CN107545536A - The image processing method and image processing system of a kind of intelligent terminal - Google Patents
The image processing method and image processing system of a kind of intelligent terminal Download PDFInfo
- Publication number
- CN107545536A CN107545536A CN201710705349.9A CN201710705349A CN107545536A CN 107545536 A CN107545536 A CN 107545536A CN 201710705349 A CN201710705349 A CN 201710705349A CN 107545536 A CN107545536 A CN 107545536A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- image processing
- reference object
- described image
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 64
- 238000003672 processing method Methods 0.000 title claims abstract description 30
- 238000003860 storage Methods 0.000 claims abstract description 17
- 210000000056 organ Anatomy 0.000 claims description 26
- 238000001514 detection method Methods 0.000 claims description 21
- 230000001568 sexual effect Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 5
- 238000012847 principal component analysis method Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 17
- 230000004069 differentiation Effects 0.000 abstract description 4
- 238000000034 method Methods 0.000 description 37
- 230000006870 function Effects 0.000 description 21
- 238000004422 calculation algorithm Methods 0.000 description 10
- 239000011159 matrix material Substances 0.000 description 9
- 230000001815 facial effect Effects 0.000 description 8
- 235000016838 Pomo dAdamo Nutrition 0.000 description 7
- 244000003138 Pomo dAdamo Species 0.000 description 7
- 238000000513 principal component analysis Methods 0.000 description 7
- 210000004709 eyebrow Anatomy 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 239000003086 colorant Substances 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 210000004209 hair Anatomy 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000002087 whitening effect Effects 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 241000406668 Loxodonta cyclotis Species 0.000 description 1
- 241001300078 Vitrea Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000003255 anti-acne Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000035882 stress Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000037303 wrinkles Effects 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention provides a kind of image processing method of intelligent terminal and image processing system, wherein, image processing method comprises the following steps：Open the image processing mode of the intelligent terminal；Obtain an image for including reference object of the intelligent terminal storage；Set the corresponding relation of the characteristic information of the reference object and the image processing mode of described image；Identify and obtain the characteristic information of the reference object；Image procossing is carried out to described image according to described image tupe corresponding with the characteristic information of the reference object；The characteristic information of the reference object includes the one or more in sex, age, the colour of skin, shape of face.Different U.S. face landscaping effects can be applicable by differentiations such as sex, age, the colour of skin, shapes of face, meets variation, personalized demand that user beautifies to image U.S. face.
Description
Technical field
The present invention relates to intelligent terminal field, more particularly to a kind of image processing method of intelligent terminal and image procossing system
System.
Background technology
Due to the convenience of intelligent terminal carrying and greatly improving for intelligent terminal camera pixel, increasing user
It is more likely to be taken pictures by intelligent terminal, to a certain extent, intelligent terminal gradually substitutes camera to turn into current bat
According to main flow instrument.And as the extensive use of intelligent terminal touch screen technology, the U.S. face of camera applications are also got over beautifying functions
Liked to get over by people, U.S. face becomes a kind of standard configuration function in camera applications with beautifying functions, it is seen that U.S. face and U.S.
The demand for changing function is big.
At present, the usual algorithm of the U.S. face beautifying functions of intelligent terminal camera is to carry out face detection of skin regions, identification
Face skin area, face skin area is obscured using Gauss algorithm etc., then carries out bloom, the operation such as highlight.This
The method of the U.S. face beautification of kind is simple and easy, but more single, and Unified Algorithm is used to all users, thus can not meet user
Variation, personalized demand to the face beautification of image U.S..In addition, the mould of taking pictures of the front camera acquiescence of many intelligent terminals
Formula is U.S. face beautification pattern, i.e., in self-timer, U.S. face beautification pattern can carry out automatic U.S. face to the photo taken certainly and beautify,
Mill skin, anti-acne, whitening such as are carried out to skin, it receives the favor of vast female user, but for male user, makes
With U.S. face beautification pattern from the photo taken may U.S. face beautification it is excessive, reduce the manhood of male user.Therefore, if
U.S. face beautification pattern is not turned off in self-timer, male user needs manual-lock beautiful after the photo beautified by U.S. face is taken certainly
Face beautification pattern and self-timer again, afterwards, if female user then self-timer, U.S. face is beautified pattern and is closed, for women
Family take certainly not by do not have U.S. face to beautify photo after need manually opened U.S. face to beautify pattern and again self-timer, i.e., at least oneself
Clap and be only possible to take the photo for meeting that user requires certainly twice.It can be seen that current shooting style is also in the presence of taking pictures, efficiency is low to ask
Topic.
Therefore, the invention provides a kind of image processing method of intelligent terminal and image processing system, can not only lead to
Cross sex and distinguish U.S. face landscaping effect, different U.S. face landscaping effects can be also applicable according to differentiations such as age, the colour of skin, shapes of face, it is full
Variation that sufficient user beautifies to image U.S. face, personalized demand.
The content of the invention
In order to overcome above-mentioned technological deficiency, it is an object of the invention to provide a kind of image processing method of intelligent terminal and
Image processing system.
The invention discloses a kind of image processing method of intelligent terminal, comprise the following steps：
Open the image processing mode of the intelligent terminal；
Obtain an image for including reference object of the intelligent terminal storage；
Set the corresponding relation of the characteristic information of the reference object and the image processing mode of described image；
Identify and obtain the characteristic information of the reference object；
Image is carried out to described image according to described image tupe corresponding with the characteristic information of the reference object
Processing；
The characteristic information of the reference object includes the one or more in sex, age, the colour of skin, shape of face.
Preferably, it is further comprising the steps of：
Establish a model database；
Send a selection request for whether storing described image tupe；
When being fed back to store described image tupe of request is selected when described, described image tupe is stored in
The model database.
