CN104463779A - Portrait caricature generating method and device - Google Patents
Portrait caricature generating method and device Download PDFInfo
- Publication number
- CN104463779A CN104463779A CN201410801968.4A CN201410801968A CN104463779A CN 104463779 A CN104463779 A CN 104463779A CN 201410801968 A CN201410801968 A CN 201410801968A CN 104463779 A CN104463779 A CN 104463779A
- Authority
- CN
- China
- Prior art keywords
- face
- portrait
- caricature
- cartoon
- hair style
- 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
- 238000000034 method Methods 0.000 title claims abstract description 69
- 239000000463 material Substances 0.000 claims abstract description 139
- 230000008859 change Effects 0.000 claims description 9
- 238000010422 painting Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 5
- 230000001815 facial effect Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 3
- 210000000697 sensory organ Anatomy 0.000 abstract 3
- 230000008569 process Effects 0.000 description 27
- 238000010586 diagram Methods 0.000 description 15
- 230000036541 health Effects 0.000 description 4
- 239000000523 sample Substances 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000003973 paint Substances 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000010425 computer drawing Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 238000010421 pencil drawing Methods 0.000 description 1
- 210000001747 pupil Anatomy 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4084—Scaling of whole images or parts thereof, e.g. expanding or contracting in the transform domain, e.g. fast Fourier transform [FFT] domain scaling
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention relates to a portrait caricature generating method and device. The portrait caricature generating method comprises the following steps that a picture of a face is obtained; features of areas of the five sense organs on the picture are recognized, and caricature materials matched with the five sense organs are found in a caricature material library; a portrait caricature is generated according to the caricature materials of the five sense organs. According to the portrait caricature generating method, through recognition of the face, appropriate elements are selected from the picture material library, the selected elements are combined, and in this way, the portrait reflecting the facial features of a person and having caricature effect can be automatically generated.
Description
Technical field
The present invention relates to computer drawing technology field, particularly relate to a kind of portrait-cartoon generation method and device thereof.
Background technology
At present, there is Freehandhand-drawing for the mode of real people being painted into caricature picture and realized by various different caricatures generation software.The mode of Freehandhand-drawing is common in street corner inferior painter, and be that true man paint the image of various different-style by the mode of Freehandhand-drawing, the validity of this kind of mode is very high, but it is time-consuming to paint, and be confined to look for the inferior painter of specialty or artist to come, therefore, different caricatures generates software application and gives birth to.
Common portrait-cartoon generates software two kinds: a kind of mode is that user manually selects the elements such as face pattern, hair style, accessories in picture library, then by these element set synthesis caricature, its this mode takes time and effort, inefficiency, can not embody personal characteristics simultaneously.Another kind of mode forms the little body caricature of major part with health by being extracted by personage's head in photo to put in caricature health picture library, its face are completely realistic, its this kind of mode cannot brush strokes that is virtually reality like reality, completely realistic face material arrange in pairs or groups with the body of cartoon material together with time have and stronger piece together sense, its picture style also can be subject to the restriction of cartoon material simultaneously, thus occurs the inharmonious situation of the overall caricature after combining.
Summary of the invention
In view of the above problems, proposing the present invention to provide overcomes the problems referred to above or the portrait-cartoon generation method solved the problem at least in part and device thereof.
According to an aspect of the present invention, provide a kind of portrait-cartoon generation method, the method comprises the following steps:
Obtain the photo comprising face;
Each face provincial characteristics according to described photo searches the caricature face material matched at caricature material database;
Portrait-cartoon is generated according to described caricature face material.
Preferably, the method also comprises: utilize caricature material database to select hair style, accessories.
Preferably, the method also comprises: the input according to user adjusts at least one element included by described portrait-cartoon.
Wherein, the input according to user adjusts at least one element included by portrait-cartoon, specifically comprises: the size and/or the position that change wherein at least one face.
Wherein, described change is the size of at least one face and/or position wherein, specifically comprises:
Increase the position of eyes and/or adjustment eyes.
Preferably, the input according to user adjusts at least one element included by portrait-cartoon, specifically comprises:
Select hair style according to user preferences from caricature material database, the hair style in portrait-cartoon is replaced.
Wherein, the input according to user adjusts at least one element included by portrait-cartoon, specifically comprises: select dress ornament material according to user preferences from Freehandhand-drawing material database, adds dress ornament to portrait painting.
Wherein, search at caricature material database the caricature face material matched according to each face provincial characteristics specifically to comprise:
Recognition of face is carried out to described photo, obtains the shape of face, position and size information and shape of face and hair style information;
From caricature material database, extract the material of face, shape of face and hair style respectively, and mate, to obtain the highest caricature material of matching degree with the shape of corresponding site obtained above, size; Obtained caricature material is combined according to above-mentioned positional information, forms portrait-cartoon image.
