CN107888707B - Picture transmission method and device and electronic equipment - Google Patents
Picture transmission method and device and electronic equipment Download PDFInfo
- Publication number
- CN107888707B CN107888707B CN201711296264.6A CN201711296264A CN107888707B CN 107888707 B CN107888707 B CN 107888707B CN 201711296264 A CN201711296264 A CN 201711296264A CN 107888707 B CN107888707 B CN 107888707B
- Authority
- CN
- China
- Prior art keywords
- picture
- transmitted
- preset
- thumbnail
- sampling
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/565—Conversion or adaptation of application format or content
- H04L67/5651—Reducing the amount or size of exchanged application data
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Editing Of Facsimile Originals (AREA)
Abstract
The embodiment of the invention provides a picture transmission method and device and electronic equipment. The method comprises the following steps: obtaining a characteristic value of a preset characteristic of a picture to be transmitted, wherein the preset characteristic comprises: character features; determining whether the picture to be transmitted is suitable for down-sampling or not by utilizing a preset picture classifier based on the characteristic value of the preset characteristic; and if the picture to be transmitted is not suitable for downsampling, sending the original picture of the picture to be transmitted and mark information representing that the picture to be transmitted is the original picture. According to the embodiment of the invention, the pictures to be transmitted with unclear characters are screened, and the original pictures of the pictures to be transmitted are directly transmitted without downsampling, so that the situation that the characters in the pictures are difficult to identify due to serious character definition loss in the downsampling process is avoided, and the user experience is improved.
Description
Technical Field
The present invention relates to the field of network transmission technologies, and in particular, to a method and an apparatus for transmitting pictures and an electronic device.
Background
With the increasing demand of the modern information society for communication services, the contradiction between communication quality and communication network bandwidth is increasingly prominent, especially for large-data-volume picture communication. In the prior art, in order to reduce the bandwidth occupied by transmitting pictures, an original picture is processed into a thumbnail picture, and then the thumbnail picture is transmitted.
However, the inventor finds that the prior art has at least the following problems in the process of implementing the invention:
for an original picture with insufficiently clear characters, in the process of processing the original picture into a thumbnail picture, the definition loss of the characters is serious, and even if the picture after transmission is restored by a picture restoration technology, the characters in the restored picture are still difficult to recognize, so that bad experience is brought to a user.
Disclosure of Invention
An object of the embodiments of the present invention is to provide a method for transmitting a picture, so as to solve a problem in the prior art that characters in a transmitted picture are not clear enough. The specific technical scheme is as follows:
in a first aspect of the present invention, there is provided a picture transmission method, including: obtaining a characteristic value of a preset characteristic of a picture to be transmitted, wherein the preset characteristic comprises: character features;
determining whether the picture to be transmitted is suitable for down-sampling or not by utilizing a preset picture classifier based on the characteristic value of the preset characteristic;
and if the picture to be transmitted is not suitable for downsampling, sending the original picture of the picture to be transmitted and mark information representing that the picture to be transmitted is the original picture.
With reference to the first aspect, in a first possible implementation manner, the preset feature further includes: a graphical feature;
the graphical feature, comprising: the resolution ratio of the picture to be transmitted and/or the length-width ratio of the picture to be transmitted.
With reference to the first aspect, in a second possible implementation manner, the text feature includes:
the area ratio of the text area to the picture to be transmitted, and the average perimeter of the text area to the perimeter of the picture to be transmitted.
With reference to the first aspect, in a third possible implementation manner, after the determining whether the picture to be transmitted is suitable for downsampling, the method further includes:
if the picture to be transmitted is determined to be a picture suitable for down-sampling, performing down-sampling processing on the picture to be transmitted to obtain a thumbnail picture;
and sending the thumbnail picture and mark information which represents that the thumbnail picture is a non-original picture.
With reference to the first aspect, in a fourth possible implementation manner, after the determining whether the picture to be transmitted is suitable for downsampling, the method further includes:
if the picture to be transmitted is determined to be suitable for down-sampling, acquiring a transmission strategy, wherein the transmission strategy comprises the following steps: the original picture or the thumbnail picture is prioritized;
if the transmission strategy is the prior original picture, sending the picture to be transmitted and mark information indicating that the picture to be transmitted is the original picture; alternatively, the first and second electrodes may be,
and if the transmission strategy is a priority thumbnail, downsampling the picture to be transmitted to obtain a thumbnail picture, and sending the thumbnail picture and mark information for indicating that the thumbnail picture is a non-original picture.
With reference to the fourth possible implementation manner of the first aspect, in a fifth possible implementation manner, the obtaining the transmission policy includes:
acquiring a communication state between a client and a server;
and acquiring a transmission strategy by utilizing a pre-established first transmission decision maker according to the communication state.
With reference to the fourth possible implementation manner of the first aspect, in a sixth possible implementation manner, the obtaining the transmission policy includes:
acquiring client state information, wherein the client state information comprises: the computing power of a CPU of the client device and/or the current remaining capacity of the client device;
and acquiring a transmission strategy by utilizing a pre-established second transmission decision maker according to the client state information.
With reference to the first aspect, in a seventh possible implementation manner, the determining, based on the feature value of the preset feature and by using a preset picture classifier, whether the picture to be transmitted is suitable for downsampling includes:
respectively normalizing the characteristic value of each preset characteristic to obtain a normalized characteristic value of each preset characteristic;
calculating the mapping value of the picture to be transmitted according to the following formula:
wherein f (x) is the mapping value, hθ(x) M is a preset threshold value theta for the reliability that the picture to be transmitted is not suitable for down samplingiFor the ith picture classifierIs determined based on a feature value of the preset feature of a plurality of sample pictures known to be suitable for down-sampling, xiThe normalized characteristic value of the ith preset characteristic is obtained, and n is the number of the preset characteristics;
when the mapping value is 1, determining the picture to be transmitted as a picture which is not suitable for downsampling; alternatively, the first and second electrodes may be,
and when the mapping value is 0, determining the picture to be transmitted as a picture suitable for down-sampling.
In a second aspect of the embodiments of the present invention, there is provided a picture transmission apparatus, the apparatus including:
the characteristic value module is used for acquiring the characteristic value of the preset characteristic of the picture to be transmitted, which is requested to be transmitted by the client, wherein the preset characteristic comprises the following steps: character features;
the classification module is used for determining whether the picture to be transmitted is suitable for down-sampling or not by utilizing a preset picture classifier based on the characteristic value of the preset characteristic;
and the sending module is used for sending the original picture of the picture to be transmitted and the mark information which represents that the picture to be transmitted is the original picture if the picture to be transmitted is not suitable for downsampling.
With reference to the second aspect, in a first possible implementation manner, the preset features further include: image features;
the image features include: the resolution ratio of the picture to be transmitted and/or the length-width ratio of the picture to be transmitted.
With reference to the second aspect, in a second possible implementation manner, the text feature includes:
the area ratio of the text area to the picture to be transmitted, and the average perimeter of the text area to the picture to be transmitted are compared with the perimeter of the picture to be transmitted.
With reference to the second aspect, in a third possible implementation manner, the apparatus further includes:
the down-sampling module is used for performing down-sampling processing on the picture to be transmitted to obtain a thumbnail picture if the picture to be transmitted is determined to be a picture suitable for down-sampling;
the sending module is further configured to send the thumbnail picture and mark information indicating that the thumbnail picture is a non-original picture.
With reference to the second aspect, in a fourth possible implementation manner, the apparatus further includes:
a decision module, configured to obtain a transmission policy if the picture to be transmitted is determined to be a picture suitable for downsampling, where the transmission policy includes: the original picture or the thumbnail picture is prioritized;
the sending module is further configured to send the picture to be transmitted and mark information indicating that the picture to be transmitted is an original picture if the transmission policy is a priority original picture; or
The down-sampling module is used for down-sampling the picture to be transmitted to obtain a thumbnail picture if the transmission strategy is a priority thumbnail;
the sending module is further configured to send the thumbnail picture and mark information indicating that the thumbnail picture is a non-original picture.
With reference to the second aspect, in a fourth possible implementation manner, in a fifth possible implementation manner, the decision module is specifically configured to acquire a communication state between the client and the server; and acquiring the transmission strategy by utilizing a pre-established first transmission decision maker according to the communication state.
With reference to the second aspect, in a fourth possible implementation manner, in a sixth possible implementation manner, the decision module is specifically configured to obtain client state information, where the client state information includes: the computing power of a CPU of the client device and/or the current remaining capacity of the client device; and obtaining the transmission strategy by utilizing a pre-established second transmission decision maker according to the client state information.
With reference to the second aspect, in a seventh possible implementation manner, the classification module is specifically configured to normalize the feature value of each preset feature respectively to obtain a normalized feature value of each preset feature; and calculating the mapping value of the picture to be transmitted according to the following formula:
wherein f (x) is the mapping value, hθ(x) M is a preset threshold value theta for the reliability that the picture to be transmitted is not suitable for down samplingiA model parameter for the ith preset feature, the model parameter being determined based on a feature value of the preset feature for a plurality of sample pictures known to be suitable for downsampling, xiThe normalized characteristic value of the ith preset characteristic is obtained, and n is the number of the preset characteristics;
when the mapping value is 1, determining the picture to be transmitted as a picture which is not suitable for downsampling; alternatively, the first and second electrodes may be,
and when the mapping value is 0, determining the picture to be transmitted as a picture suitable for down-sampling.
In a third aspect of the embodiments of the present invention, an electronic device is provided, which includes a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
and the processor is used for realizing any one of the image transmission methods when executing the program stored in the memory.
In a fourth aspect implemented by the present invention, there is provided a computer-readable storage medium having stored therein instructions, which when run on a computer, cause the computer to execute any one of the above-described picture transmission methods.
In a fifth aspect of the present invention, an embodiment of the present invention provides a computer program product including instructions, which when run on a computer, causes the computer to execute any one of the above-mentioned picture transmission methods.
According to the picture transmission solving method and device provided by the embodiment of the invention, whether the picture to be transmitted is suitable for downsampling or not can be determined according to the characteristic value of the characteristic of the picture including the character characteristic through the preset picture classifier, and for the picture which is not suitable for downsampling, the original picture which is not subjected to downsampling is directly transmitted, so that the situations that characters in the transmitted picture are not clear enough and difficult to recognize due to serious character definition loss in the downsampling process of the picture are avoided, and the user experience is improved. Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.
Fig. 1 is a schematic flowchart of a picture transmission method according to an embodiment of the present invention;
fig. 2 is another schematic flow chart of a picture transmission method according to an embodiment of the present invention;
fig. 3 is another schematic flow chart of a picture transmission method according to an embodiment of the present invention;
fig. 4 is another schematic flow chart illustrating a picture transmission method according to an embodiment of the present invention;
fig. 5 is a schematic flowchart of another image transmission method according to an embodiment of the present invention;
fig. 6a is a schematic structural diagram of a picture transmission device according to an embodiment of the present invention;
fig. 6b is a schematic structural diagram of a picture transmission device according to an embodiment of the present invention;
fig. 6c is a schematic structural diagram of a picture transmission device according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a picture transmission device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.
Referring to fig. 1, fig. 1 is a schematic flow chart of a picture transmission method according to an embodiment of the present invention, which may include the following steps:
s101, obtaining a characteristic value of a preset characteristic of a picture to be transmitted, wherein the preset characteristic comprises: and (4) character characteristics.
In this embodiment, for each preset feature of the picture to be transmitted, the feature value of the preset feature is obtained according to the actual meaning of the preset feature.
And S102, determining whether the picture to be transmitted is suitable for down-sampling or not by using a preset picture classifier based on the characteristic value of the preset characteristic.
In this embodiment, whether the sample picture is suitable for downsampling is determined manually. In an optional implementation manner, the sample picture is downsampled and restored through a super-resolution algorithm, and then whether characters in the restored picture can be clearly recognized or not is observed manually. If the sample picture can be clearly identified, the sample picture is considered to be suitable for down-sampling, and if the sample picture cannot be clearly identified, the sample picture is considered to be not suitable for down-sampling.
It can be understood that the picture classifier can be regarded as a mapping relation between the feature value of the preset feature of a picture and whether the picture is suitable for down-sampling. In this embodiment, the mapping relationship may be implemented by using a logistic regression model, or may be implemented by using a neural network model or other models in other implementations.
S103, if the picture to be transmitted is not suitable for down-sampling, the original picture of the picture to be transmitted and the mark information indicating that the picture to be transmitted is the original picture are sent.
For example, a prefix "original image" is added to the name of the original image of the transmitted image to be transmitted.
By adopting the embodiment, whether the picture to be transmitted is suitable for downsampling or not can be determined according to the characteristic value of the characteristic of the picture including the character characteristic through the preset picture classifier, and the original picture which is not subjected to downsampling is directly transmitted for the picture to be transmitted which is not suitable for downsampling, so that the situations that the characters in the transmitted picture are not clear enough and difficult to identify due to serious character definition loss in the downsampling process of the picture are avoided, and the user experience is improved.
It should be noted that, the picture transmission method provided in the embodiment of the present invention may be executed in a client (i.e., a terminal), and may also be executed in a server (e.g., a server), and the embodiment of the present invention is not limited thereto.
With reference to fig. 2 in conjunction with the above embodiments, fig. 2 is another schematic flow chart of the picture transmission method according to the embodiment of the present invention, and the method may include the following steps:
s201, the client sends a picture downloading request to the server.
S202, the server receives the picture downloading request.
S203, the server side obtains the characteristic value of the preset characteristic of the picture to be transmitted requested to be downloaded by the client side according to the picture downloading request, wherein the preset characteristic comprises the following steps: and (4) character characteristics.
In an alternative implementation, the text feature may include: the area ratio of the character area to the picture to be transmitted, and the average perimeter of the character area to the perimeter of the picture to be transmitted.
One picture may contain one or more text regions. In this embodiment, the characters whose interval does not exceed the preset threshold are divided into the same character region, and each character region is a minimum rectangular region capable of including all characters belonging to the character region.
It can be understood that the larger the ratio of the area of the character region in a picture to the area of the picture or the ratio of the average circumference of the character region to the circumference of the picture, the higher the expected value of the area ratio occupied by each character in the picture, and the larger the area ratio occupied by the character in the picture, the easier the recognition.
In an alternative implementation, the preset features may include graphical features, wherein the graphical features may include: the resolution of the picture to be transmitted and/or the aspect ratio of the picture to be transmitted.
The image characteristics can include the resolution of the picture to be transmitted but not the length-width ratio of the picture to be transmitted; the aspect ratio of the picture to be transmitted can be included, but the resolution of the picture to be transmitted is not included; the resolution of the picture to be transmitted and the aspect ratio of the picture to be transmitted can also be included.
It can be understood that the higher the resolution of a picture, the higher the expected value of the number of pixels occupied by each character in the picture, and the higher the probability that the characters in the restored picture are clear enough to be recognized after downsampling and restoration.
The aspect ratio of the picture in this embodiment is a value larger than any of the aspect ratio and the aspect ratio of the picture. When the length and width of a picture are large, the client device is limited by the length and width of the screen (e.g. conventional screen length and width ratios 16:9 and 4:3), and cannot display the picture well, which may cause the characters in the picture to be difficult to recognize.
In another implementation, the preset feature may further include a data amount of a picture, and it is understood that the larger the data amount of a picture is, the more information amount contained in the picture is, and after downsampling and restoring, the more information amount remains in the restored picture. The more information contained in a picture, the higher the probability that the characters in the picture can be clearly identified.
And S204, respectively normalizing the characteristic value of each preset characteristic of the picture to be transmitted by the server side to obtain the normalized characteristic value of each preset characteristic.
For example, assume that the characteristic value of the picture resolution of the picture to be transmitted is x0The eigenvalue may be normalized according to the following equation to obtain a normalized eigenvalue x'0：
S205, the server side takes each normalized characteristic value of the preset characteristics of the picture to be transmitted as model input, and calculates the mapping value of the picture to be transmitted by using a logistic regression model.
In this embodiment, the following logistic regression model is used to calculate the mapping value of the picture to be transmitted:
wherein f (x) is a mapping value, hθ(x) For the reliability that the picture to be transmitted is not suitable for down-sampling, m is a preset threshold value, thetaiIs the ith model parameter of the logistic regression model, the model parameter is determined based on the characteristic value of the preset characteristic of a plurality of sample pictures which are known to be suitable for downsampling, xiThe ith model input of the logistic regression model is obtained, and n is the number of the model inputs;
the model parameters are predetermined and can be determined based on feature values of preset features of a plurality of sample pictures known to be suitable for downsampling, that is, a preset picture classifier is constructed. It can be understood that the types of the preset features of the to-be-transmitted picture and the preset features of the sample picture, which are obtained in step S203, should be correspondingly consistent, for example, the preset features of the sample picture are as follows: the area ratio of the text region to the sample picture, the ratio of the average perimeter of the text region to the perimeter of the sample picture, and the resolution of the sample picture, the preset characteristics of the picture to be transmitted should be: the area ratio of the text region to the picture to be transmitted, the average perimeter of the text region to the perimeter of the picture to be transmitted, and the resolution of the picture to be transmitted.