Preferably, it is further comprising the steps of：
Obtain another image for including the reference object of the intelligent terminal storage；
Send whether one asked using the selection for the described image tupe for being stored in the model database；
When being fed back to using the described image tupe for being stored in the model database of request, root are selected when described
Image procossing is carried out to another image comprising the reference object according to described image tupe.
Preferably, it is further comprising the steps of：
Start the camera of the intelligent terminal, catch the reference object；
Judge the sex for the reference object that the camera captures；
When the sex is male, the image processing mode of the intelligent terminal is closed.
Preferably, the step of sex for judging the reference object that the camera captures, includes：
Detect the human face region for the reference object that the camera captures；
Detect at least one local organs region of the human face region；
Based on two-dimensional principal component analysis method, the feature in the human face region and each local organs region is extracted；
According to the human face region and the feature in each local organs region, two-dimensional linear discriminant analysis method is utilized
Gender Classification is carried out, obtains the Gender Classification result of the human face region and the Gender Classification result in the local organs region；
The Gender Classification result of Gender Classification result and the local organs region to the human face region merges,
Obtain final sex recognition result.
The invention also discloses a kind of image processing system of intelligent terminal, including pattern starting module, image to obtain mould
Block, pattern setting module, picture recognition module, image processing module；
The pattern starting module, open the image processing mode of the intelligent terminal；
Described image acquisition module, obtain an image for including reference object of the intelligent terminal storage；
The pattern setting module, set the characteristic information of the reference object and the image processing mode of described image
Corresponding relation, the characteristic information of the reference object include the one or more in sex, age, the colour of skin, shape of face；
Described image identification module, communicated to connect with described image acquisition module, identify and obtain the reference object
Characteristic information；
Described image processing module, with described image acquisition module, pattern setting module, picture recognition module communication link
Connect, image procossing is carried out to described image according to described image tupe corresponding with the characteristic information of the reference object.
Preferably, in addition to model data library module, selection request module；
The selection request module, communicated to connect with described image processing module, send whether one store at described image
The selection request of reason pattern；
The model data library module, with the selection request module communication connection, the anti-of request module is selected when described
When presenting to store described image tupe, described image tupe is stored in the model data library module.
Preferably, described image acquisition module, the another comprising the reference object of intelligent terminal storage is obtained
Image；
The selection request module, communicated to connect with described image acquisition module, whether described using being stored in send one
The selection request of the described image tupe of model data library module；
Described image processing module, when the use that is fed back to of the selection request module is stored in the model database mould
During the described image tupe of block, another image comprising the reference object is entered according to described image tupe
Row image procossing.
Preferably, in addition to image taking module, Sexual discriminating module, pattern closedown module；
Described image taking module, start the camera of the intelligent terminal, catch the reference object；
The Sexual discriminating module, communicated to connect with described image taking module, judge the institute that the camera captures
State the sex of reference object；
The pattern closedown module, communicated to connect with the Sexual discriminating module, when the sex is male, close institute
State the image processing mode of intelligent terminal.
Preferably, the Sexual discriminating module includes Face datection unit, local detection unit, feature extraction unit, property
Other taxon, fusion results unit；
The Face datection unit, detect the human face region for the reference object that the camera captures；
The local detection unit, it is connected with the Face datection unit communication, detects at least the one of the human face region
Individual local organs region；
The feature extraction unit, with the Face datection unit, local detection unit communicate to connect, based on two dimension it is main into
Divide analytic approach, extract the feature in the human face region and each local organs region；
The Gender Classification unit, communicated to connect with the feature extraction unit, according to the human face region and each institute
The feature in local organs region is stated, Gender Classification is carried out using two-dimensional linear discriminant analysis method, obtains the human face region
Gender Classification result and the Gender Classification result in the local organs region；
The fusion results unit, it is connected with the Gender Classification unit communication, to the Gender Classification of the human face region
As a result and the Gender Classification result in the local organs region is merged, and obtains final sex recognition result.
After employing above-mentioned technical proposal, compared with prior art, have the advantages that：
1. image processing method provided by the invention and image processing system, U.S. face beautification can be not only distinguished by sex
Effect, different U.S. face landscaping effects can be also applicable according to differentiations such as age, the colour of skin, shapes of face, meet that user is beautiful to image U.S. face
The variation of change, personalized demand.
Brief description of the drawings
Fig. 1 is the schematic flow sheet for the image processing method for meeting one embodiment of the present invention；
Fig. 2 is the schematic flow sheet of the storage image tupe of the image processing method such as Fig. 1；
Fig. 3 is the schematic flow sheet of the image processing mode of the use storage of the image processing method such as Fig. 2；
Fig. 4 is the schematic flow sheet for the other image processing method of distinction for meeting one embodiment of the present invention；
Fig. 5 is the other schematic flow sheet of distinction of the image processing method such as Fig. 4；
Fig. 6 is the structural representation for the image processing system for meeting one embodiment of the present invention.
Reference：
100- image processing systems；
11- pattern starting modules；
12- image collection modules；
13- pattern setting modules；
14- picture recognition modules；
15- image processing modules；
16- model data library modules；
17- selects request module；
18- image taking modules；
19- Sexual discriminating modules；
20- pattern closedown modules.
Embodiment
Advantages of the present invention is expanded on further below in conjunction with accompanying drawing and specific embodiment.
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Following description is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the disclosure.On the contrary, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects be described in detail in claims, the disclosure.
It is only merely for the purpose of description specific embodiment in the term that the disclosure uses, and is not intended to be limiting the disclosure.
" one " of singulative used in disclosure and the accompanying claims book, " one kind ", " described " and "the" are also intended to bag
Most forms are included, unless context clearly shows that other implications.It is also understood that term "and/or" used herein is
Refer to and any or all may be combined comprising the associated list items purpose of one or more.
In the description of the invention, unless otherwise prescribed and limit, for the ordinary skill in the art, can be with
The concrete meaning of term is understood as the case may be.
