CN109146893A - Glossy region segmentation method, device and mobile terminal - Google Patents
Glossy region segmentation method, device and mobile terminal Download PDFInfo
- Publication number
- CN109146893A CN109146893A CN201810865176.1A CN201810865176A CN109146893A CN 109146893 A CN109146893 A CN 109146893A CN 201810865176 A CN201810865176 A CN 201810865176A CN 109146893 A CN109146893 A CN 109146893A
- Authority
- CN
- China
- Prior art keywords
- skin
- face
- glossy
- region
- dark
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- 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
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The embodiment of the present application provides a kind of glossy region segmentation method, device and mobile terminal.This method comprises: extracting skin of face region from target image；The corresponding skin of face in the skin of face region is obtained secretly to scheme；The Gauss model of the dark figure of the skin of face is established based on default hyper parameter and the dark figure of the skin of face；The dark figure of the skin of face is analyzed by the Gauss model, obtains the glossy probability graph of the dark figure of the skin of face, wherein includes the glossy probability of each pixel in the dark figure of the skin of face in the glossy probability graph；Glossy region is partitioned into from the skin of face region based on the glossy probability graph.Thereby, it is possible to effectively avoid glossy erroneous detection caused by environment light, the accuracy of glossy region segmentation is improved.
Description
Technical field
This application involves field of computer technology, in particular to a kind of glossy region segmentation method, device and movement
Terminal.
Background technique
It is glossy refer to because face it is fuel-displaced and caused by face bloom.And the facial oil pump capacity usually skin quality with a people
Correlation, so commonly using glossy amount to judge the skin quality of a people.
Inventor has found in the course of the research, glossy most apparent feature be exactly it is bright, be embodied in facial area namely
Highlight area, but the highlight area of facial area again it is different establish a capital be it is glossy, some strong bias lights will also result in face
Bloom.And existing glossy splitting scheme is modeled according to the feature of bloom primarily directed to whole facial area to mention
Glossy region is taken, but carries out special processing without being directed to erroneous detection caused by environment light, causes glossy false detection rate high, it is glossy
Region segmentation inaccuracy.
Summary of the invention
In order to overcome above-mentioned deficiency in the prior art, the application's is designed to provide a kind of glossy region segmentation side
Method, device and mobile terminal can effectively avoid glossy erroneous detection caused by environment light, improve the accuracy of glossy region segmentation.
To achieve the goals above, the embodiment of the present application the technical solution adopted is as follows:
In a first aspect, the embodiment of the present application provides a kind of glossy region segmentation method, which comprises
Skin of face region is extracted from target image；
The corresponding skin of face in the skin of face region is obtained secretly to scheme；
The Gauss model of the dark figure of the skin of face is established based on default hyper parameter and the dark figure of the skin of face；
The dark figure of the skin of face is analyzed by the Gauss model, obtains the glossy of the dark figure of the skin of face
Probability graph, wherein include the glossy probability of each pixel in the dark figure of the skin of face in the glossy probability graph；
Glossy region is partitioned into from the skin of face region based on the glossy probability graph.
Optionally, described the step of skin of face region is extracted from target image, comprising:
Recognition of face is carried out to the target image, obtains human face region and multiple human face characteristic points；
The extraneous areas in the human face region is rejected according to the multiple human face characteristic point, obtains skin of face area
Domain, wherein the extraneous areas include face region, periocular area, facial fringe region, mouth week region, in nose week region
One of or multiple combinations.
It is optionally, described to obtain the step of corresponding skin of face in the skin of face region is secretly schemed, comprising:
Obtain the rgb value of each pixel in the skin of face region, wherein the rgb value include R value, G value and
B value；
Using the minimum value in the R value, the G value and the B value as the dark map values of each pixel；
Brightness processed is carried out to the skin of face region based on the dark map values of each pixel, obtains corresponding facial skin
Skin is secretly schemed.
Optionally, the Gauss that the dark figure of the skin of face is established based on default hyper parameter and the dark figure of the skin of face
The step of model, comprising:
Obtain the pixel value of each pixel in the dark figure of the skin of face；
Calculated for pixel values based on each pixel in the dark figure of the skin of face obtains in the dark figure of the skin of face
Pixel value mean value and pixel value variance；
The Gaussian mode of the dark figure of the skin of face is established based on the default hyper parameter, pixel value mean value and pixel value variance
Type.
