CN109408940A - A kind of identification of hair style and restoring method, apparatus and system - Google Patents
A kind of identification of hair style and restoring method, apparatus and system Download PDFInfo
- Publication number
- CN109408940A CN109408940A CN201811215759.6A CN201811215759A CN109408940A CN 109408940 A CN109408940 A CN 109408940A CN 201811215759 A CN201811215759 A CN 201811215759A CN 109408940 A CN109408940 A CN 109408940A
- Authority
- CN
- China
- Prior art keywords
- hair style
- hair
- fringe
- image
- identify
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
Abstract
The present invention relates to software field, especially a kind of hair style identification and restoring method, apparatus and system.Its method includes the following steps: to obtain the hair style image that user uploads;Identify the hair style feature in the hair style image;Material is matched in cartoon material database according to the hair style feature;Cartooning's hairstyle image is combined using the material.Invention can accurately identify hair style dimension and vivid reduction, and in conjunction with face reduction technique, consumer need to only upload positive self-timer can the seen every a hair style of low cost trial.Stylist can be helped to be embodied the hair style design thinking for embodying oneself, if consumer can be helped clearly to perceive again oneself has selected what kind of effect is this hair style can have, meet and see hair style, publish type, examination hair style, play the needs of hair style, to have the function that consumer is helped to carry out consumption decision.
Description
Technical field
The present invention relates to software field, especially a kind of hair style identification and restoring method, apparatus and system.
Background technique
The objectively demand of the generally existing hairdressing of consumer, while very risk of the maximum probability in the presence of failure of restyling the hair, consumption
Person's concern is not only whether popular this hair style is good-looking, focus more on whether be that this hair style is placed on good-looking on one's body.
And stylist often directly shows consumer with reference to figure with hair style during hair style design, it is difficult to visually show and set out
Tool of the type with consumer is as effect.
Summary of the invention
For the defects in the prior art, the present invention provides a kind of identification of hair style and restoring method, apparatus and system, it is intended to
Overcome the deficiencies in the prior art.
To achieve the goals above, it in a first aspect, hair style provided by the invention identifies and restoring method, including walks as follows
It is rapid: to obtain the hair style image that user uploads;Identify the hair style feature in the hair style image;According to the hair style feature in cartoon
Material is matched in material database;Cartooning's hairstyle image is combined using the material.
Second aspect, hair style provided by the present invention identification and reduction apparatus, including processor, input equipment, output are set
Standby and memory, the processor, input equipment, output equipment and memory are connected with each other, wherein the memory is for depositing
Computer program is stored up, the computer program includes program instruction, and the processor is configured for calling described program instruction,
Execute such as method of any of claims 1-8.
The third aspect, hair style provided by the present invention identify and go back original system, including hair style identification and reduction apparatus and shifting
Dynamic equipment, the hair style identification are connect with reduction apparatus with the mobile device communication;The hair style identification is held with reduction apparatus
Method described in the row first embodiment of the present invention.
The beneficial effects of the present invention are: the present invention can accurately identify hair style dimension and image reduction, also in conjunction with face
Former technology, consumer need to only upload positive self-timer can the seen every a hair style of low cost trial.It can help stylist
It is embodied and embodies oneself hair style design thinking, and if consumer can be helped clearly to perceive oneself selected this hair style energy
Enough there is what kind of effect, meets and see hair style, publish type, examination hair style, play the needs of hair style, help consumer to consume to reach
The effect of decision.
Detailed description of the invention
Fig. 1 is the flow chart of first embodiment of the invention hair style identification and restoring method;
Fig. 2 is the flow chart of second embodiment of the invention hair style identification and restoring method;
Fig. 3 is the schematic diagram of third embodiment of the invention hair style identification and reduction apparatus;
Fig. 4 is the block diagram that fourth embodiment of the invention hair style identifies and goes back original system.
Specific embodiment
Specific embodiments of the present invention are described more fully below, it should be noted that the embodiments described herein is served only for illustrating
Illustrate, is not intended to restrict the invention.In the following description, in order to provide a thorough understanding of the present invention, a large amount of spies are elaborated
Determine details.It will be apparent, however, to one skilled in the art that: this hair need not be carried out using these specific details
It is bright.In other instances, in order to avoid obscuring the present invention, well known circuit, software or method are not specifically described.
Throughout the specification, meaning is referred to " one embodiment ", " embodiment ", " example " or " example "
: a particular feature, structure, or characteristic described in conjunction with this embodiment or example is comprised at least one embodiment of the invention.
Therefore, the phrase " in one embodiment ", " in embodiment ", " example " occurred in each place of the whole instruction
Or " example " is not necessarily all referring to the same embodiment or example.Furthermore, it is possible in any suitable combination and or sub-portfolio will be specific
Feature, structure or characteristic combine in one or more embodiment or examples.In addition, those of ordinary skill in the art should manage
Solution, diagram is provided to the purpose of explanation provided herein, and diagram is not necessarily drawn to scale.
As shown in Figure 1, the identification of hair style shown in the first embodiment of the present invention and restoring method, including walk as follows
It is rapid:
S101 obtains the hair style image that user uploads.
Wherein, user can be shot by mobile device and upload the hair style image in angle front, clean background.The shifting
Dynamic equipment includes but is not limited to mobile phone, computer or other Intelligent hardwares with camera function.In other one embodiment
In, it can also be by directly acquiring hair style image from electron album.
S102 identifies the hair style feature in the hair style image.
In the present embodiment, the hair style feature includes but is not limited to 7 basic dimensions, i.e. hair length, shape, fringe, hair tail
Direction, texture, weight sense and color development.It should be appreciated that the hair style feature can also in other one or some embodiments
To be increased or be reduced according to practical situation, it is all contained among protection scope of the present invention.
S103 matches material in cartoon material database according to the hair style feature.
It include the cartoon material of various hair styles in the present embodiment, in the cartoon material database, it only need to be in the cartoon element
It carries out matching to find in material that the step of matching material can be completed with the highest material of hair style characteristic similarity.
S104 combines cartooning's hairstyle image using the material.
The material that all matchings are completed, which is combined, can be obtained cartooning's hairstyle image, and pass through sample size and element
Material amount is continuously increased, and improves the accuracy and similarity of the identification of hair style feature, has stronger scalability.
As shown in Fig. 2, the identification of hair style shown in the second embodiment of the present invention and restoring method, the hair style identification
It is suitable for hair style identification and reduction apparatus with restoring method;The hair style identification and restoring method, include the following steps:
S201, identification obtain the hair style image that user uploads with reduction apparatus.
In the present embodiment, the identification is server or server cluster with reduction apparatus.In other one embodiment
In, the figure image cartoon reduction apparatus can also be the calculating with hair style image processing function and reception output function
Machine equipment.
S202, identification identify the hair style feature in the hair style image with reduction apparatus.
It include but is not limited to following 7 basic dimensions when identifying the hair style feature in hair style image, i.e., in the present embodiment
Send out length, shape, fringe, hair tail direction, texture, weight sense and color development.Further, have when identifying above-mentioned 7 basic dimensions
Body includes:
(1) identify hair style in the hair style image sends out length long, and hair length is divided into bob, middle hair and long hair;It is described
Bob is divided into ultrashort hair, bob on ear, bob in ear, and the middle hair is divided into short bob, long bob and middle hair, during the long hair is divided into
Long hair, long hair, overlength hair.
(2) identify the shape of hair style in the hair style image, and according to hair style entirety outer contour shape be divided into up-side down triangle,
Diamond shape and triangle.
(3) identify that the fringe of hair style in the hair style image whether there is.Fringe if it does not exist, then according to hair parting position
Set, be divided into point and side point;Fringe if it exists then identifies the profile of the fringe, and is divided into fringe according to the profile of fringe
Neat fringe, tiltedly divide fringe, in divide fringe, air Liu Haihe sawtooth fringe.And identify the length of the fringe, and according to Liu
Fringe is divided into short fringe, fringe on eyebrow by the length in sea, fringe under Liu Haihe eyebrow in eyebrow.
(4) it identifies the hair tail bending direction of hair style in the hair style image, and will be sent out according to the hair tail bending direction of hair style
Tail direction is divided into internal buckle, nature and turns up.
(5) identify the length of hair style in the hair style image, and according to the length of hair style by texture be divided into texture bob class,
Class and texture long hair class are sent out in texture;The texture bob class includes straight hair, weak volume and strong volume, and hair class includes straight in the texture
Hair, half volume, middle volume and rouleau, the texture long hair class include straight hair, half volume, middle volume, big volume and rouleau.
(6) identify the form of hair style in the hair style image, and according to the form of hair style by weight sense be divided into air sense, from
Right and solid sense.
(7) to the hair style extracted region rgb value split in the hair style image, and file to corresponding color development.
S203, identification establish cartoon material database with reduction apparatus.
Wherein, the cartoon material is by the way that all different hair style dimensions are disassembled and classified, and by all hair styles
Feature abstraction comes out, and carries out mathematicization expression, by carrying out full prison learning training to a large amount of pictures, obtains a series of target ginsengs
Number, such as the shape and length of the global shape of hair, the length of hair style, fringe, curly headed degree.According to each dimension of output
As a result, transferring corresponding cartooning's material in material database, it is finally combined into a complete hair style.
S204, identification match material in cartoon material database according to the hair style feature with reduction apparatus.
It, only need to be in the card due to including the cartoon material of various hair styles in the cartoon material database in the present embodiment
It carries out matching in logical material to find with the highest material of hair style characteristic similarity, the step of matching material can be completed.
S205, identification combine cartooning's hairstyle image using the material with reduction apparatus.
Further, the material that all matchings are completed is combined can be obtained cartooning's hairstyle image.
S206, identification synthesize complete cartooning's figure image with reduction apparatus.
In one embodiment, a series of coordinating and unifyings such as autonomous personage's shape of face, body, clothes, background can also be cooperated
Material, the complete figure image that can finally synthesize.Wherein, it is carrying out being combined into face's figure using personage's shape of face material group
The process of picture is specific can include:
Obtain the image that user uploads.User can be shot by mobile device and upload angle front, uniform illumination, table
The image that feelings are normal, face are unobstructed.The mobile device include but is not limited to mobile phone, computer or other with camera function
Intelligent hardware.It, can also be by directly acquiring image in the electron album of slave mobile device in other one embodiment.
Identify the face characteristic in described image.The gender of personage, year in described image are identified by face recognition technology
Age, shape of face, the colour of skin, upper presiding judge's degree and face position.And the face parameter of face in image calculate and is abstracted classification.Into
One step obtains face and shape of face data, such as the length, type, size of shape of face;Width, height, dog-ear of eyebrow etc..
Establish cartoon material database.Classification of type is carried out to five official rank features of face, and extracts most A representative Sample,
Sample is cartoonized, a cartoon material database is established, further, the present invention can be by collecting true man personage's sample, by people
Face is divided by 5 shape of face, eyebrow, eyes, nose, lip dimensions, and wherein eyebrow chooses 12 features, and shape of face chooses 4
Feature amounts to 48 kinds of five features.By face recognition technology, identify the facial characteristics of face in image, in order to cartoon
Material database is compared.
The face characteristic and the material in pre-established cartoon material database are compared.Utilize the highest element of similarity
Material and described image restore personage's cartoon character.In one embodiment, the personage in image that certain user uploads passes through identification
It is afterwards rectangular face, face is long and big, eyebrow belongs to that eyebrow is low, eyebrow is wide and without dog-ear;It is then that user search number is by matching rule
Rectangular face, face be long and big, eyebrow belongs to that eyebrow is low, eyebrow is wide and the base map material without dog-ear, and by the self-timer of base map and user with one
Fixed weighted value mutually merges, and finally obtains the face material for having both similarity and stylization;Further, mutually melted
When conjunction, it can carry out selecting different weighted values according to the actual needs, here just without limitation.At other one or some
In embodiment, the five features of the personage in image uploaded due to user is all different, but the step of when being restored
All with it is aforementioned substantially similar, herein with regard to no longer being enumerated one by one.
Cartooning's figure image is returned into mobile device.By the way that complete figure image is returned to mobile device supply
User checks, can be really achieved the effect that user tries hair style.
As shown in figure 3, the identification of hair style shown in the third embodiment of the present invention and reduction apparatus, including input equipment
41, processor 42, memory 43 and output equipment 44, the processor 42, input equipment 41, output equipment 44 and memory 43
It is connected with each other by communication bus 40, for the memory 43 for storing computer program, the computer program includes program
Instruction, the processor 42 are configured for calling described program instruction;Further, the processor 42 is configured for adjusting
With described program instruction execution following steps:
Processor 42 obtains the hair style image that user uploads by input equipment 41.
Processor 42 identifies the hair style feature in the hair style image.Include when identifying the hair style feature in hair style image
But following 7 basic dimensions are not limited to, i.e. hair length, shape, fringe, hair tail direction, texture, weight sense and color development.Further,
It is specifically included when identifying above-mentioned 7 basic dimensions:
(1) identify hair style in the hair style image sends out length long, and hair length is divided into bob, middle hair and long hair;It is described
Bob is divided into ultrashort hair, bob on ear, bob in ear, and the middle hair is divided into short bob, long bob and middle hair, during the long hair is divided into
Long hair, long hair, overlength hair.
(2) identify the shape of hair style in the hair style image, and according to hair style entirety outer contour shape be divided into up-side down triangle,
Diamond shape and triangle.
(3) identify that the fringe of hair style in the hair style image whether there is.Fringe if it does not exist, then according to hair parting position
Set, be divided into point and side point;Fringe if it exists then identifies the profile of the fringe, and is divided into fringe according to the profile of fringe
Neat fringe, tiltedly divide fringe, in divide fringe, air Liu Haihe sawtooth fringe.And identify the length of the fringe, and according to Liu
Fringe is divided into short fringe, fringe on eyebrow by the length in sea, fringe under Liu Haihe eyebrow in eyebrow.
(4) it identifies the hair tail bending direction of hair style in the hair style image, and will be sent out according to the hair tail bending direction of hair style
Tail direction is divided into internal buckle, nature and turns up.
(5) identify the length of hair style in the hair style image, and according to the length of hair style by texture be divided into texture bob class,
Class and texture long hair class are sent out in texture;The texture bob class includes straight hair, weak volume and strong volume, and hair class includes straight in the texture
Hair, half volume, middle volume and rouleau, the texture long hair class include straight hair, half volume, middle volume, big volume and rouleau.
(6) identify the form of hair style in the hair style image, and according to the form of hair style by weight sense be divided into air sense, from
Right and solid sense.
(7) to the hair style extracted region rgb value split in the hair style image, and file to corresponding color development.
Processor 42 establishes cartoon material database.Wherein, the cartoon material is by carrying out to all different hair style dimensions
Dismantling and classification, and all hair style feature abstractions are come out, mathematicization expression is carried out, by carrying out full prison study to a large amount of pictures
Training, obtains a series of target components, such as the global shape of hair, the length of hair style, the shape of fringe and length, curly headed
Degree etc..According to each dimension of output as a result, transferring corresponding cartooning's material in material database, finally it is combined into a complete
Hair style.
Processor 42 matches material in cartoon material database according to the hair style feature.Due to being wrapped in the cartoon material database
Included the cartoon material of various hair styles, only need to be carried out in the cartoon material matching find it is highest with hair style characteristic similarity
The step of matching material can be completed in material.
Processor 42 utilizes material combination cartooning hairstyle image.Further, the material all matchings completed
It is combined and cartooning's hairstyle image can be obtained.
Processor 42 synthesizes complete cartooning's figure image.In one embodiment, autonomous personage's face can also be cooperated
A series of material of coordinating and unifyings such as type, body, clothes, background, the complete figure image that can finally synthesize.Wherein,
It is specific in the process for be combined by personage's shape of face material group face's cartoon image can include:
Obtain the image that user uploads.User can be shot by mobile device and upload angle front, uniform illumination, table
The image that feelings are normal, face are unobstructed.The mobile device include but is not limited to mobile phone, computer or other with camera function
Intelligent hardware.It, can also be by directly acquiring image in the electron album of slave mobile device in other one embodiment.
Identify the face characteristic in described image.The gender of personage, year in described image are identified by face recognition technology
Age, shape of face, the colour of skin, upper presiding judge's degree and face position.And the face parameter of face in image calculate and is abstracted classification.Into
One step obtains face and shape of face data, such as the length, type, size of shape of face;Width, height, dog-ear of eyebrow etc..
Establish cartoon material database.Classification of type is carried out to five official rank features of face, and extracts most A representative Sample,
Sample is cartoonized, a cartoon material database is established, further, the present invention can be by collecting true man personage's sample, by people
Face is divided by 5 shape of face, eyebrow, eyes, nose, lip dimensions, and wherein eyebrow chooses 12 features, and shape of face chooses 4
Feature amounts to 48 kinds of five features.By face recognition technology, identify the facial characteristics of face in image, in order to cartoon
Material database is compared.
The face characteristic and the material in pre-established cartoon material database are compared.Utilize the highest element of similarity
Material and described image restore personage's cartoon character.In one embodiment, the personage in image that certain user uploads passes through identification
It is afterwards rectangular face, face is long and big, eyebrow belongs to that eyebrow is low, eyebrow is wide and without dog-ear;It is then that user search number is by matching rule
Rectangular face, face be long and big, eyebrow belongs to that eyebrow is low, eyebrow is wide and the base map material without dog-ear, and by the self-timer of base map and user with one
Fixed weighted value mutually merges, and finally obtains the face material for having both similarity and stylization;Further, mutually melted
When conjunction, it can carry out selecting different weighted values according to the actual needs, here just without limitation.At other one or some
In embodiment, the five features of the personage in image uploaded due to user is all different, but the step of when being restored
All with it is aforementioned substantially similar, herein with regard to no longer being enumerated one by one.
Finally, cartooning's figure image is returned to mobile device using output equipment 44 by processor 42.By will be complete
Figure image return to mobile device supply user check, can be really achieved user try hair style effect.
Processor 42 is for running or executing the operating system being stored in internal storage 43, various software programs,
And the instruction set of itself, and for handling from touch input unit or the number received from other external input approach
According to and instruction, to realize various functions.Processor 42 can include but is not limited to central processing unit (CPU), general hair style image
Processor (GPU), microprocessor (MCU), digital signal processor (DSP), field programmable gate array (FPGA), application
One of specific integrated circuit (ASIC) is a variety of.In some embodiments, processor 42 and Memory Controller 104 can be
It is realized on one single chip.In some other embodiments, they can be realized on chip independent of each other respectively.
It should be appreciated that in embodiments of the present invention, alleged memory 43 may include that read-only memory and arbitrary access are deposited
Reservoir, and instruction and data is provided to processor 42.The a part of of memory 43 can also include that non-volatile random is deposited
Reservoir.For example, memory 43 can also be stored with the relevant information of device type.
Computer readable storage medium shown by the fourth embodiment of the present invention, the computer readable storage medium are deposited
Computer program is contained, the computer program includes program instruction, and described program instruction makes described when being executed by a processor
Processor executes the step of hair style identification as described in the first or second of the present invention implementation and restoring method.
Specifically, the computer readable storage medium may include caching (Cache), high-speed random access memory
(RAM), such as common double data rate Synchronous Dynamic Random Access Memory (DDR SDRAM), and may also include non-volatile
Property memory (NVRAM), such as one or more read-only memory (ROM), disk storage equipment, flash memory (Flash) memory
Equipment or other non-volatile solid state memory equipment such as CDs (CD-ROM, DVD-ROM), floppy disk or data tape etc..
As shown in figure 4, figure image cartoon also original system shown in the fifth embodiment of the present invention, including hair style are known
Not with reduction apparatus and mobile device, hair style identification connect with reduction apparatus with the mobile device communication.Wherein, hair style
Identification and reduction apparatus as described in first or second embodiments of the invention, the mobile device include but is not limited to mobile phone,
Computer or other Intelligent hardwares with camera function.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme should all cover within the scope of the claims and the description of the invention.
Claims (10)
1. a kind of hair style identification and restoring method, which comprises the steps of:
Obtain the hair style image that user uploads;
Identify the hair style feature in the hair style image;
Material is matched in cartoon material database according to the hair style feature;
Cartooning's hairstyle image is combined using the material.
2. hair style identification according to claim 1 and restoring method, which is characterized in that identify the hair in the hair style image
Type feature specifically includes:
Identify hair length, shape, fringe, hair tail direction, texture, weight sense and the color development of hair style in the hair style image.
3. hair style identification according to claim 2 and restoring method, which is characterized in that identify hair style in the hair style image
Hair length include:
Identify hair style in the hair style image sends out length long, and hair length is divided into bob, middle hair and long hair;The bob is divided into
Ultrashort hair, bob on ear, bob in ear, the middle hair are divided into short bob, long bob and middle hair, and the long hair is divided into medium-length hair, length
Hair, overlength hair.
4. hair style identification according to claim 2 and restoring method, which is characterized in that identify hair style in the hair style image
Shape include:
It identifies the global shape of hair style in the hair style image, and up-side down triangle, water chestnut is divided into according to hair style entirety outer contour shape
Shape and triangle.
5. hair style identification according to claim 2 and restoring method, which is characterized in that identify hair style in the hair style image
Fringe include:
Identify that the fringe of hair style in the hair style image whether there is;
Fringe if it does not exist, then according to hair parting position, be divided into point and side point;
Fringe if it exists then identifies the profile of the fringe, and fringe is divided into neat fringe according to the profile of fringe, tiltedly divides Liu
Sea, in divide fringe, air Liu Haihe sawtooth fringe;
And identify the length of the fringe, and fringe is divided by short fringe, fringe on eyebrow, Liu in eyebrow according to the length of fringe
Fringe under sea and eyebrow.
6. hair style identification according to claim 2 and restoring method, which is characterized in that identify hair style in the hair style image
Hair tail direction include:
It identifies the hair tail bending direction of hair style in the hair style image, and tail direction point will be sent out according to the hair tail bending direction of hair style
For internal buckle, nature and turn up.
7. hair style identification according to claim 2 and restoring method, which is characterized in that identify hair style in the hair style image
Texture include:
It identifies the length of hair style in the hair style image, and texture is divided into, in texture by texture bob class according to the length of hair style
Send out class and texture long hair class;The texture bob class includes straight hair, weak volume and strong volume, and hair class includes straight hair, half in the texture
Volume, middle volume and rouleau, the texture long hair class include straight hair, half volume, middle volume, big volume and rouleau.
8. hair style identification according to claim 2 and restoring method, which is characterized in that identify hair style in the hair style image
Weight sense include:
It identifies the form of hair style in the hair style image, and weight sense is divided by air sense, nature according to the form of hair style and is consolidated
Body-sensing.
9. a kind of identification of hair style and reduction apparatus, it is characterised in that: including processor, input equipment, output equipment and memory,
The processor, input equipment, output equipment and memory are connected with each other, wherein the memory is for storing computer journey
Sequence, the computer program include program instruction, and the processor is configured for calling described program instruction, execute such as right
It is required that method described in any one of 1-8.
10. a kind of hair style identifies and goes back original system, it is characterised in that: including hair style identification and reduction apparatus and mobile device, institute
Hair style identification is stated to connect with reduction apparatus with the mobile device communication;The hair style identification is executed with reduction apparatus as right is wanted
Seek method described in any one of 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811215759.6A CN109408940A (en) | 2018-10-18 | 2018-10-18 | A kind of identification of hair style and restoring method, apparatus and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811215759.6A CN109408940A (en) | 2018-10-18 | 2018-10-18 | A kind of identification of hair style and restoring method, apparatus and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109408940A true CN109408940A (en) | 2019-03-01 |
Family
ID=65468542
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811215759.6A Pending CN109408940A (en) | 2018-10-18 | 2018-10-18 | A kind of identification of hair style and restoring method, apparatus and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109408940A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1694110A (en) * | 2004-05-07 | 2005-11-09 | 日本先锋公司 | Hairstyle suggesting system, hairstyle suggesting method, and computer program product |
CN106372652A (en) * | 2016-08-28 | 2017-02-01 | 乐视控股(北京)有限公司 | Hair style identification method and hair style identification apparatus |
CN107545051A (en) * | 2017-08-23 | 2018-01-05 | 武汉理工大学 | Hair style design system and method based on image procossing |
CN108596091A (en) * | 2018-04-24 | 2018-09-28 | 杭州数为科技有限公司 | Figure image cartooning restoring method, system and medium |
-
2018
- 2018-10-18 CN CN201811215759.6A patent/CN109408940A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1694110A (en) * | 2004-05-07 | 2005-11-09 | 日本先锋公司 | Hairstyle suggesting system, hairstyle suggesting method, and computer program product |
CN106372652A (en) * | 2016-08-28 | 2017-02-01 | 乐视控股(北京)有限公司 | Hair style identification method and hair style identification apparatus |
CN107545051A (en) * | 2017-08-23 | 2018-01-05 | 武汉理工大学 | Hair style design system and method based on image procossing |
CN108596091A (en) * | 2018-04-24 | 2018-09-28 | 杭州数为科技有限公司 | Figure image cartooning restoring method, system and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109308682A (en) | A kind of recognition of face and cartoon restoring method, device, medium and system | |
CN108121957B (en) | Method and device for pushing beauty material | |
CN110390632B (en) | Image processing method and device based on dressing template, storage medium and terminal | |
CN109063560B (en) | Image processing method, image processing device, computer-readable storage medium and terminal | |
CN106530010B (en) | The collaborative filtering method and device of time of fusion factor | |
CN107845072B (en) | Image generating method, device, storage medium and terminal device | |
CN108182232B (en) | Personage's methods of exhibiting, electronic equipment and computer storage media based on e-book | |
CN110110118A (en) | Dressing recommended method, device, storage medium and mobile terminal | |
CN107123027A (en) | A kind of cosmetics based on deep learning recommend method and system | |
CN107704829B (en) | A kind of face key point method for tracing and application and device | |
CN109344920A (en) | Customer attributes prediction technique, storage medium, system and equipment | |
US20200005780A1 (en) | Voice interaction method and device | |
CN109643332A (en) | A kind of sentence recommended method and device | |
CN107564109A (en) | A kind of clothing management method, device, equipment and storage medium | |
CN102043863A (en) | Method for Web service clustering | |
CN105721936A (en) | Intelligent TV program recommendation system based on context awareness | |
CN114266695A (en) | Image processing method, image processing system and electronic equipment | |
Xiao et al. | Vismantic: Meaning-making with Images. | |
Li et al. | Eliminating gradient conflict in reference-based line-art colorization | |
CN110866139A (en) | Cosmetic treatment method, device and equipment | |
CN108921798A (en) | The method, apparatus and electronic equipment of image procossing | |
CN111815407A (en) | Method and device for constructing user portrait | |
CN107203646A (en) | A kind of intelligent social sharing method and device | |
CN109408940A (en) | A kind of identification of hair style and restoring method, apparatus and system | |
CN117152566A (en) | Classification model training method, model, classification method and product |
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 |