In follow-up description, using the suffix of " module " for representing element, " unit " etc. only for favourable
In the explanation of the present invention, itself do not have specific meaning, only represent a part for system.Therefore, " module " and " unit "
Can mixedly it use.
With reference to figure 1, image processing method of the invention, comprise the following steps：
S100：Open the image processing mode of the intelligent terminal；
S200：Obtain an image for including reference object of the intelligent terminal storage；
S300：Set the corresponding relation of the characteristic information of the reference object and the image processing mode of described image, institute
Stating the characteristic information of reference object includes the one or more in sex, age, the colour of skin, shape of face；
S400：Identify and obtain the characteristic information of the reference object；
S500：Described image is carried out according to described image tupe corresponding with the characteristic information of the reference object
Image procossing.
Image processing method provided by the invention, can apply to intelligent terminal, and intelligent terminal can come in a variety of manners
Implement.For example, the intelligent terminal described in the present invention can include such as mobile phone, smart phone, notebook computer, PDA
(personal digital assistant), PAD (tablet personal computer), PMP (portable media player), guider, intelligent watch etc. shifting
Dynamic terminal, and the fixed terminal of digital TV, desktop computer etc..Hereinafter it is assumed that intelligent terminal is smart mobile phone, to this
Invention illustrates.However, it will be understood by those skilled in the art that in addition to being used in particular for moving the element of purpose, root
The terminal of fixed type is can also apply to according to the construction of embodiments of the present invention.
Image processing method provided by the invention, picture is handled, changed, typically by photo handling software,
Picture is mixed colours, the modification of figure, synthesis, light and shade modification, chroma and colourity is scratched, adds special-effect, editor, reparation etc.
Deng.For example, portrait U.S. face, picture beautification etc., the method for U.S. face processing includes but is not limited to whitening, mill skin, thin face, amplification, drawing
Long etc., the method for landscaping treatment includes but is not limited to cutting, inclination, various filters etc..Certainly, those skilled in the art also may be used
It is actually needed with basis and other image processing methods is set.Below by taking U.S. face as an example, the present invention will be described.
Image processing method provided by the invention, it both can apply to user and used during smart mobile phone shooting image
U.S. face processing in real time, user can also be applied to and use later stage U.S.'s face after smart mobile phone shooting image to handle, can also be applied
The U.S. face processing of image is downloaded or preserves in user.
Step S300：Set the corresponding pass of the characteristic information of the reference object and the image processing mode of described image
System, the characteristic information of the reference object include the one or more in sex, age, the colour of skin, shape of face.
The image processing method of the present invention, can be applicable different according to feature differentiations such as sex, age, the colour of skin, shapes of face
U.S. face effect.Specifically, the combinations of features such as all ages and classes, sex, the colour of skin, shape of face can be formed to different portrait models, it is right
Different portrait models carries out the experiment of different U.S. face effects, corresponding most suitable U.S. face effect is matched, by different Xiao
As model and corresponding U.S. face effect one-to-one corresponding, so, the feature such as each age, sex, the colour of skin, shape of face or its combination will
Corresponding a kind of most suitable U.S. face effect, such as 25 years old, man, colour of skin yellow, oval face, slightly adjust brightness i.e. under test of many times
Best U.S. face effect can be shown, then this kind of combinations of features, when detecting this kind of combinations of features, makes to that should plant U.S. face effect
With this kind of U.S. face effect.
S400：Identify and obtain the characteristic information of the reference object；
For the different feature such as sex, age, the colour of skin, shape of face, it is identified has nothing in common with each other with the mode obtained.
- sex
Identification for sex, the classification that local organs (such as face) feature on face is respectively trained can be used
The Multiple Classifier Fusion mode that the grader of device and face global feature is combined, integrated classification device is constructed to carry out sex identification,
So as to improve recognition accuracy；And dimensionality reduction is carried out to image using 2DPCA method, using 2DLDA as sorting technique, protecting
On the basis of demonstrate,proving accuracy of detection, operand is reduced, improves training and detection speed.Specifically：
(1) image is pre-processed：Image is carried out at gray processing, histogram equalization and medium filtering successively
Reason.
Gray processing：Using weighted average method.Image can be generally divided into coloured image and gray level image, coloured image
Pixel is made up of three kinds of R (red), G (green), B (black) colors, and gray level image comprises only monochrome information, without colour
Information, such as the gray processing of coloured image, frequently with empirical formula：Gray=0.39*R+0.5*G+0.11*B.
Histogram equalization：Each gray level component is averagely covered with space, performance is by intensive gray scale point on histogram
Cloth is changed into uniformly being distributed, and so as to strengthen the contrast of image, can reduce interference of the light to image so that feature easily carries
Take.
Medium filtering：Its essence is a kind of wave filter of sort method.For certain point, median filter process mistake in original image
The sort method intermediate value of journey all pixels in the neighborhood centered on the point is the response of the point.Medium filtering is to certain form of
Random noise has preferable noise reduction capability, and compared with linear smoothing filtering, it will not cause higher while noise is reduced
Blurring effect.
(2) human face region detects：Using the grader AdaBoost (Adaptive based on cascade sort model
Boosting) method design grader, Face datection is carried out to an image, extracts face present in image.
The higher intelligent algorithm of most of operational efficiency is all by extracting the feature efficiently and beneficial to identification and processing
Realize, and Adaboost algorithm is also the same, Adaboost is Freund and Schapire in PAC (Probably
Approximately Correct) a kind of learning model for proposing on the basis of model, its algorithm idea is：By to a large amount of
The study of positive sample and negative sample, by the feedback of study, Weak Classifier is not on the premise of the training error of priori is known, certainly
The adjustment error rate and corresponding weight of adaptation, until strong classifier reaches predetermined performance, by Adaboost algorithm application
Combined in Face datection, while by Haar features and Cascade algorithms and Adaboost algorithm, greatly improve detection speed and
The accurate rate of detection.
