following advantages:

Small convolution kernel; replace all convolution kernels with 3x3 (1x1 is rarely used);

Small pooling kernel; compared to AlexNet's 3x3 pooling kernel, VGG is all 2x2 pooling kernel;

The feature map with deeper layers is wider; since the convolution kernel focuses on expanding the number of channels and pooling focuses on reducing the width and height, the model architecture is deeper and wider, while the increase in the amount of computation slows down;

Full connection to convolution; in the network testing phase, the three full connections in the training phase are replaced by three convolutions, and the parameters during training are reused for testing, so that the fully convolutional network obtained under the test has no restrictions on full connections, so it can receive Input of any width or height.

In another specific application scenario, an optimized convolutional neural network can be selected when the number of second images in the second image library is relatively large, and the requirements for the respective recognition accuracy of the images are not high. For example, the image of the input layer of the convolutional neural network is set to the image of the preset size, the feature extraction is performed on the image through the convolution layer, and the pooling layer reduces the image dimension. Here, the first preset size of the picture is not specifically limited. The input of the second layer of convolution is the output of the first layer of convolution, and the size is the second preset size. Here, the second preset size is not specifically limited. Convolutional layers 3 to 5 have the same structure, and instead of using the convolutional layer followed by the pooling layer, the full convolution method is used to extract as many image features as possible. Before passing into the fully connected layer, the data obtained by the previous layer is flattened, and the multi-dimensional input is one-dimensional, so that the link effect of the fully connected layer is better. The number of neural nodes in the output layer is determined according to the actual classification requirements. In addition, the classification process is continuously optimized, and the method for optimizing the classification process is a conventional method, which will not be repeated here.

S104: Identify each second image in the second image library, the corresponding image category, and the mapping relationship between each second image and the corresponding image category, to obtain corresponding identification information.

In this step, in addition to the above information, the identification information can also identify the time information of the image acquisition by the image acquisition device in order to achieve accurate positioning of each second image; the time information can be specific to: a certain date on a certain day time.

For another example, the address information used for image collection by the image collection device is identified: the address information may be specific to: a certain building in a certain cell.

S105, in response to the user's first selection instruction for selecting an image of a designated category, select at least one designated image from the second image library according to the identification information as the designated image selected by the user.

In practical applications, the selected specified image may be one or multiple, and there is no specific limitation on the number of the specified images.

In a possible implementation manner, after selecting at least one designated image from the second image library according to the identification information, the method further includes the steps of:

In response to the user's second selection instruction for selecting the designated display device, the selected at least one designated image is displayed on the corresponding display device, wherein the second selection instruction carries the MAC address information of the designated display device.

In this step, precise positioning of the specified display device can be achieved through the MAC address information of the display device.

In a possible implementation manner, displaying the selected at least one designated image on the corresponding display device includes the following steps:

When the number of specified images is two or more, calculate the weight value of each specified image respectively;

Sort each specified image according to the image weight value of each specified image;

Each designated image is displayed on the corresponding position of the designated display device according to the corresponding relationship between the order of the images and the display positions of the images on the designated display device.

In practical applications, when two or more designated images are selected, the method for calculating the weight value of each designated image is a conventional method, which will not be repeated here.

After the weight value of each designated image is obtained, the weight value of each designated image is sorted. In practical applications, the first designated image with the largest weight value of the designated image is ranked first, and the designated image corresponding to the weight value is displayed in the central area of the designated display device, and the second designated image with the smallest weight value is displayed. Displayed on the bounding area of the specified display device, for example, the top border, or the bottom border, or the left border, or the right border. Only one display method is exemplified here, and other display methods are also possible. For example, the first designated image with the largest weight value is displayed on the uppermost layer of the designated display device, and the second designated image with the smallest weight value is displayed on the top layer of the designated display device. When specifying the next layer of an image, in order to avoid mutual occlusion between images, the transparency of the display layer of each image can be set. The method is modified and will not be repeated here.

In the embodiment of the present application, each second image in the second image library, the corresponding image category, and the mapping relationship between each second image and the corresponding image category are identified, and corresponding identification information is obtained; The first selection instruction for selecting an image of a specified category, selects at least one specified image from the second image library according to the identification information, as the specified image selected by the user, because the present application introduces the ability to each second image library in the second image library. Identification information for identifying the image, the corresponding image category, and the mapping relationship between each second image and the corresponding image category. Therefore, the selected designated image can be accurately indexed according to the above identification information, and at least one designated image can be quickly and intelligently selected from the second image library as the designated image selected by the user.

The following are apparatus embodiments of the present invention, which can be used to execute method embodiments of the present invention. For details not disclosed in the device embodiments of the present invention, please refer to the method embodiments of the present invention.

Please refer to FIG. 2 , which shows a schematic structural diagram of an image selection apparatus provided by an exemplary embodiment of the present invention. The image selection device can be implemented as all or a part of the terminal through software, hardware or a combination of the two. The image selection apparatus includes a first image library construction module 10 , a preprocessing module 20 , a second image library construction module 30 , an image classification module 40 , an identification module 50 and an image selection module 60 .

Specifically, the first image library construction module 10 is configured to construct a first image library from a plurality of first images collected by a plurality of image acquisition devices;

The preprocessing module 20 is configured to preprocess each first image in the first image library according to the preprocessing model to obtain a corresponding second image;

The second image library construction module 30 is configured to construct a second image library from the plurality of second images preprocessed by the preprocessing module 20;

The image classification module 40 is used for classifying each second image in the second image library according to the preset neural network model used for classifying the image to obtain the corresponding image category;

The identification module 50 is used to identify each second image in the second image library, the corresponding image category, and the mapping relationship between each second image and the corresponding image category to obtain corresponding identification information;

The image selection module 60 is configured to select at least one designated image from the second image library according to the identification information as the designated image selected by the user in response to the user's first selection instruction for selecting an image of a designated category.

Optionally, the preprocessing model includes a first preprocessing model capable of highlighting at least one key information element in the set of key information elements, and the preprocessing module 20 is specifically configured to:

According to the first preprocessing model, first preprocessing is performed on each first image in the first image library to obtain a corresponding second image highlighting at least one key information element, and the first preprocessing is used to highlight at least one item Preprocessing of key information elements.

Optionally, the device further includes:

A reading module (not shown in FIG. 2 ), configured to read at least one item of key information before the preprocessing module 20 preprocesses each first image in the first image library according to the first preprocessing model The key information elements read by the reading module include at least one of the following: the feature information elements of the main object in the first image, the facial expression information elements of the main object in the first image, the Accessory information elements of the main object.

Optionally, the preprocessing model includes a second preprocessing model capable of removing at least one unrelated background object and/or background person, and the preprocessing module 20 is also specifically used for:

According to the second preprocessing model, a second preprocessing is performed on each of the first images in the first image library to obtain a corresponding second image with at least one background object and/or background person removed, and the second preprocessing is for removing Preprocessing of at least one unrelated background object and/or background person.

Optionally, the device further includes:

The display device is used for, after the image selection module 60 selects at least one designated image from the second image library according to the identification information, in response to the user's second selection instruction for selecting the designated display device, the selected at least one designated image is displayed in the corresponding image. The display device, wherein the second selection instruction carries the MAC address information of the designated display device.

Optionally, the display module is specifically used for:

When the number of specified images is two or more, calculate the weight value of each specified image respectively;

Sort each specified image according to the image weight value of each specified image;

Each designated image is displayed on the corresponding position of the designated display device according to the corresponding relationship between the order of the images and the display positions of the images on the designated display device.

Optionally, the multiple first images are acquired by multiple image acquisition devices respectively arranged in the preset area, and there is no overlapping acquisition area between the multiple image acquisition devices.

It should be noted that, when the image selection apparatus provided in the above embodiments executes the image selection method, only the division of the above functional modules is used for illustration. , that is, dividing the internal structure of the device into different functional modules to complete all or part of the functions described above. In addition, the image selection device and the image selection method provided in the above embodiments belong to the same concept, and the implementation process of the image selection device is described in the method embodiment, which will not be repeated here.

In the embodiment of the present application, the identification module identifies each second image in the second image library, the corresponding image category, and the mapping relationship between each second image and the corresponding image category, to obtain corresponding identification information; The selection module selects at least one designated image from the second image library according to the identification information as the designated image selected by the user in response to the user's first selection instruction for selecting an image of a designated category. Since the present application introduces identification information that can identify each second image in the second image library, the corresponding image category, and the mapping relationship between each second image and the corresponding image category, the identification information can be used according to the above identification information. The selected designated image is accurately indexed, and at least one designated image is quickly and intelligently selected from the second image library as the designated image selected by the user.

The present invention further provides a computer-readable medium on which program instructions are stored, and when the program instructions are executed by a processor, implement the image selection methods provided by the above-mentioned respective method embodiments.

The present invention also provides a computer program product containing instructions, which, when running on a computer, enables the computer to execute the image selection methods described in the above method embodiments.

Referring to FIG. 3 , a schematic structural diagram of a terminal is provided in an embodiment of the present application. As shown in FIG. 3 , the terminal 1000 may include: at least one processor 1001 , at least one network interface 1004 , user interface 1003 , memory 1005 , and at least one communication bus 1002 .

Among them, the communication bus 1002 is used to realize the connection and communication between these components.

The user interface 1003 may include a display screen (Display) and a camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.

Wherein, the network interface 1004 may optionally include a standard wired interface and a wireless interface (eg, a WI-FI interface).

The processor 1001 may include one or more processing cores. The processor 1001 uses various excuses and lines to connect various parts of the entire electronic device 1000, and executes by running or executing the instructions, programs, code sets or instruction sets stored in the memory 1005, and calling the data stored in the memory 1005. Various functions of the electronic device 1000 and processing data. Optionally, the processor 1001 may use at least one of a digital signal processing (Digital Signal Processing, DSP), a Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA), and a Programmable Logic Array (Programmable Logic Array, PLA) implemented in hardware. The processor 1001 may integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU), a modem, and the like. Among them, the CPU mainly handles the operating system, user interface, and application programs; the GPU is used for rendering and drawing of the content that needs to be displayed on the display screen; the modem is used to handle wireless communication. It can be understood that, the above-mentioned modem may not be integrated into the processor 1001, but is implemented by a single chip.

The memory 1005 may include random access memory (Random Access Memory, RAM), or may include read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. Memory 1005 may be used to store instructions, programs, codes, sets of codes, or sets of instructions. The memory 1005 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), Instructions and the like used to implement the above method embodiments; the storage data area may store the data and the like involved in the above method embodiments. Optionally, the memory 1005 may also be at least one storage device located away from the aforementioned processor 1001 . As shown in FIG. 3 , the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module and an image selection application program.

In the terminal 1000 shown in FIG. 3 , the user interface 1003 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 1001 can be used to call the image selection application stored in the memory 1005, and specifically execute the Do the following:

constructing a first image library from a plurality of first images collected by a plurality of image collection devices;

According to the preprocessing model, each first image in the first image library is preprocessed to obtain a corresponding second image, and the second image library is constructed from a plurality of second images;

Classify each second image in the second image library according to the preset neural network model for classifying images to obtain a corresponding image category;

Identifying each second image in the second image library, the corresponding image category, and the mapping relationship between each second image and the corresponding image category, to obtain corresponding identification information;

In response to the user's first selection instruction for selecting an image of a designated category, at least one designated image is selected from the second image library according to the identification information as the designated image selected by the user.

In one embodiment, the preprocessing model includes a first preprocessing model capable of highlighting at least one key information element in the set of key information elements, and the processor 1001 executes the first image library according to the preprocessing model When preprocessing each first image in to obtain the corresponding second image, specifically perform the following operations:

According to the first preprocessing model, first preprocessing is performed on each first image in the first image library to obtain a corresponding second image highlighting at least one key information element, and the first preprocessing is used to highlight at least one item Preprocessing of key information elements.

In one embodiment, before the processor 1001 performs preprocessing on each first image in the first image library according to the first preprocessing model, the processor 1001 further performs the following operations:

Read at least one key information element;

Among them, the key information elements include at least one of the following:

Feature information elements of the main object in the first image, facial expression information elements of the main object in the first image, and accessory information elements of the main object in the first image.

In one embodiment, the preprocessing model includes a second preprocessing model capable of removing at least one irrelevant background object, and the processor 1001 performs the preprocessing model for each first image in the first image library. When preprocessing is performed to obtain the corresponding second image, the following operations are also specifically performed:

According to the second preprocessing model, a second preprocessing is performed on each of the first images in the first image library to obtain a corresponding second image with at least one background object removed, and the second preprocessing is used to remove at least one unrelated background. Preprocessing of objects.

In one embodiment, after the processor 1001 performs the selection of at least one specified image from the second image library according to the identification information, the processor 1001 further performs the following operations:

In response to the user's second selection instruction for selecting the designated display device, the selected at least one designated image is displayed on the corresponding display device, wherein the second selection instruction carries the MAC address information of the designated display device.

In one embodiment, when the processor 1001 executes the displaying of the selected at least one specified image on the corresponding display device, the processor 1001 specifically performs the following operations:

When the number of specified images is two or more, calculate the weight value of each specified image respectively;

Sort each specified image according to the image weight value of each specified image;

Each designated image is displayed on the corresponding position of the designated display device according to the corresponding relationship between the order of the images and the display positions of the images on the designated display device.

In one embodiment, the plurality of first images are acquired by a plurality of image acquisition devices respectively arranged in a preset area, and there is no overlapping acquisition area among the plurality of image acquisition devices.

In the embodiment of the present application, each second image in the second image library, the corresponding image category, and the mapping relationship between each second image and the corresponding image category are identified, and corresponding identification information is obtained; The first selection instruction for selecting an image of a specified category, selects at least one specified image from the second image library according to the identification information, as the specified image selected by the user, because the present application introduces the ability to each second image library in the second image library. Identification information for identifying the image, the corresponding image category, and the mapping relationship between each second image and the corresponding image category. Therefore, the selected designated image can be accurately indexed according to the above identification information, and at least one designated image can be quickly and intelligently selected from the second image library as the designated image selected by the user. Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and the program is During execution, it may include the processes of the embodiments of the above-mentioned methods. Wherein, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, or a random storage memory, and the like.

The above disclosures are only the preferred embodiments of the present application, and of course, the scope of the rights of the present application cannot be limited by this. Therefore, equivalent changes made according to the claims of the present application are still within the scope of the present application.

Claims (10)

1. An image selection method, comprising:

constructing a first image library by a plurality of first images acquired by a plurality of image acquisition devices;

preprocessing each first image in the first image library according to a preprocessing model to obtain a corresponding second image, and forming a second image library by a plurality of second images;

classifying each second image in the second image library according to a preset neural network model for classifying the images to obtain a corresponding image category;

identifying each second image, the corresponding image category and the mapping relation between each second image and the corresponding image category in the second image library to obtain corresponding identification information;

and responding to a first selection instruction of a user for selecting the images of the designated category, and selecting at least one designated image from the second image library according to the identification information to be used as the designated image selected by the user.

2. The method according to claim 1, wherein the pre-processing model comprises a first pre-processing model capable of highlighting at least one key information element of the set of key information elements, and wherein pre-processing each first image in the first image library according to the pre-processing model to obtain a corresponding second image comprises:

according to a first preprocessing model, each first image in the first image library is subjected to first preprocessing to obtain a corresponding second image with at least one key information element highlighted, wherein the first preprocessing is preprocessing for highlighting the at least one key information element.

3. The method of claim 2, wherein prior to said pre-processing each first image in the first image library according to a first pre-processing model, the method further comprises:

reading at least one key information element;

wherein the key information elements include at least one of:

a feature information element of the subject object in the first image, a facial expression information element of the subject object in the first image, and an accessory information element of the subject object in the first image.

4. The method of claim 1, wherein the pre-processing model comprises a second pre-processing model capable of removing at least one unrelated background object and/or background person, and wherein pre-processing each first image in the first image library according to the pre-processing model to obtain a corresponding second image further comprises:

and according to a second preprocessing model, carrying out second preprocessing on each first image in the first image library to obtain a corresponding second image with at least one background object and/or background person removed, wherein the second preprocessing is preprocessing for removing at least one unrelated background object and/or background person.

5. The method of claim 1, wherein after said selecting at least one designated image from said second image library based on said identification information, said method further comprises:

and responding to a second selection instruction of a user for selecting the appointed display equipment, and displaying at least one selected appointed image on the corresponding display equipment, wherein the second selection instruction carries the MAC address information of the appointed display equipment.

6. The method according to claim 5, wherein the displaying the selected at least one designated image on the corresponding display device comprises:

under the condition that the number of the designated images is two or more, respectively calculating the weight value of each designated image;

sequencing each appointed image according to the image weight value of each appointed image;

and displaying each appointed image on the corresponding position of the appointed display equipment according to the corresponding relation between the image sequence and the display position of the image on the appointed display equipment.

7. The method of claim 1,

the plurality of first images are acquired by a plurality of image acquisition devices respectively arranged in a preset area, and no overlapping acquisition area exists among the plurality of image acquisition devices.

8. An image selection apparatus, comprising:

the first image library construction module is used for constructing a first image library by a plurality of first images acquired by a plurality of image acquisition devices;

the preprocessing module is used for preprocessing each first image in the first image library according to a preprocessing model to obtain a corresponding second image;

the second image library construction module is used for constructing a second image library by a plurality of second images obtained by preprocessing of the preprocessing module;

the image classification module is used for classifying each second image in the second image library according to a preset neural network model for classifying the images to obtain a corresponding image category;

the identification module is used for identifying each second image in the second image library, the corresponding image category and the mapping relation between each second image and the corresponding image category to obtain corresponding identification information;

and the image selecting module is used for responding to a first selecting instruction of a user for selecting the images of the appointed types, and selecting at least one appointed image from the second image library as the appointed image selected by the user according to the identification information.

9. A computer storage medium, characterized in that it stores a plurality of instructions adapted to be loaded by a processor and to carry out the method steps according to any one of claims 1 to 7.

10. A terminal, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of any of claims 1 to 7.

Images