CN104808701A - Cloud vision-based automatic eye make-up apparatus - Google Patents
Cloud vision-based automatic eye make-up apparatus Download PDFInfo
- Publication number
- CN104808701A CN104808701A CN201510217644.0A CN201510217644A CN104808701A CN 104808701 A CN104808701 A CN 104808701A CN 201510217644 A CN201510217644 A CN 201510217644A CN 104808701 A CN104808701 A CN 104808701A
- Authority
- CN
- China
- Prior art keywords
- eye
- machine
- cloud vision
- stepper motor
- automatic eye
- 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
Landscapes
- Processing Or Creating Images (AREA)
Abstract
A cloud vision-based automatic eye make-up apparatus with a control mechanism serving as a basic system comprises a camera, an LED fill light, a cloud control chip in which recognition and eye defining algorithms are loaded, a microcontroller, a wireless transmission module, a USB (universal serial bus) interface, an eyeliner, an eyelash puller clamp, a step motor and the like. By the use of the cloud vision-based automatic eye make-up apparatus, the problem that manual eye making-up is time consuming, unprofessional and the like is solved; a single setting is available for multiple usages, multiple settings are also available, and a service mode can change as required; the terminal needs of beauty pursuers are met; the cloud vision-based automatic eye make-up apparatus is finally applicable to worldwide popularization as a living necessity, and great economic and social benefits can be created.
Description
Technical field
The invention belongs to small household appliances manufacture and robot and make-up technique field, relate to the automatic eye adornment machine based on cloud vision.
Background technology
Make up and have a long history in the world, no matter in film & TV circles or daily life, a quotidian daily behavior has been become for most of crowd.And, along with the development of society, also more and more pay attention to the experience and tempering of make-up technique.Specialty make up artist industry is also more and more valued by the people, but most of crowd had both had no time also do not have money to go to engage professional to make up for oneself.And in whole facial makeup, eyes are windows of soul, the large and intelligential dressing presented by eyes is definitely regarded as successful makeups.
As the saying goes: being only of being applicable to is best, and the words is equally applicable to an adornment.Everyone shape of face is unique, and we can not just think of the good-looking all right of picture, must find oneself eye adornment applicable.The step of general eye adornment is as follows:
1. be first end adornment, what perfect dressing definitely can not be ignored is exactly end adornment, and the mode of upper foundation emulsion has a lot, and suggestion uses medium size brush slowly to sweep and opens more docile exquisiteness.
2. and then, stamp shade on eyelid, face can be made so more three-dimensional small and exquisite.
3. then we start the part of an adornment, large-area bottoming on eye socket first, use natural color relation passable.
4. in the scope then indicated in the drawings gently sweep the light green eye shadow of last layer, emphatically around informer.
5. then, sweep out gently in the place of lower informer with the excellent eye shadow dipping a little of tiny informer.
6. and then, gently sweep with more further blackish green eye shadow in the scope indicated in the drawings, especially focus on the part of a tail.
7. be then exactly informer, informer adopts the form of half bag, and upper informer describes by fine and smooth mode, lower informer extends from ball portions backward, links together triangle place and the upper informer at canthus.
Finally, the rouge of sweeping frivolous one deck pink colour at Albinus' muscle place just completes whole dressing.
In order to the effect of professional make up artist can be reached, and be convenient for people to oneself save time and professional make-up technique can be reached.The present invention have developed the automatic eye adornment machine based on cloud vision, first will have recognition device, can analyze the shape of face of user.So the chip internal of this device has the face recognizer in recognition of face, sets the design proposal of several ocular form in advance, and can be presented on screen by USB interface or wireless transport module.And rule of thumb calculate, which type of eye cosmetic and makeup color etc. is this shape of face be applicable to, also can self-defining and selection.Extracted the location of user's eye by camera, the width of automatic eye adornment machine can set different model, and user is close to face.Consist of: camera, load and identify and the high in the clouds control chip of eye adornment algorithm, wireless transport module, USB interface, eyeliner brush, draw eye liner pen, horizontal stepper motor, longitudinal stepper motor.Namely be made up of microcontroller, sensor assembly, power module, driver module, support unit, eye adornment unit etc.
Summary of the invention
The object of this invention is to provide the automatic eye adornment machine based on cloud vision.
Above-mentioned object is realized by following technical scheme:
Based on the automatic eye adornment machine of cloud vision, system based on control gear, camera, LED light supplement lamp, loading identification and retouch the high in the clouds control chip of an algorithm, microcontroller, wireless transport module, USB interface, eyeliner brush, pull out eye folder, the equipment compositions such as stepper motor, design the automatic eye adornment machine achieved based on cloud vision.The mankind can be solved by this invention and retouch time-consuming, unprofessional etc. the effect that eye makes up, both once can set and repeatedly use, and can also repeatedly set, the using forestland become with needing.Meet the terminal requirements of the personage that likes to be beautiful, finally can world-wide deployment, thus become the necessity of life, huge economic benefit and social benefit can be produced.It is characterized in that equipment to be placed in face front, capture face by camera, the image gathered is analyzed, is analyzed the eye shape of suitable face by built-in algorithms, and carry out manual confirmation by display screen or mobile phone terminal; Equipment is placed on the position of eye and eye, video camera is located existing ocular hair position again, and afterwards by ACK button, beginning intelligence is retouched a machine and retouched eye.Concrete process is: camera collection information passes to algorithm chip, microcontroller receives locating information rear drive motor and carries out fine setting location to not having pen, eye pen moves repeatedly according to the eye shape of positional information to setting, it is dark that such as eye peak place draws, form the different effect of the depth by the motion frequency, thus form stereovision.
interface of the present invention can include display and man-machine operation interface, and display is mobile phone, flat-type touch-control or non-touch-control.User draws ocular form by display predetermined analog, determines whether needed for user, also can sets itself ocular form.
This intelligence is retouched a machine and is provided with abnormal break key, if any any exception by pressing one-key emergent stop, avoids abnormal conditions to occur.
This intelligence is retouched a machine and is provided with pince-nez stationary installation, equipment can be fixed on the first half of face as wearing glasses, also can carry out auxiliary positioning by head restraint, also gently can press stationary installation by hand.
This intelligence is retouched a machine and is used step as follows:
1. starting outfit, face's picture is carried out the overall situation and captures by video camera, shown by the display terminal of equipment again, and by wireless by picture uploading to high in the clouds, analyzed by the face profile of high in the clouds algoritic module to user, and the pattern of intelligent selection and expert judgments local can be carried out to the ocular form being applicable to this shape of face replace, be shown to user, and the ocular form chosen is sent to device storage district.
2., after equipment being fixed on head, accurately located by the ocular hair position of video camera to user.This is located through rim detection and aberration is distinguished and accurately can be located ocular hair.Just be positioned on eye, so do not have other to disturb, so vision positioning method is not only simple but also reliable.
3. by eye starting point, eye peak, 3, eye tail after being analyzed in conjunction with methods such as 3 ratios and eye overshooting go out by image procossing, starting point is done from eye peak, controlling motor drives Miao Yan mechanism repeatedly to retouch painting according to positional information propelling movement eye pen, and by frequency converter to step-length and frequency setting empirical value, thus effect that is three-dimensional and level can be obtained.
4. drive folder eye device to be pulled out by unnecessary ocular hair by motor.
Algorithm of penciling one's eyebrows in high in the clouds is mainly following description: how to obtain dissimilar feature or attribute:
1. geometric attribute, emphasis is calculating shape facility by supercilium coordinate position.
2. globality: before PCA (principal component analysis (PCA)) being applied to one group of available sample, each independently image cropping is become the region of standard.Be mainly (i) and abandon background pixels as much as possible (ii) part identical with side face restriction to all frontal faces, comprise the hair that the most significant facial characteristics (forehead, nose, mouth and chin etc.) (iii) removes side image as much as possible.Also contrast standard should be used to process the image taken in uncontrolled environment.The image finally cut out is converted to gray level image and is expressed as one dimension tandem image row vector.
3. texture description, sums up the zonule textural characteristics of whole image or coordinate surrounding.
All geometric attributes and most texture properties come from the position of the key point of supercilium image.For image, active shape model (ASM) technology is used automatically to calculate 26 key points.
These descriptors sum up textural characteristics or the coordinate peripheral regions of whole image.
The invariable rotary symbiosis (RIC-LBP) of adjacent LBPs extends classical local binary patterns (LBPs), is intended to improve illumination invariant, as the term suggests, rotational invariance.In preliminary test, RIC-LBP is better than the expansion of other LBPs.For each gray level image, extract the proper vector that size is 136.
Gal cypress filtrator is widely used in rim detection and texture analysis.By each coordinate of the center calculation of window, its standardized width is the distance of between two anchor points 15%.Found through experiments the degree of accuracy that this width can optimize RIGF feature.
SIFT(Scale invariant features transform) be a kind of popular topography's descriptor, in fact, it has become the standard of computer vision aspect, such as object identification, image registration and CBIR etc.Therefore, the descriptor based on SIFT has been used to characterize the near zone of the coordinate extracted in independent image.SIFT acts on monochrome image, carries out unifying constant convergent-divergent and rotation, and the constant Affine distortion of part and illumination variation.Recently, have dissimilar based on color descriptor to different colours scheme application SIFT algorithm, this is to improve illumination unchangeability and ability to see things in their true light
].The present invention is in order to lower color descriptor:
1) opponent-SIFT, changes the color space based on opposition drawn by rgb color space
.
，
，
。
2) C-SIFT, based on the reflective spectral property of color constancy model and colored mechanism, front two parts can be represented by the opponent-SIFT color space of standard substantially,
.Part III is intensity channel.
3) rg-SIFT, it is made up of r and g two SIFT descriptors, and the colourity of r, g can be drawn by RGB color model,
.
4) rgb-SIFT is the SIFT descriptor independently calculated by RGB passage.
C-SIFT and rg-SIFT is that intensity is constant, and the light source colour change of opponent-SIFT and rgb-SIFT to different images is also constant.All colours descriptor is evaluated as independent SIFT descriptor by calculating, and its size is 128, for being associated with in simple vector by the corresponding color model of each passage.By the preliminary test on data set, color descriptor is better than the SIFT of standard.Independent consideration often plants color descriptor, and C-SIFT can provide optimum precision.When a kind of color descriptor and other attributes together divide into groups, result is that C-SIFT is again a shade better, and therefore, selection C-SIFT is the reference descriptor of imaging experiments.And C-SIFT is only that intensity is constant, this makes it be particularly suitable for processing the image obtained in controlled environment.When the image processed has less or not restriction when taking, as image, descriptor provides higher unchangeability, and this can provide better result.
accompanying drawing illustrates:
Fig. 1 is the automatic eye adornment machine based on cloud vision, 1) and Miao Yan mechanism 2) longitudinal stepper motor 3) horizontal stepper motor 4) camera 5) power module 6) pince-nez device 7) algorithm chip module 8) wireless transport module 9) Usb interface
10) frequency converter
Fig. 2 is for retouching a mechanism map, 11) eye powder groove 12) eye brush 13) folder mascara
beneficial effect
:
1) cost-saving, replace manual work, reach professional results;
2) intellectual analysis face characteristic, selects different ocular forms;
3) virtual effect display, also can once select, Reusability;
4) hi-Fix, particle is little, and stereovision is strong;
5) equipment is small and exquisite, is easy to carry about with one, easy to use, all can use whenever and wherever possible;
6) intelligent equipment, leads industry tap.Future society will be a wisdom Urban Age, and a lot of work can go to replace with intelligent machine.The research and development of this product, will cause a new change;
embodiment:
Above-mentioned object is realized by following technical scheme:
1) based on the automatic eye adornment machine of cloud vision, its composition comprises: system based on control gear, camera, LED light supplement lamp, loading identification and retouch the dsp chip of an algorithm, microcontroller, wireless transport module, USB interface, eyeliner brush, folder eye device, stepper motor equipment forms, and designs the automatic eye adornment machine achieved based on cloud vision.
2) according to claim 1, based on the automatic eye adornment machine of cloud vision, it is characterized in that by loading the dsp chip identifying and retouch an algorithm, microcontroller, wireless transport module, the board of USB interface and power interface composition, stepper motor is connected with micro controller, and LED light supplement lamp is connected with video camera, video camera is connected with micro controller, folder eyebrow device is connected with stepper motor, and pen core of penciling one's eyebrows is connected with stepper motor, and frequency converter is connected with stepper motor.
3) according to claim 1 and 2, based on the automatic eye adornment machine of cloud vision, being provided with abnormal break key, if any any exception by pressing one-key emergent stop, avoiding abnormal conditions to occur.
4) according to claim 1,2,3, this intelligence is retouched a machine and is provided with pince-nez stationary installation, equipment can be fixed on the first half of face as wearing glasses, also can carry out auxiliary positioning by head restraint.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.
Claims (4)
1. based on the automatic eye adornment machine of cloud vision, its composition comprises: system based on control gear, camera, LED light supplement lamp, loading identification and retouch the dsp chip of an algorithm, microcontroller, wireless transport module, USB interface, eyeliner brush, folder eye device, stepper motor equipment forms, and designs the automatic eye adornment machine achieved based on cloud vision.
2. according to claim 1, based on the automatic eye adornment machine of cloud vision, it is characterized in that by loading the dsp chip identifying and retouch an algorithm, microcontroller, wireless transport module, the board of USB interface and power interface composition, stepper motor is connected with micro controller, and LED light supplement lamp is connected with video camera, video camera is connected with micro controller, folder eyebrow device is connected with stepper motor, and pen core of penciling one's eyebrows is connected with stepper motor, and frequency converter is connected with stepper motor.
3., according to claim 1 and 2, based on the automatic eye adornment machine of cloud vision, being provided with abnormal break key, if any any exception by pressing one-key emergent stop, avoiding abnormal conditions to occur.
4. according to claim 1,2,3, this intelligence is retouched a machine and is provided with pince-nez stationary installation, equipment can be fixed on the first half of face as wearing glasses, also can carry out auxiliary positioning by head restraint.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510217644.0A CN104808701A (en) | 2015-05-04 | 2015-05-04 | Cloud vision-based automatic eye make-up apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510217644.0A CN104808701A (en) | 2015-05-04 | 2015-05-04 | Cloud vision-based automatic eye make-up apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104808701A true CN104808701A (en) | 2015-07-29 |
Family
ID=53693617
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510217644.0A Pending CN104808701A (en) | 2015-05-04 | 2015-05-04 | Cloud vision-based automatic eye make-up apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104808701A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112347979A (en) * | 2020-11-24 | 2021-02-09 | 郑州阿帕斯科技有限公司 | Eye line drawing method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040078278A1 (en) * | 2000-06-26 | 2004-04-22 | Christophe Dauga | Cosmetic treatment method and device, in particular for care, make-up or colouring |
| JP2008017936A (en) * | 2006-07-11 | 2008-01-31 | Fujifilm Corp | Makeup apparatus and method |
| CN101657155A (en) * | 2007-02-11 | 2010-02-24 | 里克·B·耶格尔 | Be used for providing the system and method for analog image by cosmetic monitoring |
| US20120067364A1 (en) * | 2010-09-21 | 2012-03-22 | Zong Jing Investment, Inc. | Facial make-up application machine and make-up application method using the same |
| CN102693288A (en) * | 2012-04-27 | 2012-09-26 | 上海申视汽车新技术有限公司 | Automatic recommendation method for makeup scheme |
| CN102708575A (en) * | 2012-05-17 | 2012-10-03 | 彭强 | Daily makeup design method and system based on face feature region recognition |
| CN203913827U (en) * | 2014-04-16 | 2014-11-05 | 赖柄霖 | The portable machine of automatically making up |
| CN104331564A (en) * | 2014-11-10 | 2015-02-04 | 深圳市中兴移动通信有限公司 | Dressing instruction method based on terminal equipment and terminal equipment |
-
2015
- 2015-05-04 CN CN201510217644.0A patent/CN104808701A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040078278A1 (en) * | 2000-06-26 | 2004-04-22 | Christophe Dauga | Cosmetic treatment method and device, in particular for care, make-up or colouring |
| JP2008017936A (en) * | 2006-07-11 | 2008-01-31 | Fujifilm Corp | Makeup apparatus and method |
| CN101657155A (en) * | 2007-02-11 | 2010-02-24 | 里克·B·耶格尔 | Be used for providing the system and method for analog image by cosmetic monitoring |
| US20120067364A1 (en) * | 2010-09-21 | 2012-03-22 | Zong Jing Investment, Inc. | Facial make-up application machine and make-up application method using the same |
| CN102693288A (en) * | 2012-04-27 | 2012-09-26 | 上海申视汽车新技术有限公司 | Automatic recommendation method for makeup scheme |
| CN102708575A (en) * | 2012-05-17 | 2012-10-03 | 彭强 | Daily makeup design method and system based on face feature region recognition |
| CN203913827U (en) * | 2014-04-16 | 2014-11-05 | 赖柄霖 | The portable machine of automatically making up |
| CN104331564A (en) * | 2014-11-10 | 2015-02-04 | 深圳市中兴移动通信有限公司 | Dressing instruction method based on terminal equipment and terminal equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112347979A (en) * | 2020-11-24 | 2021-02-09 | 郑州阿帕斯科技有限公司 | Eye line drawing method and device |
| CN112347979B (en) * | 2020-11-24 | 2024-03-15 | 郑州阿帕斯科技有限公司 | Eye line drawing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108765273B (en) | Virtual face-lifting method and device for face photographing | |
| US9589178B2 (en) | Image processing with facial features | |
| US10799010B2 (en) | Makeup application assist device and makeup application assist method | |
| JP3912834B2 (en) | Face image correction method, makeup simulation method, makeup method, makeup support apparatus, and foundation transfer film | |
| CN101779218B (en) | Makeup simulation system, makeup simulation apparatus, makeup simulation method, and makeup simulation program | |
| US20100189357A1 (en) | Method and device for the virtual simulation of a sequence of video images | |
| CN109952594A (en) | Image processing method, device, terminal and storage medium | |
| JP5261586B2 (en) | Makeup simulation system, makeup simulation apparatus, makeup simulation method, and makeup simulation program | |
| CN107153805A (en) | Customize makeups servicing unit and method | |
| WO2021197186A1 (en) | Auxiliary makeup method, terminal device, storage medium and program product | |
| CN104599297B (en) | A kind of image processing method for going up blush automatically to face | |
| CN103995911A (en) | Beauty matching method and system based on intelligent information terminal | |
| CN104898704A (en) | Intelligent eyebrow penciling machine device based on DSP image processing | |
| US11776187B2 (en) | Digital makeup artist | |
| US20220202168A1 (en) | Digital makeup palette | |
| CN108921856A (en) | Image cropping method, apparatus, electronic equipment and computer readable storage medium | |
| US11961169B2 (en) | Digital makeup artist | |
| Wang et al. | Learnable Stroke Models for Example-based Portrait Painting. | |
| CN116648733A (en) | Method and system for extracting color from facial image | |
| CN102737152A (en) | Cosmetic comparison method | |
| CN117157673A (en) | Method and system for forming personalized 3D head and face models | |
| CN104808701A (en) | Cloud vision-based automatic eye make-up apparatus | |
| CN111652792B (en) | Local processing method, live broadcasting method, device, equipment and storage medium for image | |
| CN106101524A (en) | A kind of intelligence is penciled one's eyebrows machine automatically | |
| CN105809612A (en) | Method of transforming image into expression and intelligent terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150729 |