(3) face local organs region intercepts：By before the step of, a face has been obtained from an image
Image, first its size is normalized, extract at least one face local organs image therefrom afterwards, a left side can be extracted respectively
This face of eye, right eye, eyebrow, face, nose.For example, can be by for the grader that eye areas in human face region detects
AdaBoost learning algorithms train to obtain, it should be noted that the problem of choosing sample, positive sample behaviour Vitrea eye area image, and instruct
Practice negative sample to be then made up of two parts, a part is to remove the view picture facial image of human eye area, and another part is by original image
The subwindow image of middle human eye area surrounding, the binocular images of face can be intercepted with similar mode.
(4) Feature Dimension Reduction：Using 2DPCA (Two-Dimensional Principal Component Analysis, two
Tie up principal component analysis) method.
PCA (Principal Component Analysis) is a classics in pattern-recognition and computer vision field
Feature extraction and Data Dimensionality Reduction instrument, and 2DPCA methods are a kind of new masters to grow up on PCA basis
Component analyzing method, relative to traditional PCA methods, 2DPCA is based on two dimensional image matrix, rather than one dimensional image vector.
This processing method in advance need not change into image one-dimensional vector, equivalent to the row vector or column vector for eliminating image
Correlation.In 2DPCA, with one covariance matrix of two dimensional image matrix direct construction, this covariance matrix characteristic value is obtained
And characteristic vector, and coordinate system is built with corresponding to characteristic vector corresponding to maximum several characteristic values, then by each image moment
Battle array is projected on this coordinate system, and so as to obtain the feature of image, this feature is influenceed smaller by number of samples.With PCA structures
The covariance matrix made is compared, much smaller using 2DPCA covariance matrix, and its major advantage has：Directly calculate training
The literary style difference matrix of sample；Time required for calculating characteristic value characteristic vector is fewer.
(5) pattern classification：The present invention uses 2DLDA (Two-Dimensional Linear Discrimination
Analysis, two-dimensional linear discriminant analysis) method.
2DLDA is also a kind of method for being directly based upon two dimensional image matrix, is calculated respectively in the class of two dimensional image between class
Scatter Matrix, optimal projected coordinate system is determined under certain optiaml ciriterion.Original image is projected to coordinate system to obtain face
The 2DLDA features of image, 2DLDA method operands are small, are effectively utilized the spatial structural form of facial image.
(6) determination and fusion of face contribution weight size：
Obtain the accuracy rate P of each sub-classifieri(i=1,2 ... 6), primarily determine that the weight Q of each sub-classifieri=
Pi/ ∑Pi；Fairly simple fusion method is addition and multiplication.
In addition, the identification of sex can be combined with other modes, for example, can identify and obtain the target in image
Feature, can be the one or more in beard, ornaments, hair style, Adam's apple and eyebrow, such as when target signature is beard, its
Corresponding target signature information can be to have beard (characteristic value 1) or without beard (characteristic value 0), it is determined that having corresponding to beard
Sex is male, further according to other target signatures, such as hair style, ornaments, Adam's apple or eyebrow during no beard, further determines that shooting
The sex of object, and for example when target signature is ornaments, such as hair fastener or ear pendant, its corresponding target signature information can be to have
Ornaments or without ornaments, it is further true further according to other target signatures during no ornaments it is determined that have sex corresponding to ornaments for i.e. women
Determine the sex of reference object；When target signature is Adam's apple, its corresponding target signature information can be to have Adam's apple or do not have an Adam's apple,
When mesh characteristic information for when having Adam's apple, the target gender for determining reference object is male, when target signature information is without Adam's apple,
The target gender for determining reference object is women, and the embodiment of the present invention does not limit.
- the age
Identification for the age, the two classification algorithm of sex identification is referred to, utilizes regression equation or multicategory classification
Algorithm, Cluster Classification training is carried out according to sample.
In a people from during child grows up to young people, face bone constantly grows, so as to which shape of face is constantly elongated
Becoming big, appearance also changes therewith, during becoming the elderly by the continuous aging of young people, the colour of skin of skin, wrinkle
It can change therewith, therefore, age discrimination can drastically decline with the change of age of people.The age recognition methods of main flow now
It is that the method based on faceform and age function, wherein age function are trained by the facial image of the people at multigroup known age
Obtain, based on this method, mainly there are following four classes：
(1) global age function is built：By substantial amounts of training image, the global age function of component one, by direct
Using this function, the age of target facial image is calculated.
(2) the specific age function of outward appearance：This age function is divided with facial characteristics and inputted.Under this approach, I
Think for the similar individual of facial characteristics, its ageing process be also it is quite similar, by input a facial image, seek
Look for has the age function of similar features therewith, then calculates its age.
(3) age function is weighted：It is similar to the specific age function of outward appearance to weight age function, but it is schemed by input
Picture, the age function for having the image of similar features to be calculated therewith is can not find, at this moment using institute's has age function pair people
The age of face image is estimated, then it is weighted, so as to obtain estimation result.
(4) the personal special age function of weighting：This method is higher to input requirements, does not require nothing more than someone's face image, also
There are sex, health, living standard, economic situation, stress level, condition of work, marital status, place of abode, touch
The factors such as weather condition, calculating process include weighting age function and the specific age function of outward appearance, while to non-image information
Influence be weighted.
- the colour of skin
Identification for the colour of skin, is detected to area of skin color first, then by extracting the colour of skin to the human face region method of average,
Or by face below, for example neck (exposed to the weather less, skin color is shallower, and skin quality is also than face below neck
Sampling obtains user's skin true colors well), by color compared with the color data in database, draws the colour of skin and affiliated people
Kind.