Wherein, mate with the shape of corresponding site obtained above, size, specifically comprise:
The caricature material extracted is rotated, convergent-divergent and/or stretching;
By rotating, the shape of convergent-divergent and/or material and corresponding site obtained above after stretching, size overlap.
Wherein, search at caricature material database the caricature face material matched according to each face provincial characteristics specifically to comprise:
Extract each face area image;
Respectively according to each face area image, obtain the profile of each face;
The profile of the profile of each face to the corresponding face in sample material database is mated, to find immediate face material;
According to the corresponding relation of face material with caricature material, search the caricature material corresponding with described immediate face material.
According to another aspect of the present invention, provide a kind of portrait-cartoon generating apparatus, this device comprises:
Caricature material database, for storing caricature face material, hair style, accessories;
Acquiring unit, for obtaining the photo comprising face;
Matched and searched unit, for searching the caricature face material matched at caricature material database according to each face provincial characteristics;
Caricature generation unit, for generating portrait-cartoon according to described caricature face material.
Preferably, this device also comprises:
Hair style, accessories selection unit, select hair style, accessories for utilizing caricature material database.
Preferably, this device also comprises:
Adjustment unit, adjusts at least one key element included by portrait-cartoon for the input according to user.
Wherein, described adjustment unit comprises face adjustment unit, for changing size and/or the position of wherein at least one face.
Wherein, described face adjustment unit comprises eyes adjustment subelement, for increasing the position of eyes and/or adjustment eyes.
Wherein, described adjustment unit comprises hair style adjustment unit, for selecting hair style according to user preferences from caricature material database, replaces the hair style in portrait-cartoon.
Wherein, described adjustment unit comprises dress ornament adjustment unit, selects dress ornament material according to user preferences from caricature material database, and add dress ornament to portrait painting, described Freehandhand-drawing material database stores dress ornament material.
Wherein, described matched and searched unit specifically comprises:
Face identification unit, carries out recognition of face to described photo, obtains the shape of face, position and size information and shape of face and hair style information;
Matching unit, for extracting the material of face, shape of face and hair style from caricature material database respectively, and mates with the shape of corresponding site obtained above, size, to obtain the highest caricature material of matching degree;
Described caricature generation unit, for being combined according to above-mentioned positional information by obtained caricature material, forms portrait-cartoon.
Wherein, described matching unit specifically comprises:
Gyrator unit, for rotating the material extracted;
Convergent-divergent subelement, for carrying out convergent-divergent to the material extracted;
Stretching subelement, stretches to the material extracted;
Coincidence subelement, for by rotating, the shape of convergent-divergent and/or material and corresponding site obtained above after stretching, size overlap.
Wherein, described matched and searched unit specifically comprises:
Extraction unit, for extracting each face area image;
Profile acquiring unit, for respectively according to each face area image, obtains the profile of each face;
Matching unit, for being mated by the profile of the profile of each face to the corresponding face in sample material database, to find immediate face material;
Search unit, for according to the corresponding relation of face material with caricature material, search the caricature material corresponding with described immediate face material.
Beneficial effect of the present invention is:
Adopt portrait-cartoon generation method disclosed in this invention and device thereof, identified by the face of comparison film, and from picture materials storehouse, choose suitable element and the element chosen is carried out to the mode of method process, everyone facial characteristics can be retained as wide as possible, thus the caricature picture higher with the similarity of real human face can be obtained fast; Meanwhile, by carrying out the operation such as convergent-divergent, skew to the material selected, can be out of shape the picture generated and the change of material, the picture of different-style can be obtained.
Above-mentioned explanation is only the general introduction of technical solution of the present invention, in order to technological means of the present invention can be better understood, and can be implemented according to the content of instructions, and can become apparent, below especially exemplified by the specific embodiment of the present invention to allow above and other objects of the present invention, feature and advantage.
Accompanying drawing explanation
By reading hereafter detailed description of the preferred embodiment, various other advantage and benefit will become cheer and bright for those of ordinary skill in the art.Accompanying drawing only for illustrating the object of preferred implementation, and does not think limitation of the present invention.And in whole accompanying drawing, represent identical parts by identical reference symbol.In the accompanying drawings:
Fig. 1 diagrammatically illustrates the process flow diagram of portrait-cartoon generation method of the present invention.
Fig. 2 diagrammatically illustrates the process flow diagram of an embodiment of the step S2 of portrait-cartoon generation method of the present invention.
Fig. 3 a-3d diagrammatically illustrates the base model schematic diagram of the eyes in the picture materials storehouse of one embodiment of the present of invention.
Fig. 4 a-4c diagrammatically illustrates the matching process schematic diagram of the eyes of one embodiment of the present of invention.
Fig. 5 a-5c diagrammatically illustrates process and the matching process schematic diagram of the eyes of an alternative embodiment of the invention.
Fig. 6 a-6b diagrammatically illustrates the schematic diagram of the portrait-cartoon generative process of another embodiment of the present invention.
Fig. 7 diagrammatically illustrates the portrait-cartoon generative process schematic diagram of one embodiment of the present of invention.
Fig. 8 diagrammatically illustrates the structured flowchart of the portrait-cartoon generating apparatus of one embodiment of the present invention;
Fig. 9 diagrammatically illustrates the structured flowchart of the portrait-cartoon generating apparatus of another embodiment of the present invention.
Embodiment
Below in conjunction with accompanying drawing and concrete embodiment, the invention will be further described.
Fig. 1 shows the process flow diagram of portrait-cartoon generation method of the present invention.
With reference to Fig. 1, the portrait-cartoon generation method of embodiments of the invention comprises the following steps:
S1, obtains the photo comprising face;
S2, each face provincial characteristics according to described photo searches the caricature face material matched at caricature material database;
Particularly, step S2 specifically comprises:
Recognition of face is carried out to described photo, obtains the shape of face, position and size information and shape of face and hair style information;
From caricature material database, extract the material of face, shape of face and hair style respectively, and mate, to obtain the highest caricature material of matching degree with the shape of corresponding site obtained above, size; Comprising rotating the caricature material extracted, convergent-divergent and/or stretching;
By rotating, the shape of convergent-divergent and/or material and corresponding site obtained above after stretching, size overlap.
Obtained caricature material is combined according to above-mentioned positional information, forms portrait-cartoon image.
Fig. 2 shows the process flow diagram of another embodiment of the step S2 of portrait-cartoon generation method of the present invention.
As shown in Figure 2, step S2 also can pass through following process implementation:
S21, extracts each face area image;
S22, respectively according to each face area image, obtains the profile of each face;
S23, mates the profile of the profile of each face to the corresponding face in sample material database, to find immediate face material;
S24, according to the corresponding relation of face material with caricature material, searches the caricature material corresponding with described immediate face material.
S3, generates portrait-cartoon according to described caricature face material.
Alternatively, caricature material database also can be utilized to select hair style and/or accessories, to generate portrait-cartoon according to caricature face material and hair style and/or accessories.
In step sl, the photo of acquisition can be obtained immediately by shooting or photographic equipment, also can select in the photo prestored or existing hand-drawing image.
In the above-mentioned methods, also comprise and according to the input of user, at least one element included by described portrait-cartoon being adjusted, and described adjustment specifically comprises: the size and/or the position that change wherein at least one face, as increased the position of eyes and/or adjustment eyes, change the size of mouth, profile etc.; Or select hair style according to user preferences from caricature material database, the hair style in portrait-cartoon is replaced; Or select dress ornament material according to user preferences from Freehandhand-drawing material database, dress ornament is added to portrait painting.
In another embodiment of the present invention, portrait-cartoon generative process is specially:
1) on the photo selected, face recognition algorithms is used to identify the face of face, as position and the size of eyes, nose and mouth; Face recognition algorithms herein can be the method that existing any one can identify the face in photo.
2) then each face are carried out to process and the coupling of image.This sentences eyes is that example is described in detail.
Fig. 3 a-3d shows the base model schematic diagram of the eyes in the picture materials storehouse of one embodiment of the present of invention.
As illustrated in figs. 3 a-3d, in picture materials storehouse, the base model of eyes comprises four kinds in figure, and comprises the multiple of other.
Fig. 4 a-4c shows the matching process schematic diagram of the eyes of one embodiment of the present of invention.
As shown in fig. 4 a, the eyes of comparison film identify, first the surface of eyes is identified, then in material database, selecting the material of eyes to be out of shape, rotating as carried out, convergent-divergent, stretching etc., make the coincident degree of the lines of the eyes material selected and eyes the highest, as shown in Figure 4 b, on this basis, carry out ratio of transformation comparatively with the eyes material in material database successively, find the eyes material the highest with former figure registration.In addition, as long as the pupil material of eyes finds corresponding position and size, as Fig. 4 c is matching result.
Fig. 5 a-5c shows process and the matching process schematic diagram of the eyes of an alternative embodiment of the invention.
Eyes matching process shown in Fig. 5 a-5c is identical with said process, is not repeating at this.
3) use the face of above-mentioned method comparison film, shape of face, hair style to mate, then the material found is combined to form piece image, the portrait-cartoon of personage can be obtained.
Fig. 6 a-6b shows the schematic diagram of the portrait-cartoon generative process of another embodiment of the present invention.
First portrait photographs is obtained, by the identification of the face of comparison film, shape of face, hair style, accessories and health, generate the profile diagram of face, shape of face, hair style, accessories and health as shown in Figure 6 a, the profile of face, shape of face, hair style, accessories is mated with the various materials in material database, thus obtains the higher portrait-cartoon of validity as shown in Figure 6 b.
In addition, after generation portrait-cartoon, multiple style can also be converted, as eyes are become large, position step-down thus the cartoon effect more lovely than true man can be realized, for another example, the size of adjustment face, even adjusts shape, to realize lovely cartoon effect, certainly, also replaceable hair style or dress ornament material can realize different figural sensations.
In yet another embodiment of the present invention, the mode that said method can be combined by the caricature material template of Freehandhand-drawing and algorithmic match facial characteristics realizes.
Fig. 7 shows the portrait-cartoon generative process schematic diagram of one embodiment of the present of invention.
As shown in Figure 7, user is by taking pictures or selecting the mode of existing photo to find the photo with frontal faces, manually find the approximate location of face, as the position of eyes, then by algorithm process, eyes are mated, as specifically comprised: the eye contour extracting user processes, as stretched, convergent-divergent etc., then go to mate the eyes in storehouse with the eyes of the user after process, find the ID of the eyes in immediate storehouse, due to the corresponding caricature eyes of typical eyes each in storehouse, therefore the caricature eye selecting ID corresponding is as the eyes of portrait, then this result is turned back to user and process interface, the face of photo and shape of face, hair style etc. are mated by same method, thus form the portrait figure of width needs.
The present invention also provides a kind of portrait-cartoon generating apparatus.
Fig. 8 shows the structured flowchart of one embodiment of the present invention.As shown in Figure 8, portrait-cartoon generating apparatus comprises:
Caricature material database 100, for storing caricature face material, hair style, accessories;
Acquiring unit 200, for obtaining the photo comprising face;
Matched and searched unit 300, for searching the caricature face material matched at caricature material database according to each face provincial characteristics;
Caricature generation unit 400, for generating portrait-cartoon according to described caricature face material.
Fig. 9 shows the structured flowchart of another kind of embodiment.As shown in Figure 9, portrait-cartoon generating apparatus, except comprising caricature material database 100, acquiring unit 200, matched and searched unit 300, also comprises: hair style, accessories selection unit 500, selects hair style, accessories for utilizing caricature material database; Caricature generation unit 400, for generating portrait-cartoon according to described caricature face material, hair style and accessories.
Further, preferably, this device also comprises:
Adjustment unit, adjusts at least one key element included by portrait-cartoon for the input according to user.
Wherein, adjustment unit comprises face adjustment unit, for changing size and/or the position of wherein at least one face; And described face adjustment unit comprises eyes adjustment subelement, for increasing the position of eyes and/or adjustment eyes.
Preferably, adjustment unit comprises hair style adjustment unit, for selecting hair style according to user preferences from caricature material database, replaces the hair style in portrait-cartoon;
And dress ornament adjustment unit, select dress ornament material according to user preferences from caricature material database, add dress ornament to portrait painting, described Freehandhand-drawing material database stores dress ornament material.
In an embodiment, matched and searched unit specifically comprises:
Face identification unit, carries out recognition of face to described photo, obtains the shape of face, position and size information and shape of face and hair style information;
Matching unit, for extracting the material of face, shape of face and hair style from caricature material database respectively, and mates with the shape of corresponding site obtained above, size, to obtain the highest caricature material of matching degree;
Caricature generation unit, for being combined according to above-mentioned positional information by obtained caricature material, forms portrait-cartoon.
In another embodiment, above-mentioned matching unit specifically comprises:
Gyrator unit, for rotating the material extracted;
Convergent-divergent subelement, for carrying out convergent-divergent to the material extracted;
Stretching subelement, stretches to the material extracted;
Coincidence subelement, for by rotating, the shape of convergent-divergent and/or material and corresponding site obtained above after stretching, size overlap.
In addition, hand-drawing image generation unit specifically comprises:
Extraction unit, for extracting each face area image;
Profile acquiring unit, for respectively according to each face area image, obtains the profile of each face;
Matching unit, for being mated by the profile of the profile of each face to the corresponding face in sample material database, to find immediate face material;
Search unit, for according to the corresponding relation of face material with caricature material, search the caricature material corresponding with described immediate face material.
Adopt portrait-cartoon generation method disclosed in this invention and device thereof, identified by the face of comparison film, and from picture materials storehouse, choose suitable element and the element chosen is carried out to the mode of method process, everyone facial characteristics can be retained as wide as possible, thus the caricature picture higher with the similarity of real human face can be obtained fast; Meanwhile, by carrying out the operation such as convergent-divergent, skew to the material selected, can be out of shape the picture generated and the change of material, the picture of different-style can be obtained.
In addition, method of the present invention and device can adapt to the drawing style of different pictures, as pencil hand drawing style, cartoon style and portrait painting style etc., and the picture of pencil style can the pencil drawing style of writing of rediscover completely, and secondary creation on the basis being drawn in photo of cartoon style, obtain extremely letter, lovely style, there is the possibility deriving other styles unlimited simultaneously.
It should be noted that:
Intrinsic not relevant to any certain computer, virtual system or miscellaneous equipment with display at this algorithm provided.Various general-purpose system also can with use based on together with this teaching.According to description above, the structure constructed required by this type systematic is apparent.In addition, the present invention is not also for any certain programmed language.It should be understood that and various programming language can be utilized to realize content of the present invention described here, and the description done language-specific is above to disclose preferred forms of the present invention.
In instructions provided herein, describe a large amount of detail.But can understand, embodiments of the invention can be put into practice when not having these details.In some instances, be not shown specifically known method, structure and technology, so that not fuzzy understanding of this description.
Similarly, be to be understood that, in order to simplify the disclosure and to help to understand in each inventive aspect one or more, in the description above to exemplary embodiment of the present invention, each feature of the present invention is grouped together in single embodiment, figure or the description to it sometimes.But, the method for the disclosure should be construed to the following intention of reflection: namely the present invention for required protection requires feature more more than the feature clearly recorded in each claim.Or rather, as claims below reflect, all features of disclosed single embodiment before inventive aspect is to be less than.Therefore, the claims following embodiment are incorporated to this embodiment thus clearly, and wherein each claim itself is as independent embodiment of the present invention.
Those skilled in the art are appreciated that and adaptively can change the module in the equipment in embodiment and they are arranged in one or more equipment different from this embodiment.Module in embodiment or unit or assembly can be combined into a module or unit or assembly, and multiple submodule or subelement or sub-component can be put them in addition.Except at least some in such feature and/or process or unit be mutually repel except, any combination can be adopted to combine all processes of all features disclosed in this instructions (comprising adjoint claim, summary and accompanying drawing) and so disclosed any method or equipment or unit.Unless expressly stated otherwise, each feature disclosed in this instructions (comprising adjoint claim, summary and accompanying drawing) can by providing identical, alternative features that is equivalent or similar object replaces.
In addition, those skilled in the art can understand, although embodiments more described herein to comprise in other embodiment some included feature instead of further feature, the combination of the feature of different embodiment means and to be within scope of the present invention and to form different embodiments.Such as, in the following claims, the one of any of embodiment required for protection can use with arbitrary array mode.
All parts embodiment of the present invention with hardware implementing, or can realize with the software module run on one or more processor, or realizes with their combination.Those skilled in the art is to be understood that, server, client that microprocessor or digital signal processor (DSP) realize according to the embodiment of the present invention can be used in practice, and the some or all functions of some or all parts in the equipment such as system.The present invention can also be embodied as part or all equipment for performing method as described herein or device program (such as, computer program and computer program).Realizing program of the present invention and can store on a computer-readable medium like this, or the form of one or more signal can be had.Such signal can be downloaded from internet website and obtain, or provides on carrier signal, or provides with any other form.
The present invention will be described instead of limit the invention to it should be noted above-described embodiment, and those skilled in the art can design alternative embodiment when not departing from the scope of claims.In the claims, any reference symbol between bracket should be configured to limitations on claims.Word " comprises " not to be got rid of existence and does not arrange element in the claims or step.Word "a" or "an" before being positioned at element is not got rid of and be there is multiple such element.The present invention can by means of including the hardware of some different elements and realizing by means of the computing machine of suitably programming.In the unit claim listing some devices, several in these devices can be carry out imbody by same hardware branch.Word first, second and third-class use do not represent any order.Can be title by these word explanations.
Claims (10)
1. a portrait-cartoon generation method, it is characterized in that, the method comprises the following steps:
Obtain the photo comprising face;
Identify each face provincial characteristics of described photo, and search the caricature face material matched at caricature material database;
Portrait-cartoon is generated according to described caricature face material.
2. portrait-cartoon generation method according to claim 1, be further characterized in that, the method also comprises:
Caricature material database is utilized to select hair style, accessories.
3. portrait-cartoon generation method according to claim 1 and 2, be further characterized in that, the method also comprises:
Input according to user adjusts at least one element included by described portrait-cartoon.
4. portrait-cartoon generation method according to claim 3, is further characterized in that, the input according to user adjusts at least one element included by portrait-cartoon, specifically comprises: the size and/or the position that change wherein at least one face.
5. portrait-cartoon generation method according to claim 4, is further characterized in that, described change is the size of at least one face and/or position wherein, specifically comprises:
Increase the position of eyes and/or adjustment eyes.
6. the portrait-cartoon generation method according to any one of claim 3-5, is further characterized in that, the input according to user adjusts at least one element included by portrait-cartoon, specifically comprises:
Select hair style according to user preferences from caricature material database, the hair style in portrait-cartoon is replaced.
7. the portrait-cartoon generation method according to any one of claim 3-6, be further characterized in that, input according to user adjusts at least one element included by portrait-cartoon, specifically comprises: select dress ornament material according to user preferences from Freehandhand-drawing material database, adds dress ornament to portrait painting.
8. the portrait-cartoon generation method according to any one of claim 1-7, is further characterized in that, searches the caricature face material matched specifically comprise according to each face provincial characteristics at caricature material database:
Recognition of face is carried out to described photo, obtains the shape of face, position and size information and shape of face and hair style information;
From caricature material database, extract the material of face, shape of face and hair style respectively, and mate, to obtain the highest caricature material of matching degree with the shape of corresponding site obtained above, size; Obtained caricature material is combined according to above-mentioned positional information, forms portrait-cartoon image.
9. portrait-cartoon generation method according to claim 8, is further characterized in that, mates, specifically comprise with the shape of corresponding site obtained above, size:
The caricature material extracted is rotated, convergent-divergent and/or stretching;
By rotating, the shape of convergent-divergent and/or material and corresponding site obtained above after stretching, size overlap.
10. a portrait-cartoon generating apparatus, is characterized in that, this device comprises:
Caricature material database, for storing caricature face material, hair style, accessories;
Acquiring unit, for obtaining the photo comprising face;
Matched and searched unit, for searching the caricature face material matched at caricature material database according to each face provincial characteristics;
Caricature generation unit, for generating portrait-cartoon according to described caricature face material.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410801968.4A CN104463779A (en) | 2014-12-18 | 2014-12-18 | Portrait caricature generating method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410801968.4A CN104463779A (en) | 2014-12-18 | 2014-12-18 | Portrait caricature generating method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104463779A true CN104463779A (en) | 2015-03-25 |
Family
ID=52909767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410801968.4A Pending CN104463779A (en) | 2014-12-18 | 2014-12-18 | Portrait caricature generating method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104463779A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105183316A (en) * | 2015-08-31 | 2015-12-23 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating emotion text |
| CN106791091A (en) * | 2016-12-20 | 2017-05-31 | 北京奇虎科技有限公司 | image generating method, device and mobile terminal |
| CN107730573A (en) * | 2017-09-22 | 2018-02-23 | 西安交通大学 | A kind of personal portrait cartoon style generation method of feature based extraction |
| CN107895045A (en) * | 2017-12-02 | 2018-04-10 | 天津大行道动漫文化发展有限公司 | A kind of animation material searching system based on user's degree of liking |
| CN108717719A (en) * | 2018-05-23 | 2018-10-30 | 腾讯科技（深圳）有限公司 | Generation method, device and the computer storage media of cartoon human face image |
| CN109191545A (en) * | 2018-08-27 | 2019-01-11 | 北京奇虎科技有限公司 | A kind of method and device making caricature |
| CN109215099A (en) * | 2018-08-27 | 2019-01-15 | 北京奇虎科技有限公司 | A kind of method and device making caricature |
| CN109308682A (en) * | 2018-10-18 | 2019-02-05 | 杭州数为科技有限公司 | A kind of recognition of face and cartoon restoring method, device, medium and system |
| CN109741247A (en) * | 2018-12-29 | 2019-05-10 | 四川大学 | A kind of portrait-cartoon generation method neural network based |
| CN109993807A (en) * | 2019-02-21 | 2019-07-09 | 百度在线网络技术（北京）有限公司 | Head portrait generation method, device and storage medium |
| CN110580676A (en) * | 2018-06-07 | 2019-12-17 | 富泰华工业（深圳）有限公司 | method for making cartoon image on human face, electronic device and storage medium |
| CN110738157A (en) * | 2019-10-10 | 2020-01-31 | 南京地平线机器人技术有限公司 | Virtual face construction method and device |
| CN110750666A (en) * | 2018-07-04 | 2020-02-04 | 北京京东尚科信息技术有限公司 | Picture generation method and system, electronic device and storage medium |
| CN111127309A (en) * | 2019-12-12 | 2020-05-08 | 杭州格像科技有限公司 | Portrait style transfer model training method, portrait style transfer method and device |
| CN111200555A (en) * | 2019-12-30 | 2020-05-26 | 咪咕视讯科技有限公司 | Chat message display method, electronic device and storage medium |
| CN111242654A (en) * | 2018-11-28 | 2020-06-05 | 北京沃东天骏信息技术有限公司 | Method and system for generating advertisement picture |
| CN111626920A (en) * | 2020-05-09 | 2020-09-04 | 北京字节跳动网络技术有限公司 | Picture processing method and device and electronic equipment |
| CN111652828A (en) * | 2020-05-27 | 2020-09-11 | 北京百度网讯科技有限公司 | Face image generation method, device, equipment and medium |
| CN113223128A (en) * | 2020-02-04 | 2021-08-06 | 北京百度网讯科技有限公司 | Method and apparatus for generating image |
| CN113345054A (en) * | 2021-05-28 | 2021-09-03 | 上海哔哩哔哩科技有限公司 | Virtual image decorating method, detection method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1202674A (en) * | 1997-06-18 | 1998-12-23 | 深圳市公安局南山分局 | Image processing method and equipment |
| CN102509316A (en) * | 2011-09-23 | 2012-06-20 | 上海华勤通讯技术有限公司 | Mobile terminal and image animating method |
| CN102542586A (en) * | 2011-12-26 | 2012-07-04 | 暨南大学 | Personalized cartoon portrait generating system based on mobile terminal and method |
| CN102682420A (en) * | 2012-03-31 | 2012-09-19 | 北京百舜华年文化传播有限公司 | Method and device for converting real character image to cartoon-style image |
| CN104063890A (en) * | 2013-03-22 | 2014-09-24 | 中国移动通信集团福建有限公司 | Method for cartooning human face and system thereof |
-
2014
- 2014-12-18 CN CN201410801968.4A patent/CN104463779A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1202674A (en) * | 1997-06-18 | 1998-12-23 | 深圳市公安局南山分局 | Image processing method and equipment |
| CN102509316A (en) * | 2011-09-23 | 2012-06-20 | 上海华勤通讯技术有限公司 | Mobile terminal and image animating method |
| CN102542586A (en) * | 2011-12-26 | 2012-07-04 | 暨南大学 | Personalized cartoon portrait generating system based on mobile terminal and method |
| CN102682420A (en) * | 2012-03-31 | 2012-09-19 | 北京百舜华年文化传播有限公司 | Method and device for converting real character image to cartoon-style image |
| CN104063890A (en) * | 2013-03-22 | 2014-09-24 | 中国移动通信集团福建有限公司 | Method for cartooning human face and system thereof |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105183316A (en) * | 2015-08-31 | 2015-12-23 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating emotion text |
| CN105183316B (en) * | 2015-08-31 | 2018-05-08 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus for generating face word |
| CN106791091A (en) * | 2016-12-20 | 2017-05-31 | 北京奇虎科技有限公司 | image generating method, device and mobile terminal |
| CN107730573A (en) * | 2017-09-22 | 2018-02-23 | 西安交通大学 | A kind of personal portrait cartoon style generation method of feature based extraction |
| CN107895045A (en) * | 2017-12-02 | 2018-04-10 | 天津大行道动漫文化发展有限公司 | A kind of animation material searching system based on user's degree of liking |
| CN108717719A (en) * | 2018-05-23 | 2018-10-30 | 腾讯科技（深圳）有限公司 | Generation method, device and the computer storage media of cartoon human face image |
| CN110580676A (en) * | 2018-06-07 | 2019-12-17 | 富泰华工业（深圳）有限公司 | method for making cartoon image on human face, electronic device and storage medium |
| CN110750666A (en) * | 2018-07-04 | 2020-02-04 | 北京京东尚科信息技术有限公司 | Picture generation method and system, electronic device and storage medium |
| CN109215099A (en) * | 2018-08-27 | 2019-01-15 | 北京奇虎科技有限公司 | A kind of method and device making caricature |
| CN109191545A (en) * | 2018-08-27 | 2019-01-11 | 北京奇虎科技有限公司 | A kind of method and device making caricature |
| CN109308682A (en) * | 2018-10-18 | 2019-02-05 | 杭州数为科技有限公司 | A kind of recognition of face and cartoon restoring method, device, medium and system |
| CN111242654A (en) * | 2018-11-28 | 2020-06-05 | 北京沃东天骏信息技术有限公司 | Method and system for generating advertisement picture |
| CN111242654B (en) * | 2018-11-28 | 2021-04-30 | 北京沃东天骏信息技术有限公司 | Method and system for generating advertisement picture |
| CN109741247A (en) * | 2018-12-29 | 2019-05-10 | 四川大学 | A kind of portrait-cartoon generation method neural network based |
| CN109741247B (en) * | 2018-12-29 | 2020-04-21 | 四川大学 | Portrait cartoon generating method based on neural network |
| CN109993807A (en) * | 2019-02-21 | 2019-07-09 | 百度在线网络技术（北京）有限公司 | Head portrait generation method, device and storage medium |
| CN110738157A (en) * | 2019-10-10 | 2020-01-31 | 南京地平线机器人技术有限公司 | Virtual face construction method and device |
| CN111127309A (en) * | 2019-12-12 | 2020-05-08 | 杭州格像科技有限公司 | Portrait style transfer model training method, portrait style transfer method and device |
| CN111127309B (en) * | 2019-12-12 | 2023-08-11 | 杭州格像科技有限公司 | Portrait style migration model training method, portrait style migration method and device |
| CN111200555A (en) * | 2019-12-30 | 2020-05-26 | 咪咕视讯科技有限公司 | Chat message display method, electronic device and storage medium |
| CN113223128A (en) * | 2020-02-04 | 2021-08-06 | 北京百度网讯科技有限公司 | Method and apparatus for generating image |
| CN113223128B (en) * | 2020-02-04 | 2022-09-13 | 北京百度网讯科技有限公司 | Method and apparatus for generating image |
| CN111626920A (en) * | 2020-05-09 | 2020-09-04 | 北京字节跳动网络技术有限公司 | Picture processing method and device and electronic equipment |
| CN111652828A (en) * | 2020-05-27 | 2020-09-11 | 北京百度网讯科技有限公司 | Face image generation method, device, equipment and medium |
| CN111652828B (en) * | 2020-05-27 | 2023-08-08 | 北京百度网讯科技有限公司 | Face image generation method, device, equipment and medium |
| CN113345054A (en) * | 2021-05-28 | 2021-09-03 | 上海哔哩哔哩科技有限公司 | Virtual image decorating method, detection method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104463779A (en) | Portrait caricature generating method and device | |
| KR101635730B1 (en) | Apparatus and method for generating montage, recording medium for performing the method | |
| Lee et al. | Shadowdraw: real-time user guidance for freehand drawing | |
| Phan et al. | Color orchestra: Ordering color palettes for interpolation and prediction | |
| Choi et al. | Sketchhelper: Real-time stroke guidance for freehand sketch retrieval | |
| Rosner et al. | The digitization of cultural practices | |
| Li et al. | Free-hand sketch synthesis with deformable stroke models | |
| Zhang et al. | Data-driven synthesis of cartoon faces using different styles | |
| CN116097320A (en) | System and method for improved facial attribute classification and use thereof | |
| Li et al. | Neural abstract style transfer for chinese traditional painting | |
| Zhang et al. | Intelligent Chinese calligraphy beautification from handwritten characters for robotic writing | |
| Liu et al. | Name your style: An arbitrary artist-aware image style transfer | |
| Tang et al. | Animated construction of Chinese brush paintings | |
| Deng et al. | Exploring the representativity of art paintings | |
| Kumar et al. | Indian art form recognition using convolutional neural networks | |
| Lin et al. | eHeritage of shadow puppetry: creation and manipulation | |
| Putra et al. | Designing translation tool: Between sign language to spoken text on kinect time series data using dynamic time warping | |
| Kuo et al. | Generating ambiguous figure-ground images | |
| KR101734212B1 (en) | Facial expression training system | |
| Akgul | Can an algorithm recognize montage portraits as human faces?[in the spotlight] | |
| Zhao et al. | Learning from the tangram to solve mini visual tasks | |
| Hu et al. | SceneCraft: An LLM Agent for Synthesizing 3D Scenes as Blender Code | |
| Matthews et al. | A sketch-based articulated figure animation tool | |
| Tang et al. | Human motion retrieval based on freehand sketch | |
| Liu et al. | Retrieving indoor objects: 2D-3D alignment using single image and interactive ROI-based refinement |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| 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: 20150325 |