CN114241584A - Face optimization identification method and terminal - Google Patents
Face optimization identification method and terminal Download PDFInfo
- Publication number
- CN114241584A CN114241584A CN202210093644.4A CN202210093644A CN114241584A CN 114241584 A CN114241584 A CN 114241584A CN 202210093644 A CN202210093644 A CN 202210093644A CN 114241584 A CN114241584 A CN 114241584A
- Authority
- CN
- China
- Prior art keywords
- face
- user
- recognition
- similarity
- dimensional 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a face optimization identification method and a terminal, wherein the method comprises the following steps: s1, acquiring the face data to be recognized, comparing the face data to be recognized with the stored face data of the user to obtain a first similarity, if the first similarity exceeds a recognition threshold, successfully recognizing the face, otherwise, executing the step S2; s2, judging whether the first similarity exceeds an approximate threshold, if so, calling the user face data to carry out three-dimensional reconstruction to obtain a user face three-dimensional model; s3, acquiring a first face orientation, first environment information and first shelter information corresponding to the face data to be recognized to obtain a simulated three-dimensional model of the face of the current user; and S4, comparing the similarity of the face data to be recognized with the three-dimensional face model of the current user to obtain a second similarity, wherein if the second similarity exceeds a recognition threshold, the face recognition is successful, otherwise, the face recognition fails. The invention can improve the flexibility and accuracy of face recognition.
Description
Technical Field
The invention relates to the technical field of face recognition, in particular to a face optimization recognition method and a terminal.
Background
Face recognition is a biometric technology for identity recognition based on facial feature information of a person. A series of related technologies, also commonly called face recognition and face recognition, are used to collect images or video streams containing faces by using a camera or a video camera, automatically detect and track the faces in the images, and then perform face recognition on the detected faces.
Compared with fingerprint recognition and iris recognition, the face recognition technology is more natural and safer, wherein the safer is mainly more difficult to be disguised and deceived. However, because the human faces among different individuals are small in difference, the stability of the human faces is poor, and the human face data is complex, two important standards of biological feature recognition are to be fast and accurate, so that the human face recognition is also a difficult direction in the field of biological feature recognition.
With the development of face recognition technology, face recognition is widely applied to daily life of people, including mobile phone unlocking, door locking, subway entrance and exit riding, face payment and the like. However, the current face recognition technology still depends on the conditions that the acquisition conditions are good, the user cooperation is good, and the face of the user is not changed, if the user performs actions such as haircut, makeup, wearing a mask and the like which affect the face characteristics, the accuracy of the face recognition is suddenly reduced, and the face recognition can not be completed seriously or even, so that the face recognition technology is restricted by inputting a password or pressing a fingerprint and other biological recognition to receive for assistance.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: a face optimization recognition method and a terminal are provided to improve the flexibility and accuracy of face recognition.
In order to solve the technical problems, the invention adopts the technical scheme that:
a face optimization recognition method comprises the following steps:
s1, acquiring face data to be recognized, comparing the face data to be recognized with stored user face data to obtain a first similarity, if the first similarity exceeds a recognition threshold, successfully recognizing the face, otherwise, executing the step S2;
s2, judging whether the first similarity exceeds an approximate threshold, if so, calling the user face data to carry out three-dimensional reconstruction to obtain a user face three-dimensional model;
s3, obtaining a first face orientation, first environment information and first obstruction information corresponding to face data to be recognized, adjusting the user face three-dimensional model according to the first face orientation, simulating the space where the user face three-dimensional model is located according to the first environment information, adding the first obstruction information to the user face three-dimensional model at the position corresponding to the first obstruction information, removing the face data of an obstructed area, and obtaining a simulated current user face three-dimensional model;
s4, comparing the similarity of the face data to be recognized with the face three-dimensional model of the current user to obtain a second similarity, if the second similarity exceeds a recognition threshold, the face recognition is successful, otherwise, the face recognition is failed.
In order to solve the technical problem, the invention adopts another technical scheme as follows:
a face optimized recognition terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
s1, acquiring face data to be recognized, comparing the face data to be recognized with stored user face data to obtain a first similarity, if the first similarity exceeds a recognition threshold, successfully recognizing the face, otherwise, executing the step S2;
s2, judging whether the first similarity exceeds an approximate threshold, if so, calling the user face data to carry out three-dimensional reconstruction to obtain a user face three-dimensional model;
s3, obtaining a first face orientation, first environment information and first obstruction information corresponding to face data to be recognized, adjusting the user face three-dimensional model according to the first face orientation, simulating the space where the user face three-dimensional model is located according to the first environment information, adding the first obstruction information to the user face three-dimensional model at the position corresponding to the first obstruction information, removing the face data of an obstructed area, and obtaining a simulated current user face three-dimensional model;
s4, comparing the similarity of the face data to be recognized with the face three-dimensional model of the current user to obtain a second similarity, if the second similarity exceeds a recognition threshold, the face recognition is successful, otherwise, the face recognition is failed.