Optionally, described that the dark figure of the skin of face is analyzed by the Gauss model, obtain the facial skin
The step of glossy probability graph of the dark figure of skin, comprising:
The glossy probability value of each pixel in the dark figure of the skin of face is calculated by the Gauss model；
The glossy probability graph of the dark figure of the skin of face is obtained according to the glossy probability value of each pixel of calculating.
Optionally, the glossy probability that each pixel in the dark figure of the skin of face is calculated by the Gauss model
The calculation formula of value are as follows:
Wherein, a, b are default hyper parameter, and μ is the pixel value mean value of the dark figure of the skin of face, and σ is the skin of face
The pixel value variance of dark figure, x are the pixel value of each pixel in the dark figure of the skin of face, and f (x) is the oil of each pixel
Light probability value.
Optionally, the step for being partitioned into glossy region from the skin of face region based on the glossy probability graph
Suddenly, comprising:
Glossy probability is searched from the skin of face region according to the glossy probability graph greater than predetermined probabilities threshold value
Each target pixel points；
Each target pixel points region is divided from the skin of face region and obtains glossy region, wherein institute
Stating glossy region includes multiple highlight areas.
Optionally, it is described each target pixel points region is divided from the skin of face region obtain glossy area
The step of domain, further includes:
The gradient of each pixel in each highlight area in the glossy region is calculated, to obtain in each highlight area
The average gradient of each pixel, wherein the gradient is the horizontal gradient of pixel and the amplitude of vertical gradient；
Judge whether the average gradient of each pixel in each highlight area is less than predetermined gradient threshold value, obtains judgement knot
Fruit；
Average gradient is less than the highlight area of predetermined gradient threshold value from the glossy region according to the judging result
It filters out.
Second aspect, the embodiment of the present application also provide a kind of glossy region segmentation device, and described device includes:
Extraction module, for extracting skin of face region from target image；
Module is obtained, is secretly schemed for obtaining the corresponding skin of face in the skin of face region；
Model building module, for establishing the skin of face based on default hyper parameter and the dark figure of the skin of face and secretly scheming
Gauss model；
Analysis module obtains the face for analyzing by the Gauss model the dark figure of the skin of face
The glossy probability graph of the dark figure of skin, wherein include each pixel in the dark figure of the skin of face in the glossy probability graph
Glossy probability；
Divide module, for being partitioned into glossy region from the skin of face region based on the glossy probability graph.
The third aspect, the embodiment of the present application also provide a kind of mobile terminal, and the mobile terminal includes:
Storage medium；
Processor；And
Glossy region segmentation device, the glossy region segmentation device are stored in the storage medium and including by described
The software function module that processor executes, described device include:
Extraction module, for extracting skin of face region from target image；
Module is obtained, is secretly schemed for obtaining the corresponding skin of face in the skin of face region；
Model building module, for establishing the skin of face based on default hyper parameter and the dark figure of the skin of face and secretly scheming
Gauss model；
Analysis module obtains the face for analyzing by the Gauss model the dark figure of the skin of face
The glossy probability graph of the dark figure of skin, wherein include each pixel in the dark figure of the skin of face in the glossy probability graph
Glossy probability；
Divide module, for being partitioned into glossy region from the skin of face region based on the glossy probability graph.
Fourth aspect, the embodiment of the present application also provide a kind of readable storage medium storing program for executing, are stored thereon with computer program, described
Computer program, which is performed, realizes above-mentioned glossy region segmentation method.
In terms of existing technologies, the application has the advantages that
Glossy region segmentation method, device and mobile terminal provided by the embodiments of the present application, by being mentioned from target image
Skin of face region is taken, and obtains the corresponding skin of face in skin of face region and secretly schemes, then, based on default hyper parameter and face
The dark figure of skin establishes the Gauss model of the dark figure of skin of face, and is analyzed by Gauss model the dark figure of skin of face, obtains
The glossy probability graph of the dark figure of skin of face, finally, being partitioned into glossy region from skin of face region based on glossy probability graph.By
This, can effectively be avoided glossy erroneous detection caused by environment light, improve the accuracy of glossy region segmentation.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the flow diagram of glossy region segmentation method provided by the embodiments of the present application；
Fig. 2 is the flow diagram for each sub-steps that step S210 shown in Fig. 1 includes；
Fig. 3 is the functional block diagram of glossy region segmentation device provided by the embodiments of the present application；
Fig. 4 is the structural representation frame of the mobile terminal provided by the embodiments of the present application for above-mentioned glossy region segmentation method
Figure.
