CN105913433A - Information pushing method and information pushing device - Google Patents
Information pushing method and information pushing device Download PDFInfo
- Publication number
- CN105913433A CN105913433A CN201610225716.0A CN201610225716A CN105913433A CN 105913433 A CN105913433 A CN 105913433A CN 201610225716 A CN201610225716 A CN 201610225716A CN 105913433 A CN105913433 A CN 105913433A
- Authority
- CN
- China
- Prior art keywords
- image
- estimate
- target
- evaluation
- picture appraisal
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an information pushing method and an information pushing device. The information pushing method comprises the steps of acquiring an objective characteristic of a to-be-processed image; determining the objective image evaluation value of the to-be-processed image according to the objective characteristic; and making an objective terminal display the objective image evaluation value. The information pushing method and the information pushing device make a user more clearly and more accurately understand image quality and photographing effect of the to-be-processed image, namely one piece of photographic works. For a photographer in photographing, the information pushing method and the information pushing device perform functions of conveniently and accurately mastering photographing level himself, and improving user experience.
Description
Technical field
It relates to technical field of image processing, particularly relate to information-pushing method and device.
Background technology
Currently for shutterbugs, desire to know the picture quality of the works oneself shot, in order to right
The camera work of oneself makes one score, but it is very inconvenient for obtaining a more authoritative evaluation.
Summary of the invention
Disclosure embodiment provides information-pushing method and device.Described technical scheme is as follows:
First aspect according to disclosure embodiment, it is provided that a kind of information-pushing method, including:
Obtain the target characteristic of pending image；
The target image evaluation of estimate of described pending image is determined according to described target characteristic；
Control target terminal and show described target image evaluation of estimate.
Optionally, the described target image evaluation of estimate determining described pending image according to described target characteristic,
Including: according to picture appraisal model and described target characteristic, obtain the target image of described pending image
Evaluation of estimate, described picture appraisal model indicates described target characteristic corresponding with described target image evaluation of estimate
Relation.
Optionally, according to picture appraisal model and described target characteristic, described pending image is obtained
Before target image evaluation of estimate, described method also includes:
Obtain sample image；
Obtain the sample characteristics of described sample image；
Obtain the predetermined image evaluation of estimate of described sample image；
Carry out model training according to described predetermined image evaluation of estimate and described sample characteristics, obtain described image
Evaluation model.
Optionally, described carry out model training according to described predetermined image evaluation of estimate and described sample characteristics,
Including:
Convolutional neural networks model training is carried out according to described predetermined image evaluation of estimate and described sample characteristics.
Optionally, described method also includes:
Obtain the image collection being labeled as the scheduled time；
Obtain the picture appraisal value set of all pending images in described image collection；
Overall merit value information is obtained according to described picture appraisal value set；
Control described target terminal and show described overall merit value information.
Optionally, described overall merit value information include following at least one:
The meansigma methods of all target image evaluations of estimate in described picture appraisal value set；
Maximum in described picture appraisal value set；
The chart of all target image evaluations of estimate in described picture appraisal value set.
Optionally, described target characteristic includes at least one feature following: characteristics of image and described image
Shooting feature；
Described characteristics of image includes at least one feature following: color characteristic, textural characteristics, shape facility,
Spatial relationship feature；
Described shooting feature includes at least one feature following: aperture during described shooting, shutter, Bai Ping
Weighing apparatus, light sensitivitys, focal length, shooting time, shooting condition, camera brand, model, color coding, bat
Sound, spot for photography and the thumbnail recorded when taking the photograph.
Second aspect according to disclosure embodiment, it is provided that a kind of information push-delivery apparatus, including:
First acquisition module, for obtaining the target characteristic of pending image；
Determine module, determine described pending image for the target characteristic obtained according to described acquisition module
Target image evaluation of estimate；
For controlling target terminal, first control module, shows that the described target image determining that module determines is commented
It is worth.
Optionally, described determine module, for according to picture appraisal model and described target characteristic, obtain
The target image evaluation of estimate of described pending image, described picture appraisal model indicate described target characteristic with
The corresponding relation of described target image evaluation of estimate.
Optionally, described device also includes:
Second acquisition module, for described determine module according to picture appraisal model and described target characteristic,
Before obtaining the target image evaluation of estimate of described pending image, obtain sample image；
3rd acquisition module, obtains the sample characteristics of the sample image that described second acquisition module obtains；
4th acquisition module, obtains the predetermined image evaluation of the sample image that described second acquisition module obtains
Value；
Training module, for the predetermined image evaluation of estimate obtained according to described 4th acquisition module and described the
The sample characteristics that three acquisition modules obtain carries out model training, obtains described picture appraisal model.
Optionally, described training module, for according to described predetermined image evaluation of estimate and described sample characteristics
Carry out convolutional neural networks model training.
Optionally, described device also includes:
5th acquisition module, for obtaining the image collection being labeled as the scheduled time；
6th acquisition module, is needed to be located for obtaining in the image collection that described 5th acquisition module obtains
The picture appraisal value set of reason image；
7th acquisition module, obtains for the picture appraisal value set obtained according to described 6th acquisition module
Overall merit value information；
Second control module, shows combining of described 7th acquisition module acquisition for controlling described target terminal
Close evaluation of estimate information.
Optionally, described 7th acquisition module obtain overall merit value information include following at least one:
The meansigma methods of all target image evaluations of estimate in described picture appraisal value set；
Maximum in described picture appraisal value set；
The chart of all target image evaluations of estimate in described picture appraisal value set.
Optionally, the target characteristic that described first acquisition module obtains includes at least one feature following: figure
As feature and the shooting feature of described image；
Described characteristics of image includes at least one feature following: color characteristic, textural characteristics, shape facility,
Spatial relationship feature；
Described shooting feature includes at least one feature following: aperture during described shooting, shutter, Bai Ping
Weighing apparatus, light sensitivitys, focal length, shooting time, shooting condition, camera brand, model, color coding, bat
Sound, spot for photography and the thumbnail recorded when taking the photograph.