Specifically, in this embodiment, a logistic regression model is initialized, and each preset feature value of each sample picture is normalized respectively, so as to obtain a normalized feature value of each preset feature of each sample picture. It will be appreciated that the use of normalized feature values as model inputs is intended to reduce the fluctuation range of the model inputs so that convergence is at a faster rate. The characteristic value with small fluctuation range can be directly used as the model input without normalization.
And then, taking the normalized characteristic value of each preset characteristic of each sample picture as model input to obtain a mapping value of each sample picture. And calculating the score of the currently used model parameter according to the mapping value of each sample picture according to the following formula:
where P is the score of the current model parameter, k is the number of sample pictures, fiFor the mapping value, r, of the ith sample picture calculated based on the current model parametersiIndicating whether the ith sample picture is suitable for down-sampling or not, if the ith sample picture is suitable for down-sampling, riIs 0, otherwise riIs 1.
And finally, continuously adjusting the model parameters, and calculating the scores of the adjusted model parameters until the scores of the adjusted model parameters are higher than a preset threshold value.
S206, if the mapping value of the picture to be transmitted is 1, determining that the picture to be transmitted is not suitable for down-sampling, executing the step S207, and if the mapping value of the picture to be transmitted is 0, determining that the picture to be transmitted is suitable for down-sampling, executing the step S208.
It will be understood that hθ(x) Indicates the reliability that the picture to be transmitted is not suitable for down-sampling, so 1hθ(x) Representing the confidence that the picture to be transmitted is suitable for downsampling. In this embodiment, when the reliability that a picture to be transmitted is not suitable for downsampling is not lower than the reliability that the picture to be transmitted is suitable for downsampling, the picture to be transmitted is determined to be a picture that is not suitable for downsampling, and therefore m is 0.5 in this embodiment. In other implementations, m may also be adjusted according to actual requirements.
And S207, the server sends the original picture of the picture to be transmitted and the mark information indicating that the picture to be transmitted is the original picture to the client.
And S208, the server performs downsampling processing on the picture to be transmitted to obtain the thumbnail picture.
S209, the server sends the thumbnail picture and mark information which represents that the thumbnail picture is a non-original picture to the client.
Referring to fig. 3, fig. 3 is another schematic flow chart of a picture transmission method according to an embodiment of the present invention, which may include the following steps:
s301, the client receives a picture uploading instruction.
S302, the client acquires a characteristic value of a preset characteristic of the picture to be transmitted to be uploaded according to the picture uploading instruction, wherein the preset characteristic comprises the following steps: and (4) character characteristics.
And S303, respectively normalizing the characteristic value of each preset characteristic of the picture to be transmitted by the client to obtain the normalized characteristic value of each preset characteristic.
S304, the client inputs each normalized characteristic value of the preset characteristics of the picture to be transmitted as a model, and calculates the mapping value of the picture to be transmitted by using a logistic regression model.
S305, if the mapping value of the picture to be transmitted is 1, determining that the picture to be transmitted is not suitable for down-sampling, executing a step S306, and if the mapping value of the picture to be transmitted is 0, determining that the picture to be transmitted is suitable for down-sampling, executing a step S307.
S306, the client sends the original picture of the picture to be transmitted and the mark information which represents that the picture to be transmitted is the original picture to the server.
S307, the client carries out down-sampling processing on the picture to be transmitted to obtain the thumbnail picture.
S308, the client sends the thumbnail picture and mark information which represents that the thumbnail picture is a non-original picture to the server.
Referring to fig. 4, another flow diagram of the picture transmission method provided by the embodiment of the present invention shown in fig. 4 may include the following steps:
s401 to S405 are the same as S201 to S205, and refer to the descriptions of S201 to S205, which are not described herein again.
S406, if the mapping value of the picture to be transmitted is 1, determining that the picture to be transmitted is not suitable for down-sampling, executing the step S407, and if the mapping value of the picture to be transmitted is 0, determining that the picture to be transmitted is suitable for down-sampling, executing the step S408.
S407, the server sends the original picture of the picture to be transmitted and the mark information indicating that the picture to be transmitted is the original picture to the client.
S408, the server acquires the transmission policy, if the transmission policy is the priority original picture, step S407 is executed, and if not, step S409 is executed.
In an optional implementation manner, obtaining the transmission policy may include: acquiring a communication state between a client and a server; and acquiring a transmission strategy by utilizing a first transmission decision maker which is created in advance according to the communication state.
The data volume of the original picture of one picture is larger than that of the thumbnail of the picture, and the time t required for transmitting the original picture is the same in the communication state1More than the time t required for transmitting the thumbnail picture2When the communication state between the server and the client is good, t1And t2The difference is not large, and at this time, in order to improve the quality of the picture transmitted by the user, the first transmission decision device may determine the transmission policy as the priority original picture. And when the communication state is poor, t1And t2The difference is large, so that a user spends a large amount of time waiting for the picture to be loaded, and the user experience is reduced, and at this time, the first transmission decision device may determine the transmission policy as the priority thumbnail.
By adopting the implementation mode, whether the original picture or the thumbnail picture is sent to the client side can be further determined according to the communication state between the client side and the server side. When the communication state is poor, the thumbnail picture is preferentially sent to the client, so that the time for the client to download the picture can be saved, and the user experience is improved.
In another optional implementation manner, the obtaining of the transmission policy may include: acquiring client state information sent by a client, wherein the client state information comprises: the computing power of a CPU of the client device and/or the current remaining capacity of the client device; and acquiring a transmission strategy by utilizing a pre-established second transmission decision maker according to the client state information.
Wherein the client state information may include a computing power of a CPU of the client device and not include a current remaining power of the client device; the current remaining capacity of the client device may also be included without including the computing power of the CPU of the client device; but also the CPU computing power of the client device and the current remaining power of the client device.
Because the visual effect of the thumbnail picture is poorer than that of the original picture, the client usually performs up-sampling on the thumbnail picture after receiving the thumbnail picture to obtain a recovered picture, and displays the recovered picture, so that the user obtains the visual effect close to the original picture. However, upsampling thumbnail pictures may introduce additional computational overhead and power consumption to the client device. These additional computational overhead and power consumption may not be much affected when the client device is in a better state (better computational power, sufficient remaining power), and at this time, in order to improve the quality of the picture transmitted by the user, the second transmission decision device may determine the transmission policy as the priority original picture. And in the case of a poor client state, for example, poor computing capability of the client device, the upsampling takes more time and affects user experience, and at this time, the second transmission decision device may determine the transmission policy as a preferential thumbnail picture.
By adopting the implementation mode, the original picture or the thumbnail picture can be further determined to be sent to the client according to the current state information of the client. When the client list state is poor, the original picture is preferentially sent to the client so as to reduce the consumption of resources of the client.
It is to be understood that similar to the picture classifier, the first/second transmission decision maker can also be regarded as a mapping relation. In this embodiment, the mapping relationship may be implemented by using a logistic regression model, or may be implemented by using a neural network model or other models in other implementation manners.
And S409, the server side performs down-sampling on the picture to be transmitted to obtain the thumbnail picture.
S410, the server side sends the thumbnail picture and mark information which represents that the thumbnail picture is a non-original picture to the client side.
Referring to fig. 5, fig. 5 is another schematic flow chart of a picture transmission method according to an embodiment of the present invention, which may include the following steps:
s501, the client receives a picture uploading instruction.
S502, the client acquires a characteristic value of a preset characteristic of the picture to be transmitted to be uploaded according to the picture uploading instruction, wherein the preset characteristic comprises the following steps: and (4) character characteristics.
S503, the client respectively normalizes the characteristic value of each preset characteristic of the picture to be transmitted to obtain the normalized characteristic value of each preset characteristic.
S504, the client inputs each normalized characteristic value of the preset characteristics of the picture to be transmitted as a model, and calculates the mapping value of the picture to be transmitted by using a logistic regression model.
S505, if the mapping value of the picture to be transmitted is 1, the picture to be transmitted is not suitable for down-sampling, the step S506 is executed, and if the mapping value of the picture to be transmitted is 0, the picture to be transmitted is suitable for down-sampling, the step S507 is executed.
S506, the client sends the original picture of the picture to be transmitted and the mark information which represents that the picture to be transmitted is the original picture to the server.
S507, the client obtains the transmission policy, if the transmission policy is the priority original picture, step S506 is executed, and if not, step S508 is executed.
And S508, the client performs down-sampling on the picture to be transmitted to obtain a thumbnail picture.
S509, the client sends the thumbnail picture and mark information indicating that the thumbnail picture is a non-original picture to the server.
Referring to fig. 6a, fig. 6a is a schematic structural diagram of a picture transmission device according to an embodiment of the present invention, which may include the following modules:
the characteristic value module 601 is configured to obtain a characteristic value of a preset characteristic of a picture to be transmitted, where the preset characteristic includes: character features;
a classification module 602, configured to determine whether a picture to be transmitted is suitable for downsampling by using a preset picture classifier based on a feature value of a preset feature;
a sending module 603, configured to send an original picture of the picture to be transmitted and flag information indicating that the picture to be transmitted is the original picture if the picture to be transmitted is not suitable for downsampling.
In an optional implementation manner, the presetting the feature value further includes: image features;
image features, comprising: the resolution of the picture to be transmitted and/or the aspect ratio of the picture to be transmitted.
In an alternative implementation, the text feature includes:
the area ratio of the character area to the picture to be transmitted, and the average perimeter of the character area to the perimeter of the picture to be transmitted.
Referring to fig. 6b, in an alternative implementation, the method may further include:
a down-sampling module 604, configured to, if the picture to be transmitted is determined to be a picture suitable for down-sampling, perform down-sampling processing on the picture to be transmitted to obtain a thumbnail picture;
the sending module 603 is further configured to send the thumbnail picture and mark information indicating that the thumbnail picture is a non-original picture.
Referring to fig. 6c, in an alternative implementation, the method may further include:
a decision module 605, configured to obtain a transmission policy if the picture to be transmitted is determined to be suitable for the downsampled picture, where the transmission policy includes: the original picture or the thumbnail picture is prioritized;
the sending module 603 is further configured to send the picture to be transmitted and the flag information indicating that the picture to be transmitted is the original picture if the transmission policy is the priority original picture; or
A down-sampling module 604, configured to, if the to-be-transmitted policy is a preferential thumbnail picture, perform down-sampling on the to-be-transmitted picture to obtain a thumbnail picture;
the sending module 603 is further configured to send the thumbnail picture and mark information indicating that the thumbnail picture is a non-original picture.
In an alternative implementation manner, the decision module 605 may specifically be configured to obtain a communication state between the client and the server; and acquiring a transmission strategy by utilizing a pre-established first transmission decision maker according to the communication state.
In an optional implementation manner, the decision module 605 may be specifically configured to obtain client state information, where the client state information includes: the computing power of a CPU of the client device and/or the current remaining capacity of the client device; and according to the client state information, a second transmission decision maker which is created in advance is utilized to obtain a transmission strategy.
In an optional implementation manner, the classification module 602 may be specifically configured to normalize the feature value of each preset feature respectively to obtain a normalized feature value of each preset feature; and calculating the mapping value of the picture to be transmitted according to the following formula:
wherein f (x) is a mapping value, hθ(x) For the reliability that the picture to be transmitted is not suitable for down-sampling, m is a preset threshold value, thetaiModel parameters, x, for the ith predetermined featureiThe normalized characteristic value of the ith preset characteristic is obtained, and n is the number of the preset characteristics;
when the mapping value is 1, determining the picture to be transmitted as a picture which is not suitable for down-sampling; alternatively, the first and second electrodes may be,
and when the mapping value is 0, determining the picture to be transmitted as a picture suitable for downsampling.
An embodiment of the present invention further provides an electronic device, as shown in fig. 7, including a processor 701, a communication interface 702, a memory 703 and a communication bus 704, where the processor 701, the communication interface 702, and the memory 703 complete mutual communication through the communication bus 704,
a memory 703 for storing a computer program;
the processor 701 is configured to implement the following steps when executing the program stored in the memory 703:
obtaining a characteristic value of a preset characteristic of a picture to be transmitted, wherein the preset characteristic comprises: character features;
determining whether the picture to be transmitted is suitable for down-sampling or not by utilizing a preset picture classifier based on the characteristic value of the preset characteristic;
and if the picture to be transmitted is not suitable for downsampling, sending the original picture of the picture to be transmitted and mark information indicating that the picture to be transmitted is the original picture.
In an alternative implementation, the text feature may include: the area ratio of the character area to the picture to be transmitted, and the average perimeter of the character area to the perimeter of the picture to be transmitted.
In an optional implementation, the preset feature may further include: image features; the graphical features may include: the resolution of the picture to be transmitted and/or the aspect ratio of the picture to be transmitted.
In an alternative implementation, the following steps may also be implemented:
if the picture to be transmitted is determined to be a picture suitable for down-sampling, the picture to be transmitted is subjected to down-sampling processing to obtain a thumbnail picture;
and sending the thumbnail picture and mark information which indicates that the thumbnail picture is a non-original picture.
In an alternative implementation, the following steps may also be implemented:
if the picture to be transmitted is determined to be suitable for down-sampling, acquiring a transmission strategy, wherein the transmission strategy comprises the following steps: the original picture or the thumbnail picture is prioritized;
if the lower acquisition strategy is to take priority to the original picture, sending the picture to be transmitted and mark information indicating that the picture to be transmitted is the original picture;
and if the transmission strategy is the priority thumbnail, downsampling the picture to be transmitted to obtain a thumbnail picture, and sending the thumbnail picture and mark information for indicating that the thumbnail picture is a non-original picture.
Further, in this implementation manner, the obtaining of the transmission policy may include:
acquiring a communication state between a client and a server;
and acquiring a transmission strategy by utilizing a pre-established first transmission decision maker according to the communication state.
Further, in this implementation manner, the obtaining of the transmission policy may include:
acquiring client state information, wherein the client state information comprises: the computing power of a CPU of the client device and/or the current remaining capacity of the client device;
and acquiring a transmission strategy by utilizing a pre-established second transmission decision maker according to the client state information.
In an optional implementation manner, determining whether the picture to be transmitted is suitable for downsampling by using a preset picture classifier based on a feature value of a preset feature may include:
respectively normalizing the characteristic value of each preset characteristic to obtain a normalized characteristic value of each preset characteristic;
calculating a mapping value of a picture to be transmitted according to the following formula:
wherein f (x) is a mapping value, hθ(x) For the reliability that the picture to be transmitted is not suitable for down-sampling, m is a preset threshold value, thetaiIs the ith model parameter, xiThe normalized characteristic value of the ith preset characteristic is obtained, and n is the number of the preset characteristics;
when the mapping value is 1, determining the picture to be transmitted as a picture which is not suitable for down-sampling; or
And when the mapping value is 0, determining the picture to be transmitted as a picture suitable for downsampling.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
In another embodiment of the present invention, a computer-readable storage medium is further provided, which stores instructions that, when executed on a computer, cause the computer to execute any one of the above-mentioned image transmission methods.
In another embodiment, a computer program product containing instructions is provided, which when run on a computer causes the computer to execute any of the above-mentioned image transmission methods.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for embodiments of the apparatus, the electronic device, the computer-readable storage medium, and the computer program product comprising instructions, which are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (17)
1. A picture transmission method, comprising:
obtaining a characteristic value of a preset characteristic of a picture to be transmitted, wherein the preset characteristic comprises: character features;
determining whether the picture to be transmitted is suitable for down-sampling or not by utilizing a preset picture classifier based on the characteristic value of the preset characteristic, wherein the picture classifier is obtained by training a sample picture marked with an artificial judgment result in advance, the artificial judgment result is used for indicating whether characters in the restored picture can be clearly recognized through artificial observation, and the restored picture is obtained by restoring the sample picture through a super-resolution algorithm after down-sampling;
and if the picture to be transmitted is not suitable for downsampling, sending the original picture of the picture to be transmitted and mark information representing that the picture to be transmitted is the original picture.
2. The method of claim 1, wherein the pre-set characteristics further comprise: a graphical feature;
the graphical feature, comprising: the resolution ratio of the picture to be transmitted and/or the length-width ratio of the picture to be transmitted.
3. The method of claim 1, wherein the text feature comprises:
the area ratio of the text area to the picture to be transmitted, and the average perimeter of the text area to the perimeter of the picture to be transmitted.
4. The method of claim 1, further comprising:
if the picture to be transmitted is determined to be a picture suitable for down-sampling, performing down-sampling processing on the picture to be transmitted to obtain a thumbnail picture;
and sending the thumbnail picture and mark information which represents that the thumbnail picture is a non-original picture.
5. The method of claim 1, further comprising:
if the picture to be transmitted is determined to be suitable for down-sampling, acquiring a transmission strategy, wherein the transmission strategy comprises the following steps: the original picture or the thumbnail picture is prioritized;
if the transmission strategy is the prior original picture, sending the picture to be transmitted and mark information indicating that the picture to be transmitted is the original picture; alternatively, the first and second electrodes may be,
and if the transmission strategy is a priority thumbnail, downsampling the picture to be transmitted to obtain a thumbnail picture, and sending the thumbnail picture and mark information for indicating that the thumbnail picture is a non-original picture.
6. The method of claim 5, wherein the obtaining the transmission policy comprises:
acquiring a communication state between a client and a server;
and acquiring a transmission strategy by utilizing a pre-established first transmission decision maker according to the communication state.
7. The method of claim 5, wherein the obtaining the transmission policy comprises:
acquiring client state information, wherein the client state information comprises: the computing power of a CPU of the client device and/or the current remaining capacity of the client device;
and acquiring a transmission strategy by utilizing a pre-established second transmission decision maker according to the client state information.
8. The method according to claim 1, wherein the determining whether the picture to be transmitted is suitable for downsampling by using a preset picture classifier based on the feature value of the preset feature comprises:
respectively normalizing the characteristic value of each preset characteristic to obtain a normalized characteristic value of each preset characteristic;
calculating the mapping value of the picture to be transmitted according to the following formula:
wherein f (x) is the mapping value,
m is a preset threshold value for the reliability that the picture to be transmitted is not suitable for down-sampling,
for the model parameter, x, of the ith said picture classifieriThe normalized characteristic value of the ith preset characteristic is obtained, and n is the number of the preset characteristics;
when the mapping value is 1, determining the picture to be transmitted as a picture which is not suitable for downsampling; alternatively, the first and second electrodes may be,
and when the mapping value is 0, determining the picture to be transmitted as a picture suitable for down-sampling.
9. A picture transmission device, comprising:
the characteristic value module is used for acquiring the characteristic value of the preset characteristic of the picture to be transmitted, wherein the preset characteristic comprises the following steps: character features;
the classification module is used for determining whether the picture to be transmitted is suitable for downsampling or not by utilizing a preset picture classifier based on the characteristic value of the preset characteristic, wherein the picture classifier is obtained by training a sample picture marked with an artificial judgment result in advance, the artificial judgment result is used for indicating whether characters in the restored picture can be clearly identified through artificial observation or not, and the restored picture is obtained by restoring the sample picture through a super-resolution algorithm after downsampling;
and the sending module is used for sending the original picture of the picture to be transmitted and the mark information which represents that the picture to be transmitted is the original picture if the picture to be transmitted is not suitable for downsampling.
10. The apparatus of claim 9, wherein the preset feature further comprises: image features;
the image features include: the resolution ratio of the picture to be transmitted and/or the length-width ratio of the picture to be transmitted.
11. The apparatus of claim 9, wherein the text feature comprises:
the area ratio of the text area to the picture to be transmitted, and the average perimeter of the text area to the perimeter of the picture to be transmitted.
12. The apparatus of claim 9, further comprising:
the down-sampling module is used for performing down-sampling processing on the picture to be transmitted to obtain a thumbnail picture if the picture to be transmitted is determined to be a picture suitable for down-sampling;
the sending module is further configured to send the thumbnail picture and mark information indicating that the thumbnail picture is a non-original picture.
13. The apparatus of claim 9, further comprising:
a decision module, configured to obtain a transmission policy if the picture to be transmitted is determined to be a picture suitable for downsampling, where the transmission policy includes: the original picture or the thumbnail picture is prioritized;
the sending module is further configured to send the picture to be transmitted and mark information indicating that the picture to be transmitted is an original picture if the transmission policy is a priority original picture; alternatively, the first and second electrodes may be,
the down-sampling module is used for down-sampling the picture to be transmitted to obtain a thumbnail picture if the transmission strategy is a priority thumbnail;
the sending module is further configured to send the thumbnail picture and mark information indicating that the thumbnail picture is a non-original picture.
14. The apparatus according to claim 13, wherein the decision module is specifically configured to obtain a communication status between the client and the server; and acquiring the transmission strategy by utilizing a pre-established first transmission decision maker according to the communication state.
15. The apparatus according to claim 13, wherein the decision module is specifically configured to obtain client state information, and the client state information includes: the computing power of a CPU of the client device and/or the current remaining capacity of the client device; and obtaining the transmission strategy by utilizing a pre-established second transmission decision maker according to the client state information.
16. The apparatus according to claim 9, wherein the classification module is specifically configured to normalize the feature value of each of the preset features respectively, to obtain a normalized feature value of each of the preset features; and calculating the mapping value of the picture to be transmitted according to the following formula:
wherein f (x) is the mapping value,
m is a preset threshold value for the reliability that the picture to be transmitted is not suitable for down-sampling,
is the ith model parameter, xiThe normalized characteristic value of the ith preset characteristic is obtained, and n is the number of the preset characteristics;
when the mapping value is 1, determining the picture to be transmitted as a picture which is not suitable for downsampling; alternatively, the first and second electrodes may be,
and when the mapping value is 0, determining the picture to be transmitted as a picture suitable for down-sampling.
17. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1 to 8 when executing a program stored in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711296264.6A CN107888707B (en) | 2017-12-08 | 2017-12-08 | Picture transmission method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711296264.6A CN107888707B (en) | 2017-12-08 | 2017-12-08 | Picture transmission method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107888707A CN107888707A (en) | 2018-04-06 |
| CN107888707B true CN107888707B (en) | 2021-04-20 |
Family
ID=61773324
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711296264.6A Active CN107888707B (en) | 2017-12-08 | 2017-12-08 | Picture transmission method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107888707B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109191554B (en) * | 2018-09-04 | 2021-01-01 | 清华-伯克利深圳学院筹备办公室 | Super-resolution image reconstruction method, device, terminal and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101122952A (en) * | 2007-09-21 | 2008-02-13 | 北京大学 | Picture words detecting method |
| CN102750686A (en) * | 2012-06-12 | 2012-10-24 | 华东师范大学 | Super-resolution file image restoration processing method based on learning |
| CN103020905A (en) * | 2012-10-09 | 2013-04-03 | 武汉大学 | Sparse-constraint-adaptive NLM (non-local mean) super-resolution reconstruction method aiming at character image |
| CN103475876A (en) * | 2013-08-27 | 2013-12-25 | 北京工业大学 | Learning-based low-bit-rate compression image super-resolution reconstruction method |
| CN104537368A (en) * | 2015-01-07 | 2015-04-22 | 北京工业大学 | Recovery and analysis method for English printed double-sided printing broken file |
| CN106709875A (en) * | 2016-12-30 | 2017-05-24 | 北京工业大学 | Compressed low-resolution image restoration method based on combined deep network |
| CN106875350A (en) * | 2017-01-05 | 2017-06-20 | 宇龙计算机通信科技(深圳)有限公司 | Method, device and the terminal of sharpening treatment are carried out to blurred picture |
| CN107403140A (en) * | 2017-07-04 | 2017-11-28 | 南京律智诚专利技术开发有限公司 | A kind of card information identification and business card image matching management method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CZ2007114A3 (en) * | 2007-02-13 | 2008-08-27 | Kochánek@Jirí | Data transformation and wireless compression method in electronic form |
| CN102164167B (en) * | 2011-02-21 | 2014-10-15 | 北京奇虎科技有限公司 | Method and system for remote-control classified transmission |
| CN102611823B (en) * | 2012-01-13 | 2014-06-04 | 百度在线网络技术（北京）有限公司 | Method and equipment capable of selecting compression algorithm based on picture content |
| CN105513100B (en) * | 2015-12-03 | 2018-07-17 | 广州一刻影像科技有限公司 | A method of automatically selecting picture compression quality and compressed picture |
| CN106445353A (en) * | 2016-11-14 | 2017-02-22 | 乐视控股（北京）有限公司 | Display method and device of super-large pictures and electronic equipment |
| CN106683409A (en) * | 2017-02-08 | 2017-05-17 | 南京杰迈视讯科技有限公司 | Heavy type lorry photographing and identifying management method and the system of the same |
-
2017
- 2017-12-08 CN CN201711296264.6A patent/CN107888707B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101122952A (en) * | 2007-09-21 | 2008-02-13 | 北京大学 | Picture words detecting method |
| CN102750686A (en) * | 2012-06-12 | 2012-10-24 | 华东师范大学 | Super-resolution file image restoration processing method based on learning |
| CN103020905A (en) * | 2012-10-09 | 2013-04-03 | 武汉大学 | Sparse-constraint-adaptive NLM (non-local mean) super-resolution reconstruction method aiming at character image |
| CN103475876A (en) * | 2013-08-27 | 2013-12-25 | 北京工业大学 | Learning-based low-bit-rate compression image super-resolution reconstruction method |
| CN104537368A (en) * | 2015-01-07 | 2015-04-22 | 北京工业大学 | Recovery and analysis method for English printed double-sided printing broken file |
| CN106709875A (en) * | 2016-12-30 | 2017-05-24 | 北京工业大学 | Compressed low-resolution image restoration method based on combined deep network |
| CN106875350A (en) * | 2017-01-05 | 2017-06-20 | 宇龙计算机通信科技(深圳)有限公司 | Method, device and the terminal of sharpening treatment are carried out to blurred picture |
| CN107403140A (en) * | 2017-07-04 | 2017-11-28 | 南京律智诚专利技术开发有限公司 | A kind of card information identification and business card image matching management method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107888707A (en) | 2018-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017101626A1 (en) | Method and apparatus for implementing image processing | |
| CN108174276B (en) | Bullet screen display method and display device | |
| CN108322789B (en) | Network picture display method and device and mobile terminal | |
| CN110012217B (en) | Method and device for determining acquisition resolution and electronic equipment | |
| CN112602088B (en) | Method, system and computer readable medium for improving quality of low light images | |
| CN110647702B (en) | Picture preloading method and device, electronic equipment and readable medium | |
| CN111325067B (en) | Illegal video identification method and device and electronic equipment | |
| CN110287361B (en) | Figure picture screening method and device | |
| CN107888707B (en) | Picture transmission method and device and electronic equipment | |
| CN111882578A (en) | Foreground image acquisition method, foreground image acquisition device and electronic equipment | |
| CN110689565B (en) | Depth map determination method and device and electronic equipment | |
| CN111145202B (en) | Model generation method, image processing method, device, equipment and storage medium | |
| CN110689496B (en) | Method and device for determining noise reduction model, electronic equipment and computer storage medium | |
| CN110288560A (en) | A kind of image fuzzy detection method and device | |
| CN110120039B (en) | Screen detection method, screen detection device, electronic equipment and readable storage medium | |
| CN106528758B (en) | Picture selection method and device | |
| CN110634173A (en) | Picture mark information adding method and device, electronic equipment and readable medium | |
| WO2020082731A1 (en) | Electronic device, credential recognition method and storage medium | |
| CN110545427A (en) | PDF document compression method and device and electronic equipment | |
| CN110399802B (en) | Method, apparatus, medium, and electronic device for processing eye brightness of face image | |
| CN110390919B (en) | Display device and color processing method and device | |
| CN109447911B (en) | Image restoration method, device, storage medium and terminal equipment | |
| CN110807300A (en) | Image processing method and device, electronic equipment and medium | |
| CN113132803B (en) | Video watching time length prediction method, device, storage medium and terminal | |
| WO2022062641A1 (en) | Calling interface display method and apparatus, electronic device, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |