CN104123741A - Method and device for generating human face sketch - Google Patents
Method and device for generating human face sketch Download PDFInfo
- Publication number
- CN104123741A CN104123741A CN201410286120.2A CN201410286120A CN104123741A CN 104123741 A CN104123741 A CN 104123741A CN 201410286120 A CN201410286120 A CN 201410286120A CN 104123741 A CN104123741 A CN 104123741A
- Authority
- CN
- China
- Prior art keywords
- sketch
- facial image
- face organ
- treat
- face
- 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)
- Image Processing (AREA)
Abstract
The invention discloses a method and a device for generating a human face sketch. The method comprises the steps of generating the images of face organs of a human face image to be sketched, generating the sketch image of each face organ of the human face image to be sketched according to the similarity of the image of each face organ of a human face image pre-stored in a training library and the same face organ of the human face image to be sketched, and generating the human face sketch of the human face image to be sketched according to the sketch images of every face organs. Due to the adopted technical scheme, the method is capable of generating the human face sketch more accurately.
Description
Technical field
The disclosure relates to technical field of image processing, relates in particular to the method and apparatus of human face sketch.
Background technology
Along with the fast development that technology is shared in the network interconnections such as mobile device is autodyned, individual photo is shared, face face sketch technology becomes more and more popular.How to carry out the sketch picture of drawing human-face portion more realistically according to the face picture of user's input and become the important research and development problem of human face sketch technical field.
In correlation technique, for human face sketch, first orient the Important Characteristic Points of face face and exterior contour by human face characteristic point location algorithm, then calculate each Important Characteristic Points place and the gray scale similarity of training facial image individual features point place in storehouse on facial image, according to the sketch template of facial image in the gray scale Similarity-Weighted stack training storehouse at each Important Characteristic Points place, and then the sketch picture of generation face.But correlation technique has only been considered in facial image the inside Important Characteristic Points and training storehouse the similarity between individual features point in facial image, therefore the human face sketch of generation is accurate not.
Summary of the invention
For overcoming the problem existing in correlation technique, the disclosure provides the method and apparatus that generates human face sketch, to solve the accurate not problem of human face sketch in correlation technique.
According to the first aspect of disclosure embodiment, a kind of method that generates human face sketch is provided, comprising:
Each face organ's image of sketch facial image is treated in generation;
According to be kept in advance the facial image of training in storehouse face organ's image and described in treat the same face organ's of sketch facial image similarity, treat each face organ's of sketch facial image sketch map picture described in generation;
Described in generating according to described each face organ's sketch map picture, treat the human face sketch of sketch facial image.
Optionally, described basis be kept in advance the facial image of training in storehouse face organ's image and described in treat the same face organ's of sketch facial image similarity, treat that each face organ's of sketch facial image sketch map looks like to comprise described in generation:
Calculate respectively face images in described training storehouse and described in treat telorism's conversion of the same face organ of sketch facial image;
According to described telorism convert face images in calculation training storehouse respectively and described in treat the same face organ's of sketch facial image similarity;
Superpose in the sketch template of facial image in described training storehouse after same face organ according to described Similarity-Weighted, treat each face organ's of sketch facial image sketch map picture described in generation.
Optionally, described calculate respectively face images in described training storehouse and described in treat that telorism's conversion of the same face organ of sketch facial image comprises:
Described face organ's image for the treatment of sketch facial image is converted to binary edge map;
Calculate non-edge pixel in described binary edge map and put the range conversion value of edge pixel point;
Respectively the unique point of the same face organ of facial image in described training storehouse is mapped in described binary edge map;
The range conversion value sum of calculating respectively the same face organ's who trains facial image in storehouse described in described binary edge map unique point line converts as described telorism.
Optionally, described according to described telorism convert respectively in calculation training storehouse face images and described in treat that the same face organ's of sketch facial image similarity comprises:
In calculation training storehouse face images and described in treat the mean value avg of the same face organ's of sketch facial image telorism conversion;
In calculation training storehouse i open facial image and described in treat the same face organ's of sketch facial image similarity Sim
i, described in
wherein, described Sum
ibe in training storehouse i open facial image and described in treat the same face organ's of sketch facial image telorism conversion, described i is the natural number that is no more than N, described N is the number of facial image in described training storehouse.
Optionally, describedly superpose in the human face sketch template of facial image in described training storehouse after same face organ according to described Similarity-Weighted, treat that each face organ's of sketch facial image sketch map looks like to comprise described in generation:
According to the sketch template of the training storehouse facial image of described similarity select progressively predetermined number from high to low;
Described in weighted stacking described in the sketch template of the training storehouse facial image of predetermined number after same face organ, treat each face organ's of sketch facial image sketch map picture described in generation.
Optionally, described generation treats that each face organ's image of sketch facial image comprises:
Described in location, treat the human face characteristic point of sketch facial image;
According to each face organ's image for the treatment of sketch facial image described in described face characteristic dot generation.
According to the second aspect of disclosure embodiment, a kind of device that generates human face sketch is provided, comprising:
Organic image generation unit, for generating each face organ's image for the treatment of sketch facial image;
Organ sketch generation unit, for according to be kept in advance training storehouse facial image face organ's image and described in treat the same face organ's of sketch facial image similarity, treat each face organ's of sketch facial image sketch map picture described in generation;
Human face sketch generation unit, for treating the human face sketch of sketch facial image described in generating according to described each face organ's sketch map picture.
Optionally, described organ sketch generation unit comprises:
Transformation calculations subelement, for calculate respectively described training storehouse face images and described in treat the same face organ's of sketch facial image telorism conversion;
Similarity computation subunit, for convert according to described telorism calculation training storehouse face images respectively and described in treat the same face organ's of sketch facial image similarity;
Weighted stacking subelement, after same face organ in the sketch template of the described training storehouse facial image that superposes according to described Similarity-Weighted, treats each face organ's of sketch facial image sketch map picture described in generation.
Optionally, described transformation calculations subelement comprises:
Two-value modular converter, for being converted to binary edge map by described face organ's image for the treatment of sketch facial image;
Two-value computing module, puts the range conversion value of edge pixel point for calculating the non-edge pixel of described binary edge map;
Unique point mapping block, for being mapped to the same face organ's of described training storehouse facial image unique point in described binary edge map respectively;
Transformation calculations module, converts as described telorism for the range conversion value sum of the unique point line that calculates respectively the same face organ who trains storehouse facial image described in described binary edge map.
Optionally, described similarity computation subunit comprises:
Mean value calculation module, for calculation training storehouse face images and described in treat the mean value avg of the same face organ's of sketch facial image telorism conversion;
Similarity calculation module, for calculation training storehouse i open facial image and described in treat the same face organ's of sketch facial image similarity Sim
i, described in
wherein, described Sum
ibe in training storehouse i open facial image and described in treat the same face organ's of sketch facial image telorism conversion, described i is the natural number that is no more than N, described N is the number of facial image in described training storehouse.
Optionally, described weighted stacking subelement comprises:
Template is chosen module, for according to the sketch template of the training storehouse facial image of described similarity select progressively predetermined number from high to low;
Weighted stacking module, after same face organ described in the sketch template of the training storehouse facial image of predetermined number described in weighted stacking, treats each face organ's of sketch facial image sketch map picture described in generation.
Optionally, described organic image generation unit comprises:
Face characteristic locator unit, for treating the human face characteristic point of sketch facial image described in locating;
Organic image generates subelement, for according to each face organ's image for the treatment of sketch facial image described in described face characteristic dot generation.
According to the third aspect of disclosure embodiment, a kind of device that generates human face sketch is provided, comprising:
Processor;
For the storer of storage of processor executable instruction;
Wherein, described processor is configured to:
Each face organ's image of sketch facial image is treated in generation;
According to be kept in advance the facial image of training in storehouse face organ's image and described in treat the same face organ's of sketch facial image similarity, treat each face organ's of sketch facial image sketch map picture described in generation;
Described in generating according to described each face organ's sketch map picture, treat the human face sketch of sketch facial image.
The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect:
The disclosure is carried out face organ's classification by treating sketch facial image, thereby can overall thinking treat sketch facial image and the similarity of training the same face organ of facial image in storehouse, generate the same face organ's who treats sketch facial image sketch map picture according to this similarity, then treat each face organ's of sketch facial image sketch map picture by global adaptation, to generate the overall human face sketch for the treatment of sketch facial image, effectively improve the degree of accuracy of human face sketch.
The disclosure can generate the sketch map picture for the treatment of the same face organ of sketch facial image by the sketch template of facial image in the higher training storehouse of weighted stacking similarity, thereby effectively improves the degree of accuracy of each face organ's sketch of face.
The disclosure is for each face organ, can only calculate the range conversion value of each pixel on this face organ's who once treats sketch facial image binary edge map, then by telorism's conversion for the treatment of described in same face organ's unique point in training storehouse is mapped to calculate the same face organ of facial image in described training storehouse in this face organ's the binary edge map of sketch facial image, reduced data processing amount.
The disclosure can be by the exponential function of computational constant e by facial image in training storehouse with treat that the same face organ's of sketch facial image telorism conversion converts the similarity between 0 to 1 to, thereby can show more intuitively facial image in training storehouse and treat the same face organ's of sketch facial image similarity degree by data.
Should be understood that, it is only exemplary and explanatory that above general description and details are hereinafter described, and can not limit the disclosure.
Brief description of the drawings
Accompanying drawing is herein merged in instructions and forms the part of this instructions, shows and meets embodiment of the present disclosure, and be used from and explain principle of the present disclosure with instructions one.
Fig. 1 is according to the process flow diagram of a kind of method that generates human face sketch shown in an exemplary embodiment.
Fig. 2 is the process flow diagram that generates the method for human face sketch according to the another kind shown in an exemplary embodiment.
Fig. 3 is according to a kind of schematic diagram of training storehouse facial image and sketch template thereof shown in an exemplary embodiment.
Fig. 4 (a) is according to the bianry image schematic diagram of a kind of eye image for the treatment of sketch facial image shown in an exemplary embodiment.
Fig. 4 (b) is according to the binary edge map schematic diagram of a kind of eye image for the treatment of sketch facial image shown in an exemplary embodiment.
Fig. 4 (c) is the schematic diagram that the LLOD unique point of opening facial image according to i in the training storehouse shown in an exemplary embodiment is mapped to the right eye binary edge map for the treatment of sketch facial image.
Fig. 4 (d) is that the LLOD unique point of opening facial image according to i in the training storehouse shown in an exemplary embodiment is mapped to the line schematic diagram after the right eye binary edge map of sketch facial image.
Fig. 5 is according to the block diagram of a kind of device that generates human face sketch shown in an exemplary embodiment.
Fig. 6 is the block diagram that generates the device of human face sketch according to the another kind shown in an exemplary embodiment.
Fig. 7 is the block diagram that generates the device of human face sketch according to the another kind shown in an exemplary embodiment.
Fig. 8 is the block diagram that generates the device of human face sketch according to the another kind shown in an exemplary embodiment.
Fig. 9 is the block diagram that generates the device of human face sketch according to the another kind shown in an exemplary embodiment.
Figure 10 is the block diagram that generates the device of human face sketch according to the another kind shown in an exemplary embodiment.
Figure 11 is a kind of for generating the structural representation of device of human face sketch according to shown in an exemplary embodiment.
Embodiment
Here will at length describe exemplary embodiment, its sample table shows in the accompanying drawings.When description below relates to accompanying drawing, unless separately there is expression, the same numbers in different accompanying drawings represents same or analogous key element.Embodiment described in following exemplary embodiment does not represent all embodiments consistent with the disclosure.On the contrary, they are only and the example of apparatus and method as consistent in some aspects that described in detail in appended claims, of the present disclosure.
The term using in the disclosure is only for describing the object of specific embodiment, but not is intended to limit the disclosure." one ", " described " and " being somebody's turn to do " of the singulative using in disclosure and the accompanying claims book are also intended to comprise most forms, unless context clearly represents other implications.It is also understood that term "and/or" used herein refer to and comprise one or more projects of listing that are associated any or all may combine.
Although should be appreciated that in the disclosure and may adopt term first, second, third, etc. to describe various information, these information should not be limited to these terms.These terms are only used for the information of same type to be distinguished from each other out.For example, in the situation that not departing from disclosure scope, the first information also can be called as the second information, and similarly, the second information also can be called as the first information.Depend on linguistic context, as used in this word " if " can be construed as into " ... time " or " when ... time " or " in response to determine ".
Fig. 1 is according to the process flow diagram of a kind of method that generates human face sketch shown in an exemplary embodiment.
As shown in Figure 1, the method for this generation human face sketch can, in the terminals such as mobile phone, computer, flat-panel devices, comprise the following steps:
In step S101, generate each face organ's image for the treatment of sketch facial image.
In the present embodiment, get after sketch facial image, can will treat that sketch facial image carries out face organ's division according to face face, treat each face organ's image of sketch facial image described in generation.
In step S102, according to be kept in advance the facial image of training in storehouse face organ's image and described in treat the same face organ's of sketch facial image similarity, treat each face organ's of sketch facial image sketch map picture described in generation.
In the present embodiment, normally face organ's image of the pre-stored various real human face images of developer of face organ's image of facial image in described training storehouse, for comparing with treating sketch facial image.
In step S103, described in generating according to described each face organ's sketch map picture, treat the human face sketch of sketch facial image.
In the present embodiment, by treating that sketch facial image carries out face organ's classification, thereby can overall thinking treat sketch facial image and the similarity of training the same face organ of facial image in storehouse, generate the same face organ's who treats sketch facial image sketch map picture according to this similarity, then treat each face organ's of sketch facial image sketch map picture by global adaptation, to generate the overall human face sketch for the treatment of sketch facial image, effectively improve the degree of accuracy of human face sketch.
Fig. 2 is the process flow diagram that generates the method for human face sketch according to the another kind shown in an exemplary embodiment.
As shown in Figure 2, the method for this generation human face sketch can, in the terminals such as mobile phone, computer, flat-panel devices, comprise the following steps:
In step S201, treat the human face characteristic point of sketch facial image described in location.
In the present embodiment, shown in treat that sketch facial image can be the photo that user uses terminal taking, can be also the photo that user chooses in the photograph album of terminal, as long as there is face.
In the present embodiment, the human face characteristic point for the treatment of sketch facial image described in location can use the various location algorithms in correlation technique, such as: SDM (Supervised Descent Method, supervision descending method), AAM (Active Appearance Model, initiatively list item model) algorithm, ASM (Active Shape Model, active shape model) algorithm etc.The disclosure is not made particular restriction to this.
In step S202, according to each face organ's image for the treatment of sketch facial image described in described face characteristic dot generation.
Based on abovementioned steps S201, described in having located after the human face characteristic point of sketch facial image, according to the positioning result of this unique point, treat that by described sketch facial image carries out face organ's division, generate face organ image.Such as: can generate respectively left eye, right eye, Zuo Mei, right eyebrow, nose, mouth, left ear, these eight face organ's images of auris dextra.After generating face organ's image, the described same facial organic image for the treatment of facial image in sketch facial image and training storehouse is carried out to geometric transformation, unification is adjusted into onesize image, so that the follow-up processing of carrying out telorism's conversion.
Please refer to Fig. 3, according to an exemplary embodiment, a kind of schematic diagram of training storehouse facial image and sketch template thereof is shown.Shown in train the normally pre-stored various real human face images of developer of facial image in storehouse, for comparing with treating sketch facial image.Meanwhile, developer also can pre-stored described training storehouse in the sketch template of facial image, the namely sketch template of above-mentioned various real human face images, thinks that generating human face sketch provides basis.In the present embodiment, developer can also preserve each face organ's image and the corresponding sketch map picture of the facial image in described training storehouse in advance, to avoid the process of face organ's image of facial image in follow-up generation training storehouse, improves treatment effeciency.
In the present embodiment, by treating that sketch facial image divides according to face organ, thereby can consider on the whole to treat the similarity of the same face organ of facial image in sketch facial image and training storehouse, effectively improve the degree of accuracy of human face sketch.
In step S203, calculate respectively face images in described training storehouse and described in treat telorism's conversion of the same face organ of sketch facial image;
In the present embodiment, suppose that training has 100 facial images in storehouse, need to calculate respectively each facial image in these 100 facial images and described in treat telorism's conversion of the same face organ of sketch facial image.
Calculating this telorism's conversion can comprise:
1. described face organ's image for the treatment of sketch facial image is converted to binary edge map.
To treat that eye image in sketch facial image, as example, carried out binaryzation, as shown in Fig. 4 (a), obtain the bianry image of this eye image.Then, the bianry image of described eye image is carried out to rim detection, as shown in Fig. 4 (b), obtain the binary edge map of described eye image.
2. the non-edge pixel in the described binary edge map of calculating is put the range conversion value of edge pixel point.
Calculate non-edge pixel in above-mentioned binary edge map and put the range conversion value of edge pixel point
namely in Fig. 4 (b) white portion pixel to the range conversion value of pixel in black lines.Wherein, (x
i, y
i) be the coordinate of non-edge pixel point in described binary edge map.Described non-edge pixel point is far away apart from edge pixel point, its range conversion value
larger.On the contrary, described non-edge pixel point is nearer apart from edge pixel point, its range conversion value
less.
3. respectively the unique point of the same face organ of facial image in described training storehouse is mapped in described binary edge map.
Based on abovementioned steps S202, the same facial organic image for the treatment of facial image in sketch facial image and training storehouse is carried out to geometric transformation, size is identical, so the unique point of the same face organ of facial image in training storehouse can be mapped in aforementioned binary edge map.
Fig. 4 (c) is the schematic diagram that LLOD unique point that in training storehouse, i opens facial image is mapped to the right eye binary edge map for the treatment of sketch facial image.As shown in Fig. 4 (c), wherein, round dot represents to train the LLOD unique point that in storehouse, i opens facial image.It should be noted that, Fig. 4 (c) only shows the palpebra inferior unique point of facial image right eye in training storehouse, and as example, and in reality mapping, whole unique points of right eye need to be mapped in the above-mentioned right eye binary edge map for the treatment of sketch facial image.
Still in training storehouse, there are 100 facial images as example, described in respectively the unique point of the eye image of 100 facial images being mapped to, treat in the right eye binary edge map of sketch facial image.
4. calculating the range conversion value sum of training described in described binary edge map the same facial organ characteristic of facial image in storehouse to put line converts as described telorism.
In this step, the unique point line of the same face organ of training storehouse facial image in above-mentioned binary edge map will be mapped to, then the range conversion value of pixel on this line is added, as facial image in training storehouse and described in treat telorism's conversion of the same face organ of sketch facial image.
Fig. 4 (d) be described in LLOD unique point that in training storehouse, i opens facial image is mapped to after the right eye binary edge map of sketch facial image line schematic diagram.As shown in Fig. 4 (d), the range conversion value of each pixel on this unique point line that previous calculations is obtained
be added, wherein, (x
i, y
i) open the coordinate of each pixel on the LLOD unique point line of facial image for i in training storehouse.It should be noted that, Fig. 4 (d) only shows the palpebra inferior of facial image right eye in training storehouse, and as example, and in the process of actual computation, need to be by all unique point lines of right eye, (x
i, y
i) be the coordinate of each pixel on all unique point lines.Like this, just can obtain training i in storehouse to open the eye image of facial image and treat that the telorism of the eye image of sketch facial image converts.Be not difficult to find out, in training storehouse facial image and described in treat that same face organ's the telorism conversion of sketch facial image is less, illustrate facial image in training storehouse and described in treat the more picture of same facial organ of sketch facial image, contrary telorism's conversion is larger, illustrate facial image in training storehouse and described in treat sketch facial image same facial organ get over unlike.
In the present embodiment, for each face organ, can only calculate the range conversion value of each pixel on this face organ's who once treats sketch facial image binary edge map, then by telorism's conversion for the treatment of described in same face organ's unique point in training storehouse is mapped to calculate the same face organ of facial image in described training storehouse in this face organ's the binary edge map of sketch facial image, reduced data processing amount.
In step S204, according to described telorism convert face images in calculation training storehouse respectively and described in treat the same face organ's of sketch facial image similarity.
In the present embodiment, still suppose that training has 100 facial images in storehouse, need to calculate respectively each facial image in these 100 facial images and described in treat the same face organ's of sketch facial image similarity.
Calculating described similarity can comprise:
In calculation training storehouse face images and described in treat the mean value avg of the same face organ's of sketch facial image telorism conversion.
Based on abovementioned steps S203, obtain respectively training face images in storehouse and described in treat telorism's conversion of the same face organ of sketch facial image.Suppose, in described training storehouse i open facial image and described in treat that the right eye telorism of sketch facial image is transformed to Sum
i, described mean value
In calculation training storehouse i open facial image and described in treat the same face organ's of sketch facial image similarity Sim
i.
Described
Described i is the natural number that is no more than N, and described N is the number of facial image in described training storehouse.
In the present embodiment, by the exponential function of computational constant e, described telorism is converted to Sum
iconvert the similarity between 0 to 1 to, thereby can show more intuitively facial image in training storehouse and treat same face organ's the similarity degree of sketch facial image by data.
In the present embodiment, convert to calculate described same face organ's similarity by facial image in calculation training storehouse with the same face organ's who treats sketch facial image telorism, thereby effectively improve the degree of accuracy of each face organ's sketch of sketch.
In step S205, superpose in the human face sketch template of facial image in described training storehouse after same face organ according to described Similarity-Weighted, treat each face organ's of sketch facial image sketch map picture described in generation.
In the present embodiment, in weighted stacking training storehouse, in the human face sketch template of facial image, same face organ can comprise:
1. according to the sketch template of the training storehouse facial image of described similarity select progressively predetermined number from high to low.
Can find out based on abovementioned steps S204, in the higher explanation of similarity training storehouse facial image and the same face organ that treats sketch facial image more as, so, in generating human face sketch, according to the sketch template of the some or all of training of described similarity select progressively from high in the end storehouse facial image.Wherein, the number of choosing sketch template can be set according to the quantity of facial image in training storehouse by developer.Have 100 facial images as example taking training in storehouse, record through test, it is best that the sketch template of choosing facial image in front 20 training storehouses according to similarity order from high in the end generates the effect of sketch map picture.Certainly,, if the quantity of facial image, less than 20, also can be considered all to choose in training storehouse, the disclosure is not made particular restriction to this.
2. described in weighted stacking described in sketch template after same face organ, treat each face organ's of sketch facial image sketch map picture described in generation.
In the present embodiment, the similarity of calculating according to abovementioned steps S204 is come facial image and the weight for the treatment of the same face organ of sketch facial image in calculation training storehouse.Suppose and choose facial image in 20 training storehouses, described 20 same face organs' of training storehouse facial image similarity is respectively { S
1, S
2..., S
20, train k in storehouse to open the same face organ's of facial image weight
according to described weights W
k, train after the same face organ of sketch template of facial image in storehouse described in weighted stacking, described in just can generating, treat this face organ's of sketch facial image sketch map picture.
In the present embodiment, generate by the sketch template of facial image in the higher training storehouse of weighted stacking similarity the sketch map picture for the treatment of the same face organ of sketch facial image, thereby effectively improve the degree of accuracy of each face organ's sketch of face.
In step S206, described in generating according to described each face organ's sketch map picture, treat the human face sketch of sketch facial image.
In the present embodiment, the each face organ's who treats sketch facial image the sketch map picture generating based on abovementioned steps S205, looks like to carry out global adaptation by all face organs' sketch map, to treat the human face sketch of sketch facial image described in generating.
As seen from the above-described embodiment, by treating that sketch facial image carries out face organ's classification, thereby can overall thinking treat sketch facial image and the similarity of training the same face organ of facial image in storehouse, generate the same face organ's who treats sketch facial image sketch map picture according to this similarity, then treat each face organ's of sketch facial image sketch map picture by global adaptation, to generate the overall human face sketch for the treatment of sketch facial image, effectively improve the degree of accuracy of human face sketch.
Corresponding with the embodiment of the method for above-mentioned generation human face sketch, the disclosure also provides and has generated the device of human face sketch and the embodiment of terminal device.
Fig. 5 is that the disclosure is according to the block diagram of a kind of device that generates human face sketch shown in an exemplary embodiment.
As shown in Figure 5, described device comprises: organic image generation unit 501, organ sketch generation unit 502 and human face sketch generation unit 503.
Wherein, described organic image generation unit 501 is configured to: generate each face organ's image for the treatment of sketch facial image.
Described organ sketch generation unit 502 is configured to: according to be kept in advance the facial image of training in storehouse face organ's image and described in treat the same face organ's of sketch facial image similarity, treat each face organ's of sketch facial image sketch map picture described in generation.
Described human face sketch generation unit 503 is configured to: the human face sketch for the treatment of sketch facial image described in generating according to described each face organ's sketch map picture.
In above-described embodiment, by treating that sketch facial image carries out face organ's classification, thereby can overall thinking treat sketch facial image and the similarity of training the same face organ of facial image in storehouse, generate the same face organ's who treats sketch facial image sketch map picture according to this similarity, then treat each face organ's of sketch facial image sketch map picture by global adaptation, to generate the overall human face sketch for the treatment of sketch facial image, effectively improve the degree of accuracy of human face sketch.
Fig. 6 is the block diagram that generates the device of human face sketch according to the another kind shown in an exemplary embodiment, as shown in Figure 6, this embodiment is on the basis of the embodiment shown in earlier figures 5, and described organ sketch generation unit 502 can comprise: transformation calculations subelement 5021, similarity computation subunit 5022 and weighted stacking subelement 5023.
Wherein, described transformation calculations subelement 5021 is configured to: calculate respectively face images in described training storehouse and described in treat telorism's conversion of the same face organ of sketch facial image.
Described similarity computation subunit 5022 is configured to: according to described telorism convert face images in calculation training storehouse respectively and described in treat the same face organ's of sketch facial image similarity.
Described weighted stacking subelement 5023 is configured to: superpose in the sketch template of facial image in described training storehouse after same face organ according to described Similarity-Weighted, treat each face organ's of sketch facial image sketch map picture described in generation.
In above-described embodiment, convert to calculate described same face organ's similarity by facial image in calculation training storehouse with the same face organ's who treats sketch facial image telorism, thereby effectively improve the degree of accuracy of each face organ's sketch of face.
Fig. 7 is the block diagram that generates the device of human face sketch according to the another kind shown in an exemplary embodiment, as shown in Figure 7, this embodiment is on the basis of the embodiment shown in earlier figures 6, described transformation calculations subelement 5021 can comprise: two-value modular converter 5021a, two-value computing module 5021b, unique point mapping block 5021c and transformation calculations module 5021d.
Wherein, described two-value modular converter 5021a is configured to: described face organ's image for the treatment of sketch facial image is converted to binary edge map.
Described two-value computing module 5021b is configured to: the range conversion value of calculating non-edge pixel in described bianry image and put edge pixel point.
Described unique point mapping block 5021c is configured to: respectively the unique point of the same face organ of facial image in described training storehouse is mapped in described bianry image.
Described transformation calculations module 5021d is configured to: calculate the range conversion value sum of training the same facial organ characteristic of facial image in storehouse to put line described in described bianry image and convert as described telorism.
In above-described embodiment, for each face organ, can only calculate the range conversion value of each pixel on this face organ's who once treats sketch facial image binary edge map, then by telorism's conversion for the treatment of described in same face organ's unique point in training storehouse is mapped to calculate the same face organ of facial image in described training storehouse in this face organ's the binary edge map of sketch facial image, reduced data processing amount.
Fig. 8 is the block diagram that generates the device of human face sketch according to the another kind shown in an exemplary embodiment, as shown in Figure 8, this embodiment is on the basis of the embodiment shown in earlier figures 6, and described similarity computation subunit 5022 can comprise: mean value calculation module 5022a and similarity calculation module 5022b.
Wherein, described mean value calculation module 5022a is configured to: in calculation training storehouse face images and described in treat the mean value avg of the same face organ's of sketch facial image telorism conversion.
Described similarity calculation module 5022b is configured to: in calculation training storehouse i open facial image and described in treat the same face organ's of sketch facial image similarity Sim (i), described in
wherein Sum (i) be in training storehouse i open facial image and described in treat the same face organ's of sketch facial image telorism conversion, described i is the natural number that is no more than N, described N is the number of facial image in described training storehouse.
In above-described embodiment, exponential function by computational constant e is by facial image in training storehouse and treat that telorism's conversion of the same face organ of sketch facial image converts the similarity between 0 to 1 to, thereby can be shown more intuitively facial image in training storehouse and be treated the same face organ's of sketch facial image similarity degree by data.
It should be noted that, the structure of the similarity computation subunit 5022 in the device embodiment shown in above-mentioned Fig. 8 also can be included in the device embodiment of earlier figures 7, and this disclosure is not limited.
Fig. 9 is the block diagram that generates the device of human face sketch according to the another kind shown in an exemplary embodiment, as shown in Figure 9, this embodiment is on the basis of the embodiment shown in earlier figures 6, and described weighted stacking subelement 5023 can comprise: template is chosen module 5023a and weighted stacking module 5023b.
Wherein, described template is chosen module 5023a and is configured to: according to the sketch template of the training storehouse facial image of described similarity select progressively predetermined number from high to low.
Described weighted stacking module 5023b is configured to: described in weighted stacking described in the sketch template of the training storehouse facial image of predetermined number after same face organ, treat each face organ's of sketch facial image sketch map picture described in generation.
In above-described embodiment, generate by the sketch template of facial image in the higher training storehouse of weighted stacking similarity the sketch map picture for the treatment of the same face organ of sketch facial image, thereby effectively improve the degree of accuracy of each face organ's sketch of face.
It should be noted that, the structure of the weighted stacking subelement 5023 in the device embodiment shown in above-mentioned Fig. 9 also can be included in the device embodiment of earlier figures 7 or Fig. 8, and this disclosure is not limited.
Figure 10 is the block diagram that generates the device of human face sketch according to the another kind shown in an exemplary embodiment, as shown in figure 10, this embodiment is on the basis of the embodiment shown in earlier figures 5, and described organic image generation unit 501 can comprise: face characteristic locator unit 5011 and organic image generate subelement 5012.
Wherein, described face characteristic locator unit 5011 is configured to: the human face characteristic point for the treatment of sketch facial image described in location;
Described organic image generates subelement 5012 and is configured to: according to each face organ's image for the treatment of sketch facial image described in described face characteristic dot generation.
In above-described embodiment, by treating that sketch map picture divides according to face organ, thereby can consider on the whole to treat the similarity of the same face organ of facial image in the training storehouse of sketch map picture, effectively improve the degree of accuracy of human face sketch.
It should be noted that, the structure of the organic image generation unit 501 in the device embodiment shown in above-mentioned Figure 10 also can be included in the device embodiment of earlier figures 6 to Fig. 9, and this disclosure is not limited.
In said apparatus, the implementation procedure of the function and efficacy of unit specifically refers to the implementation procedure of corresponding step in said method, does not repeat them here.
For device embodiment, because it corresponds essentially to embodiment of the method, so relevant part is referring to the part explanation of embodiment of the method.Device embodiment described above is only schematic, the wherein said unit as separating component explanation can or can not be also physically to separate, the parts that show as unit can be or can not be also physical locations, can be positioned at a place, or also can be distributed in multiple network element.Can select according to the actual needs some or all of module wherein to realize the object of disclosure scheme.Those of ordinary skill in the art, in the situation that not paying creative work, are appreciated that and implement.
Accordingly, the disclosure also provides a kind of device that generates human face sketch, and described device comprises: processor; For the storer of storage of processor executable instruction; Wherein, described processor is configured to: generate each face organ's image for the treatment of sketch facial image; According to be kept in advance the facial image of training in storehouse face organ's image and described in treat the same face organ's of sketch facial image similarity, treat each face organ's of sketch facial image sketch map picture described in generation; Described in generating according to described each face organ's sketch map picture, treat the human face sketch of sketch facial image.
Accordingly, the disclosure also provides a kind of non-provisional computer-readable recording medium, in the time that the instruction in described storage medium is carried out by the processor of terminal device, make terminal can carry out a kind of method that generates human face sketch, described method comprises: generate each face organ's image for the treatment of sketch facial image; According to be kept in advance the facial image in described training storehouse face organ's image and described in treat the same face organ's of sketch facial image similarity, treat each face organ's of sketch facial image sketch map picture described in generation; Described in generating according to described each face organ's sketch map picture, treat the human face sketch of sketch facial image.
What as shown in figure 11, Figure 11 was the disclosure according to shown in an exemplary embodiment is a kind of for generating another structural representation of device 1100 of human face sketch.For example, device 1100 can be the mobile phone with routing function, computing machine, digital broadcast terminal, information receiving and transmitting equipment, game console, flat-panel devices, Medical Devices, body-building equipment, personal digital assistant etc.
With reference to Figure 11, device 1100 can comprise following one or more assembly: processing components 1102, storer 1104, power supply module 1106, multimedia groupware 1108, audio-frequency assembly 1110, the interface 1112 of I/O (I/O), sensor module 1114, and communications component 1116.
The integrated operation of processing components 1102 common control device 1100, such as with demonstration, call, data communication, the operation that camera operation and record operation are associated.Processing components 1102 can comprise that one or more processors 1120 carry out instruction, to complete all or part of step of above-mentioned method.In addition, processing components 1102 can comprise one or more modules, is convenient to mutual between processing components 1102 and other assemblies.For example, processing components 1102 can comprise multi-media module, to facilitate mutual between multimedia groupware 1108 and processing components 1102.
Storer 1104 is configured to store various types of data to be supported in the operation of device 1100.The example of these data comprises for any application program of operation on device 1100 or the instruction of method, contact data, telephone book data, message, picture, video etc.Storer 1104 can be realized by the volatibility of any type or non-volatile memory device or their combination, as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM), programmable read only memory (PROM), ROM (read-only memory) (ROM), magnetic store, flash memory, disk or CD.
Power supply module 1106 provides electric power for installing 1100 various assemblies.Power supply module 1106 can comprise power-supply management system, one or more power supplys, and other and the assembly that generates, manages and distribute electric power to be associated for device 1100.
Multimedia groupware 1108 is included in the screen that an output interface is provided between described device 1100 and user.In certain embodiments, screen can comprise liquid crystal display (LCD) and touch panel (TP).If screen comprises touch panel, screen may be implemented as touch-screen, to receive the input signal from user.Touch panel comprises that one or more touch sensors are with the gesture on sensing touch, slip and touch panel.Described touch sensor is the border of sensing touch or sliding action not only, but also detects duration and the pressure relevant to described touch or slide.In certain embodiments, multimedia groupware 1108 comprises a front-facing camera and/or post-positioned pick-up head.When device 1100 is in operator scheme, during as screening-mode or video mode, front-facing camera and/or post-positioned pick-up head can receive outside multi-medium data.Each front-facing camera and post-positioned pick-up head can be fixing optical lens systems or have focal length and optical zoom ability.
Audio-frequency assembly 1110 is configured to output and/or input audio signal.For example, audio-frequency assembly 1110 comprises a microphone (MIC), and when device 1100 is in operator scheme, during as call model, logging mode and speech recognition mode, microphone is configured to receive external audio signal.The sound signal receiving can be further stored in storer 1104 or be sent via communications component 1116.In certain embodiments, audio-frequency assembly 1110 also comprises a loudspeaker, for output audio signal.
I/O interface 1112 is for providing interface between processing components 1102 and peripheral interface module, and above-mentioned peripheral interface module can be keyboard, some striking wheel, button etc.These buttons can include but not limited to: home button, volume button, start button and locking press button.
Sensor module 1114 comprises one or more sensors, is used to device 1100 that the state estimation of various aspects is provided.For example, sensor module 1114 can detect the opening/closing state of device 1100, the relative positioning of assembly, for example described assembly is display and the keypad of device 1100, the position of all right pick-up unit 1100 of sensor module 1114 or 1100 assemblies of device changes, user is with device 1100 existence that contact or do not have the temperature variation of device 1100 orientation or acceleration/deceleration and device 1100.Sensor module 1114 can comprise proximity transducer, be configured to without any physical contact time detect near the existence of object.Sensor module 1114 can also comprise optical sensor, as CMOS or ccd image sensor, for using in imaging applications.In certain embodiments, this sensor module 1114 can also comprise acceleration transducer, gyro sensor, Magnetic Sensor, pressure transducer, microwave remote sensor or temperature sensor.
Communications component 1116 is configured to be convenient to the communication of wired or wireless mode between device 1100 and other equipment.Device 1100 wireless networks that can access based on communication standard, as WiFi, 2G or 3G, or their combination.In one exemplary embodiment, communications component 1116 receives broadcast singal or the broadcast related information from external broadcasting management system via broadcast channel.In one exemplary embodiment, described communications component 1116 also comprises near-field communication (NFC) module, to promote junction service.For example, can be based on radio-frequency (RF) identification (RFID) technology in NFC module, Infrared Data Association (IrDA) technology, ultra broadband (UWB) technology, bluetooth (BT) technology and other technologies realize.
In the exemplary embodiment, device 1100 can be realized by one or more application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD) (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components, for carrying out said method.
In the exemplary embodiment, also provide a kind of non-provisional computer-readable recording medium that comprises instruction, for example, comprised the storer 1104 of instruction, above-mentioned instruction can have been carried out said method by the processor 1120 of device 1100.For example, described non-provisional computer-readable recording medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk and optical data storage equipment etc.
Those skilled in the art, considering instructions and putting into practice after disclosed herein disclosing, will easily expect other embodiment of the present disclosure.The application is intended to contain any modification of the present disclosure, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present disclosure and comprised undocumented common practise or the conventional techniques means in the art of the disclosure.Instructions and embodiment are only regarded as exemplary, and true scope of the present disclosure and spirit are pointed out by claim below.
Should be understood that, the disclosure is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendments and change not departing from its scope.The scope of the present disclosure is only limited by appended claim.
Claims (13)
1. a method that generates human face sketch, is characterized in that, comprising:
Each face organ's image of sketch facial image is treated in generation;
According to be kept in advance the facial image of training in storehouse face organ's image and described in treat the same face organ's of sketch facial image similarity, treat each face organ's of sketch facial image sketch map picture described in generation;
Described in generating according to described each face organ's sketch map picture, treat the human face sketch of sketch facial image.
2. method according to claim 1, is characterized in that,
Described basis be kept in advance the facial image of training in storehouse face organ's image and described in treat the same face organ's of sketch facial image similarity, treat that each face organ's of sketch facial image sketch map looks like to comprise described in generation:
Calculate respectively face images in described training storehouse and described in treat telorism's conversion of the same face organ of sketch facial image;
According to described telorism convert face images in calculation training storehouse respectively and described in treat the same face organ's of sketch facial image similarity;
Superpose in the sketch template of facial image in described training storehouse after same face organ according to described Similarity-Weighted, treat each face organ's of sketch facial image sketch map picture described in generation.
3. method according to claim 2, is characterized in that,
Described calculate respectively face images in described training storehouse and described in treat that telorism's conversion of the same face organ of sketch facial image comprises:
Described face organ's image for the treatment of sketch facial image is converted to binary edge map;
Calculate non-edge pixel in described binary edge map and put the range conversion value of edge pixel point;
Respectively the unique point of the same face organ of facial image in described training storehouse is mapped in described binary edge map;
The range conversion value sum of calculating respectively the same face organ's who trains facial image in storehouse described in described binary edge map unique point line converts as described telorism.
4. method according to claim 2, is characterized in that,
Described according to described telorism convert respectively in calculation training storehouse face images and described in treat that the same face organ's of sketch facial image similarity comprises:
In calculation training storehouse face images and described in treat the mean value avg of the same face organ's of sketch facial image telorism conversion;
In calculation training storehouse i open facial image and described in treat the same face organ's of sketch facial image similarity Sim
i, described in
wherein, described Sum
ibe in training storehouse i open facial image and described in treat the same face organ's of sketch facial image telorism conversion, described i is the natural number that is no more than N, described N is the number of facial image in described training storehouse.
5. method according to claim 2, is characterized in that,
Describedly superpose in the human face sketch template of facial image in described training storehouse after same face organ according to described Similarity-Weighted, treat that each face organ's of sketch facial image sketch map looks like to comprise described in generation:
According to the sketch template of the training storehouse facial image of described similarity select progressively predetermined number from high to low;
Described in weighted stacking described in the sketch template of the training storehouse facial image of predetermined number after same face organ, treat each face organ's of sketch facial image sketch map picture described in generation.
6. method according to claim 1, is characterized in that,
Described generation treats that each face organ's image of sketch facial image comprises:
Described in location, treat the human face characteristic point of sketch facial image;
According to each face organ's image for the treatment of sketch facial image described in described face characteristic dot generation.
7. a device that generates human face sketch, is characterized in that, comprising:
Organic image generation unit, for generating each face organ's image for the treatment of sketch facial image;
Organ sketch generation unit, for according to be kept in advance training storehouse facial image face organ's image and described in treat the same face organ's of sketch facial image similarity, treat each face organ's of sketch facial image sketch map picture described in generation;
Human face sketch generation unit, for treating the human face sketch of sketch facial image described in generating according to described each face organ's sketch map picture.
8. device according to claim 7, is characterized in that, described organ sketch generation unit comprises:
Transformation calculations subelement, for calculate respectively described training storehouse face images and described in treat the same face organ's of sketch facial image telorism conversion;
Similarity computation subunit, for convert according to described telorism calculation training storehouse face images respectively and described in treat the same face organ's of sketch facial image similarity;
Weighted stacking subelement, after same face organ in the sketch template of the described training storehouse facial image that superposes according to described Similarity-Weighted, treats each face organ's of sketch facial image sketch map picture described in generation.
9. device according to claim 8, is characterized in that, described transformation calculations subelement comprises:
Two-value modular converter, for being converted to binary edge map by described face organ's image for the treatment of sketch facial image;
Two-value computing module, puts the range conversion value of edge pixel point for calculating the non-edge pixel of described binary edge map;
Unique point mapping block, for being mapped to the same face organ's of described training storehouse facial image unique point in described binary edge map respectively;
Transformation calculations module, converts as described telorism for the range conversion value sum of the unique point line that calculates respectively the same face organ who trains storehouse facial image described in described binary edge map.
10. device according to claim 8, is characterized in that, described similarity computation subunit comprises:
Mean value calculation module, for calculation training storehouse face images and described in treat the mean value avg of the same face organ's of sketch facial image telorism conversion;
Similarity calculation module, for calculation training storehouse i open facial image and described in treat the same face organ's of sketch facial image similarity Sim
i, described in
wherein, described Sum
ibe in training storehouse i open facial image and described in treat the same face organ's of sketch facial image telorism conversion, described i is the natural number that is no more than N, described N is the number of facial image in described training storehouse.
11. devices according to claim 8, is characterized in that, described weighted stacking subelement comprises:
Template is chosen module, for according to the sketch template of the training storehouse facial image of described similarity select progressively predetermined number from high to low;
Weighted stacking module, after same face organ described in the sketch template of the training storehouse facial image of predetermined number described in weighted stacking, treats each face organ's of sketch facial image sketch map picture described in generation.
12. devices according to claim 7, is characterized in that, described organic image generation unit comprises:
Face characteristic locator unit, for treating the human face characteristic point of sketch facial image described in locating;
Organic image generates subelement, for according to each face organ's image for the treatment of sketch facial image described in described face characteristic dot generation.
13. 1 kinds generate the device of human face sketch, it is characterized in that, comprising:
Processor;
For the storer of storage of processor executable instruction;
Wherein, described processor is configured to:
Each face organ's image of sketch facial image is treated in generation;
According to be kept in advance the facial image of training in storehouse face organ's image and described in treat the same face organ's of sketch facial image similarity, treat each face organ's of sketch facial image sketch map picture described in generation;
Described in generating according to described each face organ's sketch map picture, treat the human face sketch of sketch facial image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410286120.2A CN104123741A (en) | 2014-06-24 | 2014-06-24 | Method and device for generating human face sketch |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410286120.2A CN104123741A (en) | 2014-06-24 | 2014-06-24 | Method and device for generating human face sketch |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104123741A true CN104123741A (en) | 2014-10-29 |
Family
ID=51769138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410286120.2A Pending CN104123741A (en) | 2014-06-24 | 2014-06-24 | Method and device for generating human face sketch |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104123741A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700439A (en) * | 2015-03-12 | 2015-06-10 | 陕西炬云信息科技有限公司 | Single target portrait-based face portrait compositing method |
| CN105512614A (en) * | 2015-11-26 | 2016-04-20 | 北京像素软件科技股份有限公司 | Game role generation method and device |
| CN105989584A (en) * | 2015-01-29 | 2016-10-05 | 北京大学 | Image stylized reconstruction method and device |
| CN106296569A (en) * | 2015-06-11 | 2017-01-04 | 腾讯科技（深圳）有限公司 | The method and apparatus drawing portrait stick figure |
| CN107729840A (en) * | 2017-10-13 | 2018-02-23 | 深圳市唯特视科技有限公司 | One kind is based on sparse figured face recognition discriminant analysis method |
| CN107967667A (en) * | 2017-12-21 | 2018-04-27 | 广东欧珀移动通信有限公司 | Generation method, device, terminal device and the storage medium of sketch |
| CN109785439A (en) * | 2018-12-27 | 2019-05-21 | 深圳云天励飞技术有限公司 | Human face sketch image generating method and Related product |
| CN110570480A (en) * | 2019-07-19 | 2019-12-13 | 广东智媒云图科技股份有限公司 | Sketch drawing method of drawing robot, electronic equipment and storage medium |
| CN113222058A (en) * | 2021-05-28 | 2021-08-06 | 新疆爱华盈通信息技术有限公司 | Image classification method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101034481A (en) * | 2007-04-06 | 2007-09-12 | 湖北莲花山计算机视觉和信息科学研究院 | Method for automatically generating portrait painting |
| CN101216882A (en) * | 2007-12-28 | 2008-07-09 | 北京中星微电子有限公司 | A method and device for positioning and tracking on corners of the eyes and mouths of human faces |
| CN101159064B (en) * | 2007-11-29 | 2010-09-01 | 腾讯科技（深圳）有限公司 | Image generation system and method for generating image |
-
2014
- 2014-06-24 CN CN201410286120.2A patent/CN104123741A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101034481A (en) * | 2007-04-06 | 2007-09-12 | 湖北莲花山计算机视觉和信息科学研究院 | Method for automatically generating portrait painting |
| CN101159064B (en) * | 2007-11-29 | 2010-09-01 | 腾讯科技（深圳）有限公司 | Image generation system and method for generating image |
| CN101216882A (en) * | 2007-12-28 | 2008-07-09 | 北京中星微电子有限公司 | A method and device for positioning and tracking on corners of the eyes and mouths of human faces |
Non-Patent Citations (1)
| Title |
|---|
| NAYE JI等: "Local Regression Model for Automatic Face Sketch Generation", 《IMAGE AND GRAPHICS(ICIG),2011 SIXTH INTERNATIONAL CONFERENCE ON》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989584A (en) * | 2015-01-29 | 2016-10-05 | 北京大学 | Image stylized reconstruction method and device |
| CN105989584B (en) * | 2015-01-29 | 2019-05-14 | 北京大学 | The method and apparatus that image stylization is rebuild |
| CN104700439B (en) * | 2015-03-12 | 2017-08-15 | 陕西炬云信息科技有限公司 | The human face portrait synthetic method drawn a portrait based on individual target |
| CN104700439A (en) * | 2015-03-12 | 2015-06-10 | 陕西炬云信息科技有限公司 | Single target portrait-based face portrait compositing method |
| CN106296569B (en) * | 2015-06-11 | 2019-08-02 | 腾讯科技（深圳）有限公司 | The method and apparatus for drawing portrait stick figure |
| CN106296569A (en) * | 2015-06-11 | 2017-01-04 | 腾讯科技（深圳）有限公司 | The method and apparatus drawing portrait stick figure |
| CN105512614A (en) * | 2015-11-26 | 2016-04-20 | 北京像素软件科技股份有限公司 | Game role generation method and device |
| CN107729840A (en) * | 2017-10-13 | 2018-02-23 | 深圳市唯特视科技有限公司 | One kind is based on sparse figured face recognition discriminant analysis method |
| CN107967667A (en) * | 2017-12-21 | 2018-04-27 | 广东欧珀移动通信有限公司 | Generation method, device, terminal device and the storage medium of sketch |
| CN109785439A (en) * | 2018-12-27 | 2019-05-21 | 深圳云天励飞技术有限公司 | Human face sketch image generating method and Related product |
| CN109785439B (en) * | 2018-12-27 | 2023-08-01 | 深圳云天励飞技术有限公司 | Face sketch image generation method and related products |
| CN110570480A (en) * | 2019-07-19 | 2019-12-13 | 广东智媒云图科技股份有限公司 | Sketch drawing method of drawing robot, electronic equipment and storage medium |
| CN110570480B (en) * | 2019-07-19 | 2023-03-24 | 广东智媒云图科技股份有限公司 | Sketch drawing method of drawing robot, electronic equipment and storage medium |
| CN113222058A (en) * | 2021-05-28 | 2021-08-06 | 新疆爱华盈通信息技术有限公司 | Image classification method and device, electronic equipment and storage medium |
| CN113222058B (en) * | 2021-05-28 | 2024-05-10 | 芯算一体(深圳)科技有限公司 | Image classification method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104123741A (en) | Method and device for generating human face sketch | |
| CN110163048B (en) | Hand key point recognition model training method, hand key point recognition method and hand key point recognition equipment | |
| CN109614876A (en) | Critical point detection method and device, electronic equipment and storage medium | |
| CN105205479A (en) | Human face value evaluation method, device and terminal device | |
| CN108121952A (en) | Face key independent positioning method, device, equipment and storage medium | |
| CN106845398B (en) | Face key point positioning method and device | |
| CN105447462A (en) | Facial pose estimation method and device | |
| CN110807325B (en) | Predicate identification method, predicate identification device and storage medium | |
| CN111696570B (en) | Voice signal processing method, device, equipment and storage medium | |
| US10326928B2 (en) | Image processing apparatus for determining whether section of target area matches section of person area and control method thereof | |
| CN106845377A (en) | Face key independent positioning method and device | |
| CN107958223B (en) | Face recognition method and device, mobile equipment and computer readable storage medium | |
| CN110147533B (en) | Encoding method, apparatus, device and storage medium | |
| CN108922531B (en) | Slot position identification method and device, electronic equipment and storage medium | |
| CN105426878B (en) | Face cluster method and device | |
| CN111931946A (en) | Data processing method and device, computer equipment and storage medium | |
| CN104077585A (en) | Image correction method and device and terminal | |
| CN104063865A (en) | Classification model creation method, image segmentation method and related device | |
| CN111581958A (en) | Conversation state determining method and device, computer equipment and storage medium | |
| CN105335753A (en) | Image recognition method and device | |
| US20210158031A1 (en) | Gesture Recognition Method, and Electronic Device and Storage Medium | |
| CN109241875B (en) | Attitude detection method and apparatus, electronic device, and storage medium | |
| CN111589138B (en) | Action prediction method, device, equipment and storage medium | |
| EP4040332A1 (en) | Method and apparatus for upgrading an intelligent model and non-transitory computer readable storage medium | |
| CN110503160A (en) | Image-recognizing method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20141029 |