CN112906608A - Layer positioning and layer fixing method of face model and application thereof - Google Patents
Layer positioning and layer fixing method of face model and application thereof Download PDFInfo
- Publication number
- CN112906608A CN112906608A CN202110244891.5A CN202110244891A CN112906608A CN 112906608 A CN112906608 A CN 112906608A CN 202110244891 A CN202110244891 A CN 202110244891A CN 112906608 A CN112906608 A CN 112906608A
- Authority
- CN
- China
- Prior art keywords
- layer
- face
- image
- positioning
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000005520 cutting process Methods 0.000 claims abstract description 13
- 238000005516 engineering process Methods 0.000 claims abstract description 11
- 238000001914 filtration Methods 0.000 claims description 15
- 230000009466 transformation Effects 0.000 claims description 12
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 230000001815 facial effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 210000001525 retina Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G06T3/02—
-
- G06T5/70—
Abstract
The invention relates to the technical field of face recognition, in particular to a layer positioning and layer fixing method of a face model and application thereof, wherein the face image is processed by a face image management system and is manually optimized, then a layer color printing can be carried out, full-automatic cutting is carried out by utilizing a layer cutting technology to generate a piece of drawing, the paper is fixed into the face model by utilizing the layer positioning and layer fixing technology, an initial 3D face model is generated after manual correction, the face image is printed by a special printer to obtain layer paper, after printing is finished, layer paper positioning is carried out by using special layer positioning software, and the layer paper is superposed by adopting the fixing technology to form a 3D face model; the invention solves the problem that the success rate of the portrait model is effectively improved when the portrait model is verified by a biological characteristic identity authentication system due to various external conditions in the manufacturing process of the face model.
Description
Technical Field
The invention relates to the technical field of face recognition, in particular to a layer positioning and layer fixing method of a face model and application thereof.
Background
Currently, the main biometric technologies include iris recognition, retina recognition, face recognition, signature recognition, voice recognition, fingerprint recognition, and the like. The face recognition is to acquire the facial features and information of a person, then process the facial features and information by a face processing management system to obtain a face image meeting the standard, print, position and cut the face image layer by a special technology, then stack the face image layer, and finally realize the process of unlocking the intelligent terminal device by using a 3D face model.
However, a leak still exists in the process of unlocking the portrait by using the 3D face model, and when the influence of uncontrollable external conditions and the influence of cutting equipment and the influence of a superposition method and the like are caused in the process of processing and manufacturing, the manufactured bionic 3D portrait cannot pass through face recognition. Therefore, in the manufacturing process, a complete layer positioning cutting and overlaying method is needed, so that a high-precision 3D portrait model can be manufactured.
Disclosure of Invention
The invention relates to the technical field of face recognition, in particular to a layer positioning and layer fixing method of a face model and application thereof.
A layer positioning and layer fixing method for a face model comprises the following steps: determining the fixed position of a face layer through an image processing management system, combining and superposing the face layers by adopting a fixing technology to form a portrait three-dimensional model, determining the positions of the face layers, superposing and fixing, arranging the face layers in sequence, fixing and superposing the arranged face layers by using a special positioning hole tool, finely adjusting images according to the display effect after finishing the arrangement and superposition of all the face layers, and keeping the appearance of the superposed layers consistent with the 3-dimensional face, thereby obtaining the face image meeting the standard.
The application of the layer positioning and layer fixing method of the face model comprises the following steps: preprocessing the face image meeting the standard by using a software processing management system; after the face image is preprocessed, the face image needs to be printed through a special printer to obtain layer paper, after the printing is finished, special layer positioning software is used for positioning the layer paper, and if the layer paper is not accurately positioned, the situations of cutting deviation, cutting failure and the like are easy to occur; if the layer paper is accurately positioned, after the positioning and cutting are finished, the layer paper is overlapped by adopting a fixing technology to form a 3D portrait model; the face image consistent with the model is collected in advance on the intelligent terminal device, the manufactured portrait 3D portrait model is unlocked and verified on the intelligent terminal, and at the moment, if the comparison result between the portrait of the login user and the face image information collected in advance is successful, the user can enter and use the device.
Further, the preprocessing includes image noise filtering, image rotation, and image pose normalization.
Further, the noise filtering includes the steps of: the algorithm for removing noise mainly comprises smooth filtering; the smooth filtering algorithm firstly needs to select a certain image area, a pixel is selected as a center in the area, a small interval is further selected in the area, the pixel of the interval is used as a base number of the pixel interval, then a new value of the center pixel is deduced through a formulaic budget change, and finally smooth filtering is realized through a convolution method.
Further, the image rotation comprises the steps of: under the condition that the image is normal and has no inclination, two eyes of a person are positioned on the same horizontal line, an included angle between the two eyes of the person is calculated, if the included angle is 0, the image is horizontal, and if the included angle is not zero, the two eyes are inclined to a certain degree; during calculation, the included angle between two eyes is set to be 0, and after the numerical value of 0 is calculated, the corrected image can be obtained by reversely rotating by 0 degree.
Further, the image pose normalization comprises the following steps: three points of eyes and nose tips are used as characteristic points, an affine change relation between two images is further solved, the images are further input for calibration, and influences caused by attitude depth deflection are further compensated; the specific calculation method is as follows:
let the positions of the feature points of the input image be (x)1，y1),(x2，y2),(x3，y3) The corresponding three feature points of the standard front view are (x)l'，y1'),(x2',y2'),(x3',y3') the affine transformation found is:
in order to ensure that each point of the transformed image has a pixel value, a reverse mapping method is adopted, namely, the inverse transformation of the transformation is solved:
therefore, the geometric transformation relation of the corresponding features of the depth deflection image and the standard frontal image can be calculated.
Furthermore, the intelligent terminal comprises a collection assembly, a central server processing end, a storage module and an early warning module.
Furthermore, the acquisition component acquires a face image of the user through an image acquisition module, processes the image and sends the processed image to a face feature extraction module to extract a face feature part; and then the central server processing end calls a face recognition module to recognize and compare the extracted face features.
Furthermore, the setting storage module is used for storing the collected face data, and the display module displays the face recognition result; and the early warning module carries out alarm prompt when finding an illegal face image.
Compared with the prior art, the method can solve the problems that the human face model cannot be correctly extracted due to various external conditions in the manufacturing process, so that the layer positioning is not clear and the layer fixing method is not accurate in the modeling process of the human face image, and can effectively improve the success rate of the human face model when the human face model is verified by a biological characteristic identity authentication system; the invention can solve the problems that partial characteristics of the portrait can not be correctly extracted due to various external conditions in the process of manufacturing the face model, so that the layer positioning is not clear and the layer fixing method is not accurate in the process of modeling the face image, and can effectively improve the success rate of the portrait model when the portrait model is verified by a biological characteristic identity authentication system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of the system of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present invention, are given by way of illustration and explanation only, not limitation.
The invention relates to the technical field of face recognition, in particular to a layer positioning and layer fixing method of a face model and application thereof.
A layer positioning and layer fixing method for a face model comprises the following steps: determining the fixed position of a face layer through an image processing management system, combining and superposing the face layers by adopting a fixing technology to form a portrait three-dimensional model, determining the positions of the face layers, superposing and fixing, arranging the face layers in sequence, fixing and superposing the arranged face layers by using a special positioning hole tool, finely adjusting images according to the display effect after finishing the arrangement and superposition of all the face layers, and keeping the appearance of the superposed layers consistent with the 3-dimensional face, thereby obtaining the face image meeting the standard.
The application of the layer positioning and layer fixing method of the face model comprises the following steps: preprocessing the face image meeting the standard by using a software processing management system; after the face image is preprocessed, the face image needs to be printed through a special printer to obtain layer paper, after the printing is finished, special layer positioning software is used for positioning the layer paper, and if the layer paper is not accurately positioned, the situations of cutting deviation, cutting failure and the like are easy to occur; if the layer paper is accurately positioned, after the positioning and cutting are finished, the layer paper is overlapped by adopting a fixing technology to form a 3D portrait model; the face image consistent with the model is collected in advance on the intelligent terminal device, the manufactured portrait 3D portrait model is unlocked and verified on the intelligent terminal, and at the moment, if the comparison result between the portrait of the login user and the face image information collected in advance is successful, the user can enter and use the device.
Preferably, the pre-processing comprises image noise filtering, image rotation and image pose normalization.
Preferably, the noise filtering comprises the steps of: the algorithm for removing noise mainly comprises smooth filtering; the smooth filtering algorithm firstly needs to select a certain image area, a pixel is selected as a center in the area, a small interval is further selected in the area, the pixel of the interval is used as a base number of the pixel interval, then a new value of the center pixel is deduced through a formulaic budget change, and finally smooth filtering is realized through a convolution method.
Preferably, the image rotation comprises the steps of: under the condition that the image is normal and has no inclination, two eyes of a person are positioned on the same horizontal line, an included angle between the two eyes of the person is calculated, if the included angle is 0, the image is horizontal, and if the included angle is not zero, the two eyes are inclined to a certain degree; during calculation, the included angle between two eyes is set to be 0, and after the numerical value of 0 is calculated, the corrected image can be obtained by reversely rotating by 0 degree.
Preferably, the image pose normalization comprises the steps of: three points of eyes and nose tips are used as characteristic points, an affine change relation between two images is further solved, the images are further input for calibration, and influences caused by attitude depth deflection are further compensated; the specific calculation method is as follows:
let the positions of the feature points of the input image be (x)1，y1),(x2，y2),(x3，y3) The corresponding three feature points of the standard front view are (x)l'，y1'),(x2',y2'),(x3',y3') the affine transformation found is:
in order to ensure that each point of the transformed image has a pixel value, a reverse mapping method is adopted, namely, the inverse transformation of the transformation is solved:
therefore, the geometric transformation relation of the corresponding features of the depth deflection image and the standard frontal image can be calculated.
Preferably, the intelligent terminal comprises an acquisition assembly, a central server processing end, a storage module and an early warning module.
Preferably, the acquisition component acquires a face image of a user through an image acquisition module, processes the image and sends the processed image to a face feature extraction module to extract a face feature part; and then the central server processing end calls a face recognition module to recognize and compare the extracted face features.
Preferably, the setting storage module is used for storing the collected face data, and the display module displays the face recognition result; and the early warning module carries out alarm prompt when finding an illegal face image.
The method can solve the problems that partial features of the portrait cannot be correctly extracted due to various external conditions in the process of manufacturing the face model, so that the layer positioning is not clear and the layer fixing method is not accurate in the process of modeling the face image, and can effectively improve the success rate of the portrait model when the portrait model is verified by a biological feature identity authentication system; the invention can solve the problems that partial characteristics of the portrait can not be correctly extracted due to various external conditions in the process of manufacturing the face model, so that the layer positioning is not clear and the layer fixing method is not accurate in the process of modeling the face image, and can effectively improve the success rate of the portrait model when the portrait model is verified by a biological characteristic identity authentication system.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (9)
1. A layer positioning and layer fixing method for a face model is characterized by comprising the following steps: determining the fixed position of a face layer through an image processing management system, combining and superposing the face layers by adopting a fixing technology to form a portrait three-dimensional model, determining the positions of the face layers, superposing and fixing, arranging the face layers in sequence, fixing and superposing the arranged face layers by using a special positioning hole tool, finely adjusting images according to the display effect after finishing the arrangement and superposition of all the face layers, and keeping the appearance of the superposed layers consistent with the 3-dimensional face, thereby obtaining the face image meeting the standard.
2. The application of the layer positioning and layer fixing method of the face model is characterized by comprising the following steps of: preprocessing the face image meeting the standard by using a software processing management system; after the face image is preprocessed, the face image needs to be printed through a special printer to obtain layer paper, after the printing is finished, special layer positioning software is used for positioning the layer paper, and if the layer paper is not accurately positioned, the situations of cutting deviation, cutting failure and the like are easy to occur; if the layer paper is accurately positioned, after the positioning and cutting are finished, the layer paper is overlapped by adopting a fixing technology to form a 3D portrait model; the face image consistent with the model is collected in advance on the intelligent terminal device, the manufactured portrait 3D portrait model is unlocked and verified on the intelligent terminal, and at the moment, if the comparison result between the portrait of the login user and the face image information collected in advance is successful, the user can enter and use the device.
3. The application of the layer positioning and layer fixing method of the human face model according to claim 2, wherein the preprocessing includes image noise filtering, image rotation and image pose normalization.
4. The application of the layer positioning and layer fixing method of the human face model according to claim 3, wherein the noise filtering comprises the following steps: the algorithm for removing noise mainly comprises smooth filtering; the smooth filtering algorithm firstly needs to select a certain image area, a pixel is selected as a center in the area, a small interval is further selected in the area, the pixel of the interval is used as a base number of the pixel interval, then a new value of the center pixel is deduced through a formulaic budget change, and finally smooth filtering is realized through a convolution method.
5. The application of the layer positioning and layer fixing method for the human face model according to claim 3, wherein the image rotation comprises the following steps: under the condition that the image is normal and has no inclination, two eyes of a person are positioned on the same horizontal line, an included angle between the two eyes of the person is calculated, if the included angle is 0, the image is horizontal, and if the included angle is not zero, the two eyes are inclined to a certain degree; during calculation, the included angle between two eyes is set to be 0, and after the numerical value of 0 is calculated, the corrected image can be obtained by reversely rotating by 0 degree.
6. The application of the layer positioning and layer fixing method of the human face model according to claim 3, wherein the image pose normalization comprises the following steps: three points of eyes and nose tips are used as characteristic points, an affine change relation between two images is further solved, the images are further input for calibration, and influences caused by attitude depth deflection are further compensated; the specific calculation method is as follows:
let the positions of the feature points of the input image be (x)1，y1),(x2，y2),(x3，y3) The corresponding three feature points of the standard front view are (x)l'，y1'),(x2',y2'),(x3',y3') the affine transformation found is:
then, a method of inverse mapping is adopted, namely, the inverse transformation of the transformation is solved:
therefore, the geometric transformation relation of the corresponding features of the depth deflection image and the standard frontal image can be calculated.
7. The application of the layer positioning and layer fixing method of the human face model according to claim 2, wherein the intelligent terminal comprises an acquisition component, a central server processing end, a storage module and an early warning module.
8. The application of the layer positioning and layer fixing method of the human face model according to claim 7, wherein the acquisition component acquires the human face image of the user through an image acquisition module, and sends the image processed image to a human face feature extraction module to extract the human face feature part; and then the central server processing end calls a face recognition module to recognize and compare the extracted face features.
9. The application of the layer positioning and layer fixing method of the human face model according to claim 7, wherein the setting storage module is used for storing the collected human face data, and the display module displays the human face recognition result; and the early warning module carries out alarm prompt when finding an illegal face image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110244891.5A CN112906608A (en) | 2021-03-05 | 2021-03-05 | Layer positioning and layer fixing method of face model and application thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110244891.5A CN112906608A (en) | 2021-03-05 | 2021-03-05 | Layer positioning and layer fixing method of face model and application thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112906608A true CN112906608A (en) | 2021-06-04 |
Family
ID=76107755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110244891.5A Pending CN112906608A (en) | 2021-03-05 | 2021-03-05 | Layer positioning and layer fixing method of face model and application thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112906608A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739676A (en) * | 2009-12-04 | 2010-06-16 | 清华大学 | Method for manufacturing face effigy with ultra-low resolution |
| CN103310179A (en) * | 2012-03-06 | 2013-09-18 | 上海骏聿数码科技有限公司 | Method and system for optimal attitude detection based on face recognition technology |
| CN107358207A (en) * | 2017-07-14 | 2017-11-17 | 重庆大学 | A kind of method for correcting facial image |
| CN111710031A (en) * | 2020-05-29 | 2020-09-25 | 上海红阵信息科技有限公司 | Method for breaking password of intelligent terminal device by counterfeiting portrait |
| CN111710030A (en) * | 2020-05-29 | 2020-09-25 | 上海红阵信息科技有限公司 | AI-based system and method for resisting deep forgery portrait |
-
2021
- 2021-03-05 CN CN202110244891.5A patent/CN112906608A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739676A (en) * | 2009-12-04 | 2010-06-16 | 清华大学 | Method for manufacturing face effigy with ultra-low resolution |
| CN103310179A (en) * | 2012-03-06 | 2013-09-18 | 上海骏聿数码科技有限公司 | Method and system for optimal attitude detection based on face recognition technology |
| CN107358207A (en) * | 2017-07-14 | 2017-11-17 | 重庆大学 | A kind of method for correcting facial image |
| CN111710031A (en) * | 2020-05-29 | 2020-09-25 | 上海红阵信息科技有限公司 | Method for breaking password of intelligent terminal device by counterfeiting portrait |
| CN111710030A (en) * | 2020-05-29 | 2020-09-25 | 上海红阵信息科技有限公司 | AI-based system and method for resisting deep forgery portrait |
Non-Patent Citations (1)
| Title |
|---|
| 杨帆: "《精通图像处理经典算法 MATLAB版 第2版》", 31 March 2018 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4946730B2 (en) | Face image processing apparatus, face image processing method, and computer program | |
| US8170295B2 (en) | Personal authentication system and personal authentication method | |
| CN108615016B (en) | Face key point detection method and face key point detection device | |
| US7436988B2 (en) | 3D face authentication and recognition based on bilateral symmetry analysis | |
| JP4699139B2 (en) | Security system | |
| US7512255B2 (en) | Multi-modal face recognition | |
| JP4899551B2 (en) | Authentication device, authentication method, authentication program, and computer-readable recording medium | |
| US20040114782A1 (en) | Iris image data processing for use with iris recognition system | |
| WO2016159052A1 (en) | Biological pattern information processing device, biological pattern information processing method, and program | |
| US20110142297A1 (en) | Camera Angle Compensation in Iris Identification | |
| CN105787454A (en) | Method And System Of Texture Features For Biometric Authentication | |
| JP2004284344A (en) | Id card preparation device, id card, face authentication terminal equipment, and device and system for face authentication | |
| WO2016159390A1 (en) | Biological pattern information processing device, biological pattern information processing method and program | |
| CN111344703A (en) | User authentication device and method based on iris recognition | |
| CN109934207A (en) | A kind of characteristic distance modification method of driver face based on facial expression fatigue driving detection algorithm | |
| CN111710031A (en) | Method for breaking password of intelligent terminal device by counterfeiting portrait | |
| CN112529231A (en) | Social security card information acquisition system and acquisition method thereof | |
| CN106156739B (en) | A kind of certificate photo ear detection and extracting method based on face mask analysis | |
| CN105631285A (en) | Biological feature identity recognition method and apparatus | |
| CN111710030A (en) | AI-based system and method for resisting deep forgery portrait | |
| CN112906608A (en) | Layer positioning and layer fixing method of face model and application thereof | |
| CN107423687B (en) | Identity authentication method and device based on face recognition technology | |
| CN110309814A (en) | A kind of iris identification method and device based on edge detection | |
| EP2138950A1 (en) | Iris feature extraction, identification and verification system based on directionlets | |
| Gupta et al. | Iris recognition system using biometric template matching technology |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210604 |