WO2019052351A1 - Image processing method and system, and computer device - Google Patents

Abstract

An image processing system comprises a client, a first server, and a second server. The client is used for sending an image set to be processed to the first server, receiving a clustering feature set sent by the first server, sending to the second server a clustering request generated according to the clustering feature set, and classifying the image set to be processed according to the clustering processing result sent by the second server. The first server is used for extracting the clustering feature set according to the image set to be processed that is sent by the client, and returning the clustering feature set to the client. The second server is used for receiving the clustering request sent by the client, performing clustering processing according to the clustering feature set in the clustering request, and sending the clustering processing result to the client.

Description

Image processing method and system, computer equipment

Cross-reference to related applications

The present application claims priority to Chinese Patent Application No. 200910854137.7, entitled "Image Processing Method and Apparatus, System, Computer Equipment", filed on September 15, 2017, the entire contents of which are hereby incorporated by reference. In this application.

Technical field

The present application relates to the field of computer technology, and in particular, to an image processing method and system, and a computer device.

Background technique

Users can implement various application requirements through smart terminals. However, due to the limited processing power and storage capacity of smart terminals, it is often impossible to process a large number of user operations locally. Therefore, in order to better provide services for the user, after receiving the operation request of the user, the smart terminal sends the operation request to the server for processing, and then returns the processing result to the smart terminal. In this way, the application requirements of the user can be realized without consuming too many resources of the intelligent terminal.

For a single user request, the server can respond quickly and accurately. If you face thousands of users, and a single user may have multiple requests, the server's pressure will multiply. For example, the smart terminal needs to send an album to the server for backup, and at the same time, classify the photos in the album.

Summary of the invention

The embodiment of the present application provides an image processing method and system, and a computer device.

An image processing system, the system comprising:

a client, configured to obtain a to-be-processed image set, send the to-be-processed image set to a first server, receive a clustering feature set sent by the first server, and generate a clustering request according to the clustering feature set Sending to the second server, and receiving the clustering processing result sent by the second server, and classifying the to-be-processed image set according to the clustering processing result;

a first server, configured to receive the to-be-processed image set sent by the client, extract a cluster feature set of the to-be-processed image set, and return the cluster feature set to the client;

And a second server, configured to receive the clustering request sent by the client, perform clustering processing according to the clustering feature set in the clustering request, and send the clustering processing result to the client.

An image processing method, the method comprising:

Obtaining a to-be-processed image collection, and sending the to-be-processed image collection to a first server;

Receiving a cluster feature set sent by the first server, and sending a clustering request generated according to the cluster feature set to a second server, where the cluster feature set is extracted according to the to-be-processed image set ;

Receiving a clustering processing result sent by the second server, and classifying the to-be-processed image set according to the clustering processing result, where the clustering processing result is performed by the second server according to the clustering feature set Clustered processing.

A computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following operations:

Obtaining a to-be-processed image collection, and sending the to-be-processed image collection to a first server;

Receiving, by the first server, a cluster feature set extracted according to the to-be-processed image set, and sending a clustering request generated according to the cluster feature set to a second server;

And receiving, by the second server, a clustering processing result obtained by performing clustering processing according to the clustering feature set, and classifying the to-be-processed image set according to the clustering processing result.

A computer readable storage medium having stored thereon a computer program, the computer program being executed by the processor as follows:

Obtaining a to-be-processed image collection, and sending the to-be-processed image collection to a first server;

Receiving, by the first server, a cluster feature set extracted according to the to-be-processed image set, and sending a clustering request generated according to the cluster feature set to a second server;

And receiving, by the second server, a clustering processing result obtained by performing clustering processing according to the clustering feature set, and classifying the to-be-processed image set according to the clustering processing result.

An image processing method, the method comprising:

Receiving the to-be-processed image set sent by the client;

Extracting a cluster feature set of the to-be-processed image set, and returning the cluster feature set to the client, instructing the client to perform a clustering request generated according to the clustering feature set, sending to a second The server receives the clustering processing result obtained by performing clustering processing according to the clustering feature set returned by the second server, and classifying the to-be-processed image set according to the clustering processing result.

A computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following operations:

Receiving the to-be-processed image set sent by the client;

Extracting a cluster feature set of the to-be-processed image set, and returning the cluster feature set to the client, instructing the client to perform a clustering request generated according to the clustering feature set, sending to a second The server receives the clustering processing result obtained by performing clustering processing according to the clustering feature set returned by the second server, and classifying the to-be-processed image set according to the clustering processing result.

A computer readable storage medium having stored thereon a computer program, the computer program being executed by the processor as follows:

Receiving the to-be-processed image set sent by the client;

Extracting a cluster feature set of the to-be-processed image set, and returning the cluster feature set to the client, instructing the client to perform a clustering request generated according to the clustering feature set, sending to a second The server receives the clustering processing result obtained by performing clustering processing according to the clustering feature set returned by the second server, and classifying the to-be-processed image set according to the clustering processing result.

An image processing method, the method comprising:

Receiving, by the client, the clustering request, where the clustering request is generated by the client according to a clustering feature set sent by the first server, where the clustering feature set is generated by the first server Extracted according to the set of to-be-processed images sent by the client;

And performing clustering processing according to the clustering feature set in the clustering request to obtain a clustering processing result, and sending the clustering processing result to the client, instructing the client to perform a clustering processing result according to the clustering process Sorting the set of images to be processed.

A computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following operations:

Receiving, by the client, the clustering request, where the clustering request is generated by the client according to a clustering feature set sent by the first server, where the clustering feature set is generated by the first server Extracted according to the set of to-be-processed images sent by the client;

And performing clustering processing according to the clustering feature set in the clustering request to obtain a clustering processing result, and sending the clustering processing result to the client, instructing the client to perform a clustering processing result according to the clustering process Sorting the set of images to be processed.

A computer readable storage medium having stored thereon a computer program, the computer program being executed by the processor as follows:

Receiving, by the client, the clustering request, where the clustering request is generated by the client according to a clustering feature set sent by the first server, where the clustering feature set is generated by the first server Extracted according to the set of to-be-processed images sent by the client;

And performing clustering processing according to the clustering feature set in the clustering request to obtain a clustering processing result, and sending the clustering processing result to the client, instructing the client to perform a clustering processing result according to the clustering process Sorting the set of images to be processed.

DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the prior art description will be briefly described below. Obviously, the drawings in the following description are only It is a certain embodiment of the present application, and other drawings can be obtained according to the drawings without any creative work for those skilled in the art.

1 is a schematic diagram of an application environment of an image processing method in an embodiment;

2 is a schematic diagram of an application environment of an image processing method in another embodiment;

3 is a hardware interaction timing diagram of an image processing method in an embodiment;

4 is a flow chart of an image processing method in an embodiment;

5 is a display diagram of a mobile terminal album classification result in an embodiment;

6 is a flow chart of an image processing method in another embodiment;

Figure 7 is a flow chart of an image processing method in still another embodiment;

Figure 8 is a system architecture diagram of an image processing system in an embodiment;

FIG. 9 is a schematic structural diagram of an image processing apparatus in an embodiment; FIG.

FIG. 10 is a schematic structural diagram of an image processing apparatus in another embodiment; FIG.

11 is a schematic structural diagram of an image processing apparatus in still another embodiment;

12 is a schematic diagram showing the internal structure of a server in an embodiment;

FIG. 13 is a block diagram showing a part of a structure of a mobile phone related to a computer device according to an embodiment of the present application.

Detailed ways

In order to make the objects, technical solutions, and advantages of the present application more comprehensible, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting.

It will be understood that the terms "first", "second" and the like, as used herein, may be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another. For example, a first client may be referred to as a second client, and similarly, a second client may be referred to as a first client, without departing from the scope of the present application. Both the first client and the second client are clients, but they are not the same client.

FIG. 1 is a schematic diagram of an application environment of an image processing method in an embodiment. As shown in FIG. 1, the application environment includes a client 12, a first server 14, and a second server 16. The client 12 is configured to acquire a to-be-processed image set, and send the obtained to-be-processed image set to the first server 14. After receiving the image set to be processed, the first server 14 extracts the cluster feature set of the image set to be processed, and returns the cluster feature set to the client 12. The client 12 generates a clustering request according to the clustering feature set, and sends the clustering request to the second server 16. After receiving the clustering request sent by the client 12, the second server 16 performs clustering processing according to the clustering feature set in the clustering request, and sends the clustering processing result to the client 12. The client 12 is an electronic device that is mainly used to input user information and output processing results at the outermost periphery of the computer network, and may be, for example, a personal computer, a mobile terminal, a personal digital assistant, a wearable electronic device, or the like. The first server 14 and the second server 16 are devices for providing a computing service in response to a service request, and may be, for example, one or more computers.

2 is a schematic diagram of an application environment of an image processing method in another embodiment. As shown in FIG. 2, the application environment includes a client 22, a first server cluster 24, and a second server cluster 26. The client 22 is configured to acquire a to-be-processed image set, and send the obtained to-be-processed image set to the first server cluster 24. After receiving the image set to be processed, the first server cluster 24 extracts the cluster feature set of the image set to be processed, and returns the cluster feature set to the client 22. The client 22 generates a clustering request based on the clustering feature set and sends the clustering request to the second server cluster 26. After receiving the clustering request sent by the client 22, the second server cluster 26 performs clustering processing according to the clustering feature set in the clustering request, and sends the clustering processing result to the client 22. The first server cluster 24 includes one or more first servers 242 for implementing distributed task processing. The second server cluster 26 includes one or more second servers 262 for implementing distributed task processing. The client 22 is an electronic device that is mainly used to input user information and output processing results at the outermost periphery of the computer network, and may be, for example, a personal computer, a mobile terminal, a personal digital assistant, a wearable electronic device, or the like. In the embodiment provided by the present application, the client 22 may include one or more, which is not limited herein. The first server 242 and the second server 262 are devices for providing a computing service in response to a service request, and may be, for example, one or more computers.

FIG. 3 is a hardware interaction timing diagram of an image processing method in an embodiment. As shown in FIG. 3, the interaction timing diagram includes operations 302 through 316. among them:

In operation 302, the client acquires a to-be-processed image collection, and sends the to-be-processed image collection to the first server.

In one embodiment, the image to be processed refers to an image that needs to be processed, for example, the image to be processed may be an image that requires process of feature recognition, classification, and the like. The image set to be processed refers to a set of images to be processed, and one or more images to be processed may be included in the image set to be processed. The client refers to the outermost part of the computer network, and is mainly used for inputting user information and outputting the processing result of the electronic device. The first server refers to a server that can be used for feature recognition processing. Feature recognition processing refers to a process of identifying specific feature attributes of an image to be processed.

Operation 304, the first server receives the image set to be processed, and extracts a cluster feature set according to the image set to be processed.

In the embodiment provided by the present application, the clustering feature set refers to a set of features obtained by performing clustering processing. After receiving the image set to be processed, the first server performs feature recognition processing on each image to be processed in the image set to be processed. Each image to be processed corresponds to one or more clustering features, and the clustering features extracted by all the images to be processed constitute a clustering feature set.

Operation 306, the first server sends the extracted cluster feature set to the client.

Operation 308, the client receives the cluster feature set, and generates a clustering request according to the cluster feature set.

A clustering request is a command for clustering a clustering object set. The clustering object set refers to the object set used for performing the clustering process. For example, the clustering object set may be a to-be-processed image set, and the to-be-processed image in the to-be-processed image set is clustered. The generated clustering request includes information such as the request originating device identifier, the request receiving device identifier, the request initiation time, and the cluster object identifier. It can be understood that, in the client, multiple application accounts can be logged in, and when the application account needs to perform clustering processing, the clustering request is initiated by the client to the second server. That is, when the client initiates a clustering request to the second server, the request originating object may refer to an application account identifier or a terminal identifier. The application account identifier refers to a unique identity identifier used to represent the identity of the user. The terminal identifier refers to a unique identifier that distinguishes different smart terminal devices.

Operation 310, the client sends the generated clustering request to the second server.

In an embodiment, after receiving the clustering request, the second server performs clustering processing on the corresponding clustering feature set. If multiple clustering requests sent by multiple clients are received, a clustering request queue is formed according to the multiple clustering requests, and the clustering request in the clustering request queue is processed.

Operation 312, the second server receives the clustering request, and performs clustering processing according to the clustering feature set in the clustering request.

Clustering processing refers to dividing a clustering object set into multiple categories according to one or more clustering features. Specifically, the cluster feature set is clustered according to the clustering model, and the cluster model can be trained according to the training image set. The training image set refers to an image set used for training to obtain a clustering model. The training image set may be an image set generated according to a to-be-processed image set, or may be an image set specifically used for training a clustering model.

Operation 314, the second server sends the clustering processing result to the client.

In an embodiment, the second server performs clustering processing to obtain a clustering processing result, and the label data may be generated according to the clustering processing result, and the label data is stored on the disk of the second server. The clustering result can be pushed to the client through the PUSH service. Among them, the PUSH service is a service for pushing data.

In operation 316, the client receives the clustering processing result, and classifies the image set to be processed according to the clustering processing result.

Classification refers to dividing the images to be processed in the image set to be processed into different types according to a unified standard. Each image to be processed corresponds to one or more cluster features, and one cluster feature corresponds to one classification type. That is, the image to be processed may be divided into one or more types. The image to be processed, the clustering feature, and the classification type have corresponding relationships. The client may establish a relationship between the image to be processed and the clustering feature according to the clustering feature returned by the first server, and establish a correspondence between the clustering feature and the classification type according to the clustering processing result returned by the second server. The client classifies the set of images to be processed according to this correspondence.

4 is a flow chart of an image processing method in one embodiment. As shown in FIG. 4, the flowchart includes operations 402 through 406. among them:

Operation 402: Acquire a set of images to be processed, and send the set of images to be processed to the first server.

In one embodiment, the image to be processed refers to an image that needs to be processed, for example, the image to be processed may be an image that requires process of feature recognition, classification, and the like. The image set to be processed refers to a set of images to be processed, and one or more images to be processed may be included in the image set to be processed.

The first server refers to a server that can be used for feature recognition processing. Feature recognition processing refers to a process of identifying specific feature attributes of an image to be processed. For example, the feature recognition process may be to identify information such as face features, color features, edge features, and texture features in the image to be processed. Different features are identified and the recognition models used are different. For example, commonly used edge detection models include Sobel edge detection algorithm, Canny edge detection algorithm and Roberts edge detection algorithm. The feature recognition process is performed on the image to be processed, and the feature recognition values are represented by the feature values, and a feature set is formed by the feature recognition result. The formed feature set can be used to cluster the image to be processed. Clustering is the process of dividing a collection of objects into multiple objects, each of which consists of one or more similar objects.

It can be understood that the first server can be a server cluster, that is, distributed processing that implements feature recognition processing through multiple servers. If the first server is a server cluster, the first server is composed of a plurality of first child servers. Each first sub-server can report the working status to the registration server in real time, and the registration server generates a list of available services according to the working status reported by the first sub-server. The server ID of the first subserver in the available state is recorded in the list of available services, and the first subserver in the available state can be selected by obtaining the list of available services. Before the client needs to send the to-be-processed image set, the server may obtain the available service list from the registration server, obtain the server identifier in the available service list, and select the target server identifier from the obtained server identifier by using a preset routing algorithm, and the image to be processed is to be processed. The collection is sent to the first subserver corresponding to the target server ID. The preset routing algorithm is an algorithm for selecting a target server identifier. For example, the preset routing algorithm may be a load balancing algorithm, and the load balancing algorithm may be a random algorithm, a polling algorithm, a source address hash algorithm, or the like, which is not limited herein. The server identifier refers to a unique identifier that distinguishes different servers, and searches for a server according to the server identifier.

Operation 404: Receive a cluster feature set sent by the first server, and send the clustering request generated according to the cluster feature set to the second server, where the cluster feature set is extracted according to the to-be-processed image set.

In the embodiment provided by the present application, the clustering feature set refers to a set of features obtained by performing clustering processing. After receiving the image set to be processed, the first server performs feature recognition processing on each image to be processed in the image set to be processed. One or more clustering features may be extracted from each image to be processed, and a clustering feature set is generated according to the obtained clustering features. For example, a face area of each image to be processed in the image set to be processed is traversed, and the face area is extracted to form a face area set. Then, the face region is a clustering feature, and each of the to-be-processed images includes one or more human faces, and the extracted face regions in the aggregated image to be processed form a clustering feature set.

The clustering request refers to a command for clustering the cluster feature set. Generally, when the sending device sends a clustering request to the receiving device, the clustering request includes information such as a requesting device identifier, a requesting device identifier, a request initiation time, and a clustering feature identifier. The request initiation device identifier refers to the unique identifier of the device that initiates the clustering request, and the request receiving device identifier refers to the unique identifier of the device that receives the clustering request, and the cluster initiation time refers to the time when the clustering request is initiated, and the clustering feature The identifier refers to a unique identifier corresponding to the cluster feature set, and the cluster feature set can be searched according to the cluster feature identifier. After receiving the clustering request, the receiving device performs clustering processing according to the clustering feature set. If the receiving device receives multiple clustering requests of multiple sending devices, a clustering request queue is formed according to the multiple clustering requests, and the clustering request in the clustering request queue is processed.

The second server refers to a server that can be used for clustering processing. The client may initiate a clustering request to the second server, and the second server may connect to multiple clients and receive clustering requests sent by multiple clients. It can be understood that, in the client, multiple application accounts can be logged in, and when the application account needs to perform clustering processing, the clustering request is initiated by the client to the second server. That is, when the client initiates a clustering request to the second server, the requesting device identifier may be an application account identifier or a terminal identifier. The application account identifier refers to a unique identity identifier used to represent the identity of the user. The terminal identifier refers to a unique identifier that distinguishes different smart terminal devices. For example, the terminal identifier may refer to an IP (Internet Protocol) protocol, a MAC (Media Access Control) address, and the like of the smart terminal. For example, the user can log in to the client through the application account, and send a request for clustering the photos in the album to the second server through the client, and the second server receives the cluster request sent by the client, and then takes the photo in the album. Perform clustering processing and return the result of the clustering processing to the client.

After the second server receives multiple clustering requests, a clustering request queue can be formed. If the same request originating object sends multiple clustering requests to the second server, the second server may merge the clustering requests corresponding to the same request initiating object. The merge clustering request refers to combining multiple clustering requests into one clustering request, and processing the merged clustering request to realize simultaneous processing of multiple clustering requests. Specifically, the request initiation device identifier included in each cluster request in the cluster request queue is obtained, and the cluster request requesting the same device identifier in the cluster request queue is merged. The requesting initiating device identifies the same clustering request, that is, the clustering request sent by the same request initiating object. It can be understood that the request initiation device identifier may refer to the terminal identifier, and may also refer to an application account identifier.

For example, the clustering request queue includes three clustering requests, which are arranged in chronological order: clustering request 1, and application account A sends a clustering request at 03:30 on August 20, 2017, including Clustering feature set 1; clustering request 2, clustering request sent by application account B on August 21, 2017 at 02:41, including clustering feature set 2; clustering request 3, application account A in August 2017 The clustering request sent at 04:02 on the 22nd contains the clustering feature set 3. Then, the clustering request 1 and the clustering request 3 are merged, and the clustering feature set obtained after the combination is the union of the clustering feature set 1 and the clustering feature set 3.

In an embodiment, the client may preset a condition for triggering a clustering request to the second server, and the set clustering triggering condition includes at least one of the following methods: the number of newly added photos in the client's album is greater than the preset number. The current time is the preset time; the time from the last time the clustering request is initiated exceeds the preset time period; the mobile terminal is currently in the charging state. For example, when the mobile terminal adds more than 50 pictures, if the current time is between 2 am and 5 am, and the mobile terminal is in a charging state, the mobile terminal initiates a clustering request.

Operation 406: Receive a clustering processing result sent by the second server, and classify the image processing group to be processed according to the clustering processing result, where the clustering processing result is obtained by the second server performing clustering processing according to the clustering feature set.

In an embodiment, after the clustering process is performed on the cluster feature set, the second server forms a group, and each cluster feature has a corresponding group. Corresponding tag data may be formed according to the clustering feature, and the tag data is used to mark a specific grouping attribute of the clustering feature. For example, if the tag data of the clustering feature 1 is "packet 1", then the clustering feature 1 belongs to the grouping of "packet 1". The formed tag data can be stored on the disk of the second server for storage.

Classification refers to dividing the images to be processed in the image set to be processed into different types according to a unified standard. Each image to be processed corresponds to one or more cluster features, and one cluster feature corresponds to one classification type. That is to say, the image to be processed may be divided into one or more types, which is not limited in this embodiment. Generally, the image to be processed, the clustering feature, and the classification type have corresponding relationships. The client may establish a relationship between the image to be processed and the clustering feature according to the clustering feature returned by the first server, and establish a correspondence between the clustering feature and the classification type according to the clustering processing result returned by the second server.

For example, according to the face, the photos in the album are classified. Each face corresponds to one category, and each photo may contain one or more faces. If a photo contains multiple faces, this photo Will belong to multiple categories. Specifically, the client sends the album to the first server, and the first server traverses each photo in the album, extracts the face region in each photo, and returns the extracted face region set to the client. The client sends a clustering request to the second server, and sends the set of face regions to the second server for clustering processing. The client classifies the photos in the album according to the clustering processing result returned by the second server.

FIG. 5 is a diagram showing a result of classification of a mobile terminal album in one embodiment. As shown in FIG. 5, the mobile terminal sends the album to the first server, and the first server traverses each photo in the album, extracts the cluster feature in each photo, and returns the extracted cluster feature set to the mobile terminal. The mobile terminal sends a clustering request to the second server, and sends the clustering feature set to the second server for clustering processing. The mobile terminal classifies the photos in the album according to the clustering processing result returned by the second server. Six classification results are displayed on the interface in this embodiment, including "Class 1", "Class 2", "Class 3", "Class 4", "Class 5" and "Class 6", respectively. Contains a number of common photos, click on the corresponding category to view the photos in the category.

The image processing method provided in the above embodiment sends the image set to be processed to the first server for feature recognition processing, and sends the cluster feature set processed by the first server to the second server for clustering processing. The image set to be processed is classified according to the clustering processing result returned by the second server. They are processed on different servers, and different servers perform different processing. In the face of huge data volume, they can also be synchronized, which improves the accuracy of image processing and improves the accuracy of image processing.

Figure 6 is a flow chart of an image processing method in another embodiment. As shown in FIG. 6, the flowchart includes operations 602 through 604. among them:

Operation 602: Receive a to-be-processed image set sent by the client.

The set of pending images is obtained by the client. The client's storage space stores the image to be processed. The client can directly obtain the image to be processed from the preset storage address, or traverse all the folders in the client to obtain the image to be processed. Generally speaking, the storage space of the client is divided into internal memory and external storage. The internal memory refers to the memory that comes with the client itself and is part of the client hardware structure. The external storage refers to the external storage device of the client, and the external storage amount can be transmitted to the client through a dedicated interface. For example, the external storage may be an SD card, a USB flash drive or the like.

In one embodiment, the set of to-be-processed images sent by the client may include all the to-be-processed images stored by the client, or may only include a part of the to-be-processed images stored by the client. For example, the image set to be processed sent by the client may include all images in the internal memory and the external memory, and may also be included in the image included in the internal memory.

Operation 604, extracting a cluster feature set of the to-be-processed image set, and returning the cluster feature set to the client, instructing the client to perform a clustering request generated according to the cluster feature set, and sending the clustering request to the second server, and receiving the second server to return The clustering processing result obtained by clustering according to the clustering feature set, and classifying the image set to be processed according to the clustering processing result.

In the embodiment provided by the present application, after receiving the image set to be processed, the image set to be processed needs to be subjected to feature recognition processing to obtain a cluster feature set. The extracting the clustering feature set of the image set to be processed may include: generating a to-be-processed image queue according to the to-be-processed image set, and extracting the clustering feature set according to the to-be-processed image in the image queue to be processed. The image queue to be processed refers to a queue formed by the image to be processed, and the image to be processed can be processed according to the image queue to be processed to realize the orderly processing of the image to be processed. After forming the image queue to be processed, a preset number of to-be-processed images may be acquired from the image queue to be processed each time the feature recognition process is performed, and the acquired preset number of to-be-processed images are subjected to feature recognition processing.

The image queue to be processed may be randomly generated, or may be generated according to attributes such as the size and format of the image to be processed. For example, the images to be processed are arranged according to the format, and the images to be processed in the same format are processed together. Generally, the image to be processed can be divided into JPG, PNG, TIFF, RAW and the like. After the image queue to be processed is formed, the processing speed of the image to be processed can also be controlled, and a preset number of images to be processed are processed each time. For example, there are a total of 500 images to be processed, 100 sheets at a time.

In an embodiment, the clustering feature set of the image set to be processed may further include: performing an encryption process on the image set to be processed, and generating a to-be-processed image queue according to the image set to be processed after the encryption process; The image to be processed is decrypted, and the cluster feature set is extracted according to the image to be processed after the decryption process. Encryption processing refers to the process of changing the original information by a special algorithm so that unauthorized users cannot know the original information. The image set to be processed can be encrypted by an encryption algorithm such as 3DES (Triple Data Encryption Algorithm) or RC5. The image to be processed after the encryption process cannot obtain the real information of the image to be processed when accessed by an unauthorized user. The decryption process refers to the process of restoring the encrypted information to the original information, and the encryption process and the decryption process are the opposite processes. Before the queue is formed, the image to be processed is subjected to encryption processing, and the processing speed of the image to be processed is controlled by the queue. When the image to be processed is processed, the image to be processed after the encryption process needs to be decrypted, and then the image to be processed after the decryption process is subjected to feature recognition processing.

Further, in order to improve the feature recognition efficiency of the image to be processed, the image to be processed may be subjected to a certain degree of compression or cropping processing. Specifically, the image to be processed in the to-be-processed image set is compressed or clipped, and the cluster feature set is extracted according to the compressed or cropped image set to be processed. The compression process refers to a process of compressing a to-be-processed image to a certain extent to make the space occupied by the image to be processed smaller. The trimming process refers to a process of cutting a to-be-processed image to a certain extent, so that the occupied image takes up less space. Generally, the degree of image compression or cropping processing should not be too large, and the degree of multi-compression or cropping processing is too large, which will seriously affect the feature recognition accuracy of the image to be processed.

The image processing method provided by the foregoing embodiment receives a set of to-be-processed images sent by a client, and extracts a cluster feature set of the image set to be processed. The client sends the clustering request generated by the clustering feature set to the second server, and receives the clustering processing result obtained by the clustering process according to the clustering feature set returned by the second server, and processes the image set according to the clustering processing result. sort. In this way, the huge amount of data can be faced in real time, and the processing can be performed simultaneously, which improves the accuracy of image processing. The processing is performed on different servers, and different servers perform different processing, so that the division processing ensures the accuracy of image processing.

Figure 7 is a flow chart of an image processing method in still another embodiment. As shown in FIG. 7, the flowchart includes operations 702 through 704. among them:

In operation 702, the clustering request sent by the client is received, where the clustering request is generated by the client according to the clustering feature set sent by the first server, and the clustering feature set is to be processed by the first server according to the client. Image collection extracted.

In an embodiment, multiple clustering requests may be received at the same time, and the multiple clustering requests may be sent by the same client or by different clients. Then, according to the received multiple clustering requests, a clustering request queue is formed, and the clustering request in the clustering request queue is processed according to a certain rule. The clustering request includes information such as the request originating device identifier, the request receiving device identifier, the request originating time, and the clustering feature set. Generally, the clustering request queues are arranged in the order of the clustering request initiation time, that is, the clustering request with the top requesting time is prioritized, and the clustering request located first in the clustering request queue is preferentially processed each time. . It can be understood that the clustering request queue can also be sorted according to other rules, and is not further limited herein. For example, the clustering request queue may also perform sorting according to the space occupied by the request originating device priority and the clustering feature set.

When the client sends a clustering request, the clustering request may include a requesting device identifier, which is used to distinguish different devices that initiate the clustering request. The request initiation device identifier may be a terminal identifier of the client or an application account identifier. Among them, the application account can be logged in on multiple different clients.

In an embodiment, the client may preset a condition for triggering a clustering request to the second server, and the set clustering triggering condition includes at least one of the following methods: the number of newly added photos in the client's album is greater than the preset number. The current time is the preset time; the time from the last time the clustering request is initiated exceeds the preset time period; the mobile terminal is currently in the charging state. For example, when the mobile terminal adds more than 50 pictures, if the current time is between 2 am and 5 am, and the mobile terminal is in a charging state, the mobile terminal initiates a clustering request.

Operation 704, performing clustering processing according to the clustering feature set in the clustering request to obtain a clustering processing result, and sending the clustering processing result to the client, instructing the client to perform classification according to the clustering processing result.

In the embodiment provided by the present application, if the cluster request queue includes multiple clustering requests, the clustering request with the same requesting device identifier may be merged. The merge clustering request refers to combining multiple clustering requests into one clustering request, and processing the merged clustering request to realize simultaneous processing of multiple clustering requests. Specifically, the request initiation device identifier included in each cluster request in the cluster request queue is obtained, and the cluster request requesting the same device identifier in the cluster request queue is merged. It can be understood that the requesting initiating device identifies the same clustering request, that is, the clustering request sent by the same request initiating object. Then, the clustering feature set is clustered according to the clustering request, and the clustering processing result includes: generating a clustering request queue according to the clustering request sent by the client, and requesting the same clustering request in the clustering request queue The merging is performed; the clustering feature set is clustered according to the merged clustering request, and the clustering processing result is obtained.

In an embodiment, combining the clustering request request with the same clustering request in the clustering request queue includes: sorting the clustering request in the clustering request queue according to the request initiation time, and acquiring the sorted clustering request queue The specified clustering request in the clustering request; the same clustering request in the clustering request queue as the requesting initiating object of the specified clustering request is merged. The clustering request in the clustering request queue is sorted according to the request initiation time, for example, the clustering request is sorted in ascending order according to the request initiation time, or the clustering request is sorted in descending order according to the request initiation time. Generally, after receiving a plurality of clustering requests, the request receiving device cannot process all clustering requests simultaneously due to limited processing capability. Then, the request receiving device forms a clustering request queue according to the order of the request initiation time, and processes the clustering request with the top request initiation time first, and requests the clustering request post-processing after the initiation time.

The specified clustering request refers to a clustering request in the clustering request queue that meets the specified conditions, and the obtained specified clustering request is used as the clustering request currently processed. After the clustering request queues are sorted according to the request initiation time, the specified clustering request may be obtained according to the request initiation time, and the specified clustering request may also be obtained according to the attribute parameters of the clustering object. For example, a clustering request in the clustering request queue for sorting the first position, sorting the clustering request of the last bit, or acquiring a clustering request with the largest occupied space of the image collection to be processed.

In one embodiment, the specified clustering request may be a first-level clustering request, that is, a clustering requesting team to select the first clustering request in the team. The merging of the same clustering request requesting the object in the clustering request queue may include: arranging the clustering request in the clustering request queue according to the request initiation time in a first-to-last order, and acquiring the clustering request queue The first clustering request; the clustering request queue is merged with the same clustering request as the first clustering request requesting object. After the clustering requests are merged, the clustering feature sets corresponding to the clustering requests also need to be merged. Then, the merged cluster feature set is a union of the cluster feature sets corresponding to each cluster request, and the merged cluster feature set is clustered.

Clustering feature sets are clustered to obtain clustering processing results. The image processing method provided by the embodiment of the present application further includes: generating tag data according to the clustering processing result, and storing the tag data in a preset storage space. The tag data refers to the identifier used to mark the clustering feature in the clustering feature set. According to the tag data generated by the clustering process result, a one-to-one correspondence can be established with the clustering feature identifier, and the tag data is stored in the pre-predetermined relationship. Set the storage space.

The clustering process can divide the cluster object set into a plurality of categories according to one or more features. For example, people can be divided into men and women according to their gender. They can be divided into teenagers, youth, middle-aged and so on according to age. There are more combinations according to gender and age. Generally, clustering object sets can be classified according to the clustering model. Commonly used clustering models include k-means clustering model, hierarchical clustering model, SOM clustering model and FCM clustering model. In this embodiment, the clustering model can be obtained by training according to the training image set. The training image set refers to a set of images used for training to obtain a clustering model, and the training image set may take a part of the image set to be processed, or may be an image set specifically used for training the clustering model. Specifically, the training image set is trained to obtain a clustering model and a feature recognition model, and the clustering feature set is clustered according to the clustering model, and the feature recognition model is sent to the first server to extract the aggregate of the image set to be processed. Class feature set.

The image processing method provided by the foregoing embodiment receives the clustering request sent by the client, performs clustering processing according to the clustering feature set in the clustering request, and obtains a clustering processing result, and sends the clustering processing result to the client. , so that the client classifies according to the clustering processing results. The clustering request is generated by the client according to the clustering feature set sent by the first server, and the clustering feature set is extracted by the first server according to the to-be-processed image set sent by the client. It can be seen that in the face of a huge amount of data, it is also possible to perform feature recognition and clustering processing at the same time, thereby improving the accuracy of image processing. The processing is performed on different servers, and different servers perform different processing, so that the division processing ensures the accuracy of image processing.

Figure 8 is a system architecture diagram of an image processing system in one embodiment. As shown in FIG. 8, the system architecture diagram includes a client 802, a first server 804, and a second server 806. among them:

The client 802 is configured to obtain a to-be-processed image set, send the to-be-processed image set to the first server 804, receive the clustering feature set sent by the first server 804, and send the clustering request generated according to the clustering feature set to the first The second server receives the clustering processing result sent by the second server, and classifies the image set to be processed according to the clustering processing result.

The first server 804 is configured to receive a set of to-be-processed images sent by the client 802, extract a cluster feature set of the to-be-processed image set, and return the cluster feature set to the client 802.

In one embodiment, the first server is further configured to generate a to-be-processed image queue according to the to-be-processed image set, and extract a clustering feature set according to the to-be-processed image in the image queue to be processed. The image queue to be processed may be randomly generated, or may be generated according to attributes such as the size and format of the image to be processed. After the image queue to be processed is formed, the processing speed of the image to be processed can also be controlled, and a preset number of images to be processed are processed each time.

In an embodiment, the first server may further perform encryption processing on the to-be-processed image set, and generate a to-be-processed image queue according to the encrypted processed image set; and decrypt the to-be-processed image in the image queue to be processed. And extracting a cluster feature set according to the to-be-processed image after decryption processing. Further, the image to be processed in the image set to be processed may be compressed or trimmed, and the cluster feature set is extracted according to the image set to be processed after compression or cropping.

The first server may be a server cluster, that is, distributed processing that implements feature recognition processing through multiple servers. If the first server is a server cluster, the first server is composed of a plurality of first child servers. Each first sub-server can report the working status to the registration server in real time, and the registration server generates a list of available services according to the working status reported by the first sub-server. The server ID of the first subserver in the available state is recorded in the list of available services, and the first subserver in the available state can be selected by obtaining the list of available services. Before the client needs to send the to-be-processed image set, the server may obtain the available service list from the registration server, obtain the server identifier in the available service list, and select the target server identifier from the obtained server identifier by using a preset routing algorithm, and the image to be processed is to be processed. The collection is sent to the first subserver corresponding to the target server ID.

In the embodiments provided herein, the first server 804 can be, but is not limited to, providing a data transfer service, an encryption and decryption service, a feature recognition service, a storage interface service, and a storage service. The data transmission service is used for data transmission, for example, receiving an image set to be processed sent by a client through an IO service, or sending a cluster feature set to a client. The encryption and decryption service is used for encrypting and decrypting data. For example, the encryption and decryption service may be a Privacy service, and the image to be processed is encrypted by the Privacy service. The feature recognition service refers to a service that provides feature recognition processing, such as extracting cluster features in a set of images to be processed. A storage service is a service that stores data, such as storing a collection of images to be processed on a first server. A storage interface service refers to a service that interfaces with a storage service, such as a docking service with a storage service.

The second server 806 is configured to receive the clustering request sent by the client 802, perform clustering processing according to the clustering feature set in the clustering request, and send the clustering processing result to the client 802.

In an embodiment, the second server is further configured to generate a clustering request queue according to the clustering request sent by the client, and merge the clustering request queue with the same clustering request requesting object; according to the merged clustering The clustering feature set is requested to be clustered.

The method may further include: sorting the clustering request in the clustering request queue according to the request initiation time, and acquiring the specified clustering request in the sorted clustering request queue; and the clustering request queue and the specified clustering request The request initiates the same cluster request for the object to merge. Further, the clustering request in the clustering request queue is arranged in a first-to-last order according to the request initiation time, and the first clustering request in the clustering request queue is obtained; the clustering request queue is combined with the first clustering request The request initiates the same clustering request for the object to merge. It is also possible to generate tag data according to the clustering processing result and store the tag data in a preset storage space.

The second server may further train the training image set to obtain a clustering model and a feature recognition model, cluster the cluster feature set according to the clustering model, and send the feature recognition model to the first server to extract the image set to be processed. A collection of clustering features.

It can be understood that, in one embodiment, the second server can include, but is not limited to, a tag data service, a clustering service, a machine learning service, and a data transfer service. The tag data service refers to a service that generates tag data according to a clustering process result. The clustering service refers to a service that clusters data sets, for example, clustering feature sets. The machine learning service refers to a service that provides model training, for example, training a cluster model and a feature recognition model according to a training image set. A data transmission service refers to a service that provides data transmission, for example, pushing a cluster processing result to a client through a PUSH method.

The image processing system provided by the foregoing embodiment sends the image set to be processed to the first server for feature recognition processing by the client, and sends the cluster feature set processed by the first server to the second server for clustering processing. The client classifies the image set to be processed according to the clustering processing result returned by the second server. Instantly facing a huge amount of data, it can also be processed synchronously, improving the accuracy of image processing. The processing is performed on different servers, and different servers perform different processing, so that the division processing ensures the accuracy of image processing.

Figure 9 is a block diagram showing the structure of an image processing apparatus in an embodiment. As shown in FIG. 9, the image processing apparatus 900 includes an image acquisition module 902, a feature acquisition module 904, and an image classification module 906. among them:

The image obtaining module 902 is configured to acquire a to-be-processed image set, and send the to-be-processed image set to the first server.

The feature acquisition module 904 is configured to receive a cluster feature set that is sent by the first server according to the to-be-processed image set, and send a clustering request generated according to the cluster feature set to a second server.

The image classification module 906 is configured to receive a clustering processing result sent by the second server, and classify the to-be-processed image collection according to the clustering processing result, where the clustering processing result is determined by the second server according to The cluster feature set is obtained by clustering.

The image processing apparatus provided in the foregoing embodiment sends the image set to be processed to the first server for feature recognition processing, and sends the cluster feature set processed by the first server to the second server for clustering processing. The image set to be processed is classified according to the clustering processing result returned by the second server. Instantly facing a huge amount of data, it can also be processed synchronously, improving the accuracy of image processing. The processing is performed on different servers, and different servers perform different processing, so that the division processing ensures the accuracy of image processing.

Figure 10 is a block diagram showing the structure of an image processing apparatus in another embodiment. As shown in FIG. 10, the image processing apparatus 1000 includes an image receiving module 1002 and a feature acquiring module 1004. among them:

The image receiving module 1002 is configured to receive the to-be-processed image set sent by the client.

a feature acquiring module 1004, configured to extract a cluster feature set of the to-be-processed image set, and return the cluster feature set to the client, instructing the client to perform generating according to the cluster feature set The clustering request is sent to the second server, and the clustering processing result obtained by performing clustering processing according to the clustering feature set returned by the second server is received, and the to-be-processed image collection is obtained according to the clustering processing result. sort.

The image processing apparatus provided by the foregoing embodiment receives a set of to-be-processed images sent by a client, and extracts a cluster feature set of the image set to be processed. The client sends the clustering request generated by the clustering feature set to the second server, and receives the clustering processing result obtained by the clustering process according to the clustering feature set returned by the second server, and processes the image set according to the clustering processing result. sort. In this way, in the face of a huge amount of data, it is also possible to perform synchronization processing, which improves the accuracy of image processing. The processing is performed on different servers, and different servers perform different processing, so that the division processing ensures the accuracy of image processing.

In an embodiment, the feature acquiring module 1004 is further configured to generate a to-be-processed image queue according to the to-be-processed image set, and extract a clustering feature set according to the to-be-processed image in the to-be-processed image queue.

In the embodiment provided by the present application, the feature acquiring module 1004 is further configured to perform encryption processing on the to-be-processed image set, and generate a to-be-processed image queue according to the encrypted processed image set; and set the to-be-processed image queue The image to be processed is decrypted, and the cluster feature set is extracted according to the image to be processed after the decryption process.

In one embodiment, the feature acquisition module 1004 is further configured to compress or trim the image to be processed in the to-be-processed image set, and extract a cluster feature set according to the compressed or trimmed image set to be processed.

Figure 11 is a block diagram showing the structure of an image processing apparatus in still another embodiment. As shown in FIG. 11, the image processing apparatus 1100 includes a request receiving module 1102 and a feature clustering module 1104. among them:

The request receiving module 1102 is configured to receive the clustering request sent by the client, where the clustering request is generated by the client according to a clustering feature set sent by the first server, the clustering The feature set is extracted by the first server according to the set of to-be-processed images sent by the client.

The feature clustering module 1104 is configured to perform clustering processing according to the clustering feature set in the clustering request to obtain a clustering processing result, and send the clustering processing result to the client, instructing the client Performing to classify the to-be-processed image set according to the clustering processing result.

The image processing apparatus provided by the foregoing embodiment receives a clustering request sent by a client, performs clustering processing according to the clustering feature set in the clustering request, and obtains a clustering processing result, and sends the clustering processing result to the client. , so that the client classifies according to the clustering processing results. The clustering request is generated by the client according to the clustering feature set sent by the first server, and the clustering feature set is extracted by the first server according to the to-be-processed image set sent by the client. It can be seen that in the face of a huge amount of data, it is also possible to perform feature recognition and clustering processing at the same time, thereby improving the accuracy of image processing. The processing is performed on different servers, and different servers perform different processing, so that the division processing ensures the accuracy of image processing.

In one embodiment, the feature clustering module 1104 is further configured to generate a clustering request queue according to the clustering request sent by the client, and merge the clustering request request with the same clustering request object in the clustering request queue. And performing clustering processing on the clustering feature set according to the merged clustering request to obtain a clustering processing result.

In an embodiment, the feature clustering module 1104 is further configured to sort the clustering request in the clustering request queue according to the request initiation time, and obtain a specified clustering request in the sorted clustering request queue; The clustering request queue has the same clustering request as the request originating object of the specified clustering request for merging.

In the embodiment provided by the present application, the image processing apparatus 1100 may further include a label generation module 1106, configured to generate label data according to the clustering processing result, and store the label data in a preset storage space. .

In an embodiment, the image processing apparatus 1100 may further include a model training module 1108, configured to train the training image set to obtain a clustering model and a feature recognition model, according to the clustering model The clustering feature set performs clustering processing, and sends the feature recognition model to the first server to extract a clustering feature set of the to-be-processed image set.

The division of each module in the above image processing apparatus is for illustrative purposes only. In other embodiments, the image processing apparatus may be divided into different modules as needed to complete all or part of the functions of the image processing apparatus.

The embodiment of the present application also provides a computer readable storage medium. One or more non-transitory computer readable storage media containing a computer program, when executed by one or more processors, cause the processor to perform the image processing method described above.

Figure 12 is a schematic diagram showing the internal structure of a server in an embodiment. As shown in FIG. 12, the server includes a processor, a non-volatile storage medium, an internal memory, and a network interface connected by a system bus. The non-volatile storage medium of the server stores an operating system and a computer program. The computer program is executed by a processor to implement an image processing method. The server's processor is used to provide computing and control capabilities that support the operation of the entire server. The network interface of the server is used to communicate with an external terminal through a network connection, such as receiving a clustering request sent by the terminal and returning a clustering processing result to the terminal. The server can be implemented with a stand-alone server or a server cluster consisting of multiple servers. It will be understood by those skilled in the art that the structure shown in FIG. 12 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the server to which the solution of the present application is applied. The specific server may include More or fewer components are shown in the figures, or some components are combined, or have different component arrangements.

The embodiment of the present application also provides a computer device. As shown in FIG. 13 , for the convenience of description, only the parts related to the embodiments of the present application are shown. For the specific technical details not disclosed, refer to the method part of the embodiment of the present application. The computer device may be any terminal device including a mobile phone, a tablet computer, a PDA (Personal Digital Assistant), a POS (Point of Sales), a vehicle-mounted computer, a wearable device, and the like, taking a computer device as a mobile phone as an example. :

FIG. 13 is a block diagram showing a part of a structure of a mobile phone related to a computer device according to an embodiment of the present application. Referring to FIG. 13 , the mobile phone includes: a radio frequency (RF) circuit 1310 , a memory 1320 , an input unit 1330 , a display unit 1340 , a sensor 1350 , an audio circuit 1360 , a wireless fidelity (WiFi) module 1370 , and a processor 1380 . And power supply 1390 and other components. It will be understood by those skilled in the art that the structure of the handset shown in FIG. 13 does not constitute a limitation to the handset, and may include more or less components than those illustrated, or some components may be combined, or different components may be arranged.

The RF circuit 1310 can be used for receiving and transmitting information during the transmission and reception of information or during the call. The downlink information of the base station can be received and processed by the processor 1380. The uplink data can also be sent to the base station. Generally, RF circuits include, but are not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, RF circuitry 1310 can also communicate with the network and other devices via wireless communication. The above wireless communication may use any communication standard or protocol, including but not limited to Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (Code Division). Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), e-mail, Short Messaging Service (SMS), and the like.

The memory 1320 can be used to store software programs and modules, and the processor 1380 executes various functional applications and data processing of the mobile phone by running software programs and modules stored in the memory 1320. The memory 1320 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as an application of a sound playing function, an application of an image playing function, etc.); The data storage area can store data (such as audio data, address book, etc.) created according to the use of the mobile phone. Moreover, memory 1320 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

The input unit 1330 can be configured to receive input numeric or character information and to generate key signal inputs related to user settings and function control of the handset 1300. Specifically, the input unit 1330 may include a touch panel 1331 and other input devices 1332. The touch panel 1331, which may also be referred to as a touch screen, can collect touch operations on or near the user (such as a user using a finger, a stylus, or the like on the touch panel 1331 or near the touch panel 1331. Operation) and drive the corresponding connection device according to a preset program. In one embodiment, the touch panel 1331 can include two portions of a touch detection device and a touch controller. Wherein, the touch detection device detects the touch orientation of the user, and detects a signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts the touch information into contact coordinates, and sends the touch information. The processor 1380 is provided and can receive commands from the processor 1380 and execute them. In addition, the touch panel 1331 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch panel 1331, the input unit 1330 may further include other input devices 1332. Specifically, other input devices 1332 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.).

The display unit 1340 can be used to display information input by the user or information provided to the user as well as various menus of the mobile phone. The display unit 1340 can include a display panel 1341. In one embodiment, the display panel 1341 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like. In one embodiment, the touch panel 1331 may cover the display panel 1341. When the touch panel 1331 detects a touch operation thereon or nearby, the touch panel 1331 transmits to the processor 1380 to determine the type of the touch event, and then the processor 1380 is The type of touch event provides a corresponding visual output on display panel 1341. Although in FIG. 13 , the touch panel 1331 and the display panel 1341 are used as two independent components to implement the input and input functions of the mobile phone, in some embodiments, the touch panel 1331 and the display panel 1341 may be integrated. Realize the input and output functions of the phone.

The handset 1300 can also include at least one type of sensor 1350, such as a light sensor, motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 1341 according to the brightness of the ambient light, and the proximity sensor may close the display panel 1341 and/or when the mobile phone moves to the ear. Or backlight. The motion sensor may include an acceleration sensor, and the acceleration sensor can detect the magnitude of the acceleration in each direction, and the magnitude and direction of the gravity can be detected at rest, and can be used to identify the gesture of the mobile phone (such as horizontal and vertical screen switching), and vibration recognition related functions (such as Pedometer, tapping, etc.; in addition, the phone can also be equipped with gyroscopes, barometers, hygrometers, thermometers, infrared sensors and other sensors.

Audio circuitry 1360, speaker 1361, and microphone 1362 can provide an audio interface between the user and the handset. The audio circuit 1360 can transmit the converted electrical data of the received audio data to the speaker 1361, and convert it into a sound signal output by the speaker 1361; on the other hand, the microphone 1362 converts the collected sound signal into an electrical signal, by the audio circuit 1360. After receiving, it is converted into audio data, and then processed by the audio data output processor 1380, transmitted to another mobile phone via the RF circuit 1310, or outputted to the memory 1320 for subsequent processing.

WiFi is a short-range wireless transmission technology. The mobile phone can help users to send and receive emails, browse web pages and access streaming media through the WiFi module 1370. It provides users with wireless broadband Internet access. Although FIG. 13 shows the WiFi module 1370, it will be understood that it does not belong to the essential configuration of the handset 1300 and may be omitted as needed.

The processor 1380 is a control center for the handset that connects various portions of the entire handset using various interfaces and lines, by executing or executing software programs and/or modules stored in the memory 1320, and by invoking data stored in the memory 1320. The phone's various functions and processing data, so that the overall monitoring of the phone. In one embodiment, processor 1380 can include one or more processing units. In one embodiment, processor 1380 can integrate an application processor and a modem processor, where the application processor primarily processes an operating system, user interface, and applications, etc.; the modem processor primarily processes wireless communications. It will be appreciated that the above described modem processor may also not be integrated into the processor 1380.

The handset 1300 also includes a power source 1390 (such as a battery) that powers the various components. Preferably, the power source can be logically coupled to the processor 1380 via a power management system to enable management of charging, discharging, and power management functions through the power management system.

In one embodiment, the handset 1300 can also include a camera, a Bluetooth module, and the like.

In the embodiment of the present application, the processor 1380 included in the mobile terminal implements the image processing method described above when executing a computer program stored in a memory.

One of ordinary skill in the art can understand that all or part of the process of implementing the above embodiments can be completed by a computer program to instruct related hardware, and the program can be stored in a non-volatile computer readable storage medium. Wherein, the program, when executed, may include the flow of an embodiment of the methods as described above. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or the like.

Any reference to a memory, storage, database or other medium as used herein may include non-volatile and/or volatile memory. Suitable non-volatile memories can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM), which acts as an external cache. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronization. Link (Synchlink) DRAM (SLDRAM), Memory Bus (Rambus) Direct RAM (RDRAM), Direct Memory Bus Dynamic RAM (DRDRAM), and Memory Bus Dynamic RAM (RDRAM).

The above-mentioned embodiments are merely illustrative of several embodiments of the present application, and the description thereof is more specific and detailed, but is not to be construed as limiting the scope of the claims. It should be noted that a number of variations and modifications may be made by those skilled in the art without departing from the spirit and scope of the present application. Therefore, the scope of the invention should be determined by the appended claims.

Claims (31)

1. An image processing system, the system comprising:

   a client, configured to obtain a to-be-processed image set, send the to-be-processed image set to a first server, receive a clustering feature set sent by the first server, and generate a clustering request according to the clustering feature set Sending to the second server, and receiving the clustering processing result sent by the second server, and classifying the to-be-processed image set according to the clustering processing result;

   a first server, configured to receive the to-be-processed image set sent by the client, extract a cluster feature set of the to-be-processed image set, and return the cluster feature set to the client;

   And a second server, configured to receive the clustering request sent by the client, perform clustering processing according to the clustering feature set in the clustering request, and send the clustering processing result to the client.
2. An image processing method, the method comprising:

   Obtaining a to-be-processed image collection, and sending the to-be-processed image collection to a first server;

   Receiving a cluster feature set sent by the first server, and sending a clustering request generated according to the cluster feature set to a second server, where the cluster feature set is extracted according to the to-be-processed image set ;

   Receiving a clustering processing result sent by the second server, and classifying the to-be-processed image set according to the clustering processing result, where the clustering processing result is performed by the second server according to the clustering feature set Clustered processing.
3. An image processing method, the method comprising:

   Receiving the to-be-processed image set sent by the client;

   Extracting a cluster feature set of the to-be-processed image set, and returning the cluster feature set to the client, instructing the client to perform a clustering request generated according to the clustering feature set, sending to a second The server receives the clustering processing result obtained by performing clustering processing according to the clustering feature set returned by the second server, and classifying the to-be-processed image set according to the clustering processing result.
4. The image processing method according to claim 3, wherein the extracting the cluster feature set of the to-be-processed image set comprises:

   Generating a queue of images to be processed according to the to-be-processed image set, and extracting a cluster feature set according to the to-be-processed image in the image queue to be processed.
5. The image processing method according to claim 4, wherein the extracting the cluster feature set of the to-be-processed image set comprises:

   Performing an encryption process on the to-be-processed image set, and generating a to-be-processed image queue according to the encrypted processed image set;

   Decoding the image to be processed in the image queue to be processed, and extracting a cluster feature set according to the image to be processed after the decryption process.
6. The image processing method according to any one of claims 3 to 5, wherein the extracting the cluster feature set of the to-be-processed image set comprises:

   The image to be processed in the image set to be processed is compressed or clipped, and the cluster feature set is extracted according to the image set to be processed after compression or cropping.
7. An image processing method, the method comprising:

   Receiving, by the client, the clustering request, where the clustering request is generated by the client according to a clustering feature set sent by the first server, where the clustering feature set is generated by the first server Extracted according to the set of to-be-processed images sent by the client;

   And performing clustering processing according to the clustering feature set in the clustering request to obtain a clustering processing result, and sending the clustering processing result to the client, instructing the client to perform a clustering processing result according to the clustering process Sorting the set of images to be processed.
8. The image processing method according to claim 7, wherein the clustering processing result by clustering the clustering feature set according to the clustering request comprises:

   Generating a clustering request queue according to the clustering request sent by the client, and combining the clustering request requesting the same clustering request in the clustering request queue;

   And clustering the cluster feature set according to the merged cluster request to obtain a clustering process result.
9. The image processing method according to claim 8, wherein the merging the clustering request requesting the same clustering request in the clustering request queue comprises:

   Sorting the clustering requests in the clustering request queue according to the request initiation time, and obtaining the specified clustering request in the sorted clustering request queue;

   The clustering request in the clustering request queue that is the same as the request initiating object of the specified clustering request is merged.
10. The image processing method according to claim 7, wherein the method further comprises:

    The tag data is generated according to the clustering processing result, and the tag data is stored in a preset storage space.
11. The image processing method according to claim 7, wherein the method further comprises:

    Training the training image set to obtain a clustering model and a feature recognition model, performing clustering processing on the clustering feature set according to the clustering model, and sending the feature recognition model to the first server to extract the to-be-processed A collection of clustering features that process an image collection.
12. A computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following operations:

    Obtaining a to-be-processed image collection, and sending the to-be-processed image collection to a first server;

    Receiving a cluster feature set sent by the first server, and sending a clustering request generated according to the cluster feature set to a second server, where the cluster feature set is extracted according to the to-be-processed image set ;

    Receiving a clustering processing result sent by the second server, and classifying the to-be-processed image set according to the clustering processing result, where the clustering processing result is performed by the second server according to the clustering feature set Clustered processing.
13. A computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following operations:

    Receiving the to-be-processed image set sent by the client;

    Extracting a cluster feature set of the to-be-processed image set, and returning the cluster feature set to the client, instructing the client to perform a clustering request generated according to the clustering feature set, sending to a second The server receives the clustering processing result obtained by performing clustering processing according to the clustering feature set returned by the second server, and classifying the to-be-processed image set according to the clustering processing result.
14. The computer device according to claim 13, wherein when the processor performs the extracting the cluster feature set of the to-be-processed image set, the processor further performs the following operations:

    Generating a queue of images to be processed according to the to-be-processed image set, and extracting a cluster feature set according to the to-be-processed image in the image queue to be processed.
15. The computer device according to claim 14, wherein when the processor performs the extracting the cluster feature set of the to-be-processed image set, the processor further performs the following operations:

    Performing an encryption process on the to-be-processed image set, and generating a to-be-processed image queue according to the encrypted processed image set;

    Decoding the image to be processed in the image queue to be processed, and extracting a cluster feature set according to the image to be processed after the decryption process.
16. The computer device according to any one of claims 13 to 15, wherein when the processor performs the extracting the cluster feature set of the to-be-processed image set, the processor further performs the following operations:

    The image to be processed in the image set to be processed is compressed or clipped, and the cluster feature set is extracted according to the image set to be processed after compression or cropping.
17. A computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following operations:

    Receiving, by the client, the clustering request, where the clustering request is generated by the client according to a clustering feature set sent by the first server, where the clustering feature set is generated by the first server Extracted according to the set of to-be-processed images sent by the client;

    And performing clustering processing according to the clustering feature set in the clustering request to obtain a clustering processing result, and sending the clustering processing result to the client, instructing the client to perform a clustering processing result according to the clustering process Sorting the set of images to be processed.
18. The computer device according to claim 17, wherein when the processor performs the clustering processing on the clustering feature set according to the clustering request to obtain a clustering processing result, the processor further performs the following operations:

    Generating a clustering request queue according to the clustering request sent by the client, and combining the clustering request requesting the same clustering request in the clustering request queue;

    And clustering the cluster feature set according to the merged cluster request to obtain a clustering process result.
19. The computer device according to claim 18, wherein when the processor performs the merging of the clustering request requesting the same object in the clustering request queue, the processor further performs the following operations:

    Sorting the clustering requests in the clustering request queue according to the request initiation time, and obtaining the specified clustering request in the sorted clustering request queue;

    The clustering request in the clustering request queue that is the same as the request initiating object of the specified clustering request is merged.
20. The computer device according to claim 17, wherein the processor is further configured to perform the following operations:

    The tag data is generated according to the clustering processing result, and the tag data is stored in a preset storage space.
21. The computer device according to claim 17, wherein the processor is further configured to perform the following operations:

    Training the training image set to obtain a clustering model and a feature recognition model, performing clustering processing on the clustering feature set according to the clustering model, and sending the feature recognition model to the first server to extract the to-be-processed A collection of clustering features that process an image collection.
22. A computer readable storage medium having stored thereon a computer program, the computer program being executed by a processor as follows:

    Obtaining a to-be-processed image collection, and sending the to-be-processed image collection to a first server;

    Receiving a cluster feature set sent by the first server, and sending a clustering request generated according to the cluster feature set to a second server, where the cluster feature set is extracted according to the to-be-processed image set ;

    Receiving a clustering processing result sent by the second server, and classifying the to-be-processed image set according to the clustering processing result, where the clustering processing result is performed by the second server according to the clustering feature set Clustered processing.
23. A computer readable storage medium having stored thereon a computer program, the computer program being executed by a processor as follows:

    Receiving the to-be-processed image set sent by the client;

    Extracting a cluster feature set of the to-be-processed image set, and returning the cluster feature set to the client, instructing the client to perform a clustering request generated according to the clustering feature set, sending to a second The server receives the clustering processing result obtained by performing clustering processing according to the clustering feature set returned by the second server, and classifying the to-be-processed image set according to the clustering processing result.
24. The computer readable storage medium according to claim 23, wherein when the computer program is executed by the processor to extract the cluster feature set of the to-be-processed image set, the computer program further performs the following operations:

    Generating a queue of images to be processed according to the set of images to be processed, and extracting a cluster feature set according to the to-be-processed image in the image queue to be processed.
25. The computer readable storage medium according to claim 24, wherein when the computer program is executed by the processor to extract the cluster feature set of the to-be-processed image set, the computer program further performs the following operations:

    Performing an encryption process on the to-be-processed image set, and generating a to-be-processed image queue according to the encrypted processed image set;

    Decoding the image to be processed in the image queue to be processed, and extracting a cluster feature set according to the image to be processed after the decryption process.
26. The computer readable storage medium according to any one of claims 23 to 25, wherein when the computer program is executed by the processor to extract the cluster feature set of the to-be-processed image set, the computer program is further executed Do the following:

    The image to be processed in the image set to be processed is compressed or clipped, and the cluster feature set is extracted according to the image set to be processed after compression or cropping.
27. A computer readable storage medium having stored thereon a computer program, the computer program being executed by a processor as follows:

    Receiving, by the client, the clustering request, where the clustering request is generated by the client according to a clustering feature set sent by the first server, where the clustering feature set is generated by the first server Extracted according to the set of to-be-processed images sent by the client;

    And performing clustering processing according to the clustering feature set in the clustering request to obtain a clustering processing result, and sending the clustering processing result to the client, instructing the client to perform a clustering processing result according to the clustering process Sorting the set of images to be processed.
28. The computer readable storage medium according to claim 27, wherein said computer program is executed by said processor to perform clustering processing on said clustering feature set according to said clustering request When the result is, the following operations are also performed:

    Generating a clustering request queue according to the clustering request sent by the client, and combining the clustering request requesting the same clustering request in the clustering request queue;

    And clustering the cluster feature set according to the merged cluster request to obtain a clustering process result.
29. The computer readable storage medium according to claim 28, wherein said computer program is executed by said processor when said clustering request requesting the same clustering request in said clustering request queue is merged Do the following:

    Sorting the clustering requests in the clustering request queue according to the request initiation time, and obtaining the specified clustering request in the sorted clustering request queue;

    The clustering request in the clustering request queue that is the same as the request initiating object of the specified clustering request is merged.
30. The computer readable storage medium of claim 27, wherein the processor is further configured to perform the following operations:

    The tag data is generated according to the clustering processing result, and the tag data is stored in a preset storage space.
31. The computer readable storage medium of claim 27, wherein the processor is further configured to perform the following operations:

    Training the training image set to obtain a clustering model and a feature recognition model, performing clustering processing on the clustering feature set according to the clustering model, and sending the feature recognition model to the first server to extract the to-be-processed A collection of clustering features that process an image collection.

Images