During being detected to area of skin color, single Gauss model method, mixed Gauss model method, ellipse are normally based on
What the methods of complexion model method, was realized.Single Gauss model method assumes that skin distribution obeys uni-modal Gaussian, passes through statistical
Analysis, the parameter of prediction Gaussian Profile, are established model based on the parameter, are judged whether new pixel or region are skin using model
Color.But due to not fully meeting uni-modal Gaussian with not agnate skin distribution, therefore propose mixed Gaussian mould
Type method, mixed Gauss model method use the Gaussian distribution model of multimodal determine image pixel or region whether for the colour of skin.Due to
Under normal circumstances, for Skin Color Information when being transformed into YCbCr space, it is positioned at a similar oval collection under CbCr coordinate systems
Within the scope of cluster, so oval complexion model can also be detected based on determined by Skin Color Information to the colour of skin of people.When
So, also other methods for Face Detection, such as the detection method based on regional model, the detection based on histogram model
Method etc..
Skin color detection method in coloured image can use：
(1) color space conversion：
Give a coloured image to be checked, it is transformed into the colour of skin from primitive color space aggregation is good, the colour of skin with it is non-
The good color space of the distinction of the colour of skin, classification color space (color space after changing) can into YCrCb, YUV, Lab,
HSV, HIS, normalized RGB etc., or the aggregation of the colour of skin is good under the conditions of same light photograph, the area of the colour of skin and the non-colour of skin
Divide property good other color spaces.
(2) face is detected, non-skin part on face is removed, obtains face skin area：
Original color image is converted into gray level image, and therefrom detects face, such as spy is used as by the use of Haar small echos
The waterfall type AdaBoost graders of sign carry out detection method of face etc., and the detailed process on Face datection is no longer superfluous herein
State.The human face region detected is represented with rectangle, and the skin and non-skin part (such as eyebrow of face have been preferably comprised in the rectangle
Hair, eyes, nostril, face etc.), it is also possible to include some background areas.
In the human face region detected, outline, eyebrow, eyes, nostril, the face of locating human face.In locating human face
All parts after, retain and the region after eyebrow, eyes, nostril, face eliminated within face outline as people's face skin
Region.
(3) colour of skin sample is gathered：
On the coloured image in converting colors space, pixel color in the face skin area of determination in extraction step (2)
As colour of skin sample.
(4) according to the colour of skin sample of collection, skin color classifier is established.
(5) using the skin color classifier established in step (4), whole image is classified pixel by pixel.It is categorized as
The pixel of the colour of skin, mark is on Face Detection result images, otherwise mark is to obtain Face Detection result figure
Picture.
- shape of face
Identification for shape of face, face contour extraction is carried out after being identified by human face region.Detecting face area
Domain and after positioning facial key feature points, main human face region can is cropped out, after pretreatment, with storehouse
The known shape of face deposited is compared, and completes final shape of face classification.
With reference to figure 2,3, in a preferred embodiment, image processing method of the invention also includes：
S600：Establish a model database；
S700：Send a selection request for whether storing described image tupe；
S800：When being fed back to store described image tupe of request is selected when described, by described image tupe
It is stored in the model database.
S900：Obtain another image for including the reference object of the intelligent terminal storage；
S1000：Send whether one asked using the selection for the described image tupe for being stored in the model database；
S1100：When being fed back to using the described image processing mould for being stored in the model database for the selection request
During formula, image procossing is carried out to another image comprising the reference object according to described image tupe.
The image processing method of the present invention, U.S. face processing is carried out to image for the convenience of the user, can be in user to its image
After being handled, storage, when user opens another image, directly uses storage suitable for the U.S. face effect of the user characteristics
U.S. face effect image is handled, it is not necessary to be identified to image, reduce calculating process, improve operation efficiency,
It ensure that the unification of user images U.S. face effect.
With reference to figure 4, in a preferred embodiment, image processing method of the invention also includes：
S1200：Start the camera of the intelligent terminal, catch the reference object；
S1300：Judge the sex for the reference object that the camera captures；
S1400：When the sex is male, the image processing mode of the intelligent terminal is closed.
In the present embodiment, when the sex judged as male when, and U.S. face pattern open when, close U.S. face pattern；When sentencing
When disconnected sex is male, and during the closing of U.S. face pattern, maintain U.S. face pattern closed mode；When the sex judged as women when,
And U.S. face pattern maintains U.S. face pattern opening when opening；When the sex judged as women when, and U.S. face pattern close when,
Open U.S. face pattern.The image processing method of the present invention, it is capable of the sex of automatic identification reference object, and when the sex identified
For male when, the state for the U.S. face pattern that automatically switches, reduce the manually operated of user, improve the efficiency of taking pictures of user, enter
And improve the usage experience of user.To introduction of the neutral other identification process of image referring to step 400 and Fig. 5, repeat no more.
With reference to figure 6, the invention also discloses a kind of image processing system 100 of intelligent terminal, including pattern starting module
11st, image collection module 12, pattern setting module 13, picture recognition module 14, image processing module 15；
The pattern starting module 11, open the image processing mode of the intelligent terminal；
Described image acquisition module 12, obtain an image for including reference object of the intelligent terminal storage；
The pattern setting module 13, sets the characteristic information of the reference object and the image processing mode of described image
Corresponding relation, the characteristic information of the reference object includes the one or more in sex, age, the colour of skin, shape of face；
Described image identification module 14, communicated to connect with described image acquisition module 12, identify and obtain the shooting pair
The characteristic information of elephant；
Described image processing module 15, with described image acquisition module 12, pattern setting module 13, picture recognition module
14 communication connections, figure is carried out according to described image tupe corresponding with the characteristic information of the reference object to described image
As processing.
In a preferred embodiment, in addition to model data library module 16, selection request module 17；
The selection request module 17, communicates to connect with described image processing module 15, sends whether one store the figure
As the selection of tupe is asked；
The model data library module 16, communicated to connect with the selection request module 17, when the selection request module
17 when being fed back to store described image tupe, the model data library module is stored in by described image tupe
In 16.
In a preferred embodiment, described image acquisition module 12, obtain described the another of intelligent terminal storage and include institute
State the image of reference object；
The selection request module 17, is communicated to connect with described image acquisition module 12, whether sends one using being stored in
The selection request of the described image tupe of the model data library module 16；
Described image processing module 15, when the use that is fed back to of the selection request module 17 is stored in the model data
During the described image tupe of library module 16, according to described image tupe to described another comprising the reference object
Image carries out image procossing.
In a preferred embodiment, in addition to image taking module 18, Sexual discriminating module 19, pattern closedown module 20；
Described image taking module 18, start the camera of the intelligent terminal, catch the reference object；
The Sexual discriminating module 19, is communicated to connect with described image taking module 18, judges that the camera captures
The reference object sex；
The pattern closedown module 20, communicate to connect with the Sexual discriminating module 19, when the sex is male, close
Close the image processing mode of the intelligent terminal.
In a preferred embodiment, the Sexual discriminating module 19 includes Face datection unit, local detection unit, feature
Extraction unit, Gender Classification unit, fusion results unit；
The Face datection unit, detect the human face region for the reference object that the camera captures；
The local detection unit, it is connected with the Face datection unit communication, detects at least the one of the human face region
Individual local organs region；
The feature extraction unit, with the Face datection unit, local detection unit communicate to connect, based on two dimension it is main into
Divide analytic approach, extract the feature in the human face region and each local organs region；
The Gender Classification unit, communicated to connect with the feature extraction unit, according to the human face region and each institute
The feature in local organs region is stated, Gender Classification is carried out using two-dimensional linear discriminant analysis method, obtains the human face region
Gender Classification result and the Gender Classification result in the local organs region；
The fusion results unit, it is connected with the Gender Classification unit communication, to the Gender Classification of the human face region
As a result and the Gender Classification result in the local organs region is merged, and obtains final sex recognition result.
It should be noted that embodiments of the invention have preferable implementation, and not the present invention is made any type of
Limitation, any one skilled in the art change or are modified to possibly also with the technology contents of the disclosure above equivalent effective
Embodiment, as long as without departing from the content of technical solution of the present invention, above example is made according to technical spirit of the invention
Any modification or equivalent variations and modification, in the range of still falling within technical solution of the present invention.
Claims (10)
1. a kind of image processing method of intelligent terminal, it is characterised in that comprise the following steps：
Open the image processing mode of the intelligent terminal；
Obtain an image for including reference object of the intelligent terminal storage；
Set the corresponding relation of the characteristic information of the reference object and the image processing mode of described image；
Identify and obtain the characteristic information of the reference object；
Image procossing is carried out to described image according to described image tupe corresponding with the characteristic information of the reference object；
The characteristic information of the reference object includes the one or more in sex, age, the colour of skin, shape of face.
2. image processing method as claimed in claim 1, it is characterised in that
It is further comprising the steps of：
Establish a model database；
Send a selection request for whether storing described image tupe；
When being fed back to store described image tupe of request is selected when described, described image tupe is stored in described
Model database.
3. image processing method as claimed in claim 2, it is characterised in that
It is further comprising the steps of：
Obtain another image for including the reference object of the intelligent terminal storage；
Send whether one asked using the selection for the described image tupe for being stored in the model database；
When being fed back to using the described image tupe for being stored in the model database of request is selected when described, according to institute
State image processing mode and image procossing is carried out to another image comprising the reference object.
4. image processing method as claimed in claim 1, it is characterised in that
It is further comprising the steps of：
Start the camera of the intelligent terminal, catch the reference object；
Judge the sex for the reference object that the camera captures；
When the sex is male, the image processing mode of the intelligent terminal is closed.
5. image processing method as claimed in claim 4, it is characterised in that
The step of sex for judging the reference object that the camera captures, includes：
Detect the human face region for the reference object that the camera captures；
Detect at least one local organs region of the human face region；
Based on two-dimensional principal component analysis method, the feature in the human face region and each local organs region is extracted；
According to the human face region and the feature in each local organs region, carried out using two-dimensional linear discriminant analysis method
Gender Classification, obtain the Gender Classification result of the human face region and the Gender Classification result in the local organs region；
The Gender Classification result of Gender Classification result and the local organs region to the human face region merges, and obtains
Final sex recognition result.
A kind of 6. image processing system of intelligent terminal, it is characterised in that
Including pattern starting module, image collection module, pattern setting module, picture recognition module, image processing module；
The pattern starting module, open the image processing mode of the intelligent terminal；
Described image acquisition module, obtain an image for including reference object of the intelligent terminal storage；
The pattern setting module, set the corresponding of the characteristic information of the reference object and the image processing mode of described image
Relation, the characteristic information of the reference object include the one or more in sex, age, the colour of skin, shape of face；
Described image identification module, communicated to connect with described image acquisition module, identify and obtain the feature of the reference object
Information；
Described image processing module, communicated to connect with described image acquisition module, pattern setting module, picture recognition module, root
Image procossing is carried out to described image according to described image tupe corresponding with the characteristic information of the reference object.
7. image processing system as claimed in claim 6, it is characterised in that
Also include model data library module, selection request module；
The selection request module, communicated to connect with described image processing module, send whether one store described image processing mould
The selection request of formula；
The model data library module, with the selection request module communication connection, being fed back to for request module is selected when described
When storing described image tupe, described image tupe is stored in the model data library module.
8. image processing system as claimed in claim 7, it is characterised in that
Described image acquisition module, obtain another image for including the reference object of the intelligent terminal storage；
The selection request module, communicated to connect with described image acquisition module, whether send one using being stored in the model
The selection request of the described image tupe of database module；
Described image processing module, when being fed back to using being stored in the model data library module for the selection request module
During described image tupe, figure is carried out to another image comprising the reference object according to described image tupe
As processing.
9. image processing system as claimed in claim 6, it is characterised in that
Also include image taking module, Sexual discriminating module, pattern closedown module；
Described image taking module, start the camera of the intelligent terminal, catch the reference object；
The Sexual discriminating module, communicated to connect with described image taking module, judge the bat that the camera captures
Take the photograph the sex of object；
The pattern closedown module, communicated to connect with the Sexual discriminating module, when the sex is male, close the intelligence
The image processing mode of energy terminal.
10. image processing system as claimed in claim 9, it is characterised in that
The Sexual discriminating module include Face datection unit, local detection unit, feature extraction unit, Gender Classification unit,
Fusion results unit；
The Face datection unit, detect the human face region for the reference object that the camera captures；
The local detection unit, it is connected with the Face datection unit communication, detects at least one office of the human face region
Portion's organic region；
The feature extraction unit, communicated to connect with the Face datection unit, local detection unit, based on two-dimentional principal component point
Analysis method, extract the feature in the human face region and each local organs region；
The Gender Classification unit, communicated to connect with the feature extraction unit, according to the human face region and each office
The feature of portion's organic region, Gender Classification is carried out using two-dimensional linear discriminant analysis method, obtains the sex of the human face region
Classification results and the Gender Classification result in the local organs region；
The fusion results unit, it is connected with the Gender Classification unit communication, to the Gender Classification result of the human face region
And the Gender Classification result in the local organs region is merged, final sex recognition result is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710705349.9A CN107545536A (en) | 2017-08-17 | 2017-08-17 | The image processing method and image processing system of a kind of intelligent terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710705349.9A CN107545536A (en) | 2017-08-17 | 2017-08-17 | The image processing method and image processing system of a kind of intelligent terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107545536A true CN107545536A (en) | 2018-01-05 |
Family
ID=60970545
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710705349.9A Pending CN107545536A (en) | 2017-08-17 | 2017-08-17 | The image processing method and image processing system of a kind of intelligent terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107545536A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108093178A (en) * | 2018-01-03 | 2018-05-29 | 上海传英信息技术有限公司 | A kind of method and shooting mobile phone that the variation of the photo colour of skin is realized by PCA linear transformations |
| CN108391602A (en) * | 2018-04-25 | 2018-08-14 | 中国农业科学院农业信息研究所 | A kind of chick gender identifying system and its recognition methods |
| CN108520221A (en) * | 2018-03-30 | 2018-09-11 | 百度在线网络技术（北京）有限公司 | Method, apparatus, storage medium and the terminal device of build identification |
| CN110443769A (en) * | 2019-08-08 | 2019-11-12 | Oppo广东移动通信有限公司 | Image processing method, image processing apparatus and terminal device |
| WO2019233341A1 (en) * | 2018-06-08 | 2019-12-12 | Oppo广东移动通信有限公司 | Image processing method and apparatus, computer readable storage medium, and computer device |
| CN111028214A (en) * | 2019-12-05 | 2020-04-17 | 北京美医医学技术研究院有限公司 | Skin detection device based on cloud platform |
| CN111798367A (en) * | 2019-04-09 | 2020-10-20 | Oppo广东移动通信有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
| CN112102153A (en) * | 2020-08-20 | 2020-12-18 | 北京百度网讯科技有限公司 | Cartoon processing method and device for image, electronic equipment and storage medium |
| CN112184580A (en) * | 2020-09-27 | 2021-01-05 | 北京金山云网络技术有限公司 | Face image enhancement method, device, equipment and storage medium |
| WO2021036853A1 (en) * | 2019-08-31 | 2021-03-04 | 华为技术有限公司 | Image processing method and electronic apparatus |
| CN112561822A (en) * | 2020-12-17 | 2021-03-26 | 苏州科达科技股份有限公司 | Beautifying method and device, electronic equipment and storage medium |
| WO2021208709A1 (en) * | 2020-04-13 | 2021-10-21 | 北京字节跳动网络技术有限公司 | Image processing method and apparatus, and electronic device and computer-readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120081568A1 (en) * | 2010-09-30 | 2012-04-05 | Nintendo Co., Ltd. | Storage medium recording information processing program, information processing method, information processing system and information processing device |
| CN103198303A (en) * | 2013-04-12 | 2013-07-10 | 南京邮电大学 | Gender identification method based on facial image |
| CN103413270A (en) * | 2013-08-15 | 2013-11-27 | 北京小米科技有限责任公司 | Method and device for image processing and terminal device |
| CN103995911A (en) * | 2013-02-15 | 2014-08-20 | 北京银万特科技有限公司 | Beauty matching method and system based on intelligent information terminal |
| CN105721770A (en) * | 2016-01-20 | 2016-06-29 | 广东欧珀移动通信有限公司 | Shooting control method and shooting control device |
| US9603437B2 (en) * | 2013-04-08 | 2017-03-28 | Panasonic Intellectual Property Corporation Of America | Image processing device, image processing method, and program, capable of virtual reproduction of makeup application state |
-
2017
- 2017-08-17 CN CN201710705349.9A patent/CN107545536A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120081568A1 (en) * | 2010-09-30 | 2012-04-05 | Nintendo Co., Ltd. | Storage medium recording information processing program, information processing method, information processing system and information processing device |
| CN103995911A (en) * | 2013-02-15 | 2014-08-20 | 北京银万特科技有限公司 | Beauty matching method and system based on intelligent information terminal |
| US9603437B2 (en) * | 2013-04-08 | 2017-03-28 | Panasonic Intellectual Property Corporation Of America | Image processing device, image processing method, and program, capable of virtual reproduction of makeup application state |
| CN103198303A (en) * | 2013-04-12 | 2013-07-10 | 南京邮电大学 | Gender identification method based on facial image |
| CN103413270A (en) * | 2013-08-15 | 2013-11-27 | 北京小米科技有限责任公司 | Method and device for image processing and terminal device |
| CN105721770A (en) * | 2016-01-20 | 2016-06-29 | 广东欧珀移动通信有限公司 | Shooting control method and shooting control device |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108093178A (en) * | 2018-01-03 | 2018-05-29 | 上海传英信息技术有限公司 | A kind of method and shooting mobile phone that the variation of the photo colour of skin is realized by PCA linear transformations |
| CN108520221A (en) * | 2018-03-30 | 2018-09-11 | 百度在线网络技术（北京）有限公司 | Method, apparatus, storage medium and the terminal device of build identification |
| CN108520221B (en) * | 2018-03-30 | 2019-08-09 | 百度在线网络技术（北京）有限公司 | Method, apparatus, storage medium and the terminal device of figure identification |
| CN108391602A (en) * | 2018-04-25 | 2018-08-14 | 中国农业科学院农业信息研究所 | A kind of chick gender identifying system and its recognition methods |
| CN108391602B (en) * | 2018-04-25 | 2023-06-06 | 中国农业科学院农业信息研究所 | Chick gender identification system and chick gender identification method |
| WO2019233341A1 (en) * | 2018-06-08 | 2019-12-12 | Oppo广东移动通信有限公司 | Image processing method and apparatus, computer readable storage medium, and computer device |
| CN111798367A (en) * | 2019-04-09 | 2020-10-20 | Oppo广东移动通信有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
| CN110443769A (en) * | 2019-08-08 | 2019-11-12 | Oppo广东移动通信有限公司 | Image processing method, image processing apparatus and terminal device |
| CN110443769B (en) * | 2019-08-08 | 2022-02-08 | Oppo广东移动通信有限公司 | Image processing method, image processing device and terminal equipment |
| WO2021036853A1 (en) * | 2019-08-31 | 2021-03-04 | 华为技术有限公司 | Image processing method and electronic apparatus |
| CN111028214A (en) * | 2019-12-05 | 2020-04-17 | 北京美医医学技术研究院有限公司 | Skin detection device based on cloud platform |
| WO2021208709A1 (en) * | 2020-04-13 | 2021-10-21 | 北京字节跳动网络技术有限公司 | Image processing method and apparatus, and electronic device and computer-readable storage medium |
| CN112102153A (en) * | 2020-08-20 | 2020-12-18 | 北京百度网讯科技有限公司 | Cartoon processing method and device for image, electronic equipment and storage medium |
| CN112102153B (en) * | 2020-08-20 | 2023-08-01 | 北京百度网讯科技有限公司 | Image cartoon processing method and device, electronic equipment and storage medium |
| CN112184580A (en) * | 2020-09-27 | 2021-01-05 | 北京金山云网络技术有限公司 | Face image enhancement method, device, equipment and storage medium |
| CN112561822A (en) * | 2020-12-17 | 2021-03-26 | 苏州科达科技股份有限公司 | Beautifying method and device, electronic equipment and storage medium |
| CN112561822B (en) * | 2020-12-17 | 2022-07-01 | 苏州科达科技股份有限公司 | Beautifying method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107545536A (en) | The image processing method and image processing system of a kind of intelligent terminal | |
| CN103914699B (en) | A kind of method of the image enhaucament of the automatic lip gloss based on color space | |
| CN106056064B (en) | A kind of face identification method and face identification device | |
| CN108717524B (en) | Gesture recognition system based on double-camera mobile phone and artificial intelligence system | |
| CN105608447B (en) | To the detection method of human body face smile expression depth convolutional neural networks | |
| Kashem et al. | Face recognition system based on principal component analysis (PCA) with back propagation neural networks (BPNN) | |
| CN103984948B (en) | A kind of soft double-deck age estimation method based on facial image fusion feature | |
| KR100882476B1 (en) | Method for distinguishing obscene image and apparatus therefor | |
| CN106485222A (en) | A kind of method for detecting human face being layered based on the colour of skin | |
| CN109271930B (en) | Micro-expression recognition method, device and storage medium | |
| CN108647625A (en) | A kind of expression recognition method and device | |
| CN104008364B (en) | Face identification method | |
| CN104504383B (en) | A kind of method for detecting human face based on the colour of skin and Adaboost algorithm | |
| CN106067016B (en) | A kind of facial image eyeglass detection method and device | |
| Radu et al. | A robust sclera segmentation algorithm | |
| CN109685713A (en) | Makeup analog control method, device, computer equipment and storage medium | |
| CN109902561A (en) | A kind of face identification method and device, robot applied to robot | |
| CN110046544A (en) | Digital gesture identification method based on convolutional neural networks | |
| CN114187166A (en) | Image processing method, intelligent terminal and storage medium | |
| CN111860250A (en) | Image identification method and device based on character fine-grained features | |
| Sahu et al. | Study on face recognition techniques | |
| Rahman et al. | An automatic face detection and gender classification from color images using support vector machine | |
| CN104573673A (en) | Face image age recognition method | |
| Karacs et al. | Bionic eyeglass: an audio guide for visually impaired | |
| Monwar et al. | Eigenimage based pain expression recognition |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221223 Address after: 201203 1st floor, building 1, Lane 36, Xuelin Road, Pudong New Area Free Trade Zone, Shanghai Applicant after: SHANGHAI TRANSSION INFORMATION TECHNOLOGY Ltd. Address before: Room 922 / 926, block a, No.1 Lane 399, shengxia Road, Pudong New Area pilot Free Trade Zone, Shanghai 201203 Applicant before: SHANGHAI SPREADRISE COMMUNICATION TECHNOLOGY Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180105 |
|
| RJ01 | Rejection of invention patent application after publication |