Icon: 100- mobile terminal；110- bus；120- processor；130- storage medium；140- bus interface；150-
Network adapter；160- user interface；The glossy region segmentation device of 200-；210- extraction module；220- obtains module；230- mould
Type establishes module；240- analysis module；250- divides module.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Usually herein
The component of the embodiment of the present application described and illustrated in place's attached drawing can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiments herein provided in the accompanying drawings is not intended to limit below claimed
Scope of the present application, but be merely representative of the selected embodiment of the application.Based on the embodiment in the application, this field is common
Technical staff's all other embodiment obtained without creative labor belongs to the application protection
Range.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
Referring to Fig. 1, being a kind of flow diagram of glossy region segmentation method provided by the embodiments of the present application.It should say
Bright, glossy region segmentation method provided by the embodiments of the present application is not limitation with Fig. 1 and specific order as described below.Institute
The detailed process for stating method is as follows:
Step S210 extracts skin of face region from target image.
As an implementation, referring to Fig. 2, the step S210 can be realized by following sub-step:
Sub-step S211 carries out recognition of face to the target image, obtains human face region and multiple human face characteristic points.
Optionally, the present embodiment carries out recognition of face to the target image by facial feature points detection model, obtains
Human face region and multiple human face characteristic points.Wherein, which can be trained by deep learning, for example,
User can be trained by marking multiple human face characteristic points in training sample image and being input in deep learning model, most
After obtain the human face characteristic point detection model.It is special that the human face characteristic point detection model can carry out face to the image of each input
Sign point detection, exports multiple human face characteristic points, such as can be the coordinate of facial 108 positions, such as the corners of the mouth, canthus etc.,
With this come come the positioning that obtains facial positions.
Extraneous areas in the human face region is rejected according to the multiple human face characteristic point, is obtained by sub-step S212
Skin of face region.
Inventor has found under study for action, and some extraneous areas are generally comprised in facial area, these extraneous areas can be to rear
Continuous glossy region segmentation interferes, these extraneous areas may include face region, periocular area, facial fringe region, mouth
One of which or multiple combinations in all regions, nose week region.For example, may have eye shadow influence, face in periocular area
Portion's fringe region may have an influence of facial shade, mouth week region and nose week region may exist because caused by face
The influence of facial shade.
For this purpose, the height in the human face region can be extracted by multiple human face characteristic points obtained above in the present embodiment
Reliability area, high reliability area namely the skin of face region for weeding out above-mentioned extraneous areas utilize face characteristic in this way
Point chooses high reliability area and carries out subsequent glossy segmentation, and the robustness of algorithm can be improved, reduce shade, illumination etc. pair
The influence of glossy segmentation.
It is worth noting that in other embodiments, above-mentioned nothing can also be rejected using other image partition methods
Region is closed, such as can also directly be partitioned into above-mentioned skin of face area by a large amount of training sample training convolutional neural networks etc.
Domain.
Step S220 obtains the corresponding skin of face in the skin of face region and secretly schemes.
Since some strong bias lights will cause the bloom of face, existing glossy splitting scheme is primarily directed to whole
Facial area is modeled according to the feature of bloom to extract glossy region, but without for erroneous detection caused by environment light
Special processing is carried out, causes glossy false detection rate high, glossy region segmentation inaccuracy.For this purpose, inventor sends out in the course of the research
Existing, in the regional area of most non-skies, certain some pixel, which always has at least one Color Channel, has very low value,
In other words, the minimum value of the region luminous intensity is the number of a very little.
Based on above-mentioned analysis, inventor innovatively has found by obtaining the corresponding skin of face in the skin of face region
Dark figure, can effectively reduce influence of the environment light to glossy segmentation.
In detail, as an implementation, firstly, obtaining the rgb value of each pixel in the skin of face region,
Wherein, the rgb value includes R value, G value and B value.Rgb color mode is by red (R), green (G), blue (B) three colors
To obtain miscellaneous color, RGB is to represent red, green, blue three for the variation in channel and their mutual superpositions
The color in a channel.
After the rgb value for obtaining each pixel, the minimum value in the R value, the G value and the B value can be made
For each pixel dark map values namely each pixel dark map values DarkImage (i, j)=min ImageRGB (i,
j)}.Then, brightness processed is carried out to the skin of face region based on the dark map values of each pixel, obtains corresponding face
Skin is secretly schemed.For example, the skin of face region just has altogether 128*128 if the skin of face region is 128*128 size
(R, G, B), the dark map values of the pixel can be represented by taking Min (R, G, B) then, available after obtaining 128*128 dark map values
The corresponding skin of face in the skin of face region is secretly schemed.
Step S230 establishes the Gaussian mode of the dark figure of the skin of face based on default hyper parameter and the dark figure of the skin of face
Type.
As described above, obtaining each pixel in the dark figure of the skin of face first after obtaining the dark figure of skin of face
Pixel value, the calculated for pixel values for being then based on each pixel in the dark figure of the skin of face obtain in the dark figure of the skin of face
Pixel value mean value and pixel value variance, wherein pixel value mean value can be used as the desired value of Gauss model, and pixel value variance can
Using the standard deviation as Gauss model.Then, based on described in the default hyper parameter, pixel value mean value and the foundation of pixel value variance
The Gauss model of the dark figure of skin of face.
Wherein, default hyper parameter is the preset parameter being determined by experiment, and specific value can carry out really according to actual needs
It is fixed, it is not specifically limited herein.
Step S240 analyzes the dark figure of the skin of face by the Gauss model, obtains the skin of face
The glossy probability graph of dark figure.
In the present embodiment, each pixel in the dark figure of the skin of face can be calculated by the Gauss model of above-mentioned foundation
Glossy probability value, specific formula for calculation can be such that
Wherein, a, b are default hyper parameter, and μ is the pixel value mean value of the dark figure of the skin of face, and σ is the skin of face
The pixel value variance of dark figure, x are the pixel value of each pixel in the dark figure of the skin of face, and f (x) is the oil of each pixel
Light probability value, glossy probability value is bigger, and the surface pixel is that the probability in glossy region is bigger.
Then, the glossy probability of the dark figure of the skin of face can be obtained according to the glossy probability value of each pixel of calculating
Figure, it is partially glossy region which, which can be obtained in the skin of face region, based on glossy probability graph.
Step S250 is partitioned into glossy region from the skin of face region based on the glossy probability graph.
In this implementation, glossy area can be partitioned into from the skin of face region with predetermined probabilities threshold value by setting
Domain, that is, glossy probability can be searched according to the glossy probability graph from the skin of face region greater than predetermined probabilities threshold value
Each target pixel points, then each target pixel points region is divided from the skin of face region obtain it is glossy
Region.As a result, by avoiding glossy erroneous detection caused by environment light, the glossy region split in this way, accuracy is higher.
It is worth noting that above-mentioned predetermined probabilities threshold value can be configured according to the actual situation, the present embodiment does not make this
Concrete restriction.
Inventor also found that the above-mentioned glossy region being partitioned into includes multiple highlight areas in the course of the research, these are high
Some regions are glossy region in light region, but some regions are erroneous detection region caused by bias light.Therefore, although passing through acquisition
The corresponding skin of face in the skin of face region is secretly schemed, and can effectively reduce influence of the environment light to glossy segmentation, but on
State the glossy region being partitioned into still there is also the influence of bias light namely it is non-it is glossy caused by highlight area can also be divided out
Come.
Based on the studies above, inventor proposes following proposal to improve above-mentioned erroneous detection problem:
Firstly, the gradient of each pixel in each highlight area in the glossy region is calculated, to obtain each bloom
The average gradient of each pixel in region, wherein the gradient is the horizontal gradient of pixel and the amplitude of vertical gradient.It connects
, judge whether the average gradient of each pixel in each highlight area is less than predetermined gradient threshold value, obtains judging result.Most
Afterwards, the highlight area that average gradient is less than predetermined gradient threshold value is filtered out from the glossy region according to the judging result.
The error detection for dexterously eliminating glossy segmentation caused by environment light using gradient as a result, improves the essence of glossy partitioning algorithm
Accuracy.
Further, referring to Fig. 3, the embodiment of the present application also provides a kind of glossy region segmentation device 200, described device
May include:
Extraction module 210, for extracting skin of face region from target image.
Module 220 is obtained, is secretly schemed for obtaining the corresponding skin of face in the skin of face region.
Model building module 230, for establishing the skin of face based on default hyper parameter and the dark figure of the skin of face
The Gauss model of dark figure.
Analysis module 240 obtains the face for analyzing by the Gauss model the dark figure of the skin of face
The glossy probability graph of the dark figure of portion's skin, wherein include each pixel in the dark figure of the skin of face in the glossy probability graph
The glossy probability of point.
Divide module 250, for being partitioned into glossy region from the skin of face region based on the glossy probability graph.
It is understood that the concrete operation method of each functional module in the present embodiment can refer to above method embodiment
The detailed description of middle corresponding steps, it is no longer repeated herein.
Further, referring to Fig. 4, being the movement provided by the embodiments of the present application for above-mentioned glossy region segmentation method
A kind of structural schematic block diagram of terminal 100.In the present embodiment, the mobile terminal 100 can be made general total by bus 110
Wire body architecture is realized.According to the concrete application of mobile terminal 100 and overall design constraints condition, bus 110 may include
Any number of interconnection bus and bridge joint.Together by various circuit connections, these circuits include processor 120, deposit bus 110
Storage media 130 and bus interface 140.Optionally, bus interface 140 can be used by network adapter 150 etc. in mobile terminal 100
It is connected via bus 110.Network adapter 150 can be used for realizing the signal processing function of physical layer in mobile terminal 100, and lead to
It crosses antenna and realizes sending and receiving for radiofrequency signal.User interface 160 can connect external equipment, such as: keyboard, display,
Mouse or control stick etc..Bus 110 can also connect various other circuits, as timing source, peripheral equipment, voltage regulator or
Person's management circuit etc., these circuits are known in the art, therefore are no longer described in detail.
It can replace, mobile terminal 100 may also be configured to generic processing system, such as be commonly referred to as chip, the general place
Reason system includes: to provide the one or more microprocessors of processing function, and provide at least part of of storage medium 130
External memory, it is all these all to be linked together by external bus architecture and other support circuits.
Alternatively, following realize can be used in mobile terminal 100: having processor 120, bus interface 140, user
The ASIC (specific integrated circuit) of interface 160；And it is integrated at least part of the storage medium 130 in one single chip, or
Following realize can be used in person, mobile terminal 100: one or more FPGA (field programmable gate array), PLD are (programmable
Logical device), controller, state machine, gate logic, discrete hardware components, any other suitable circuit or be able to carry out this
Any combination of the circuit of various functions described in application in the whole text.
Wherein, processor 120 is responsible for management bus 110 and general processing (is stored on storage medium 130 including executing
Software).One or more general processors and/or application specific processor can be used to realize in processor 120.Processor 120
Example includes microprocessor, microcontroller, dsp processor and the other circuits for being able to carry out software.It should be by software broadly
It is construed to indicate instruction, data or any combination thereof, regardless of being called it as software, firmware, middleware, microcode, hard
Part description language or other.
Storage medium 130 is illustrated as separating with processor 120 in Fig. 4, however, those skilled in the art be easy to it is bright
White, storage medium 130 or its arbitrary portion can be located at except mobile terminal 100.For example, storage medium 130 may include
Transmission line, the carrier waveform modulated with data, and/or the computer product that separates with radio node, these media can be with
It is accessed by processor 120 by bus interface 140.Alternatively, storage medium 130 or its arbitrary portion can integrate everywhere
It manages in device 120, for example, it may be cache and/or general register.
Above-described embodiment can be performed in the processor 120, specifically, can store in the storage medium 130 described
Glossy region segmentation device 200, the processor 120 can be used for executing the glossy region segmentation device 200.
Further, the embodiment of the present application also provides a kind of nonvolatile computer storage media, the computer is deposited
Storage media is stored with computer executable instructions, which can be performed the oil in above-mentioned any means embodiment
Light region segmentation method.
In conclusion glossy region segmentation method, device and mobile terminal provided by the embodiments of the present application, by from target
Skin of face region is extracted in image, and obtains the corresponding skin of face in skin of face region and secretly schemes, then, based on default super ginseng
The several and dark figure of skin of face establishes the Gauss model of the dark figure of skin of face, and is divided by Gauss model the dark figure of skin of face
Analysis, obtains the glossy probability graph of the dark figure of skin of face, finally, being partitioned into from skin of face region based on glossy probability graph glossy
Region.Thereby, it is possible to effectively avoid glossy erroneous detection caused by environment light, the accuracy of glossy region segmentation is improved.
In embodiment provided herein, it should be understood that disclosed device and method, it can also be by other
Mode realize.Device and method embodiment described above is only schematical, for example, flow chart and frame in attached drawing
Figure shows the system frame in the cards of the system of multiple embodiments according to the application, method and computer program product
Structure, function and operation.In this regard, each box in flowchart or block diagram can represent a module, section or code
A part, a part of the module, section or code includes one or more for implementing the specified logical function
Executable instruction.It should also be noted that function marked in the box can also be with not in some implementations as replacement
It is same as the sequence marked in attached drawing generation.For example, two continuous boxes can actually be basically executed in parallel, they have
When can also execute in the opposite order, this depends on the function involved.It is also noted that in block diagram and or flow chart
Each box and the box in block diagram and or flow chart combination, can function or movement as defined in executing it is dedicated
Hardware based system realize, or can realize using a combination of dedicated hardware and computer instructions.
In addition, each functional module in each embodiment of the application can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It can replace, can be realized wholly or partly by software, hardware, firmware or any combination thereof.When
When using software realization, can entirely or partly it realize in the form of a computer program product.The computer program product
Including one or more computer instructions.It is all or part of when loading on computers and executing the computer program instructions
Ground is generated according to process or function described in the embodiment of the present application.The computer can be general purpose computer, special purpose computer,
Computer network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, or
Person is transmitted from a computer readable storage medium to another computer readable storage medium, for example, the computer instruction
Wired (such as coaxial cable, optical fiber, digital subscriber can be passed through from a web-site, computer, server or data center
Line (DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or data
It is transmitted at center.The computer readable storage medium can be any usable medium that computer can access and either wrap
The data storage devices such as electronic equipment, server, the data center integrated containing one or more usable mediums.The usable medium
It can be magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid-state
Hard disk Solid State Disk (SSD)) etc..
It should be noted that, in this document, term " including ", " including " or its any other variant are intended to non-row
Its property includes, so that the process, method, article or equipment for including a series of elements not only includes those elements, and
And further include the other elements being not explicitly listed, or further include for this process, method, article or equipment institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence " including one ... ", it is not excluded that including institute
State in the process, method, article or equipment of element that there is also other identical elements.
It is obvious to a person skilled in the art that the application is not limited to the details of above-mentioned exemplary embodiment, Er Qie
In the case where without departing substantially from spirit herein or essential characteristic, the application can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and scope of the present application is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included in the application.Any reference signs in the claims should not be construed as limiting the involved claims.
Claims (10)
1. a kind of glossy region segmentation method, which is characterized in that the described method includes:
Skin of face region is extracted from target image；
The corresponding skin of face in the skin of face region is obtained secretly to scheme；
The Gauss model of the dark figure of the skin of face is established based on default hyper parameter and the dark figure of the skin of face；
The dark figure of the skin of face is analyzed by the Gauss model, obtains the glossy probability of the dark figure of the skin of face
Figure, wherein include the glossy probability of each pixel in the dark figure of the skin of face in the glossy probability graph；
Glossy region is partitioned into from the skin of face region based on the glossy probability graph.
2. glossy region segmentation method according to claim 1, which is characterized in that described to extract face from target image
The step of skin area, comprising:
Recognition of face is carried out to the target image, obtains human face region and multiple human face characteristic points；
The extraneous areas in the human face region is rejected according to the multiple human face characteristic point, obtains skin of face region,
In, the extraneous areas includes face region, periocular area, facial fringe region, mouth week region, wherein one in nose week region
Kind or multiple combinations.
3. glossy region segmentation method according to claim 1, which is characterized in that described to obtain the skin of face region
The step of corresponding skin of face is secretly schemed, comprising:
Obtain the rgb value of each pixel in the skin of face region, wherein the rgb value includes R value, G value and B value；
Using the minimum value in the R value, the G value and the B value as the dark map values of each pixel；
Brightness processed is carried out to the skin of face region based on the dark map values of each pixel, it is dark to obtain corresponding skin of face
Figure.
4. glossy region segmentation method according to claim 1, which is characterized in that described based on default hyper parameter and described
The dark figure of skin of face establishes the step of Gauss model of the dark figure of the skin of face, comprising:
Obtain the pixel value of each pixel in the dark figure of the skin of face；
Calculated for pixel values based on each pixel in the dark figure of the skin of face obtains the pixel in the dark figure of the skin of face
It is worth mean value and pixel value variance；
The Gauss model of the dark figure of the skin of face is established based on the default hyper parameter, pixel value mean value and pixel value variance.
5. glossy region segmentation method according to claim 4, which is characterized in that it is described by the Gauss model to institute
State the step of dark figure of skin of face is analyzed, obtains the glossy probability graph of the dark figure of the skin of face, comprising:
The glossy probability value of each pixel in the dark figure of the skin of face is calculated by the Gauss model；
The glossy probability graph of the dark figure of the skin of face is obtained according to the glossy probability value of each pixel of calculating.
6. glossy region segmentation method according to claim 5, which is characterized in that described to be calculated by the Gauss model
The calculation formula of the glossy probability value of each pixel in the dark figure of skin of face are as follows:
Wherein, a, b are default hyper parameter, and μ is the pixel value mean value of the dark figure of the skin of face, and σ is that the skin of face is secretly schemed
Pixel value variance, x is the pixel value of each pixel in the dark figure of the skin of face, and f (x) is the glossy general of each pixel
Rate value.
7. glossy region segmentation method according to claim 1, which is characterized in that it is described based on the glossy probability graph from
The step of being partitioned into glossy region in the skin of face region, comprising:
It is each greater than predetermined probabilities threshold value that glossy probability is searched from the skin of face region according to the glossy probability graph
Target pixel points；
Each target pixel points region is divided from the skin of face region and obtains glossy region, wherein the oil
Light region includes multiple highlight areas.
8. glossy region segmentation method according to claim 7, which is characterized in that it is described will be where each target pixel points
Divide the step of obtaining glossy region from the skin of face region in region, further includes:
The gradient of each pixel in each highlight area in the glossy region is calculated, it is each in each highlight area to obtain
The average gradient of pixel, wherein the gradient is the horizontal gradient of pixel and the amplitude of vertical gradient；
Judge whether the average gradient of each pixel in each highlight area is less than predetermined gradient threshold value, obtains judging result；
The highlight area that average gradient is less than predetermined gradient threshold value is filtered out from the glossy region according to the judging result.
9. a kind of glossy region segmentation device, which is characterized in that described device includes:
Extraction module, for extracting skin of face region from target image；
Module is obtained, is secretly schemed for obtaining the corresponding skin of face in the skin of face region；
Model building module, for establishing the height of the dark figure of the skin of face based on default hyper parameter and the dark figure of the skin of face
This model；
Analysis module obtains the skin of face for analyzing by the Gauss model the dark figure of the skin of face
The glossy probability graph of dark figure, wherein include the oil of each pixel in the dark figure of the skin of face in the glossy probability graph
Light probability；
Divide module, for being partitioned into glossy region from the skin of face region based on the glossy probability graph.
10. a kind of mobile terminal, which is characterized in that the mobile terminal includes:
Storage medium；
Processor；And
Glossy region segmentation device, the glossy region segmentation device are stored in the storage medium and including by the processing
The software function module that device executes, described device include:
Extraction module, for extracting skin of face region from target image；
Module is obtained, is secretly schemed for obtaining the corresponding skin of face in the skin of face region；
Model building module, for establishing the height of the dark figure of the skin of face based on default hyper parameter and the dark figure of the skin of face
This model；
Analysis module obtains the skin of face for analyzing by the Gauss model the dark figure of the skin of face
The glossy probability graph of dark figure, wherein include the oil of each pixel in the dark figure of the skin of face in the glossy probability graph
Light probability；
Divide module, for being partitioned into glossy region from the skin of face region based on the glossy probability graph.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810865176.1A CN109146893B (en) | 2018-08-01 | 2018-08-01 | Oil light area segmentation method and device and mobile terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810865176.1A CN109146893B (en) | 2018-08-01 | 2018-08-01 | Oil light area segmentation method and device and mobile terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109146893A true CN109146893A (en) | 2019-01-04 |
| CN109146893B CN109146893B (en) | 2020-10-09 |
Family
ID=64798676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810865176.1A Active CN109146893B (en) | 2018-08-01 | 2018-08-01 | Oil light area segmentation method and device and mobile terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109146893B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022105270A1 (en) * | 2020-11-17 | 2022-05-27 | 北京达佳互联信息技术有限公司 | Image processing method and apparatus |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020579A (en) * | 2011-09-22 | 2013-04-03 | 上海银晨智能识别科技有限公司 | Face recognition method and system, and removing method and device for glasses frame in face image |
| US20150145257A1 (en) * | 2013-11-25 | 2015-05-28 | Bryan P. Hendricks | Energy generating apparatus for gas or liquid flowing conditions |
| CN105719234A (en) * | 2016-01-26 | 2016-06-29 | 厦门美图之家科技有限公司 | Automatic gloss removing method and system for face area and shooting terminal |
| CN107911625A (en) * | 2017-11-30 | 2018-04-13 | 广东欧珀移动通信有限公司 | Light measuring method, device, readable storage medium storing program for executing and computer equipment |
-
2018
- 2018-08-01 CN CN201810865176.1A patent/CN109146893B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020579A (en) * | 2011-09-22 | 2013-04-03 | 上海银晨智能识别科技有限公司 | Face recognition method and system, and removing method and device for glasses frame in face image |
| US20150145257A1 (en) * | 2013-11-25 | 2015-05-28 | Bryan P. Hendricks | Energy generating apparatus for gas or liquid flowing conditions |
| CN105719234A (en) * | 2016-01-26 | 2016-06-29 | 厦门美图之家科技有限公司 | Automatic gloss removing method and system for face area and shooting terminal |
| CN107911625A (en) * | 2017-11-30 | 2018-04-13 | 广东欧珀移动通信有限公司 | Light measuring method, device, readable storage medium storing program for executing and computer equipment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022105270A1 (en) * | 2020-11-17 | 2022-05-27 | 北京达佳互联信息技术有限公司 | Image processing method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109146893B (en) | 2020-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jiang et al. | Salient object detection: A discriminative regional feature integration approach | |
| CN107358242B (en) | Target area color identification method and device and monitoring terminal | |
| CN112215180B (en) | Living body detection method and device | |
| CN106557774B (en) | The method for real time tracking of multichannel core correlation filtering | |
| Agrawal et al. | Grape leaf disease detection and classification using multi-class support vector machine | |
| CN109960988A (en) | Image analysis method, device, electronic equipment and readable storage medium storing program for executing | |
| CN107644213A (en) | Video person extraction method and device | |
| CN109697416A (en) | A kind of video data handling procedure and relevant apparatus | |
| Aslan et al. | Benchmarking algorithms for food localization and semantic segmentation | |
| CN108229344A (en) | Image processing method and device, electronic equipment, computer program and storage medium | |
| CN108664838A (en) | Based on the monitoring scene pedestrian detection method end to end for improving RPN depth networks | |
| Cao et al. | Efficient saliency detection using convolutional neural networks with feature selection | |
| Ngugi et al. | A new approach to learning and recognizing leaf diseases from individual lesions using convolutional neural networks | |
| WO2022152009A1 (en) | Target detection method and apparatus, and device and storage medium | |
| CN112883902A (en) | Video detection method and device, electronic equipment and storage medium | |
| Kang et al. | A coarse-to-fine method for cloud detection in remote sensing images | |
| Wu et al. | Natural scene text detection by multi-scale adaptive color clustering and non-text filtering | |
| CN105631405B (en) | Traffic video intelligent recognition background modeling method based on Multilevel Block | |
| Huo et al. | Semisupervised learning based on a novel iterative optimization model for saliency detection | |
| Ge et al. | Coarse-to-fine foraminifera image segmentation through 3D and deep features | |
| Lee et al. | Tracking-by-segmentation using superpixel-wise neural network | |
| Wang et al. | Salient object detection by robust foreground and background seed selection | |
| CN110175500A (en) | Refer to vein comparison method, device, computer equipment and storage medium | |
| Liu et al. | Presentation attack detection for face in mobile phones | |
| CN112686122B (en) | Human body and shadow detection method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211209 Address after: 361100 568, No. 942, tonglong Second Road, torch high tech Zone (Xiang'an) Industrial Zone, Xiang'an District, Xiamen City, Fujian Province Patentee after: Xiamen Meitu Yifu Technology Co.,Ltd. Address before: B1f-089, Zone C, Huaxun building, software park, torch high tech Zone, Xiamen City, Fujian Province Patentee before: XIAMEN HOME MEITU TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |