CN117496019B - Image animation processing method and system for driving static image - Google Patents
Image animation processing method and system for driving static image Download PDFInfo
- Publication number
- CN117496019B CN117496019B CN202311841510.7A CN202311841510A CN117496019B CN 117496019 B CN117496019 B CN 117496019B CN 202311841510 A CN202311841510 A CN 202311841510A CN 117496019 B CN117496019 B CN 117496019B
- Authority
- CN
- China
- Prior art keywords
- module
- face
- image
- dimensional
- user
- 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 230000003068 static effect Effects 0.000 title abstract description 8
- 238000010276 construction Methods 0.000 claims abstract description 58
- 238000005286 illumination Methods 0.000 claims abstract description 53
- 238000012545 processing Methods 0.000 claims abstract description 42
- 238000001914 filtration Methods 0.000 claims abstract description 27
- 230000002146 bilateral effect Effects 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000012360 testing method Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 9
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000003014 reinforcing effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 5
- 238000000605 extraction Methods 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005477 standard model Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
- G06T13/20—3D [Three Dimensional] animation
- G06T13/40—3D [Three Dimensional] animation of characters, e.g. humans, animals or virtual beings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an image animation processing method and system for driving a static image, which relates to the field of image processing and comprises the following steps: the user login module is used for logging in the system by the user; the algorithm reading module is used for reading the user information sent by the user login module and reading a face three-dimensional construction algorithm of a corresponding user in the database module; according to the image animation processing method and the system for driving the static image, the image animation processing for driving the static image can be realized by carrying out three-dimensional reconstruction on the image, meanwhile, the illumination component is filtered through bilateral filtering, and the edge information in the face image is kept; and eliminating halation artifacts generated in the face enhancement process by using the thought of local standard deviation; and the color tone reconstruction is carried out, the image saturation and color distortion are prevented, and the accuracy of the image extraction of the low-illumination image can be ensured.
Description
Technical Field
The invention relates to an image processing technology, in particular to an image animation processing method and system for driving a static image.
Background
With the popularization and application of intelligent electronic devices such as mobile phones and tablet computers, especially with the continuous upgrade of camera hardware and the maturation of face recognition technology, more and more users like to take pictures by using mobile phones, and mobile phone photographing has gradually replaced camera photographing. Although the existing mobile phone photographing technology can perform some simple processes on photos, such as beautifying, toning, blurring the background, etc., photos processed by the image processing technology are still images.
The current method of reconstructing three-dimensional faces from single Zhang Ren face images uses the most two main classes. One type is a method based on standard model deformation, i.e. personalized information (most of key point information) of a face is extracted from an image, and a standard face model is deformed into a personalized face model according to the personalized information. The model is deformed without prior knowledge of the face, so that the method has weak sense of reality and is easy to generate a non-face. The second type of method is a method based on a face deformation model, namely, a face deformation model is built from a face model which is actually scanned, and the shape and texture of the face are obtained by fitting an input image. The method can obtain a reconstruction result with sense of reality, and has the defects of large calculation amount and incapability of complete automation.
Disclosure of Invention
The present invention is directed to a method and a system for processing an image animation for driving a still image, which solve the above-mentioned drawbacks of the prior art.
In order to achieve the above object, the present invention provides the following technical solutions: an image animation processing system that drives a still image, comprising:
the user login module is used for logging in the system by the user;
the algorithm reading module is used for reading the user information sent by the user login module and reading a face three-dimensional construction algorithm of a corresponding user in the database module;
the face image acquisition module is used for acquiring a face two-dimensional image of a current login user;
the face illuminance judging module is used for judging the face illuminance in the face two-dimensional image acquired by the face picture acquiring module;
the low-illumination face recognition module is used for carrying out low-illumination face recognition on the two-dimensional image with the face judgment result of low illumination in the face illumination judgment module;
the face classification module is used for classifying pictures according to the face positions in the face two-dimensional images and the face shooting angles;
the three-dimensional construction module is used for constructing a face three-dimensional animation according to the face two-dimensional image;
the system comprises a portrait video acquisition module, a portrait video processing module and a portrait video processing module, wherein the portrait video acquisition module is used for collecting the portrait video of the current user in real time;
the video portrait acquisition module is used for acquiring the user portrait in the portrait video acquired by the portrait video acquisition module;
the comparison module is used for comparing the user portrait acquired by the video portrait acquisition module with the three-dimensional portrait constructed by the three-dimensional construction module;
and the database module is used for storing the comparison result in the comparison module through a three-dimensional construction algorithm and binding the comparison result with the current user identity information.
Further, the low-illumination face recognition module includes:
an illuminance enhancement module, the illuminance enhancement module comprising:
the bilateral filtering processing module is used for keeping the edge and detail information of the image;
the local standard deviation processing module is used for processing the image processed by the bilateral filtering processing module, eliminating the influence of illumination components and removing halation and artifacts;
the tone reconstruction module is used for reconstructing the components of the image processed by the contrast components;
and the face recognition module is used for carrying out face recognition.
Further, the specific working method of the illumination enhancement module is as follows:
a1, collecting a low-illumination face image;
a2, carrying out logarithmic transformation on the face image, extracting an illumination component, and stretching the illumination component by using Gamma correction to improve the overall brightness of the image;
a3, taking the Gamma corrected image as an input image for improving the Retinex algorithm, and using bilateral filtering processing to enable the image to keep edge and detail information;
a4, processing the image after bilateral filtering through a local standard deviation, eliminating the influence of illumination components, and removing halation and artifacts;
and A5, reconstructing the components of the image processed by the bilateral filtering and the local standard deviation through the adaptive tone reconstruction after the illumination components of the image processed by the bilateral filtering and the local standard deviation are processed.
Further, the specific working method of the face recognition module is as follows:
b1, obtaining a face image reinforced by an illuminance reinforcing module;
b2, extracting features from the edge area of the face image with enhanced contrast by using a Gabor filter to obtain a histogram sequence;
b3, adding 4 symbiotic matrixes in different directions on the basis of an LBP algorithm to extract the features of the illumination-unchanged local area of the face image to obtain a histogram sequence;
converting the edge features of the face image extracted by Gabor filtering and the local face feature histogram extracted by improving multiple thresholds into one-dimensional feature vectors, and carrying out serial fusion on all the feature vectors;
and B5, reducing the dimension of the feature vector of the fused histogram to generate a final feature map.
Further, the three-dimensional building block includes:
the three-dimensional construction algorithm input module is used for inputting three-dimensional construction algorithms aiming at different pictures;
the three-dimensional construction algorithm selection module is used for selecting a proper three-dimensional construction algorithm according to the currently acquired face picture;
the three-dimensional construction module is used for carrying out three-dimensional construction on the current picture according to the three-dimensional construction algorithm selected by the three-dimensional construction algorithm selection module.
Further, the face classification module includes:
the data preprocessing module is used for carrying out gray processing on the data picture and converting a plurality of channels into single-channel data;
the template selecting module is used for selecting a proper picture template;
the classification template making module is used for making a proper classification template according to the template selected by the classification template selecting module;
the picture dividing module is used for dividing the pictures into a training set and a testing set;
a data set construction module for reconstructing a data set;
the data tag module is used for reconstructing the data tag;
and the data equalization module is used for performing data equalization.
Further, the specific working method of the face classification module is as follows:
c1, carrying out gray processing on the data picture, and converting a plurality of channels into single-channel data;
c2, dividing the picture subjected to the graying treatment into a training set and a testing set;
c3, selecting a proper picture template;
c4, making a proper classification template according to the picture template;
c5, constructing a new data set by the classification template, the training set and the test set together;
c6, setting a new data tag according to the new data set;
and C7, carrying out data equalization according to the new data tag.
An image animation processing method for driving a still image, wherein the image animation processing method for driving the still image comprises the following steps:
s1, a user logs in a system through a user login module;
s2, the algorithm reading module reads the user information sent by the user login module and reads the face three-dimensional construction algorithm of the corresponding user in the database module, if the algorithm reading module reads the face three-dimensional construction algorithm of the corresponding user, the step S7 is executed, and if the algorithm reading module does not read the face three-dimensional construction algorithm of the corresponding user, the step S3 is executed;
s3, acquiring a face two-dimensional image of the current login user through a face picture acquisition module;
s4, judging the face illuminance in the face two-dimensional image through a face illuminance judging module, executing a step S5 if the judging result is low illuminance, and executing a step S6 if the judging result is non-low illuminance;
s5, carrying out low-illumination face recognition on the two-dimensional image with the low illumination by the low-illumination face recognition module;
s6, classifying pictures according to the face positions in the face two-dimensional images and the face shooting angles through a face classification module;
s7, constructing a face three-dimensional animation according to the face two-dimensional image through a three-dimensional construction module;
s8, collecting the portrait video of the current user in real time through a portrait video acquisition module;
s9, acquiring a user figure in the figure video acquired by the figure video acquisition module through the video figure acquisition module;
s10, comparing the user portrait acquired by the video portrait acquisition module with the three-dimensional portrait constructed by the three-dimensional construction module through the comparison module, if the comparison result passes, executing the step S11, and if the comparison result does not pass, executing the step S6;
and S11, storing a three-dimensional construction algorithm passing through the comparison result in the comparison module through the database module, and binding with the current user identity information.
Compared with the prior art, the image animation processing method and the system for driving the static image can realize the image animation processing for driving the static image by carrying out three-dimensional reconstruction on the picture, and simultaneously filter the illumination component through bilateral filtering to keep the edge information in the face image; and eliminating halation artifacts generated in the face enhancement process by using the thought of local standard deviation; and the color tone reconstruction is carried out, the image saturation and color distortion are prevented, and the accuracy of the image extraction of the low-illumination image can be ensured.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to these drawings for a person having ordinary skill in the art.
FIG. 1 is a schematic diagram of an overall structure according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a workflow structure of an illuminance enhancement module according to an embodiment of the present invention;
fig. 3 is a schematic workflow structure diagram of a face recognition module according to an embodiment of the present invention.
Detailed Description
In order to make the technical scheme of the present invention better understood by those skilled in the art, the present invention will be further described in detail with reference to the accompanying drawings.
Referring to fig. 1-3, an image animation processing system for driving a still image, comprising:
the user login module is used for logging in the system by the user;
the algorithm reading module is used for reading the user information sent by the user login module and reading a face three-dimensional construction algorithm of a corresponding user in the database module;
the face image acquisition module is used for acquiring a face two-dimensional image of a current login user;
the face illuminance judging module is used for judging the face illuminance in the face two-dimensional image acquired by the face picture acquiring module;
the low-illumination face recognition module is used for carrying out low-illumination face recognition on the two-dimensional image with the face judgment result of low illumination in the face illumination judgment module;
the face classification module is used for classifying pictures according to the face positions in the face two-dimensional images and the face shooting angles;
the three-dimensional construction module is used for constructing a face three-dimensional animation according to the face two-dimensional image;
the human image video acquisition module is used for collecting human image videos of the current user in real time;
the video portrait acquisition module is used for acquiring the user portrait in the portrait video acquired by the portrait video acquisition module;
the comparison module is used for comparing the user portrait acquired by the video portrait acquisition module with the three-dimensional portrait constructed by the three-dimensional construction module;
and the database module is used for storing the comparison result in the comparison module through a three-dimensional construction algorithm and binding the comparison result with the current user identity information.
The low-light face recognition module comprises:
the illumination enhancement module, the illumination enhancement module includes:
the bilateral filtering processing module is used for keeping the edge and detail information of the image;
the specific processing method of the bilateral filtering processing module comprises the following steps:
wherein (i, j) is the pixel coordinate of the central pixel point, (k, l) represents the position coordinate of the neighborhood pixel point of the image, g (i, j) represents the pixel value of the image after bilateral filtering processing, f (k, l) represents the pixel value of the neighborhood pixel point, w represents the weight proportionality coefficient, and the weight proportionality coefficient is obtained by multiplying the space domain kernel of the pixel value and the pixel range value domain kernel.
Where d represents the Euclidean distance of the current pixel point from the center pixel point.
Wherein the r value represents the absolute value of the difference of the pixel gray values between any point and the center point of the image calculated based on the Gaussian function. The calculation formula of the weight coefficient can be obtained by the calculation formulas of the spatial domain kernel and the pixel range value domain kernel, and the calculation formulas are as follows:
wherein the luminance varianceIn connection with the smoothing effect of the pixel +.>And when the brightness change is small, the area with large brightness change in the image is stable in edge protection capability. Standard deviation of distance between pixels +.>The larger the convolutionThe more pixels of each convolution block are in the process, the wider the coverage distance of the interval of the whole picture is when the illumination is estimated by using bilateral filtering, and the better the smooth illumination effect is.
The local standard deviation processing module is used for processing the image processed by the bilateral filtering processing module, eliminating the influence of illumination components and removing halation and artifacts;
the tone reconstruction module is used for reconstructing the components of the image processed by the contrast components;
the tone reconstruction algorithm is as follows:
where v (x, y) is the luminance value component of the original image, and v' (x, y) is the luminance enhanced component; s (x, y) original saturation value components, s' (x, y) is an enhanced saturation component after tone reconstruction, and t represents a proportionality constant.
Where w represents the pixel value range of the image, v w Luminance value s representing a neighborhood w A saturation value representing a neighborhood;
wherein the method comprises the steps ofRepresenting the average of all the brightnesses in the neighborhood, +.>Representing the saturation mean value in the neighborhood, and verifying the brightness improvement effect of the image through the mean value.
Wherein the method comprises the steps ofAnd->Representing the variance of the luminance and saturation components, the quality of the image is verified.
And the face recognition module is used for carrying out face recognition.
The arrangement is that the bilateral filtering is utilized to filter the illumination component, so that the edge information in the face image is maintained; and eliminating halation artifacts generated in the face enhancement process by using the thought of local standard deviation; tone reconstruction is performed to prevent image saturation and color distortion.
The specific working method of the illumination enhancement module is as follows:
a1, collecting a low-illumination face image;
a2, carrying out logarithmic transformation on the face image, extracting an illumination component, and stretching the illumination component by using Gamma correction to improve the overall brightness of the image;
a3, taking the Gamma corrected image as an input image for improving the Retinex algorithm, and using bilateral filtering processing to enable the image to keep edge and detail information;
a4, processing the image after bilateral filtering through a local standard deviation, eliminating the influence of illumination components, and removing halation and artifacts;
and A5, reconstructing the components of the image processed by the bilateral filtering and the local standard deviation through the adaptive tone reconstruction after the illumination components of the image processed by the bilateral filtering and the local standard deviation are processed.
The specific working method of the face recognition module is as follows:
b1, obtaining a face image reinforced by an illuminance reinforcing module;
b2, extracting features from the edge area of the face image with enhanced contrast by using a Gabor filter to obtain a histogram sequence;
b3, adding 4 symbiotic matrixes in different directions on the basis of an LBP algorithm to extract the features of the illumination-unchanged local area of the face image to obtain a histogram sequence;
converting the edge features of the face image extracted by Gabor filtering and the local face feature histogram extracted by improving multiple thresholds into one-dimensional feature vectors, and carrying out serial fusion on all the feature vectors;
and B5, reducing the dimension of the feature vector of the fused histogram to generate a final feature map.
The three-dimensional building block comprises:
the three-dimensional construction algorithm input module is used for inputting three-dimensional construction algorithms aiming at different pictures;
the three-dimensional construction algorithm selection module is used for selecting a proper three-dimensional construction algorithm according to the currently acquired face picture;
the three-dimensional construction module is used for carrying out three-dimensional construction on the current picture according to the three-dimensional construction algorithm selected by the three-dimensional construction algorithm selection module.
The face classification module comprises:
the data preprocessing module is used for carrying out gray processing on the data picture and converting a plurality of channels into single-channel data;
the template selecting module is used for selecting a proper picture template;
the classification template making module is used for making a proper classification template according to the template selected by the classification template selecting module;
the picture dividing module is used for dividing the pictures into a training set and a testing set;
a data set construction module for reconstructing a data set;
the data tag module is used for reconstructing the data tag;
and the data equalization module is used for performing data equalization.
The specific working method of the face classification module is as follows:
c1, carrying out gray processing on the data picture, and converting a plurality of channels into single-channel data;
c2, dividing the picture subjected to the graying treatment into a training set and a testing set;
c3, selecting a proper picture template;
c4, making a proper classification template according to the picture template;
c5, constructing a new data set by the classification template, the training set and the test set together;
c6, setting a new data tag according to the new data set;
and C7, carrying out data equalization according to the new data tag.
An image animation processing method for driving a still image, wherein the image animation processing method for driving the still image comprises the following steps:
s1, a user logs in a system through a user login module;
s2, the algorithm reading module reads the user information sent by the user login module and reads the face three-dimensional construction algorithm of the corresponding user in the database module, if the algorithm reading module reads the face three-dimensional construction algorithm of the corresponding user, the step S7 is executed, and if the algorithm reading module does not read the face three-dimensional construction algorithm of the corresponding user, the step S3 is executed;
s3, acquiring a face two-dimensional image of the current login user through a face picture acquisition module;
s4, judging the face illuminance in the face two-dimensional image through a face illuminance judging module, executing a step S5 if the judging result is low illuminance, and executing a step S6 if the judging result is non-low illuminance;
s5, carrying out low-illumination face recognition on the two-dimensional image with the low illumination by the low-illumination face recognition module;
s6, classifying pictures according to the face positions in the face two-dimensional images and the face shooting angles through a face classification module;
s7, constructing a face three-dimensional animation according to the face two-dimensional image through a three-dimensional construction module;
s8, collecting the portrait video of the current user in real time through a portrait video acquisition module;
s9, acquiring a user figure in the figure video acquired by the figure video acquisition module through the video figure acquisition module;
s10, comparing the user portrait acquired by the video portrait acquisition module with the three-dimensional portrait constructed by the three-dimensional construction module through the comparison module, if the comparison result passes, executing the step S11, and if the comparison result does not pass, executing the step S6;
and S11, storing a three-dimensional construction algorithm passing through the comparison result in the comparison module through the database module, and binding with the current user identity information.
While certain exemplary embodiments of the present invention have been described above by way of illustration only, it will be apparent to those of ordinary skill in the art that modifications may be made to the described embodiments in various different ways without departing from the spirit and scope of the invention. Accordingly, the drawings and description are to be regarded as illustrative in nature and not as restrictive of the scope of the invention, which is defined by the appended claims.
Claims (4)
1. An image animation processing system for driving a still image, comprising:
the user login module is used for logging in the system by the user;
the algorithm reading module is used for reading the user information sent by the user login module and reading a face three-dimensional construction algorithm of a corresponding user in the database module;
the face image acquisition module is used for acquiring a face two-dimensional image of a current login user;
the face illuminance judging module is used for judging the face illuminance in the face two-dimensional image acquired by the face picture acquiring module;
the low-illumination face recognition module is used for carrying out low-illumination face recognition on the two-dimensional image with the face judgment result of low illumination in the face illumination judgment module, and the low-illumination face recognition module comprises:
an illuminance enhancement module, the illuminance enhancement module comprising:
the bilateral filtering processing module is used for keeping the edge and detail information of the image;
the local standard deviation processing module is used for processing the image processed by the bilateral filtering processing module, eliminating the influence of illumination components and removing halation and artifacts;
the tone reconstruction module is used for reconstructing the components of the image processed by the contrast components;
the specific working method of the illumination enhancement module comprises the following steps:
a1, collecting a low-illumination face image;
a2, carrying out logarithmic transformation on the face image, extracting an illumination component, and stretching the illumination component by using Gamma correction to improve the overall brightness of the image;
a3, taking the Gamma corrected image as an input image for improving the Retinex algorithm, and using bilateral filtering processing to enable the image to keep edge and detail information;
a4, processing the image after bilateral filtering through a local standard deviation, eliminating the influence of illumination components, and removing halation and artifacts;
a5, reconstructing the components of the image processed by the bilateral filtering and the local standard deviation through the adaptive tone reconstruction after the illumination components of the image processed by the bilateral filtering and the local standard deviation are processed
The face recognition module is used for carrying out face recognition, and the specific working method of the face recognition module is as follows:
b1, obtaining a face image reinforced by an illuminance reinforcing module;
b2, extracting features from the edge area of the face image with enhanced contrast by using a Gabor filter to obtain a histogram sequence;
b3, adding 4 symbiotic matrixes in different directions on the basis of an LBP algorithm to extract the features of the illumination-unchanged local area of the face image to obtain a histogram sequence;
converting the edge features of the face image extracted by Gabor filtering and the local face feature histogram extracted by improving multiple thresholds into one-dimensional feature vectors, and carrying out serial fusion on all the feature vectors;
b5, reducing the dimension of the feature vector of the fused histogram to generate a final feature map;
the face classification module is used for classifying pictures according to face positions and face shooting angles in the face two-dimensional images, and comprises:
the data preprocessing module is used for carrying out gray processing on the data picture and converting a plurality of channels into single-channel data;
the template selecting module is used for selecting a proper picture template;
the classification template making module is used for making a proper classification template according to the template selected by the classification template selecting module;
the picture dividing module is used for dividing the pictures into a training set and a testing set;
a data set construction module for reconstructing a data set;
the data tag module is used for reconstructing the data tag;
the data equalization module is used for performing data equalization;
the three-dimensional construction module is used for constructing a face three-dimensional animation according to the face two-dimensional image;
the system comprises a portrait video acquisition module, a portrait video processing module and a portrait video processing module, wherein the portrait video acquisition module is used for collecting the portrait video of the current user in real time;
the video portrait acquisition module is used for acquiring the user portrait in the portrait video acquired by the portrait video acquisition module;
the comparison module is used for comparing the user portrait acquired by the video portrait acquisition module with the three-dimensional portrait constructed by the three-dimensional construction module;
and the database module is used for storing the comparison result in the comparison module through a three-dimensional construction algorithm and binding the comparison result with the current user identity information.
2. The image animation processing system of claim 1, wherein the three-dimensional building block comprises:
the three-dimensional construction algorithm input module is used for inputting three-dimensional construction algorithms aiming at different pictures;
the three-dimensional construction algorithm selection module is used for selecting a proper three-dimensional construction algorithm according to the currently acquired face picture;
the three-dimensional construction module is used for carrying out three-dimensional construction on the current picture according to the three-dimensional construction algorithm selected by the three-dimensional construction algorithm selection module.
3. The image animation processing system of claim 2, wherein the face classification module works as follows:
c1, carrying out gray processing on the data picture, and converting a plurality of channels into single-channel data;
c2, dividing the picture subjected to the graying treatment into a training set and a testing set;
c3, selecting a proper picture template;
c4, making a proper classification template according to the picture template;
c5, constructing a new data set by the classification template, the training set and the test set together;
c6, setting a new data tag according to the new data set;
and C7, carrying out data equalization according to the new data tag.
4. An image animation processing method for driving a still image, which is applied to an image animation processing system for driving a still image according to any one of claims 1 to 3, wherein the image animation processing method for driving a still image comprises:
s1, a user logs in a system through a user login module;
s2, the algorithm reading module reads the user information sent by the user login module and reads the face three-dimensional construction algorithm of the corresponding user in the database module, if the algorithm reading module reads the face three-dimensional construction algorithm of the corresponding user, the step S7 is executed, and if the algorithm reading module does not read the face three-dimensional construction algorithm of the corresponding user, the step S3 is executed;
s3, acquiring a face two-dimensional image of the current login user through a face picture acquisition module;
s4, judging the face illuminance in the face two-dimensional image through a face illuminance judging module, executing a step S5 if the judging result is low illuminance, and executing a step S6 if the judging result is non-low illuminance;
s5, carrying out low-illumination face recognition on the two-dimensional image with the low illumination by the low-illumination face recognition module;
s6, classifying pictures according to the face positions in the face two-dimensional images and the face shooting angles through a face classification module;
s7, constructing a face three-dimensional animation according to the face two-dimensional image through a three-dimensional construction module;
s8, collecting the portrait video of the current user in real time through a portrait video acquisition module;
s9, acquiring a user figure in the figure video acquired by the figure video acquisition module through the video figure acquisition module;
s10, comparing the user portrait acquired by the video portrait acquisition module with the three-dimensional portrait constructed by the three-dimensional construction module through the comparison module, if the comparison result passes, executing the step S11, and if the comparison result does not pass, executing the step S6;
and S11, storing a three-dimensional construction algorithm passing through the comparison result in the comparison module through the database module, and binding with the current user identity information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311841510.7A CN117496019B (en) | 2023-12-29 | 2023-12-29 | Image animation processing method and system for driving static image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311841510.7A CN117496019B (en) | 2023-12-29 | 2023-12-29 | Image animation processing method and system for driving static image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117496019A CN117496019A (en) | 2024-02-02 |
| CN117496019B true CN117496019B (en) | 2024-04-05 |
Family
ID=89676757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311841510.7A Active CN117496019B (en) | 2023-12-29 | 2023-12-29 | Image animation processing method and system for driving static image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117496019B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663810A (en) * | 2012-03-09 | 2012-09-12 | 北京航空航天大学 | Full-automatic modeling approach of three dimensional faces based on phase deviation scanning |
| CN104240293A (en) * | 2014-09-26 | 2014-12-24 | 上海水晶石视觉展示有限公司 | Method for implementing high-reality virtual stages |
| CN105069745A (en) * | 2015-08-14 | 2015-11-18 | 济南中景电子科技有限公司 | face-changing system based on common image sensor and enhanced augmented reality technology and method |
| CN106652025A (en) * | 2016-12-20 | 2017-05-10 | 五邑大学 | Three-dimensional face modeling method and three-dimensional face modeling printing device based on video streaming and face multi-attribute matching |
| CN107066966A (en) * | 2017-04-17 | 2017-08-18 | 宜宾学院 | A kind of face identification method based on key point area image |
| CN107392866A (en) * | 2017-07-07 | 2017-11-24 | 武汉科技大学 | A kind of facial image local grain Enhancement Method of illumination robust |
| CN111027350A (en) * | 2018-10-10 | 2020-04-17 | 成都理工大学 | Improved PCA algorithm based on human face three-dimensional reconstruction |
| WO2020140832A1 (en) * | 2019-01-04 | 2020-07-09 | 北京达佳互联信息技术有限公司 | Three-dimensional facial reconstruction method and apparatus, and electronic device and storage medium |
| WO2021012647A1 (en) * | 2019-07-24 | 2021-01-28 | 创新先进技术有限公司 | Face verification method and apparatus, server and readable storage medium |
| CN114299206A (en) * | 2021-12-31 | 2022-04-08 | 清华大学 | Three-dimensional cartoon face generation method and device, electronic equipment and storage medium |
| CN116884070A (en) * | 2023-07-17 | 2023-10-13 | 罗国庆 | Efficient image processing algorithm and application thereof in face recognition |
| CN116977547A (en) * | 2023-04-11 | 2023-10-31 | 腾讯科技（深圳）有限公司 | Three-dimensional face reconstruction method and device, electronic equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10796480B2 (en) * | 2015-08-14 | 2020-10-06 | Metail Limited | Methods of generating personalized 3D head models or 3D body models |
-
2023
- 2023-12-29 CN CN202311841510.7A patent/CN117496019B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663810A (en) * | 2012-03-09 | 2012-09-12 | 北京航空航天大学 | Full-automatic modeling approach of three dimensional faces based on phase deviation scanning |
| CN104240293A (en) * | 2014-09-26 | 2014-12-24 | 上海水晶石视觉展示有限公司 | Method for implementing high-reality virtual stages |
| CN105069745A (en) * | 2015-08-14 | 2015-11-18 | 济南中景电子科技有限公司 | face-changing system based on common image sensor and enhanced augmented reality technology and method |
| CN106652025A (en) * | 2016-12-20 | 2017-05-10 | 五邑大学 | Three-dimensional face modeling method and three-dimensional face modeling printing device based on video streaming and face multi-attribute matching |
| CN107066966A (en) * | 2017-04-17 | 2017-08-18 | 宜宾学院 | A kind of face identification method based on key point area image |
| CN107392866A (en) * | 2017-07-07 | 2017-11-24 | 武汉科技大学 | A kind of facial image local grain Enhancement Method of illumination robust |
| CN111027350A (en) * | 2018-10-10 | 2020-04-17 | 成都理工大学 | Improved PCA algorithm based on human face three-dimensional reconstruction |
| WO2020140832A1 (en) * | 2019-01-04 | 2020-07-09 | 北京达佳互联信息技术有限公司 | Three-dimensional facial reconstruction method and apparatus, and electronic device and storage medium |
| WO2021012647A1 (en) * | 2019-07-24 | 2021-01-28 | 创新先进技术有限公司 | Face verification method and apparatus, server and readable storage medium |
| CN114299206A (en) * | 2021-12-31 | 2022-04-08 | 清华大学 | Three-dimensional cartoon face generation method and device, electronic equipment and storage medium |
| CN116977547A (en) * | 2023-04-11 | 2023-10-31 | 腾讯科技（深圳）有限公司 | Three-dimensional face reconstruction method and device, electronic equipment and storage medium |
| CN116884070A (en) * | 2023-07-17 | 2023-10-13 | 罗国庆 | Efficient image processing algorithm and application thereof in face recognition |
Non-Patent Citations (3)
| Title |
|---|
| Cartoon Face to Human Face Translation using Contour Loss based CycleGAN;Mayank Singhal;《IEEE》;20211231;全文 * |
| 杜明 ; 赵向军 ; .改进Retinex的光照变化人脸图像增强算法.《计算机科学》.2016,全文. * |
| 阳策 ; 李重 ; 任义 ; 刘恒 ; .基于标准肤色的人脸图像纹理合成与三维重建应用.《计算机***应用》.2019,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117496019A (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ren et al. | Low-light image enhancement via a deep hybrid network | |
| CN106778928B (en) | Image processing method and device | |
| CN108717524B (en) | Gesture recognition system based on double-camera mobile phone and artificial intelligence system | |
| Li et al. | Visual-salience-based tone mapping for high dynamic range images | |
| CN112766160A (en) | Face replacement method based on multi-stage attribute encoder and attention mechanism | |
| US20060082849A1 (en) | Image processing apparatus | |
| US20240062530A1 (en) | Deep perceptual image enhancement | |
| CN109711268B (en) | Face image screening method and device | |
| JP2021531571A (en) | Certificate image extraction method and terminal equipment | |
| CN110458792B (en) | Method and device for evaluating quality of face image | |
| CN110674759A (en) | Monocular face in-vivo detection method, device and equipment based on depth map | |
| CN107172354A (en) | Method for processing video frequency, device, electronic equipment and storage medium | |
| CN110298796B (en) | Low-illumination image enhancement method based on improved Retinex and logarithmic image processing | |
| CN116681636B (en) | Light infrared and visible light image fusion method based on convolutional neural network | |
| CN111222433A (en) | Automatic face auditing method, system, equipment and readable storage medium | |
| CN114627034A (en) | Image enhancement method, training method of image enhancement model and related equipment | |
| CN112633221A (en) | Face direction detection method and related device | |
| Fathy et al. | Benchmarking of pre-processing methods employed in facial image analysis | |
| CN111274851A (en) | Living body detection method and device | |
| CN109447942A (en) | Image blur determines method, apparatus, computer equipment and storage medium | |
| CN112839167A (en) | Image processing method, image processing device, electronic equipment and computer readable medium | |
| JP3962517B2 (en) | Face detection method and apparatus, and computer-readable medium | |
| CN117496019B (en) | Image animation processing method and system for driving static image | |
| CN115690934A (en) | Master and student attendance card punching method and device based on batch face recognition | |
| CN114698398A (en) | Image processing method, image processing apparatus, electronic device, and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |