CN109259528A - A kind of home furnishings intelligent mirror based on recognition of face and skin quality detection - Google Patents
A kind of home furnishings intelligent mirror based on recognition of face and skin quality detection Download PDFInfo
- Publication number
- CN109259528A CN109259528A CN201811140558.4A CN201811140558A CN109259528A CN 109259528 A CN109259528 A CN 109259528A CN 201811140558 A CN201811140558 A CN 201811140558A CN 109259528 A CN109259528 A CN 109259528A
- Authority
- CN
- China
- Prior art keywords
- face
- skin quality
- image
- module
- mirror
- 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
- 238000001514 detection method Methods 0.000 title claims description 27
- 238000000605 extraction Methods 0.000 claims description 21
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 230000001815 facial effect Effects 0.000 claims description 14
- 239000000049 pigment Substances 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 13
- 240000007651 Rubus glaucus Species 0.000 claims description 12
- 235000011034 Rubus glaucus Nutrition 0.000 claims description 12
- 235000009122 Rubus idaeus Nutrition 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 12
- 239000011148 porous material Substances 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 8
- 238000001303 quality assessment method Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 230000010339 dilation Effects 0.000 claims description 5
- 230000003862 health status Effects 0.000 claims description 5
- 230000000877 morphologic effect Effects 0.000 claims description 5
- 238000003708 edge detection Methods 0.000 claims description 4
- 230000036541 health Effects 0.000 claims description 4
- 230000000474 nursing effect Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims 1
- 239000002344 surface layer Substances 0.000 claims 1
- 230000008901 benefit Effects 0.000 abstract description 3
- 238000003745 diagnosis Methods 0.000 abstract 1
- 238000012423 maintenance Methods 0.000 abstract 1
- 239000000284 extract Substances 0.000 description 6
- 239000000463 material Substances 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47G—HOUSEHOLD OR TABLE EQUIPMENT
- A47G1/00—Mirrors; Picture frames or the like, e.g. provided with heating, lighting or ventilating means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/45—Analysis of texture based on statistical description of texture using co-occurrence matrix computation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Pathology (AREA)
- Computing Systems (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of home furnishings intelligent mirrors detected based on recognition of face and skin quality.The present invention includes fixed shell, display interface, camera, temperature sensor, control device；Fixed enclosure interior is provided with temperature sensor and control device；Display interface includes display screen and atom mirror, and the setting of atom mirror is external in set casing, and display screen is arranged in set casing body, is connected with control device, and be disposed adjacent with atom mirror；Display interface is shown information on atom mirror by the superposition of display screen and atom mirror using the principle of atom mirror Unidirectional transparent；By the control to display screen, so that front atom mirror is in general mirror state also or under mirror-state.Invention increases the practicabilities of mirror, it can be applied to the scenes such as parlor, bathroom, dressing table, off-line experience store, existing Intelligent mirror is compared on the market, have many advantages, such as recognition of face speed faster, can be carried out skin quality diagnosis, can provide the skin quality maintenance side of customization.
Description
Technical field
The present invention relates to artificial intelligence fields, and in particular, to a kind of household intelligence based on recognition of face and skin quality detection
It can mirror.
Background technique
In recent years, it as artificial intelligence is increasingly becoming the hot spot of academia's research, is led as artificial intelligence in bio-identification
The branch in domain, recognition of face are developed rapidly in recent years.Meanwhile skin detect in medicine, in terms of daily nursing gradually
It gets more and more people's extensive concerning.But current either face recognition device and skin quality detector all exist, and expensive, volume is big,
The poor disadvantage of globality greatly limits it and promotes and apply.
It is well known that mirror is ubiquitous in we live, almost everyone family can see mirror.However
Mirror has a single function at present, and would generally occupy sizable space.In view of people usually have the habit looked in the mirror, such as
The simple function of fruit energy beyond tradition mirror integrates the function of recognition of face and skin quality detection on mirror, and mirror display is allowed to use
Family needs the function and content seen to complete the diversification in role that mirror is lived from traditional life to Internet of Things, realizes the intelligence of mirror
Energy household and integral device miniaturization, it will further promote people's lives quality.
Summary of the invention
The purpose of the present invention is disclose a kind of home furnishings intelligent mirror based on recognition of face and skin quality detection, the smart mirror
Son imparts the completely new definition of mirror, so that mirror is no longer the article with simple function, improves the practicability of mirror.
The present invention includes fixed shell, display interface, camera, temperature sensor, control device；Temperature sensor and control
In fixed enclosure interior, fixed shell is to provide physical structure as the carrier of mirror other parts in rectangle for device setting processed
Support；The display interface includes the atom mirror of display screen and one piece of Unidirectional transparent, and the setting of atom mirror is external in set casing, is made
For a rectangle lateral wall of fixed shell, display screen is arranged in set casing body, is connected with control device, and with atom mirror phase
Neighbour's setting；Display interface is shown information by the superposition of display screen and atom mirror using the principle of atom mirror Unidirectional transparent
On atom mirror；By the control to display screen, so that front atom mirror is in general mirror state also or under intellectual status, intelligence
Weather, time, face skin quality health information can be shown when state.
The control device, for handling, calculating, analyzing camera and the collected information of temperature sensor.
Further, the control device, including the detection of raspberry pie, information display module, face recognition module, skin quality
Module and power module.
The information display module, the result information handled for showing raspberry pie, content include: weather, when
Between, face skin quality health status and related advisory；
The raspberry pie, for handling the information of face recognition module, skin quality detection module；
The face recognition module wakes up screen by the face information that camera is read, increases user experience；
The skin quality detection module, analyzes the face information that camera is read, is handled, and user's skin quality is returned
It evaluates situation and corresponding nursing is suggested；
The power module is that the modules of Intelligent mirror are powered.
Further, the skin quality detection module, including image capture module, face image processing module, face skin
Matter index extraction module, face skin quality assessment indicator system model module.
The image capture module acquires information by the camera of Intelligent mirror；
The face image processing module, handles picture, obtains the digital information of face；Including each to different
Property filter module, binary image module, edge detection module, gray level co-occurrence matrixes.
The anisotropic filtering module, for being smoothed to image, specifically, in the pretreatment rank of image
Section replaces gaussian filtering using the anisotropic filtering that perona and malik is proposed, it is intended to reduce picture noise, and not go
Except the pith in picture material.
The binary image module, for specifically, being acquired according to camera to pigment and oil content characteristic processing
High definition picture carries out binaryzation to the space S of image and the space V using hsv color space, by the luminance information of image from figure
It is separated in the color of piece, and then light and shade region is divided, then use maximum variance between clusters by the background in image with before
Scenic spot separates.By both the above method, brightly painted image can be converted to corresponding binaryzation black white image, with after an action of the bowels
The continuous image for skin surface carries out pigment and oil content is analyzed.
The edge detection module specifically, by the data of gray value of image, is used for extracting pore image
Canny operator finds the violent pixel region of grey scale change in image, and it is the edge of pore that, which there is great probability in such region,
Region just can extract the corresponding region area information of pore and distributed intelligence in this way.
The gray level co-occurrence matrixes, for extracting image texture information, specifically, the degree of roughness of skin is mainly by right
Skin image textural characteristics are analyzed, and this programme uses gray level co-occurrence matrixes at a distance of for δ=(two gray scales of Δ x, Δ y)
The joint probability distribution that pixel occurs is analyzed, and the Gray Correlation of two pixels (x1, y1), (x2, y2) is shown.I.e.
Make to exist and changes frequent texture, the textural characteristics for reflecting image that can also quantify.
The face skin quality index extraction module specifically includes color spy for extracting the key index of face skin quality
It seeks peace textural characteristics, color characteristic includes oil content index and pigment index again, and textural characteristics include degree of roughness, is handled；
The face skin quality assessment indicator system model module, skin quality detection module is according to face skin quality index extraction mould
Color characteristic, textural characteristics and the degree of roughness that block extracts, obtain evaluation result in conjunction with existing face skin quality assessment indicator system.
Further, the skin quality index extraction module, including oil content and pigment index extraction module, degree of roughness refer to
Mark extraction module.
The oil content and pigment index extraction module represents oil content, dark-coloured generation by simple logical operation with light tone
Table pigment.The area ratio of face, calculated numerical value are accounted for by it respectively, corresponding corresponding indication range determines color characteristic
Index.
The degree of roughness index extraction module, the data after image to be carried out to binaryzation, carries out at morphological dilations
Reason.After expansion, the region of texture pixel, thus available more parts of observation data can be expanded.If morphological dilations 2
It is secondary, then possess 2 width texture image datas, is compared with the image of expansion number corresponding in image library.Use angular second moment
(ASM), entropy (ENT), contrast (CON) are weighted analysis, consider further that the pore size comprehensive analysis of Canny operator extraction,
Finally obtain face degree of roughness grade.
Further, the face skin quality assessment indicator system model module, using based on the improved BP of genetic algorithm
Neural network carries out overall merit classification, weight and threshold value of the GA-BP neural network for initial value existing for BP neural network
Randomness is adjusted, it is intended to which weight and threshold value in Optimized BP Neural Network determine weight by the principle of " hereditary trial and error "
And threshold value further specifically includes: image pattern module extracts skin quality Index module, GA operator threshold value and weight
Module, BP neural network classification grading module, optimal opinion rating determining module.
Processing step are as follows: obtain a large amount of image pattern first, carry out image procossing with the above method, extract corresponding
Skin quality index is calculated the weight and threshold value of BP neural network by GA operator, is classified using BP neural network.It again will classification
Standard as primary standard, then to pattern sample repeat before operation, until the mean square error (MSE) in each opinion rating
When being both less than certain statistical appraisal value with mean value (Mean), optimal opinion rating scheme is determined, according to opinion rating scheme
The scheme for formulating skin care, by display interface to user feedback.
The advantages and benefits of the present invention are:
The present invention is detected as two big core functions using Internet of Things as theory, with recognition of face and skin quality, improves traditional mirror
The single disadvantage of subfunction, increases the practicability of mirror, improves the convenience of user, realizes the smart home of mirror.
The present invention use raspberry pie, be a singlechip microcomputer based on Linux, for handle face recognition module,
The information of skin quality detection module.Using the low energy consumption of raspberry pie, mobile portability, there are the characteristics such as a variety of GPIO interfaces, is protecting
When hindering the working performance of mirror, moreover it is possible to which the weight and volume for reducing mirror substantially increase the practicability of Intelligent mirror.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention without any creative labor, may be used also for those of ordinary skill in the art
To obtain other attached drawings according to these attached drawings.
Fig. 1 (a) is modular structure schematic diagram in the embodiment of the present invention；
Fig. 1 (b) is schematic structural view of the invention；
Fig. 1 (c) is structure of the invention cross-sectional view；
Fig. 2 is a kind of Intelligent mirror interface and interactive schematic diagram in the embodiment of the present invention；
Fig. 3 is a kind of block flow diagram of the skin quality detection module of Intelligent mirror in the embodiment of the present invention；
Fig. 4 is the block flow diagram of the skin quality appraisement system in the embodiment of the present invention in skin quality detection module.
Specific embodiment
With reference to the accompanying drawing and embodiment, the present invention is made a detailed description.
As shown in Fig. 1 (a) -1 (c), a kind of Intelligent mirror based on recognition of face and skin quality detection provided by the invention, packet
Include fixed shell 4, display interface, camera 1, temperature sensor, control device 5；Temperature sensor and the setting of control device 5 exist
Inside fixed shell 4, fixed shell 4 is, as the carrier of mirror other parts, to provide physical structure support in rectangle；It is described
Display interface include display screen 3 and one piece of Unidirectional transparent atom mirror 2, the setting of atom mirror 2 is outside fixed shell 4, as solid
One rectangle lateral wall of fixed shell 4, the setting of display screen 3 are connected in fixed shell 4 with control device, and with atom mirror 2
It is disposed adjacent；Display interface is shown information by the superposition of display screen 3 and atom mirror 2 using the principle of atom mirror Unidirectional transparent
Show on atom mirror 2；By the control to display screen, so that front atom mirror is in general mirror state also or intellectual status
Under, when intellectual status, shows weather, time, face skin quality health information.
One of embodiment of the present invention Intelligent mirror display interface is used for the display of face and information, as shown in Figure 2.It adopts
It uses the atom mirror of single side light transmission as material, one piece of screen being connected with raspberry pie is installed behind atom mirror, by right
The control of screen, so that front atom mirror is in general mirror state also or under " mirror " state.When camera captures people
When picture, screen is waken up, the content of screen is enable to show on mirror.The content of screen includes: that weather, time, face skin quality are strong
Health situation and related advisory.
In order to cover mirror by too many information, cause to put the cart before the horse, the present invention is on mirror interface, in mirror
Interface in terms of, it is desirable to mirror does not need to be covered by too many information, causes to put the cart before the horse.So intending on " mirror "
Using clock plate and weather plate.For clock plate and weather plate, opened using HTML, CSS, Javascript
Hair.In the design of api interface, mesh the first two plate uses openweathermap.org and iCal Calender.Pass through
The two api interfaces can transmit the messages such as the weather on the same day and detect the face skin quality health status obtained as 3 with skin quality
Independent panel displays are on mirror.
Control device of the invention, including raspberry pie, information display module, face recognition module, skin quality detection module, electricity
Source module.Wherein, recognition of face uses OpenCV as main exploitation software.Specific step: it Step1: collects corresponding
Training sample (including face information) is as passive image；Step2: batch reading facial image is converted into gray level image and is instructed
Practice, extracts corresponding face characteristic information in passive image；Step3: join the face characteristic information of training result as feature
Number, is stored in feature space；Step4: the image that camera is captured carries out feature extraction, by the spy in feature and training set
Sign parameter compares, to carry out Face datection.
In above-mentioned embodiment, the face characteristic information extracted is stored in corresponding library.Real-time
In the Face datection stage, we only need that corresponding library is called to carry out feature identification, can complete the module of recognition of face.?
In OpenCV, realized using the function findHaarFeatures in the library SimpleCV in Python.When camera captures
When image, which is stored in raspberry pie and is handled, call findHarrFeatures function, carried out portrait and catch
It catches.The feature of portrait will not wake up " mirror " if it does not exist.It if capturing portrait feature, then can wake up " mirror ", be easy
Meet the requirement handled in real time.And handled by frame skipping techniques and multicore, the frame number of image is improved, the delay effect of identification frame is improved
It answers.
In image processing stage, frame skipping techniques are used after considering the too low reason of frame number, i.e., all without the picture of each frame
It is detected accordingly, but it is primary every the identification of several frames, and image recognition is completed using the multicore process of raspberry pie.
Face skin quality detection, by image capture module, face image processing module, face skin quality index extraction module,
Face skin quality evaluation index model realization detects the skin quality of face.Since skin quality detection needs more careful picture material,
High-pixel camera (more than 500w pixel) is needed to carry out Image Acquisition.To greatest extent guarantee picture material integrality and can
Operability.After obtaining facial image, in the pretreatment stage of image, filtered using the anisotropy that perona and malik is proposed
Wave replaces gaussian filtering, it is intended to reduce picture noise, and not remove the pith in picture material.Due to the place of image
Environmental factor it is complicated, it is understood that there may be the problems such as illumination disorder, complex environment, thus image is performed corresponding processing, be dashed forward
The content to be analyzed out, binaryzation is usually as one step of key in image pre-processing.
According to the high definition picture that camera acquires, two-value is carried out to the space S of image and the space V using hsv color space
Change, the luminance information of image is separated from the color of picture, and then light and shade region is divided, then using side between maximum kind
Poor method separates background and the foreground zone in image.By both the above method, can convert brightly painted image to accordingly
Binaryzation black white image, so that the subsequent image for skin surface carries out pigment and oil content is analyzed, algorithm steps: Step1:
Read the RGB image in image；Step2: it is converted into hsv color space；Step3: the space color space S and the space V are carried out
Binaryzation operation；Step4: logical operation is carried out for the S and V of extraction, corresponding numerical value is marked to handle image.
By the data of gray value of image, the violent pixel region of grey scale change in image is found with Canny operator, this
It is the fringe region of pore that, which there is great probability in the region of sample, just can extract the corresponding region area information of pore and distribution in this way
Information.The degree of roughness of skin mainly by analyzing skin image textural characteristics, uses gray level co-occurrence matrixes at a distance of for δ
=(joint probability distribution that two gray-scale pixels of Δ x, Δ y) occur is analyzed, show two pixels (x1, y1),
The Gray Correlation of (x2, y2).Change frequent texture even if existing, the textural characteristics for reflecting image that can also quantify.
After being analyzed by last point it is found that converting HSV space for smoothed out image, wherein S indicates saturation degree, V table
Show brightness.S is more saturated closer to 1 expression color, and V indicates that color is brighter closer to 1.Pass through simple logical operation, light tone generation
Table oil content, dead color represent pigment.The area ratio of face is accounted for by it respectively, calculated numerical value corresponds to corresponding indication range,
Determine the index of color characteristic.
Since biggish change will not occur in the texture train of thought short time of face, often with the variation of time, embody
In the variation of texture train of thought thickness.Then image is carried out the data after binaryzation by this programme, carries out morphological dilations processing.By
After expansion, the region of texture pixel, thus available more parts of observation data can be expanded.If morphological dilations 2 times, then
Possess 2 width texture image datas, is compared with the image of expansion number corresponding in image library.Using angular second moment (ASM),
Entropy (ENT), contrast (CON) are weighted analysis, consider further that the pore size comprehensive analysis of Canny operator extraction, final to obtain
Face degree of roughness grade out.
Face skin quality evaluation model is used to be carried out based on the improved BP neural network of genetic algorithm (GA-BP neural network)
Overall merit classification, GA-BP neural network adjust the weight of initial value existing for BP neural network and the randomness of threshold value
It is whole, it is intended to which that weight and threshold value in Optimized BP Neural Network determine weight and threshold value by the principle of " hereditary trial and error ".
As shown in figure 4, obtaining a large amount of image pattern first, image procossing is carried out with the above method, is extracted corresponding
Skin quality index is calculated the weight and threshold value of BP neural network by GA operator, is classified using BP neural network.It again will classification
Standard as primary standard, then to pattern sample repeat before operation, until the mean square error (MSE) in each opinion rating
When being both less than certain statistical appraisal value with mean value (Mean), optimal opinion rating scheme is determined.
Hereafter it is reference with optimal case, the index of input picture is extracted, is compared, finally obtains corresponding skin
Matter health status, and nursing suggestion and safeguard procedures are provided to user.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although referring to before
Stating embodiment, invention is explained in detail, those skilled in the art should understand that: it still can be to preceding
Technical solution documented by each embodiment is stated to modify or equivalent replacement of some of the technical features；And these
It modifies or replaces, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (6)
1. a kind of home furnishings intelligent mirror based on recognition of face and skin quality detection, it is characterised in that including fixed shell (4), display
Interface, camera (1), temperature sensor, control device (5)；Temperature sensor and control device (5) setting are in fixed shell
(4) internal, fixed shell (4) are, as the carrier of mirror other parts, to provide physical structure support in rectangle；Described is aobvious
Show that interface includes the atom mirror (2) of display screen (3) and one piece of Unidirectional transparent, atom mirror (2) setting is being fixed shell (4) outside, made
For a rectangle lateral wall of fixed shell (4), display screen (3) setting is connected in fixed shell (4) with control device, and
It is disposed adjacent with atom mirror (2)；Display interface utilizes the principle of atom mirror Unidirectional transparent, passes through display screen (3) and atom mirror (2)
Superposition, information is shown on atom mirror (2)；By the control to display screen, so that front atom mirror is in general mirror
State is also or under intellectual status, and when intellectual status shows weather, time, face skin quality health information.
2. a kind of home furnishings intelligent mirror based on recognition of face and skin quality detection according to claim 1, it is characterised in that
The control device, including raspberry pie, information display module, face recognition module, skin quality detection module and power module；
The information display module, the result information for handling raspberry pie pass through face skin quality health status plate
Block, clock plate and weather plate show on a display screen, result information include: weather, the time, face skin quality health status and
Related advisory；
The raspberry pie, the information for handling face recognition module, skin quality detection module is read；
The face recognition module wakes up screen by the face information that camera is read；
The skin quality detection module, analyzes the face information that camera is read, is handled, and the evaluation of user's skin quality is returned
Situation and corresponding nursing are suggested；
The power module is that the modules of Intelligent mirror are powered.
3. a kind of home furnishings intelligent mirror based on recognition of face and skin quality detection according to claim 1, it is characterised in that
The skin quality detection module, including image capture module, face image processing module, face skin quality index extraction module, people
Face skin quality assessment indicator system model module；
The image capture module acquires facial image by the camera of Intelligent mirror；
The face image processing module handles the facial image of image capture module acquisition, obtains the number of face
Word information；
The face skin quality index extraction module is used to extract the key index of face skin quality, specifically includes color characteristic and line
Feature is managed, color characteristic includes oil content index and pigment index again, and textural characteristics include degree of roughness, is handled；
The face skin quality assessment indicator system model module, the color extracted according to face skin quality index extraction module are special
Sign, textural characteristics and degree of roughness, obtain evaluation result in conjunction with existing face skin quality assessment indicator system.
4. a kind of home furnishings intelligent mirror based on recognition of face and skin quality detection according to claim 3, it is characterised in that
The face image processing module includes that anisotropic filtering module, binary image module, edge detection module, gray scale are total
Raw matrix；
The anisotropic filtering module is for being smoothed facial image, specifically: using perona and malik
The anisotropic filtering of proposition replaces gaussian filtering, obtains facial image I；
The binary image module is used for pigment and oil content characteristic processing, specifically: to facial image I, utilizing HSV face
The colour space carries out binaryzation to the space S of facial image I and the space V, by the luminance information of facial image I from facial image I
It is separated in color, and then light and shade region is divided, then use maximum variance between clusters by the background in facial image I with before
Scenic spot separates；To convert corresponding binaryzation black white image II for brightly painted facial image I, so as to subsequent for skin
The image on skin surface layer carries out pigment and oil content analysis；
The edge detection module is for extracting pore image, specifically: according to the gray value number of binaryzation black white image II
According to the violent pixel region of grey scale change in image being found with Canny operator, to extract pore corresponding region area letter
Breath and distributed intelligence；
The gray level co-occurrence matrixes are for extracting image texture characteristic, and specifically: the degree of roughness of skin is mainly by skin
Image texture characteristic is analyzed；For the gray value data of binaryzation black white image II, using gray level co-occurrence matrixes to apart
For δ=(joint probability distribution that two gray-scale pixels of Δ x, Δ y) occur is analyzed, show two pixels (x1,
Y1), the Gray Correlation of (x2, y2), thus the quantitative textural characteristics for reflecting image.
5. a kind of home furnishings intelligent mirror based on recognition of face and skin quality detection according to claim 4, it is characterised in that
Face skin quality index extraction module is implemented as follows:
Color feature extracted includes the extraction of oil content index and pigment index, by simple logic operation, with light tone represent oil content,
Dead color represents pigment, calculates separately oil content index and pigment index accounts for the area ratio of face, according to area the corresponding finger of ratio
Range is marked, determines the index of color characteristic；
The extraction for being extracted as degree of roughness index of textural characteristics carries out at n times morphological dilations binaryzation black white image II
Reason obtains N texture images, and the texture image that will acquire is compared with the image of expansion number corresponding in image library, uses
Angular second moment (ASM), entropy (ENT), contrast (CON) are weighted, in conjunction with comprehensive point of pore size of Canny operator extraction
Analysis, finally obtains face degree of roughness grade.
6. a kind of home furnishings intelligent mirror based on recognition of face and skin quality detection according to claim 5, it is characterised in that
The realization process of face skin quality assessment indicator system model module is as follows: a large amount of facial image sample is 1. collected, by face figure
Decent is used as passive image, by face image processing module and face skin quality index extraction module to face images sample
This is handled, and corresponding face skin quality index is extracted；2. referring to using based on the improved BP neural network of genetic algorithm to skin quality
Mark carries out overall merit classification；1. and 2. 3. carrying out step to facial image sample again using classification results as primary standard
Operation, until the mean square error (MSE) and mean value (Mean) in Process of Comprehensive Assessment are determined as when being both less than statistical appraisal value
Optimal assessment indicator system model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811140558.4A CN109259528A (en) | 2018-09-28 | 2018-09-28 | A kind of home furnishings intelligent mirror based on recognition of face and skin quality detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811140558.4A CN109259528A (en) | 2018-09-28 | 2018-09-28 | A kind of home furnishings intelligent mirror based on recognition of face and skin quality detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109259528A true CN109259528A (en) | 2019-01-25 |
Family
ID=65199096
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811140558.4A Pending CN109259528A (en) | 2018-09-28 | 2018-09-28 | A kind of home furnishings intelligent mirror based on recognition of face and skin quality detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109259528A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110097973A (en) * | 2019-05-10 | 2019-08-06 | 重庆邮电大学 | The prediction algorithm of human health index based on genetic algorithm and BP neural network |
| CN110215044A (en) * | 2019-05-19 | 2019-09-10 | 厦门知晓物联技术服务有限公司 | A kind of intelligence makeups mirror |
| CN110398899A (en) * | 2019-06-24 | 2019-11-01 | 杭州电子科技大学 | A kind of intelligent home control system based on Kinect |
| CN112581383A (en) * | 2020-11-19 | 2021-03-30 | 北京迈格威科技有限公司 | Image processing method, apparatus, device and medium |
| CN113298841A (en) * | 2021-07-26 | 2021-08-24 | 四川大学华西医院 | Skin oil typing method, computer equipment, system and storage medium |
| CN113347259A (en) * | 2021-06-07 | 2021-09-03 | 湖北经济学院 | Intelligent magic mirror based on Internet of things |
| CN113342095A (en) * | 2021-05-19 | 2021-09-03 | 浙江工业大学 | Intelligent mirror control system based on raspberry group |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104223858A (en) * | 2014-09-28 | 2014-12-24 | 广州视睿电子科技有限公司 | Self-recognition intelligent mirror |
| CN106983493A (en) * | 2017-03-04 | 2017-07-28 | 武汉嫦娥医学抗衰机器人股份有限公司 | A kind of skin image processing method based on three spectrum |
| CN107280350A (en) * | 2017-06-12 | 2017-10-24 | 美的集团股份有限公司 | Control method, control device, Intelligent mirror and computer-readable recording medium |
| CN206946300U (en) * | 2017-07-31 | 2018-01-30 | 天津农学院 | Intelligent mirror control system for smart home |
| CN207096740U (en) * | 2017-06-30 | 2018-03-13 | 天津职业技术师范大学 | A kind of SCM Based Intelligent mirror |
-
2018
- 2018-09-28 CN CN201811140558.4A patent/CN109259528A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104223858A (en) * | 2014-09-28 | 2014-12-24 | 广州视睿电子科技有限公司 | Self-recognition intelligent mirror |
| CN106983493A (en) * | 2017-03-04 | 2017-07-28 | 武汉嫦娥医学抗衰机器人股份有限公司 | A kind of skin image processing method based on three spectrum |
| CN107280350A (en) * | 2017-06-12 | 2017-10-24 | 美的集团股份有限公司 | Control method, control device, Intelligent mirror and computer-readable recording medium |
| CN207096740U (en) * | 2017-06-30 | 2018-03-13 | 天津职业技术师范大学 | A kind of SCM Based Intelligent mirror |
| CN206946300U (en) * | 2017-07-31 | 2018-01-30 | 天津农学院 | Intelligent mirror control system for smart home |
Non-Patent Citations (3)
| Title |
|---|
| PING-CHENG: "Illumination-Robust Face Recognition Using an Efficient Mirror Technique" * |
| 李丹;陈潼升;杨国文;莫朝胜;: "基于Raspberry Pi的智能"魔镜"" * |
| 李丹;陈潼升;杨国文;莫朝胜;: "基于Raspberry Pi的智能"魔镜"", 现代交际, no. 06 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110097973A (en) * | 2019-05-10 | 2019-08-06 | 重庆邮电大学 | The prediction algorithm of human health index based on genetic algorithm and BP neural network |
| CN110215044A (en) * | 2019-05-19 | 2019-09-10 | 厦门知晓物联技术服务有限公司 | A kind of intelligence makeups mirror |
| CN110398899A (en) * | 2019-06-24 | 2019-11-01 | 杭州电子科技大学 | A kind of intelligent home control system based on Kinect |
| CN112581383A (en) * | 2020-11-19 | 2021-03-30 | 北京迈格威科技有限公司 | Image processing method, apparatus, device and medium |
| CN113342095A (en) * | 2021-05-19 | 2021-09-03 | 浙江工业大学 | Intelligent mirror control system based on raspberry group |
| CN113347259A (en) * | 2021-06-07 | 2021-09-03 | 湖北经济学院 | Intelligent magic mirror based on Internet of things |
| CN113298841A (en) * | 2021-07-26 | 2021-08-24 | 四川大学华西医院 | Skin oil typing method, computer equipment, system and storage medium |
| CN113298841B (en) * | 2021-07-26 | 2024-01-12 | 四川大学华西医院 | Skin oil parting method, computer equipment, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109259528A (en) | A kind of home furnishings intelligent mirror based on recognition of face and skin quality detection | |
| CN108446617B (en) | Side face interference resistant rapid human face detection method | |
| CN106874871B (en) | Living body face double-camera identification method and identification device | |
| CN101359365B (en) | Iris positioning method based on maximum between-class variance and gray scale information | |
| Le et al. | An automated fish counting algorithm in aquaculture based on image processing | |
| TW202014984A (en) | Image processing method, electronic device, and storage medium | |
| CN109886153B (en) | Real-time face detection method based on deep convolutional neural network | |
| CN108459785A (en) | A kind of video multi-scale visualization method and exchange method | |
| CN110929593A (en) | Real-time significance pedestrian detection method based on detail distinguishing and distinguishing | |
| CN109190475A (en) | A kind of recognition of face network and pedestrian identify network cooperating training method again | |
| CN104484652A (en) | Method for fingerprint recognition | |
| CN109360179A (en) | A kind of image interfusion method, device and readable storage medium storing program for executing | |
| CN110032932A (en) | A kind of human posture recognition method based on video processing and decision tree given threshold | |
| CN109886170A (en) | A kind of identification of oncomelania intelligent measurement and statistical system | |
| Khan et al. | Comparitive study of tree counting algorithms in dense and sparse vegetative regions | |
| Reddy et al. | Texton based shape features on local binary pattern for age classification | |
| CN111080585A (en) | Intelligent analysis method for detecting reflective region of colon endoscope | |
| KR101174103B1 (en) | A face recognition method of Mathematics pattern analysis for muscloskeletal in basics | |
| CN109241932A (en) | A kind of thermal infrared human motion recognition method based on movement variogram phase property | |
| CN112488165A (en) | Infrared pedestrian identification method and system based on deep learning model | |
| CN103824058A (en) | Face recognition system and method based on locally distributed linear embedding algorithm | |
| Zhang | Image enhancement method based on deep learning | |
| CN110147764A (en) | A kind of static gesture identification method based on machine learning | |
| Shengze et al. | Research based on the HSV humanoid robot soccer image processing | |
| CN107463864A (en) | A kind of face identification system of binding sequence image super-resolution rebuilding |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190125 |