The third aspect according to disclosure embodiment, it is provided that a kind of information push-delivery apparatus, including:
Processor；
For storing the memorizer of processor executable；
Wherein, described processor is configured to:
Obtain the target characteristic of pending image；
The target image evaluation of estimate of described pending image is determined according to described target characteristic；
Control target terminal and show described target image evaluation of estimate.
Embodiment of the disclosure that the technical scheme of offer can include following beneficial effect:
In the present embodiment, by the target characteristic according to pending image, pending image is evaluated,
Thus displaying for a user the picture appraisal value of these images so that pending image can i.e. be photographed by user
The picture quality of works and shooting effect have more clearly and accurately to be understood, for shooting the photography of image
Person, can understand the camera work of oneself easily and accurately, improves the Experience Degree of user.
In another embodiment, by the evaluation model learnt in advance, pending image is evaluated,
Obtain the evaluation of estimate of pending image so that the evaluation to pending image is more accurate and quicker
Convenient, user the pending image i.e. picture quality of photographic work and shooting effect can be had clearer,
Understand exactly, for shooting the cameraman of image, can easily and accurately understand the camera work of oneself,
Improve the Experience Degree of user.
In another embodiment, by the sample spy to the substantial amounts of photographic work sample with evaluation of estimate
Property be trained study, the corresponding relation between the sample characteristics of image and evaluation of estimate can be obtained, to obtain final product
To picture appraisal model.So, when after the target characteristic of image pending to picture appraisal mode input,
I.e. can get the target image evaluation of estimate of pending image.
In another embodiment, due to convolutional network model be inherently a kind of be input to output reflect
Penetrating, it can learn the mapping relations between substantial amounts of input and output, without any input and defeated
Accurate mathematic(al) representation between going out, as long as by known pattern to convolutional network model training,
Network model just has the mapping ability between input and output.
In another embodiment, user can according to overall merit value information treat process image i.e. photograph
The picture quality of works and shooting effect have more clearly and accurately to be understood, for shooting the photography of image
Person, can understand the camera work of oneself easily and accurately, improves the Experience Degree of user.
In another embodiment, user can treat process image i.e. according to multiple overall merit value information
The picture quality of photographic work and shooting effect have more clearly and accurately to be understood, for shooting image
Cameraman, can understand the camera work of oneself easily and accurately, improves the Experience Degree of user.
It should be appreciated that it is only exemplary and explanatory that above general description and details hereinafter describe
, the disclosure can not be limited.
Accompanying drawing explanation
Accompanying drawing herein is merged in description and constitutes the part of this specification, it is shown that meet these public affairs
The embodiment opened, and for explaining the principle of the disclosure together with description.
Fig. 1 is the flow chart according to a kind of information-pushing method shown in an exemplary embodiment.
Fig. 2 is the flow chart according to a kind of information-pushing method shown in another exemplary embodiment.
Fig. 3 is the flow chart according to a kind of information-pushing method shown in another exemplary embodiment.
Fig. 4 is the block diagram according to a kind of information push-delivery apparatus shown in an exemplary embodiment.
Fig. 5 is the block diagram according to a kind of information push-delivery apparatus shown in another exemplary embodiment.
Fig. 6 is the block diagram according to a kind of information push-delivery apparatus shown in another exemplary embodiment.
Fig. 7 is the block diagram according to the device for information pushing shown in an exemplary embodiment.
Fig. 8 is the block diagram according to the device for information pushing shown in an exemplary embodiment.
Detailed description of the invention
Here will illustrate exemplary embodiment in detail, its example represents in the accompanying drawings.Following retouches
Stating when relating to accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represents same or analogous and wants
Element.Embodiment described in following exemplary embodiment does not represent own consistent with the disclosure
Embodiment.On the contrary, they only with as appended claims describes in detail, the disclosure some
The example of the apparatus and method that aspect is consistent.
The technical scheme that disclosure embodiment provides, relates to terminal or server, the spy to pending image
Dot image feature is extracted, according to the evaluation of estimate of this pending image of the feature analysis extracted, thus
Control target terminal and show this evaluation of estimate so that user can know that the picture quality of this pending image is commented
It is worth.This terminal can be mobile phone, computer, digital broadcast terminal, messaging devices, trip
Play control station, tablet device, armarium, body-building equipment, personal digital assistant etc. is arbitrary has image
Process the equipment of function.
Fig. 1 is the flow chart according to a kind of information-pushing method shown in an exemplary embodiment, such as Fig. 1 institute
Showing, information-pushing method, in terminal or server, comprises the following steps:
In step s 11, the target characteristic of pending image is obtained.
Wherein, can be by obtaining exchangeable image file (the Exchangeable Image of pending image
File, is called for short exif) extract the target characteristic of pending image, exif contains exclusively for digital phase
The photo of machine and the metadata that customizes.Target characteristic can include at least one feature following: characteristics of image
And the shooting feature of image.
Characteristics of image includes at least one feature following: color characteristic, textural characteristics, shape facility, sky
Between relationship characteristic.
Shooting feature includes at least one feature following: aperture during shooting, shutter, white balance, photosensitive
Record when degree, focal length, shooting time, shooting condition, camera brand, model, color coding, shooting
Sound, spot for photography and thumbnail.
In step s 12, the target image evaluation of estimate of pending image is determined according to target characteristic.
In step s 13, target terminal target image evaluation of estimate is controlled.Wherein, target terminal can
Think the terminal performing information-pushing method, it is also possible to be other terminal.
In the present embodiment, by the target characteristic according to pending image, pending image is evaluated,
Thus displaying for a user the picture appraisal value of these images so that pending image can i.e. be photographed by user
The picture quality of works and shooting effect have more clearly and accurately to be understood, for shooting the photography of image
Person, can understand the camera work of oneself easily and accurately, improves the Experience Degree of user.
In another embodiment, the target image evaluation of estimate of pending image can be by the figure learnt in advance
As evaluation model calculates.The above-mentioned target image evaluation of estimate determining pending image according to target characteristic,
Including:
According to picture appraisal model and target characteristic, obtain the target image evaluation of estimate of pending image, figure
Corresponding relation as evaluation model instruction target characteristic with target image evaluation of estimate.
Wherein, picture appraisal model can be neural network model, and neural network model includes: convolution net
Network model, multilayer feedforward (BP) network model, perceptron (Perceptron) model, Hopfield net
Network model, Bpltzmann machine model, bi-directional associative memory network model, adaptive resonance network model,
To passing network model etc..Use neural network model, using the target characteristic of pending image as image
The input data of evaluation model, due to picture appraisal model instruction target characteristic and target image evaluation of estimate
Corresponding relation, therefore, can calculate, according to the target characteristic of input, the target figure that this pending image is corresponding
As evaluation of estimate.
In the present embodiment, by the evaluation model learnt in advance, pending image is evaluated, it is thus achieved that treat
Process the evaluation of estimate of image so that the evaluation to pending image is more accurate and more quick and convenient,
It is clearer, accurate that the pending image i.e. picture quality of photographic work and shooting effect can be had by user
Ground is understood, and for shooting the cameraman of image, can easily and accurately understand the camera work of oneself, carry
The Experience Degree of high user.
In another embodiment, according to picture appraisal model and target characteristic, pending image is obtained
Target image evaluation of estimate before, picture appraisal model can use following methods to obtain, and Fig. 2 is basis
The flow chart of a kind of information-pushing method shown in another exemplary embodiment, as in figure 2 it is shown, the method
Further comprising the steps of:
In the step s 21, sample image is obtained.Sample image can obtain from the competition works of photographic match
, can according to the prize-winning equivalence of competition works as the foundation of the predetermined image evaluation of estimate of sample image, or
Person, it is also possible to photography professional person please be given a mark by photographic work, thus obtain sample image
Set.
In step S22, obtain the sample characteristics of sample image.Wherein, the type of sample characteristics is with upper
The type stating target characteristic is identical.
In step S23, obtain the predetermined image evaluation of estimate of sample image.
In step s 24, carry out model training according to predetermined image evaluation of estimate and sample characteristics, obtain figure
As evaluation model.
Wherein, model training can use corresponding Learning Algorithm according to the version selected.
Such as, convolutional network model correspondence convolutional neural networks algorithm, multilayer feedforward (Back Propagation,
It is called for short BP) network model's correspondence BP algorithm, perceptron (Perceptron) neural network model is corresponding
Perceptron neural network algorithm, Hopfield network model correspondence Hopfield algorithm, etc..
In the present embodiment, by the substantial amounts of sample properties with the photographic work sample of evaluation of estimate is carried out
Training study, can obtain the corresponding relation between the sample characteristics of image and evaluation of estimate, i.e. obtain image
Evaluation model.So, when after the target characteristic of image pending to picture appraisal mode input,
Target image evaluation of estimate to pending image.
In another embodiment, carry out model training according to predetermined image evaluation of estimate and sample characteristics, bag
Include: carry out convolutional neural networks model training according to predetermined image evaluation of estimate and sample characteristics.
Wherein, convolutional neural networks model training can use guidance learning network, for there being guidance
Pattern recognition, owing to the classification of arbitrary sample is known, the sample distribution in space is no longer based on it
NATURAL DISTRIBUTION tendency divides, and between being intended to according to similar sample distribution and inhomogeneity sample in space
Separation degree look for a kind of suitable space-division method, or find a classification boundaries so that different
Class sample lays respectively in different regions.This is accomplished by a long-time and complicated learning process, no
The position of the disconnected classification boundaries adjusted in order to divide sample space, makes the fewest sample be divided into non-
In homogeneous region.
Owing to convolutional network model is inherently a kind of mapping being input to output, it can learn in a large number
Input with output between mapping relations, without any input and output between accurate mathematics
Expression formula, as long as just having input by known pattern to convolutional network model training, network model
Mapping ability between output.
In another embodiment, after obtaining the evaluation of estimate of every photographic work of certain user, permissible
According to the evaluation of estimate of every pending image, all photographic works of this user are carried out overall merit.Figure
3 is the flow chart according to a kind of information-pushing method shown in another exemplary embodiment, as it is shown on figure 3,
The method also includes:
In step S31, obtain the image collection being labeled as the scheduled time；
In step s 32, the picture appraisal value set of all pending images in image collection is obtained；
In step S33, obtain overall merit value information according to picture appraisal value set；
In step S34, control target terminal display overall merit value information.
For example, it is possible to obtain the image artifacts that a certain user shoots in nearest month, according to these images
The picture appraisal value of works combines, and the image artifacts shooting this user carries out overall merit, and will be comprehensive
The result evaluated shows this user.
In the present embodiment, user can treat process image i.e. photographic work according to overall merit value information
Picture quality and shooting effect have and more clearly and accurately understand, for shooting the cameraman of image,
Can easily and accurately understand the camera work of oneself, improve the Experience Degree of user.
In the above-described embodiments, overall merit value information can include following at least one:
The meansigma methods of all target image evaluations of estimate in picture appraisal value set；
Maximum in picture appraisal value set；
The chart of all target image evaluations of estimate in picture appraisal value set.
Such as, in nearest to this user one month, the picture appraisal value of all image artifacts of shooting is averaging
Value is as overall merit value information；Or, all figures that this user shoots in nearest month can be obtained
In picture works, the maximum of picture appraisal value is as overall merit value information；Or, can make according to image
The picture appraisal value of the shooting time of product and every image artifacts generates this user shooting figure in nearest month
As the chart of works, i.e. draw out the growth curve of user's camera work.So, user can be according to this
The works shooting effect of nearest one month is become apparent from, gets more information about by overall merit value information.
In the present embodiment, user can treat process image according to multiple overall merit value information and i.e. photograph work
The picture quality of product and shooting effect have more clearly and accurately to be understood, for shooting the cameraman of image,
Can easily and accurately understand the camera work of oneself, improve the Experience Degree of user.
Following for disclosure device embodiment, may be used for performing method of disclosure embodiment.
Fig. 4 is the block diagram according to a kind of information push-delivery apparatus shown in an exemplary embodiment, and this device can
With by software, hardware or both be implemented in combination with become the some or all of of electronic equipment.Such as figure
Shown in 4, this information push-delivery apparatus includes:
First acquisition module 41, is configured to obtain the target characteristic of pending image.Wherein, can pass through
The exchangeable image file (Exchangeable Image File is called for short exif) obtaining pending image comes
Extract the target characteristic of pending image, exif contains and customizes exclusively for the photo of digital camera
Metadata.Target characteristic can include at least one feature following: the shooting feature of characteristics of image and image.
Characteristics of image includes at least one feature following: color characteristic, textural characteristics, shape facility, sky
Between relationship characteristic.Shooting feature includes at least one feature following: aperture during shooting, shutter, Bai Ping
Weighing apparatus, light sensitivitys, focal length, shooting time, shooting condition, camera brand, model, color coding, bat
Sound, spot for photography and the thumbnail recorded when taking the photograph.
Determine module 42, be configured to the target characteristic according to acquisition module 41 obtains and determine pending figure
The target image evaluation of estimate of picture；
First control module 43, is configured to control target terminal and shows the target determining that module 42 determines
Picture appraisal value.
In the present embodiment, determine that pending image is commented by module according to the target characteristic of pending image
Valency, the first control module displays for a user the picture appraisal value of these images so that user can treat place
The reason image i.e. picture quality of photographic work and shooting effect have more clearly and accurately to be understood, for clapping
Take the photograph the cameraman of image, can easily and accurately understand the camera work of oneself, improve the Experience Degree of user.
In another embodiment, the target image evaluation of estimate of pending image can be by the figure learnt in advance
As evaluation model calculates.Determine module 42, be configured to according to picture appraisal model and target characteristic,
Obtain the target image evaluation of estimate of pending image, picture appraisal model instruction target characteristic and target image
The corresponding relation of evaluation of estimate.
Wherein, picture appraisal model can be neural network model, and neural network model includes: convolution net
Network model, multilayer feedforward (BP) network model, perceptron (Perceptron) model, Hopfield net
Network model, Bpltzmann machine model, bi-directional associative memory network model, adaptive resonance network model,
To passing network model etc..Use neural network model, using the target characteristic of pending image as image
The input data of evaluation model, due to picture appraisal model instruction target characteristic and target image evaluation of estimate
Corresponding relation, therefore, can calculate, according to the target characteristic of input, the target figure that this pending image is corresponding
As evaluation of estimate.
In the present embodiment, determine that pending image is evaluated by the evaluation model that module is passed through to learn in advance,
Obtain the evaluation of estimate of pending image so that the evaluation to pending image is more accurate and quicker
Convenient, user the pending image i.e. picture quality of photographic work and shooting effect can be had clearer,
Understand exactly, for shooting the cameraman of image, can easily and accurately understand the camera work of oneself,
Improve the Experience Degree of user.
Fig. 5 is the block diagram according to a kind of information push-delivery apparatus shown in another exemplary embodiment, such as Fig. 5
Shown in, in another embodiment, this device also includes:
Second acquisition module 51, is configured to determining that module 42 is special according to picture appraisal model and target
Levy, before obtaining the target image evaluation of estimate of pending image, obtain sample image.Sample image can be from
The competition works of photographic match obtain, can be according to pre-as sample image of prize-winning equivalence of competition works
Determine the foundation of picture appraisal value, or, it is also possible to please photography professional person carry out photographic work beating
Point, thus obtain the set of sample image.
3rd acquisition module 52, obtains the sample characteristics of the sample image that the second acquisition module 51 obtains.
Wherein, the type of sample characteristics is identical with the type of above-mentioned target characteristic.
4th acquisition module 53, the predetermined image obtaining the sample image that the second acquisition module 51 obtains is commented
It is worth；
Training module 54, be configured to according to the 4th acquisition module 53 obtain predetermined image evaluation of estimate and
The sample characteristics that 3rd acquisition module 52 obtains carries out model training, obtains picture appraisal model.
Wherein, model training can use corresponding Learning Algorithm according to the version selected.
Such as, convolutional network model correspondence convolutional neural networks algorithm, multilayer feedforward (Back Propagation,
It is called for short BP) network model's correspondence BP algorithm, perceptron (Perceptron) neural network model is corresponding
Perceptron neural network algorithm, Hopfield network model correspondence Hopfield algorithm, etc..
In the present embodiment, the training module sample properties to the substantial amounts of photographic work sample with evaluation of estimate
It is trained study, the corresponding relation between the sample characteristics of image and evaluation of estimate can be obtained, i.e. obtain
Picture appraisal model.So, when after the target characteristic of image pending to picture appraisal mode input, i.e.
The target image evaluation of estimate of available pending image.
In another embodiment, training module 54, it is configured to according to predetermined image evaluation of estimate and sample
Feature carries out convolutional neural networks model training.
Wherein, convolutional neural networks model training can use guidance learning network, for there being guidance
Pattern recognition, owing to the classification of arbitrary sample is known, the sample distribution in space is no longer based on it
NATURAL DISTRIBUTION tendency divides, and between being intended to according to similar sample distribution and inhomogeneity sample in space
Separation degree look for a kind of suitable space-division method, or find a classification boundaries so that different
Class sample lays respectively in different regions.This is accomplished by a long-time and complicated learning process, no
The position of the disconnected classification boundaries adjusted in order to divide sample space, makes the fewest sample be divided into non-
In homogeneous region.
Owing to convolutional network model is inherently a kind of mapping being input to output, it can learn in a large number
Input with output between mapping relations, without any input and output between accurate mathematics
Expression formula, as long as just having input by known pattern to convolutional network model training, network model
Mapping ability between output.
In another embodiment, after obtaining the evaluation of estimate of every photographic work of certain user, permissible
According to the evaluation of estimate of every pending image, all photographic works of this user are carried out overall merit.Figure
6 is the block diagram according to a kind of information push-delivery apparatus shown in another exemplary embodiment, as shown in Figure 6,
This device also includes:
5th acquisition module 61, is configured to obtain the image collection being labeled as the scheduled time；
6th acquisition module 62, is configured to obtain institute in the image collection that the 5th acquisition module 61 obtains
There is the picture appraisal value set of pending image；
7th acquisition module 63, is configured to the picture appraisal value collection obtained according to the 6th acquisition module 62
Close and obtain overall merit value information；
Second control module 64, is configured to control target terminal and shows what the 7th acquisition module 63 obtained
Overall merit value information.
Such as, the 5th acquisition module 61 can obtain the image work that a certain user shoots in nearest month
Product, this user, according to the picture appraisal value set of these image artifacts, is shot by the 7th acquisition module 63
Image artifacts carries out overall merit, and the result of overall merit is showed this user by the second control module 64.
In the present embodiment, user can treat process image i.e. photographic work according to overall merit value information
Picture quality and shooting effect have and more clearly and accurately understand, for shooting the cameraman of image,
Can easily and accurately understand the camera work of oneself, improve the Experience Degree of user.
In the above-described embodiments, the 7th acquisition module 63 obtain overall merit value information include following at least
One:
The meansigma methods of all target image evaluations of estimate in picture appraisal value set；
Maximum in picture appraisal value set；
The chart of all target image evaluations of estimate in picture appraisal value set.
Such as, in nearest to this user one month, the picture appraisal value of all image artifacts of shooting is averaging
Value is as overall merit value information；Or, all figures that this user shoots in nearest month can be obtained
In picture works, the maximum of picture appraisal value is as overall merit value information；Or, can make according to image
The picture appraisal value of the shooting time of product and every image artifacts generates this user shooting figure in nearest month
As the chart of works, i.e. draw out the growth curve of user's camera work.So, user can be according to this
The works shooting effect of nearest one month is become apparent from, gets more information about by overall merit value information.
In the present embodiment, user can treat according to overall merit value information and process the i.e. photographic work of image
Picture quality and shooting effect have more clearly and accurately to be understood, for shooting the cameraman of image, and can
Easily and accurately to understand the camera work of oneself, improve the Experience Degree of user.
The disclosure also provides for a kind of information push-delivery apparatus, including:
Processor；
For storing the memorizer of processor executable；
Wherein, processor is configured to:
Obtain the target characteristic of pending image；
The target image evaluation of estimate of described pending image is determined according to described target characteristic；
Control target terminal and show described target image evaluation of estimate.
Fig. 7 is according to a kind of block diagram for information push-delivery apparatus shown in an exemplary embodiment, this dress
Put and be applicable to terminal unit.Such as, device 1700 can be video camera, sound pick-up outfit, mobile phone,
Computer, digital broadcast terminal, messaging devices, game console, tablet device, armarium,
Body-building equipment, personal digital assistant etc..
Device 1700 can include following one or more assembly: processes assembly 1702, memorizer 1704,
Power supply module 1706, multimedia groupware 1708, audio-frequency assembly 1710, input/output (I/O) connects
Mouth 1712, sensor cluster 1714, and communications component 1716.
Process assembly 1702 and generally control the integrated operation of device 1700, such as with display, call,
The operation that data communication, camera operation and record operation are associated.Process assembly 1702 and can include one
Or multiple processor 1720 performs instruction, to complete all or part of step of above-mentioned method.Additionally,
Process assembly 1702 and can include one or more module, it is simple to process assembly 1702 and other assemblies it
Between mutual.Such as, process assembly 1702 and can include multi-media module, to facilitate multimedia groupware
1708 and process between assembly 1702 mutual.
Memorizer 1704 is configured to store various types of data to support the operation at equipment 1700.
The example of these data includes any application program for operation on device 1700 or the instruction of method,
Contact data, telephone book data, message, picture, video etc..Memorizer 1704 can be by any class
The volatibility of type or non-volatile memory device or combinations thereof realize, such as static random access memory
Device (SRAM), Electrically Erasable Read Only Memory (EEPROM), erasable programmable is read-only
Memorizer (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic
Memorizer, flash memory, disk or CD.
The various assemblies that power supply module 1706 is device 1700 provide electric power.Power supply module 1706 can wrap
Include power-supply management system, one or more power supplys, and other generate with for device 1700, manage and distribute
The assembly that electric power is associated.
One output interface of offer that multimedia groupware 1708 is included between described device 1700 and user
Screen.In certain embodiments, screen can include liquid crystal display (LCD) and touch panel (TP).
If screen includes that touch panel, screen may be implemented as touch screen, to receive the input from user
Signal.Touch panel includes that one or more touch sensor touches with sensing, slides and on touch panel
Gesture.Described touch sensor can not only sense touch or the border of sliding action, but also detects
The persistent period relevant to described touch or slide and pressure.In certain embodiments, multimedia group
Part 1708 includes a front-facing camera and/or post-positioned pick-up head.When equipment 1700 is in operator scheme,
During such as screening-mode or video mode, front-facing camera and/or post-positioned pick-up head can receive many matchmakers of outside
Volume data.Each front-facing camera and post-positioned pick-up head can be a fixing optical lens system or tool
There are focal length and optical zoom ability.
Audio-frequency assembly 1710 is configured to output and/or input audio signal.Such as, audio-frequency assembly 1710
Including a mike (MIC), when device 1700 is in operator scheme, such as call model, record mould
When formula and speech recognition mode, mike is configured to receive external audio signal.The audio frequency letter received
Number can be further stored at memorizer 1704 or send via communications component 1716.Implement at some
In example, audio-frequency assembly 1710 also includes a speaker, is used for exporting audio signal.
I/O interface 1712 is to process to provide interface between assembly 1702 and peripheral interface module, above-mentioned outside
Enclosing interface module can be keyboard, puts striking wheel, button etc..These buttons may include but be not limited to: homepage
Button, volume button, start button and locking press button.
Sensor cluster 1714 includes one or more sensor, for providing each side for device 1700
The state estimation in face.Such as, what sensor cluster 1714 can detect equipment 1700 beats opening/closing shape
State, the relative localization of assembly, the most described assembly is display and the keypad of device 1700, sensor
Assembly 1714 can also detect device 1700 or the position change of 1,700 1 assemblies of device, user and dress
Put the presence or absence of 1700 contacts, device 1700 orientation or acceleration/deceleration and the temperature of device 1700
Degree change.Sensor cluster 1714 can include proximity transducer, is configured to do not having any thing
The existence of object near detection during reason contact.Sensor cluster 1714 can also include optical sensor, as
CMOS or ccd image sensor, for using in imaging applications.In certain embodiments, should
Sensor cluster 1714 can also include acceleration transducer, gyro sensor, Magnetic Sensor, pressure
Sensor or temperature sensor.
Communications component 1716 is configured to facilitate wired or wireless mode between device 1700 and other equipment
Communication.Device 1700 can access wireless network based on communication standard, such as WiFi, 2G or 3G,
Or combinations thereof.In one exemplary embodiment, communications component 1716 receives via broadcast channel
From broadcast singal or the broadcast related information of external broadcasting management system.In one exemplary embodiment,
Described communications component 1716 also includes near-field communication (NFC) module, to promote junction service.Such as,
Can be based on RF identification (RFID) technology in NFC module, Infrared Data Association (IrDA) technology,
Ultra broadband (UWB) technology, bluetooth (BT) technology and other technologies realize.
In the exemplary embodiment, device 1700 can be by one or more application specific integrated circuits
(ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), able to programme patrol
Collect device (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor
Or other electronic components realize, it is used for performing said method.
In the exemplary embodiment, a kind of non-transitory computer-readable storage including instruction is additionally provided
Medium, such as, include the memorizer 1704 of instruction, and above-mentioned instruction can be by the processor 1720 of device 1700
Perform to complete said method.Such as, described non-transitory computer-readable recording medium can be ROM,
Random access memory (RAM), CD-ROM, tape, floppy disk and optical data storage devices etc..
Fig. 8 is the block diagram according to a kind of device for information pushing shown in an exemplary embodiment.Example
As, device 1900 may be provided in a server.Device 1900 includes processing assembly 1922, and it enters
One step includes one or more processor, and by the memory resource representated by memorizer 1932, is used for
Storage can be by the instruction of the execution processing assembly 1922, such as application program.Memorizer 1932 stores
Application program can include one or more each corresponding to one group instruction module.Additionally,
Process assembly 1922 to be configured to perform instruction, to perform said method.
Device 1900 can also include that a power supply module 1926 is configured to perform the power supply of device 1900
Management, a wired or wireless network interface 1950 is configured to device 1900 is connected to network, and
One input and output (I/O) interface 1958.Device 1900 can operate based on being stored in memorizer 1932
Operating system, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM,
FreeBSDTM or similar.
A kind of non-transitory computer-readable recording medium, when the instruction in described storage medium is by device
1700 or device 1900 processor perform time so that device 1700 or device 1900 are able to carry out
The method stating information pushing, described method includes:
Obtain the target characteristic of pending image；
The target image evaluation of estimate of described pending image is determined according to described target characteristic；
Control target terminal and show described target image evaluation of estimate.
Optionally, the described target image evaluation of estimate determining described pending image according to described target characteristic,
Including: according to picture appraisal model and described target characteristic, obtain the target image of described pending image
Evaluation of estimate, described picture appraisal model indicates described target characteristic corresponding with described target image evaluation of estimate
Relation.
Optionally, according to picture appraisal model and described target characteristic, described pending image is obtained
Before target image evaluation of estimate, described method also includes:
Obtain sample image；
Obtain the sample characteristics of described sample image；
Obtain the predetermined image evaluation of estimate of described sample image；
Carry out model training according to described predetermined image evaluation of estimate and described sample characteristics, obtain described image
Evaluation model.
Optionally, described carry out model training according to described predetermined image evaluation of estimate and described sample characteristics,
Including:
Convolutional neural networks model training is carried out according to described predetermined image evaluation of estimate and described sample characteristics.
Optionally, described method also includes:
Obtain the image collection being labeled as the scheduled time；
Obtain the picture appraisal value set of all pending images in described image collection；
Overall merit value information is obtained according to described picture appraisal value set；
Control described target terminal and show described overall merit value information.
Optionally, described overall merit value information include following at least one:
The meansigma methods of all target image evaluations of estimate in described picture appraisal value set；
Maximum in described picture appraisal value set；
The chart of all target image evaluations of estimate in described picture appraisal value set.
Optionally, described target characteristic includes at least one feature following: characteristics of image and described image
Shooting feature；
Described characteristics of image includes at least one feature following: color characteristic, textural characteristics, shape facility,
Spatial relationship feature；
Described shooting feature includes at least one feature following: aperture during described shooting, shutter, Bai Ping
Weighing apparatus, light sensitivitys, focal length, shooting time, shooting condition, camera brand, model, color coding, bat
Sound, spot for photography and the thumbnail recorded when taking the photograph.
Those skilled in the art, after considering description and putting into practice disclosure disclosed herein, will readily occur to this
Other embodiment disclosed.The application is intended to any modification, purposes or the adaptability of the disclosure
Change, these modification, purposes or adaptations are followed the general principle of the disclosure and include these public affairs
Open undocumented common knowledge in the art or conventional techniques means.Description and embodiments only by
Being considered as exemplary, the true scope of the disclosure and spirit are pointed out by claim below.
It should be appreciated that the disclosure be not limited to described above and illustrated in the accompanying drawings accurately
Structure, and various modifications and changes can carried out without departing from the scope.The scope of the present disclosure is only by institute
Attached claim limits.
Claims (15)
1. an information-pushing method, it is characterised in that including:
Obtain the target characteristic of pending image；
The target image evaluation of estimate of described pending image is determined according to described target characteristic；
Control target terminal and show described target image evaluation of estimate.
Method the most according to claim 1, it is characterised in that described true according to described target characteristic
The target image evaluation of estimate of fixed described pending image, including: according to picture appraisal model and described target
Feature, obtains the target image evaluation of estimate of described pending image, and the instruction of described picture appraisal model is described
Target characteristic and the corresponding relation of described target image evaluation of estimate.
Method the most according to claim 2, it is characterised in that according to picture appraisal model and institute
Stating target characteristic, before obtaining the target image evaluation of estimate of described pending image, described method also includes:
Obtain sample image；
Obtain the sample characteristics of described sample image；
Obtain the predetermined image evaluation of estimate of described sample image；
Carry out model training according to described predetermined image evaluation of estimate and described sample characteristics, obtain described image
Evaluation model.
Method the most according to claim 3, it is characterised in that described comment according to described predetermined image
It is worth and described sample characteristics carries out model training, including:
Convolutional neural networks model training is carried out according to described predetermined image evaluation of estimate and described sample characteristics.
Method the most according to claim 1, it is characterised in that described method also includes:
Obtain the image collection being labeled as the scheduled time；
Obtain the picture appraisal value set of all pending images in described image collection；
Overall merit value information is obtained according to described picture appraisal value set；
Control described target terminal and show described overall merit value information.
Method the most according to claim 5, it is characterised in that described overall merit value information includes
Below at least one:
The meansigma methods of all target image evaluations of estimate in described picture appraisal value set；
Maximum in described picture appraisal value set；
The chart of all target image evaluations of estimate in described picture appraisal value set.
Method the most according to claim 1, it is characterised in that described target characteristic include with down to
One item missing feature: the shooting feature of characteristics of image and described image；
Described characteristics of image includes at least one feature following: color characteristic, textural characteristics, shape facility,
Spatial relationship feature；
Described shooting feature includes at least one feature following: aperture during described shooting, shutter, Bai Ping
Weighing apparatus, light sensitivitys, focal length, shooting time, shooting condition, camera brand, model, color coding, bat
Sound, spot for photography and the thumbnail recorded when taking the photograph.
8. an information push-delivery apparatus, it is characterised in that including:
First acquisition module, for obtaining the target characteristic of pending image；
Determine module, determine described pending image for the target characteristic obtained according to described acquisition module
Target image evaluation of estimate；
For controlling target terminal, first control module, shows that the described target image determining that module determines is commented
It is worth.
Device the most according to claim 8, it is characterised in that described determine module, for basis
Picture appraisal model and described target characteristic, obtain the target image evaluation of estimate of described pending image, institute
State picture appraisal model and indicate the corresponding relation of described target characteristic and described target image evaluation of estimate.
Device the most according to claim 9, it is characterised in that described device also includes:
Second acquisition module, for described determine module according to picture appraisal model and described target characteristic,
Before obtaining the target image evaluation of estimate of described pending image, obtain sample image；
3rd acquisition module, obtains the sample characteristics of the sample image that described second acquisition module obtains；
4th acquisition module, obtains the predetermined image evaluation of the sample image that described second acquisition module obtains
Value；
Training module, for the predetermined image evaluation of estimate obtained according to described 4th acquisition module and described the
The sample characteristics that three acquisition modules obtain carries out model training, obtains described picture appraisal model.
11. devices according to claim 10, it is characterised in that described training module, for root
Convolutional neural networks model training is carried out according to described predetermined image evaluation of estimate and described sample characteristics.
12. devices according to claim 8, it is characterised in that described device also includes:
5th acquisition module, for obtaining the image collection being labeled as the scheduled time；
6th acquisition module, is needed to be located for obtaining in the image collection that described 5th acquisition module obtains
The picture appraisal value set of reason image；
7th acquisition module, obtains for the picture appraisal value set obtained according to described 6th acquisition module
Overall merit value information；
Second control module, shows combining of described 7th acquisition module acquisition for controlling described target terminal
Close evaluation of estimate information.
13. devices according to claim 12, it is characterised in that described 7th acquisition module obtains
Overall merit value information include following at least one:
The meansigma methods of all target image evaluations of estimate in described picture appraisal value set；
Maximum in described picture appraisal value set；
The chart of all target image evaluations of estimate in described picture appraisal value set.
14. devices according to claim 8, it is characterised in that described first acquisition module obtains
Target characteristic include at least one feature following: the shooting feature of characteristics of image and described image；
Described characteristics of image includes at least one feature following: color characteristic, textural characteristics, shape facility,
Spatial relationship feature；
Described shooting feature includes at least one feature following: aperture during described shooting, shutter, Bai Ping
Weighing apparatus, light sensitivitys, focal length, shooting time, shooting condition, camera brand, model, color coding, bat
Sound, spot for photography and the thumbnail recorded when taking the photograph.
15. 1 kinds of information push-delivery apparatus, it is characterised in that including:
Processor；
For storing the memorizer of processor executable；
Wherein, described processor is configured to:
Obtain the target characteristic of pending image；
The target image evaluation of estimate of described pending image is determined according to described target characteristic；
Control target terminal and show described target image evaluation of estimate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610225716.0A CN105913433A (en) | 2016-04-12 | 2016-04-12 | Information pushing method and information pushing device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610225716.0A CN105913433A (en) | 2016-04-12 | 2016-04-12 | Information pushing method and information pushing device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105913433A true CN105913433A (en) | 2016-08-31 |
Family
ID=56745919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610225716.0A Pending CN105913433A (en) | 2016-04-12 | 2016-04-12 | Information pushing method and information pushing device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105913433A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107978185A (en) * | 2017-12-07 | 2018-05-01 | 何旭连 | A kind of good children learning machine of teaching efficiency |
| CN112418273A (en) * | 2020-11-02 | 2021-02-26 | 深圳大学 | Clothing popularity evaluation method and device, intelligent terminal and storage medium |
| CN115034810A (en) * | 2022-05-18 | 2022-09-09 | 北京羽乐创新科技有限公司 | Data analysis method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101282481A (en) * | 2008-05-09 | 2008-10-08 | 中国传媒大学 | Method for evaluating video quality based on artificial neural net |
| CN101426150A (en) * | 2008-12-08 | 2009-05-06 | 青岛海信电子产业控股股份有限公司 | Video image quality evaluation method and system |
| CN102622741A (en) * | 2011-01-30 | 2012-08-01 | 联想(北京)有限公司 | Method for detecting image file and apparatus thereof |
| US20150243041A1 (en) * | 2013-12-23 | 2015-08-27 | Tufts University | Systems and methods for image and video signal measurement |
| CN105138610A (en) * | 2015-08-07 | 2015-12-09 | 深圳码隆科技有限公司 | Image element based image feature value prediction method and apparatus |
-
2016
- 2016-04-12 CN CN201610225716.0A patent/CN105913433A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101282481A (en) * | 2008-05-09 | 2008-10-08 | 中国传媒大学 | Method for evaluating video quality based on artificial neural net |
| CN101426150A (en) * | 2008-12-08 | 2009-05-06 | 青岛海信电子产业控股股份有限公司 | Video image quality evaluation method and system |
| CN102622741A (en) * | 2011-01-30 | 2012-08-01 | 联想(北京)有限公司 | Method for detecting image file and apparatus thereof |
| US20150243041A1 (en) * | 2013-12-23 | 2015-08-27 | Tufts University | Systems and methods for image and video signal measurement |
| CN105138610A (en) * | 2015-08-07 | 2015-12-09 | 深圳码隆科技有限公司 | Image element based image feature value prediction method and apparatus |
Non-Patent Citations (1)
| Title |
|---|
| 何书前，蒋文娜，吴淑雷: "《现代网络视频编码技术》", 30 November 2009 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107978185A (en) * | 2017-12-07 | 2018-05-01 | 何旭连 | A kind of good children learning machine of teaching efficiency |
| CN107978185B (en) * | 2017-12-07 | 2019-12-03 | 南京白下高新技术产业园区投资发展有限责任公司 | A kind of good children learning machine of teaching efficiency |
| CN112418273A (en) * | 2020-11-02 | 2021-02-26 | 深圳大学 | Clothing popularity evaluation method and device, intelligent terminal and storage medium |
| CN112418273B (en) * | 2020-11-02 | 2024-03-26 | 深圳大学 | Clothing popularity evaluation method and device, intelligent terminal and storage medium |
| CN115034810A (en) * | 2022-05-18 | 2022-09-09 | 北京羽乐创新科技有限公司 | Data analysis method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105809704B (en) | Identify the method and device of image definition | |
| CN106408603A (en) | Camera method and device | |
| CN105069083B (en) | The determination method and device of association user | |
| CN104700353B (en) | Image filters generation method and device | |
| CN105491284B (en) | The display methods and device of preview image | |
| CN110572711B (en) | Video cover generation method and device, computer equipment and storage medium | |
| CN104580886B (en) | Filming control method and device | |
| CN107123081A (en) | image processing method, device and terminal | |
| CN106204435A (en) | Image processing method and device | |
| CN104219445B (en) | Screening-mode method of adjustment and device | |
| CN105704369B (en) | A kind of information processing method and device, electronic equipment | |
| CN106600530B (en) | Picture synthesis method and device | |
| TW202113670A (en) | An image processing method, an electronic device and a storage medium | |
| CN107944447A (en) | Image classification method and device | |
| CN105528078B (en) | The method and device of controlling electronic devices | |
| CN106210496A (en) | Method, photo taking and device | |
| CN104035674B (en) | Picture displaying method and device | |
| CN104460185A (en) | Automatic focusing method and device | |
| CN104867112B (en) | Photo processing method and device | |
| CN108353129A (en) | Capture apparatus and its control method | |
| CN106303198A (en) | Photographing information acquisition methods and device | |
| CN107886410A (en) | The method, apparatus and storage medium of Products Show | |
| CN105208284A (en) | Photographing reminding method and device | |
| CN105203456A (en) | Plant species identification method and apparatus thereof | |
| CN106339705A (en) | Image acquisition method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160831 |