CN111460195B - Image processing method, device, storage medium and electronic equipment - Google Patents

Abstract

The application discloses a picture processing method, a picture processing device, a storage medium and electronic equipment. The picture processing method can be applied to the electronic equipment, and comprises the following steps: acquiring a plurality of pictures; classifying the plurality of pictures to obtain at least one category; determining a target category meeting preset conditions from the at least one category; and clustering the pictures contained in each target category to obtain a clustering result of each target category. The method and the device can effectively manage the pictures.

Description

Image processing method, device, storage medium and electronic equipment

technical field

The present application belongs to the technical field of pictures, and in particular relates to a picture processing method, device, storage medium and electronic equipment.

Background technique

As the photographing capabilities of electronic devices become stronger and stronger, users often use electronic devices to take photos. For example, users can take pictures of landscapes, people, and so on. The photos taken by the user are generally stored in the photo album of the electronic device, so that the user can consult these photos at any time. In addition, pictures downloaded by the user from the Internet are generally stored in the photo album. However, in related technologies, electronic devices cannot effectively manage pictures.

Contents of the invention

Embodiments of the present application provide a picture processing method, device, storage medium, and electronic equipment, which can effectively manage pictures.

In the first aspect, the embodiment of the present application provides an image processing method, which is applied to an electronic device, and the method includes:

Get multiple pictures;

Classifying the multiple pictures to obtain at least one category;

determining a target category satisfying a preset condition from the at least one category;

The pictures included in each target category are clustered to obtain a clustering result for each target category.

In the second aspect, the embodiment of the present application provides an image processing device, which is applied to electronic equipment, and the device includes:

Acquisition module, used to obtain multiple pictures;

A classification module, configured to classify the multiple pictures to obtain at least one category;

a determining module, configured to determine a target category satisfying preset conditions from the at least one category;

The clustering module is used for clustering the pictures contained in each target category, and obtaining the clustering result of each target category.

In the third aspect, the embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed on the computer, the computer executes the image processing method provided in the embodiment of the present application in the process.

In the fourth aspect, the embodiment of the present application further provides an electronic device, including a memory and a processor, and the processor executes the process in the image processing method provided in the embodiment of the present application by calling the computer program stored in the memory .

In the embodiment of the present application, after acquiring multiple pictures, the electronic device may classify the multiple pictures to obtain at least one category. The electronic device may determine a target category satisfying a preset condition from the at least one category, and perform clustering on pictures under each target category, so as to obtain a clustering result of pictures under each target category. Therefore, in the embodiment of the present application, the electronic device may first classify the pictures once, and then perform clustering once on the pictures of the target category based on the classification, so as to realize the subdivision of the pictures. Since the subdivision of pictures is helpful for searching and browsing pictures, this embodiment of the present application can realize effective management of pictures.

Description of drawings

The technical solutions and beneficial effects of the present application will be apparent through the detailed description of the specific embodiments of the present application below in conjunction with the accompanying drawings.

FIG. 1 is a schematic flowchart of an image processing method provided by an embodiment of the present application.

FIG. 2 is another schematic flowchart of the image processing method provided by the embodiment of the present application.

Fig. 3 is a schematic diagram of the architecture of the Siamese neural network provided by the embodiment of the present application.

FIG. 4 to FIG. 8 are schematic diagrams of scenes of the image processing method provided by the embodiment of the present application.

FIG. 9 is a schematic structural diagram of an image processing device provided by an embodiment of the present application.

FIG. 10 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

FIG. 11 is another schematic structural diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

Referring to the drawings, where the same reference numerals represent the same components, the principle of the present application is illustrated by being implemented in a suitable computing environment. The following description is based on illustrated specific embodiments of the present application, which should not be construed as limiting other specific embodiments of the present application that are not described in detail here.

It can be understood that, the execution subject of the embodiment of the present application may be an electronic device such as a smart phone or a tablet computer.

Please refer to Fig. 1, Fig. 1 is a schematic flow diagram of the image processing method provided by the embodiment of the present application, the flow may include:

101. Obtain multiple pictures.

As the photographing capabilities of electronic devices become stronger and stronger, users often use electronic devices to take photos. For example, users can take pictures of landscapes, people, and so on. The photos taken by the user are generally stored in the photo album of the electronic device, so that the user can consult these photos at any time. In addition, pictures downloaded by the user from the Internet are generally stored in the photo album. However, in related technologies, electronic devices generally can only classify pictures stored in an album according to shooting time or shooting location. That is, in the related art, the electronic device cannot effectively manage pictures.

In the embodiment of the present application, for example, the electronic device may acquire multiple pictures first. For example, an electronic device can obtain all pictures stored in a photo album.

102. Classify the multiple pictures to obtain at least one category.

For example, after acquiring multiple pictures, the electronic device may classify the multiple pictures to obtain at least one category.

For example, after obtaining the pictures saved in the photo album, the electronic device can classify the pictures saved in the photo album, so as to divide the pictures saved in the photo album into multiple categories, such as pictures of landscapes, pictures of plants, and pictures of animals. pictures of , pictures of vehicle classes, etc.

103. Determine a target category satisfying a preset condition from at least one category.

For example, after classifying a plurality of pictures to obtain at least one category, the electronic device may determine a target category satisfying a preset condition from the at least one category.

For example, after dividing the pictures saved in the photo album into pictures of the landscape category, pictures of the plant category, pictures of the animal category, and pictures of the vehicle category, the electronic device can select from the four categories of scenery category, plant category, animal category, and vehicle category. The category that satisfies the preset condition is determined from the categories, and it is determined as the target category. For example, the electronic device determines a landscape category and a plant category as target categories.

104. Cluster the pictures included in each target category to obtain a clustering result for each target category.

For example, after the target category is determined, the electronic device may perform clustering processing on the pictures included in each target category, so as to obtain a clustering result under each target category.

For example, after the landscape category and the plant category are determined as target categories, the electronic device may cluster pictures of the landscape category to obtain a clustering result under the landscape category. The electronic device can also cluster the pictures of the plant category, so as to obtain the clustering result under the plant category. For example, after clustering, pictures belonging to the landscape category are clustered into three clusters, and these three clusters are pictures of the mountain category, pictures of the seascape category, and pictures of the lakescape category. The pictures belonging to the plant category are clustered into two clusters after being clustered, and the two clusters are pictures of the flower category, pictures of the tree category, and the like.

It can be understood that, in the embodiment of the present application, after acquiring multiple pictures, the electronic device may classify the multiple pictures to obtain at least one category. The electronic device may determine a target category satisfying a preset condition from the at least one category, and perform clustering on pictures under each target category, so as to obtain a clustering result of pictures under each target category. Therefore, in the embodiment of the present application, the electronic device may first classify the pictures once, and then perform clustering once on the pictures of the target category based on the classification, so as to realize the subdivision of the pictures. Since the subdivision of pictures is helpful for searching and browsing pictures, this embodiment of the present application can realize effective management of pictures.

Please refer to FIG. 2. FIG. 2 is another schematic flowchart of the image processing method provided by the embodiment of the present application. The process may include:

201. The electronic device acquires multiple pictures.

For example, an electronic device may first obtain all pictures in its photo album.

202. The electronic device classifies the multiple pictures by using a lightweight picture classification algorithm to obtain at least one category.

For example, after obtaining all the pictures in the photo album, the electronic device can classify all the pictures in the photo album by using the lightweight picture classification algorithm MobileNet V2 to obtain at least one category.

It should be noted that MobileNet V2 is a general-purpose computer vision neural network designed for electronic devices, especially mobile devices. It can be used for image classification, object detection and semantic segmentation. Of course, in addition to MobileNetV2, the electronic device in this embodiment of the application can also use other lightweight image classification algorithms such as MobileNet V1, MobileNet V3, etc., which is not specifically limited in this embodiment.

Wherein, in the embodiment of the present application, the lightweight image classification algorithm used for classifying images may be a neural network that has been learned and trained in advance. For example, the lightweight image classification algorithm can be pre-trained according to the required categories. When a picture to be classified is input to a pre-learned and trained lightweight picture classification algorithm such as the MobileNet V2 neural network, the lightweight picture classification algorithm can output the classification of the picture, that is, the electronic device can get the picture Classification.

For example, by using MobileNet V2, a lightweight image classification algorithm that has been trained in advance, the electronic device can classify all the images in the photo album into pictures of landscapes, plants, animals, vehicles, and so on.

In an implementation manner, the electronic device may create a corresponding folder or picture collection for each category of pictures to store the pictures of the category. For example, the electronic device can create a folder named "landscape" for storing pictures of the landscape category, create a folder named "plants" for storing pictures of the plant category, and create a file named "animal" folder to store pictures of the animal category, create a folder named "vehicles" to store pictures of the vehicle category, and so on.

203. The electronic device determines a target category that satisfies a preset condition from at least one category, where the target category that meets the preset condition is a category that includes a number of pictures greater than or equal to a preset value.

For example, after classifying all the pictures in the photo album into four categories: pictures of landscapes, plants, animals, and vehicles, the electronic device can determine from the four categories that satisfy the preset The target category of the condition, wherein, the target category satisfying the preset condition may be a category whose number of included pictures is greater than or equal to a preset value.

For example, the default value is 30 sheets. Then, the electronic device may determine the category containing at least 30 pictures as the target category. For example, there are 50 pictures of the landscape category, 35 pictures of the plant category, 20 pictures of the animal category, and 5 pictures of the vehicle category. Then, since there are more than 30 pictures of the landscape category and pictures of the plant category, the electronic device can determine the landscape category and the plant category as target categories. However, since the number of pictures of the animal category and the pictures of the vehicle category is less than 30, the electronic device will not determine the animal category and the vehicle category as the target category.

204. The electronic device performs similarity calculation on every two pictures included in each target category, and obtains the similarity between every two pictures included in each target category.

205. The electronic device clusters according to the similarity of every two pictures contained in each target category, and obtains at least one cluster under each target category, wherein the similarity between two pictures contained in the same cluster are greater than or equal to the preset threshold.

For example, 204 and 205 could include:

After the target category is determined, the electronic device may perform clustering processing on the pictures included in each target category, so as to obtain a clustering result of the pictures in each target category.

In the embodiment of the present application, the electronic device may cluster the pictures included in each target category in the following manner: the electronic device may perform similarity calculation on every two pictures contained in each target category, Thus, the similarity of every two pictures contained in each target category is obtained. Afterwards, the electronic device can cluster the pictures according to the similarity of every two pictures contained in each target category, and obtain at least one cluster under each target category, wherein the pictures contained in the same cluster are paired The similarity between them is greater than the preset threshold.

For example, the electronic device may perform clustering processing on pictures of the landscape category, and perform clustering processing on pictures of the plant category. Wherein, when clustering the pictures of the landscape category, the electronic device can calculate the similarity of every two pictures in the landscape category, and then cluster the pictures of the landscape category according to the similarity of every two pictures of the landscape category , so as to obtain at least one cluster under the landscape category, wherein the similarity between any two pictures contained in the same cluster is greater than or equal to a preset threshold. For example, pictures in the landscape category are clustered into three clusters, and the three clusters are pictures in the mountain category, pictures in the seascape category, and pictures in the lakescape category. Among them, the similarity between the pictures in the category of mountains is greater than or equal to the preset threshold, the similarity between the pictures in the category of seascapes is also greater than or equal to the preset threshold, and the similarity between the pictures in the category of lake is greater than or equal to the preset threshold. The similarities between pairs of pictures in a category are also greater than or equal to a preset threshold.

For another example, when clustering pictures of plant categories, the electronic device can calculate the similarity of every two pictures of plant categories, and then cluster the pictures of plant categories according to the similarity of every two pictures of plant categories. classes, so as to obtain at least one cluster under the plant category, wherein the similarity between any two pictures contained in the same cluster is greater than or equal to a preset threshold. For example, the pictures in the plant scene category are clustered into two clusters, and the two clusters are pictures of the flower category and pictures of the tree category respectively. Wherein, the similarity between any two pictures in the flower category is greater than or equal to a preset threshold, and the similarity between any two pictures in the tree category is also greater than or equal to a preset threshold.

In an implementation manner, the electronic device may create a corresponding folder or picture set for each cluster under each target category to store the pictures included in the cluster. For example, for pictures under the landscape category, the electronic device can create a folder for pictures of the mountain category (peak cluster) to store pictures of the mountain category, and the electronic device can create a folder for pictures of the seascape category (seascape cluster). In order to store the pictures of the seascape category, the electronic device may create a folder for storing the pictures of the lakescape category (lakescape cluster) for the pictures of the lakescape category. For pictures under the plant category, the electronic device can create a folder for storing pictures of the flower category (flower clusters), and the electronic device can create a folder for storing pictures of the tree category (tree clusters). Pictures of tree categories, etc.

It can be understood that, in the embodiment of the present application, the electronic device may first perform a rough classification on the pictures, and then perform a clustering on the pictures of the target category based on the classification, so as to realize the subdivision of the pictures. Since the subdivision of pictures is helpful for searching and browsing pictures, this embodiment of the present application can realize effective management of pictures.

In one embodiment, when the electronic device executes the process of calculating the similarity of every two pictures contained in each target category in 204, it may include:

The electronic device uses a Siamese neural network to perform similarity calculation on every two pictures contained in each target category.

For example, the electronic device can use the Siamese neural network to calculate the similarity between every two pictures contained in each target category.

It should be noted that the Siamese Network can be used to measure the similarity of two inputs. The twin neural network has two inputs (for example, Input 1 and Input 2 respectively), and these two inputs Input 1 and Input 2 are respectively input into two neural networks (for example, Network 1 and Network 2, Network 1 and Network 2 can be a convolutional neural network (CNN, etc.), and these two neural networks can respectively map the input to a new space to form a representation of the input in the new space. Through the calculation of the loss function Loss, the similarity between two inputs can be evaluated. When the neural networks used for two image training are exactly the same, the left and right networks can share all the weights. The twin neural network uses Contrastive Loss as a loss function, which can effectively deal with the relationship of paired data in the twin neural network. The architecture of the Siamese neural network can be shown in Figure 3.

In an implementation manner, the above-mentioned Siamese neural network may be configured in a cloud device corresponding to the electronic device, and the cloud device may be a device deployed in the cloud for calculating the similarity between pictures.

Then, when the electronic device executes the above-mentioned process of calculating the similarity of every two pictures contained in each target category by using the twin neural network, it may include:

The electronic device uploads the pictures contained in the target category to the cloud device;

The electronic device receives the similarity information of every two pictures contained in each target category from the cloud device, and the similarity information is the similarity information calculated by using the Siamese neural network.

For example, Siamese neural networks used to calculate image similarity can be deployed on cloud devices. Then, after the target category is determined, the electronic device can upload the pictures contained in each target category to the cloud device, so that the cloud device can use the twin neural network to analyze every two pictures contained in each target category. Perform similarity calculations. After calculating the similarity, the cloud device can feed back the similarity information between each two pictures under each target category to the electronic device.

It can be understood that since the calculation of the image similarity has high requirements on resources such as device memory, the image similarity calculation can be performed on a cloud device, thereby saving computing resources of the electronic device. When it is necessary to calculate the similarity between pictures, the electronic device can upload the picture that needs to be calculated to the cloud device, and the cloud device uses the configured twin neural network to calculate the similarity of the picture.

In one embodiment, the electronic device can upload the pictures contained in each target category to the cloud device at a preset triggering time, and the cloud device can calculate the similarity between every two pictures in the same target category. Wherein, the preset triggering timing may be that the device is in an idle state or a specific time period at night, and so on.

206. The electronic device acquires the selected first picture, where the first picture is one of the multiple pictures.

207. According to the clustering result of each target category, the electronic device determines a similar picture to the first picture.

208. The electronic device recommends pictures similar to the first picture.

For example, 206, 207, 208 may include:

After the electronic device classifies and clusters the pictures in the album, the pictures belonging to the same cluster can be considered as pictures similar to each other. Then, for example, when the user selects or collects a certain picture (ie, the first picture) in the album, the electronic device can determine similar pictures to the first picture according to the clustering results of the pictures in the album, and store the first picture Similar pictures to a picture are recommended. For example, the electronic device may recommend 3 or 5 pictures with the highest similarity among similar pictures to the first picture to the user. For example, if the user selects or favorites a certain flower picture, then the electronic device can determine 5 pictures that are most similar to the selected or favorite flower picture from the pictures of flower clusters and recommend them to the user, so that the user can also select these pictures. Browse and collect similar pictures.

Please refer to FIG. 4 to FIG. 8 . FIG. 4 to FIG. 8 are schematic diagrams of scenes of the image processing method provided by the embodiment of the present application.

For example, many pictures are stored in the photo album of the electronic device, and the electronic device may first obtain all the pictures in the photo album. Afterwards, the electronic device can classify all the pictures in the album by using MobileNet V2, a lightweight picture classification algorithm that has been trained in advance. For example, the electronic device classifies all the pictures in the photo album into pictures of the landscape category, pictures of the plant category, pictures of the animal category, and pictures of the vehicle category.

After classifying the pictures, the electronic device may create a corresponding folder for each category of pictures to store the pictures of this category. For example, Electronics creates four folders, namely Landscapes, Plants, Animals, and Vehicles. Among them, the "landscape" folder is used to store pictures of the landscape category, the "plant" folder is used to store pictures of the plant category, the "animal" folder is used to store pictures of the animal category, and the "vehicle" folder It is used to store pictures of vehicle categories, as shown in Figure 4.

Afterwards, the electronic device may acquire the number of pictures in each category, and determine the target category for the category whose number of pictures reaches 30. For example, there are 50 pictures of the landscape category, 35 pictures of the plant category, 20 pictures of the animal category, and 5 pictures of the vehicle category. Then, the electronic device may determine the landscape category and the plant category as target categories.

After the target category is determined, the electronic device may perform clustering processing on the pictures of the landscape category, and perform clustering processing on the pictures of the plant category. Among them, the electronic device can upload the pictures of the landscape category and the pictures of the plant category to the cloud device during a specific time period at night, such as 02:00 to 03:00, and the electronic device is turned on and can be connected to the network. . Wherein, a twin neural network is configured on the cloud device, and the cloud device can use the twin neural network to calculate the similarity between two pictures. For example, after receiving a picture of the landscape category and a picture of the plant category from the electronic device, the cloud device may use a Siamese neural network to calculate the similarity between every two pictures in the landscape category. Afterwards, the cloud device can use the Siamese neural network to calculate the similarity between every two pictures in the plant category. After the similarity is calculated, the cloud device can send the similarity information between the pictures of the landscape category and the similarity information between the pictures of the plant category to the electronic device.

After the electronic device receives the similarity information between the pictures of the landscape category and the similarity information between the pictures of the plant category sent by the cloud device, it can respectively compare the pictures of the landscape category and the plant category according to the similarity information. Category images are clustered. When clustering the pictures of the landscape category, the electronic device can cluster the pictures of the landscape category according to the similarity of every two pictures of the landscape category, so as to obtain at least one cluster under the landscape category, wherein the same cluster The similarity between the pictures contained in is greater than or equal to the preset threshold. For example, pictures in the landscape category are clustered into three clusters, and the three clusters are pictures in the mountain category, pictures in the seascape category, and pictures in the lakescape category. Among them, the similarity between the pictures in the category of mountains is greater than or equal to the preset threshold, the similarity between the pictures in the category of seascapes is also greater than or equal to the preset threshold, and the similarity between the pictures in the category of lake is greater than or equal to the preset threshold. The similarities between pairs of pictures in a category are also greater than or equal to a preset threshold.

As another example, when performing clustering processing on pictures of plant categories, the electronic device may cluster pictures of plant categories according to the similarity between each two pictures of plant categories, so as to obtain at least one cluster under the plant category, wherein, The similarities between any two pictures included in the same cluster are greater than or equal to a preset threshold. For example, the pictures in the plant scene category are clustered into two clusters, and the two clusters are pictures of the flower category and pictures of the tree category respectively. Wherein, the similarity between any two pictures in the flower category is greater than or equal to a preset threshold, and the similarity between any two pictures in the tree category is also greater than or equal to a preset threshold.

For example, in the embodiment of the present application, the electronic device can create three subfolders under the folder corresponding to the scenery category, namely mountain peak, sea view, and lake view, wherein the subfolder "mountain peak" is used to store pictures of the mountain peak category, The subfolder "seascape" is used to store pictures of the category of seascape, and the subfolder "lakeview" is used to store pictures of the category of lakescape, as shown in Figure 5.

The electronic device can create two subfolders under the folder corresponding to the plant category, namely flowers and trees, wherein the subfolder "flowers" is used to store pictures of the flower category, and the subfolder "trees" is used to store the tree category , as shown in Figure 6.

After a period of time, for example, when the user browses the picture A of a certain mountain category, he thinks that this picture is taken particularly well, so he clicks "Favorite" to save this picture, as shown in Figure 7. After detecting that the user has favorited the picture A of the mountain category, the electronic device may search for 3 pictures with the highest similarity to picture A from the subfolder "Mountain", and recommend these 3 similar pictures to the user. For example, the three most similar pictures to picture A in the subfolder "Mountain Peak" are B, C, and D respectively. Then, the electronic device may recommend the three pictures B, C, and D to the user, as shown in FIG. 8 .

It can be understood that the embodiment of the present application can implement the subdivision of pictures in the album, and recommend the most similar pictures to the user when the user collects pictures. Therefore, the embodiments of the present application can improve the effectiveness and intelligence of album management.

Please refer to FIG. 9 . FIG. 9 is a schematic structural diagram of an image processing device provided by an embodiment of the present application. The image processing apparatus 300 may include: an acquisition module 301 , a classification module 302 , a determination module 303 , and a clustering module 304 .

An acquisition module 301, configured to acquire multiple pictures.

A classification module 302, configured to classify the multiple pictures to obtain at least one category.

A determining module 303, configured to determine a target category satisfying a preset condition from the at least one category.

The clustering module 304 is configured to cluster the pictures included in each target category to obtain a clustering result for each target category.

In one embodiment, the clustering module 304 can be used for:

Carry out similarity calculation for every two pictures contained in each target category, and obtain the similarity of every two pictures contained in each target category;

Clustering is carried out according to the similarity of every two pictures contained in each target category to obtain at least one cluster under each target category, wherein the similarity between two pictures contained in the same cluster is greater than or equal to the preset threshold.

In one embodiment, the clustering module 304 can also be used for:

Acquiring the selected first picture, where the first picture is one of the multiple pictures;

determining similar pictures to the first picture according to the clustering results of each target category;

Recommending pictures similar to the first picture.

In one embodiment, the clustering module 304 can be used for:

The Siamese neural network is used to calculate the similarity of every two images contained in each target category.

In one embodiment, the Siamese neural network is configured in a cloud device corresponding to the electronic device, and the cloud device is a device deployed in the cloud for calculating the similarity between pictures.

Then, the clustering module 304 can be used for:

uploading the pictures contained in the target category to the cloud device;

The similarity information of every two pictures contained in each target category is received from the cloud device, and the similarity information is the similarity information calculated by using a Siamese neural network.

In an implementation manner, the determination module 303 may be used to:

A target category that meets a preset condition is determined from the at least one category, wherein the target category that meets the preset condition is a category that includes a number of pictures greater than or equal to a preset value.

In one embodiment, the classification module 302 can be used to:

Using a light-weight image classification algorithm to classify the plurality of images to obtain at least one category.

An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed on a computer, the computer is made to execute the procedures in the method provided in this embodiment.

The embodiment of the present application also provides an electronic device, including a memory and a processor, and the processor is used to execute the process in the image processing method provided in the embodiment by calling the computer program stored in the memory.

For example, the above-mentioned electronic device may be a mobile terminal such as a tablet computer or a smart phone. Please refer to FIG. 10 . FIG. 10 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

The electronic device 400 may include components such as a touch screen 401 , a memory 402 , and a processor 403 . Those skilled in the art can understand that the structure of the electronic device shown in FIG. 10 does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine some components, or arrange different components.

The touch display screen 401 can be used to display information such as images and texts, and can also be used to receive user touch operations.

Memory 402 may be used to store applications and data. The application programs stored in the memory 402 include executable codes. Applications can be composed of various functional modules. The processor 403 executes various functional applications and data processing by running the application programs stored in the memory 402 .

The processor 403 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing the application program stored in the memory 402 and calling the data stored in the memory 402, the electronic device executes Various functions and processing data, so as to monitor the electronic equipment as a whole.

In this embodiment, the processor 403 in the electronic device loads the executable code corresponding to the process of one or more application programs into the memory 402 according to the following instructions, and the processor 403 runs the executable code stored in the memory. 402 in the application, thus executing:

Get multiple pictures;

Classifying the multiple pictures to obtain at least one category;

determining a target category satisfying a preset condition from the at least one category;

The pictures included in each target category are clustered to obtain a clustering result for each target category.

Referring to FIG. 11 , an electronic device 400 may include a touch screen 401 , a memory 402 , a processor 403 , a battery 404 , a microphone 405 , a speaker 406 and other components.

The touch display screen 401 can be used to display information such as images and texts, and can also be used to receive user touch operations.

Memory 402 may be used to store applications and data. The application programs stored in the memory 402 include executable codes. Applications can be composed of various functional modules. The processor 403 executes various functional applications and data processing by running the application programs stored in the memory 402 .

The processor 403 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing the application program stored in the memory 402 and calling the data stored in the memory 402, the electronic device executes Various functions and processing data, so as to monitor the electronic equipment as a whole.

The battery 404 can be used to supply power to various modules and components of the electronic device.

The microphone 405 can be used to pick up sound signals in the surrounding environment, such as receiving voice commands issued by the user.

Speaker 406 may be used to play sound signals.

In this embodiment, the processor 403 in the electronic device loads the executable code corresponding to the process of one or more application programs into the memory 402 according to the following instructions, and the processor 403 runs the executable code stored in the memory. 402 in the application, thus executing:

Get multiple pictures;

Classifying the multiple pictures to obtain at least one category;

determining a target category satisfying a preset condition from the at least one category;

The pictures included in each target category are clustered to obtain a clustering result for each target category.

In one embodiment, when the processor 403 executes the clustering of pictures contained in each target category, and obtains the clustering result of each target category, it may perform: clustering the pictures contained in each target category Carry out similarity calculation for every two pictures to obtain the similarity of every two pictures contained in each target category; perform clustering according to the similarity of every two pictures contained in each target category to obtain each target At least one cluster under the category, wherein the similarities between any two pictures contained in the same cluster are greater than or equal to a preset threshold.

In one embodiment, the processor 403 may also execute: acquiring the selected first picture, where the first picture is one of the multiple pictures; according to the clustering result of each target category, determine Similar pictures to the first picture; recommending similar pictures to the first picture.

In one embodiment, when the processor 403 executes the calculation of the similarity of every two pictures included in each target category, it may perform: using a Siamese neural network to Perform similarity calculations.

In one embodiment, the Siamese neural network is configured in a cloud device corresponding to the electronic device, and the cloud device is a device deployed in the cloud for calculating the similarity between pictures.

Then, when the processor 403 performs the similarity calculation for every two pictures contained in each target category by using the twin neural network, it may perform: upload the pictures contained in the target category to the cloud device; The cloud device receives the similarity information of every two pictures contained in each target category, and the similarity information is the similarity information calculated by using a Siamese neural network.

In one embodiment, when the processor 403 executes the step of determining the target category satisfying the preset condition from the at least one category, it may perform: determining the target category satisfying the preset condition from the at least one category , wherein, the target category satisfying the preset condition is a category whose number of included pictures is greater than or equal to a preset value.

In one embodiment, when the processor 403 executes the classifying the multiple pictures to obtain at least one category, it may perform: classify the multiple pictures by using a lightweight picture classification algorithm to obtain at least one category. a category.

In the above-mentioned embodiments, the descriptions of each embodiment have their own emphases. For the part that is not described in detail in a certain embodiment, refer to the detailed description of the image processing method above, and will not be repeated here.

The image processing device provided in the embodiment of the present application belongs to the same idea as the image processing method in the above embodiment, and any method provided in the embodiment of the image processing method can be run on the image processing device, and its specific For the implementation process, refer to the embodiment of the image processing method, and details are not repeated here.

It should be noted that, for the image processing method described in the embodiment of the present application, those skilled in the art can understand that all or part of the flow of the image processing method described in the embodiment of the application can be controlled by computer programs. To complete, the computer program can be stored in a computer-readable storage medium, such as stored in a memory, and executed by at least one processor, and the execution process can include the flow of the embodiment of the image processing method . Wherein, the storage medium may be a magnetic disk, an optical disk, a read only memory (ROM, Read Only Memory), a random access memory (RAM, Random Access Memory) and the like.

For the image processing device in the embodiment of the present application, its various functional modules may be integrated into one processing chip, each module may exist separately physically, or two or more modules may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software function modules. If the integrated modules are implemented in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium, such as read-only memory, magnetic disk or optical disk, etc. .

A picture processing method, device, storage medium and electronic equipment provided by the embodiment of the present application have been introduced in detail above. In this paper, specific examples are used to illustrate the principle and implementation of the present application. The description of the above embodiment is only It is used to help understand the method and its core idea of this application; at the same time, for those skilled in the art, according to the idea of this application, there will be changes in the specific implementation and application scope. In summary, this specification The content should not be construed as a limitation of the application.

Claims (6)

1. A picture processing method, applied to electronic equipment, is characterized in that, described method comprises: Get multiple pictures; Classifying the plurality of pictures by using a lightweight picture classification algorithm to obtain at least one category; Create a corresponding folder or picture collection for each category of pictures to store the pictures of this category; A target category that meets a preset condition is determined from the at least one category; wherein, the target category that meets the preset condition is a category that contains a number of pictures greater than or equal to a preset value; Using the twin neural network to cluster the pictures contained in each target category to obtain the clustering results of each target category; including: using the twin neural network to perform similarity on every two pictures contained in each target category Calculating; performing clustering according to the similarity of every two pictures included in each target category to obtain at least one cluster under each target category; Create a corresponding folder or picture set for each cluster under each target category to store the pictures contained in this cluster; Acquiring the selected first picture, where the first picture is one of the multiple pictures; According to the clustering result of each target category, determine the similar pictures of the first picture from the clusters under the target category; Recommending pictures similar to the first picture. 2 . The image processing method according to claim 1 , wherein the similarity between any two images included in the same cluster is greater than or equal to a preset threshold. 3 . 3. The image processing method according to claim 1, wherein the twin neural network is configured in a cloud device corresponding to the electronic device, and the cloud device is deployed in the cloud for computing images similarity equipment; The use of the twin neural network to perform similarity calculations on every two pictures contained in each target category includes: uploading the pictures contained in the target category to the cloud device; The similarity information of every two pictures contained in each target category is received from the cloud device, and the similarity information is the similarity information calculated by using a Siamese neural network. 4. A picture processing device applied to electronic equipment, characterized in that the device comprises: Acquisition module, used to obtain multiple pictures; A classification module, configured to classify the plurality of pictures by using a lightweight picture classification algorithm to obtain at least one category; A category creation module is used to create a corresponding folder or picture set for each category of pictures to store the pictures of this category; A determining module, configured to determine a target category satisfying a preset condition from the at least one category; wherein, the target category satisfying the preset condition is a category whose number of included pictures is greater than or equal to a preset value; The clustering module is used to cluster the pictures contained in each target category by using the twin neural network to obtain the clustering result of each target category; specifically for: using the twin neural network to cluster the pictures contained in each target category Carry out similarity calculation for every two pictures of each target category; perform clustering according to the similarity of every two pictures contained in each target category, and obtain at least one cluster under each target category; The cluster creation module is used to create a corresponding folder or picture set for each cluster under each target category to store the pictures contained in the cluster; The clustering module is also used to obtain the selected first picture, the first picture is a picture in the plurality of pictures; according to the clustering result of each target category, from the clusters under the target category determining similar pictures to the first picture; and recommending similar pictures to the first picture. 5. A computer-readable storage medium, on which a computer program is stored, characterized in that, when the computer program is executed on a computer, the computer is made to execute the computer according to any one of claims 1 to 3. Methods. 6. An electronic device comprising a memory and a processor, wherein the processor executes the method according to any one of claims 1 to 3 by invoking a computer program stored in the memory.