The invention has the beneficial effects that: a human face optimization recognition method and a terminal thereof, when normal human face recognition fails, considering that a user is possibly influenced by environmental factors such as illumination, weather, brightness and the like or the user performs behaviors similar to hairdressing, makeup, wearing a mask and the like and capable of shielding human face features, therefore, an approximate threshold value is used as a judgment basis for the user, on the premise that the user is possible, three-dimensional simulation is performed on the current human face orientation, environmental information and shielding object information of the user, and then further human face recognition is performed, so that different environments can be adapted and the behaviors of the user shielding the human face features can be adapted on the basis of ensuring the accuracy of the human face recognition, and the flexibility and the accuracy of the human face recognition are improved.
Drawings
Fig. 1 is a schematic flow chart of a face optimization recognition method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a face optimization recognition terminal according to an embodiment of the present invention.
Description of reference numerals:
1. a face optimization recognition terminal; 2. a processor; 3. a memory.
Detailed Description
In order to explain technical contents, achieved objects, and effects of the present invention in detail, the following description is made with reference to the accompanying drawings in combination with the embodiments.
Referring to fig. 1, a face optimization recognition method includes the steps of:
s1, acquiring face data to be recognized, comparing the face data to be recognized with stored user face data to obtain a first similarity, if the first similarity exceeds a recognition threshold, successfully recognizing the face, otherwise, executing the step S2;
s2, judging whether the first similarity exceeds an approximate threshold, if so, calling the user face data to carry out three-dimensional reconstruction to obtain a user face three-dimensional model;
s3, obtaining a first face orientation, first environment information and first obstruction information corresponding to face data to be recognized, adjusting the user face three-dimensional model according to the first face orientation, simulating the space where the user face three-dimensional model is located according to the first environment information, adding the first obstruction information to the user face three-dimensional model at the position corresponding to the first obstruction information, removing the face data of an obstructed area, and obtaining a simulated current user face three-dimensional model;
s4, comparing the similarity of the face data to be recognized with the face three-dimensional model of the current user to obtain a second similarity, if the second similarity exceeds a recognition threshold, the face recognition is successful, otherwise, the face recognition is failed.
From the above description, the beneficial effects of the present invention are: when normal face recognition fails, considering that a user is possibly influenced by environmental factors such as illumination, weather and brightness or the user performs actions such as hairdressing, makeup, wearing a mask and the like and can shield face features, an approximate threshold value is used as a judgment basis for the user, and on the premise that the user is possible, the current face orientation, environmental information and shielding object information of the user are subjected to three-dimensional simulation and then further face recognition is performed, so that different environments can be adapted and the actions of shielding the face features of the user can be self-adapted on the basis of ensuring the accuracy of the face recognition, and the flexibility and the accuracy of the face recognition are improved.
Further, the step S3 further includes the steps of:
acquiring auxiliary face data of which the face orientation difference value with face data to be recognized exceeds an orientation threshold value in real time, acquiring a second face orientation, second environment information and second shelter information corresponding to the auxiliary face data, adjusting the user face three-dimensional model according to the second face orientation, simulating the space where the user face three-dimensional model is located according to the second environment information, adding first shelter information to the user face three-dimensional model at a position corresponding to the second shelter information, removing face data of a sheltered area, and acquiring a simulated auxiliary user face three-dimensional model;
the step S4 specifically includes the following steps:
comparing the similarity of the face data to be recognized with the face three-dimensional model of the current user to obtain a second similarity;
comparing the similarity of the auxiliary face data with the three-dimensional face model of the auxiliary user to obtain a third similarity;
if the second similarity and the third similarity both exceed the recognition threshold, the face recognition is successful, otherwise, the face recognition is failed.
From the above description, it can be known that the safety of face recognition is reduced to a certain extent because the face features are shielded or the face features are discarded after being distorted due to environmental factors, so that the auxiliary face data corresponding to different face orientations are limited, and more face information is obtained to perform secondary face recognition verification, thereby improving the safety performance of face recognition.
Further, in step S2, the three-dimensional model of the user face is generated by three-dimensional reconstruction when the user face data is entered.
According to the description, three-dimensional reconstruction generation is carried out when the face data of the user is input, and a face three-dimensional model can be rapidly extracted for face recognition when needed, so that the face recognition speed is increased.
Further, in step S3, if the occlusion ratio of the first occluder information exceeds the occlusion threshold, it is directly determined that the face recognition has failed.
As can be seen from the above description, if the shielding ratio exceeds the shielding threshold, for example, exceeds fifty percent of face information, this phenomenon exceeds the normal operation behavior of the user, and therefore, subsequent face recognition is not performed, and face recognition is directly considered, so that a lawbreaker is prevented from cheating face recognition through this hole, and the safety of face recognition is improved.
Further, in step S4, if the face recognition fails, an adjustment prompt message is output to guide the user to cooperate with the face recognition.
From the above description, the adjustment prompt information is output to guide the user to cooperate with the face recognition, so that the success rate of the face recognition is improved.
Referring to fig. 2, a face optimization recognition terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the following steps:
s1, acquiring face data to be recognized, comparing the face data to be recognized with stored user face data to obtain a first similarity, if the first similarity exceeds a recognition threshold, successfully recognizing the face, otherwise, executing the step S2;
s2, judging whether the first similarity exceeds an approximate threshold, if so, calling the user face data to carry out three-dimensional reconstruction to obtain a user face three-dimensional model;
s3, obtaining a first face orientation, first environment information and first obstruction information corresponding to face data to be recognized, adjusting the user face three-dimensional model according to the first face orientation, simulating the space where the user face three-dimensional model is located according to the first environment information, adding the first obstruction information to the user face three-dimensional model at the position corresponding to the first obstruction information, removing the face data of an obstructed area, and obtaining a simulated current user face three-dimensional model;
s4, comparing the similarity of the face data to be recognized with the face three-dimensional model of the current user to obtain a second similarity, if the second similarity exceeds a recognition threshold, the face recognition is successful, otherwise, the face recognition is failed.
From the above description, the beneficial effects of the present invention are: when normal face recognition fails, considering that a user is possibly influenced by environmental factors such as illumination, weather and brightness or the user performs actions such as hairdressing, makeup, wearing a mask and the like and can shield face features, an approximate threshold value is used as a judgment basis for the user, and on the premise that the user is possible, the current face orientation, environmental information and shielding object information of the user are subjected to three-dimensional simulation and then further face recognition is performed, so that different environments can be adapted and the actions of shielding the face features of the user can be self-adapted on the basis of ensuring the accuracy of the face recognition, and the flexibility and the accuracy of the face recognition are improved.
Further, the step S3 further includes the steps of:
acquiring auxiliary face data of which the face orientation difference value with face data to be recognized exceeds an orientation threshold value in real time, acquiring a second face orientation, second environment information and second shelter information corresponding to the auxiliary face data, adjusting the user face three-dimensional model according to the second face orientation, simulating the space where the user face three-dimensional model is located according to the second environment information, adding first shelter information to the user face three-dimensional model at a position corresponding to the second shelter information, removing face data of a sheltered area, and acquiring a simulated auxiliary user face three-dimensional model;
the step S4 specifically includes the following steps:
comparing the similarity of the face data to be recognized with the face three-dimensional model of the current user to obtain a second similarity;
comparing the similarity of the auxiliary face data with the three-dimensional face model of the auxiliary user to obtain a third similarity;
if the second similarity and the third similarity both exceed the recognition threshold, the face recognition is successful, otherwise, the face recognition is failed.
From the above description, it can be known that the safety of face recognition is reduced to a certain extent because the face features are shielded or the face features are discarded after being distorted due to environmental factors, so that the auxiliary face data corresponding to different face orientations are limited, and more face information is obtained to perform secondary face recognition verification, thereby improving the safety performance of face recognition.
Further, in step S2, the three-dimensional model of the user face is generated by three-dimensional reconstruction when the user face data is entered.
According to the description, three-dimensional reconstruction generation is carried out when the face data of the user is input, and a face three-dimensional model can be rapidly extracted for face recognition when needed, so that the face recognition speed is increased.
Further, in step S3, if the occlusion ratio of the first occluder information exceeds the occlusion threshold, it is directly determined that the face recognition has failed.
As can be seen from the above description, if the shielding ratio exceeds the shielding threshold, for example, exceeds fifty percent of face information, this phenomenon exceeds the normal operation behavior of the user, and therefore, subsequent face recognition is not performed, and face recognition is directly considered, so that a lawbreaker is prevented from cheating face recognition through this hole, and the safety of face recognition is improved.
Further, in step S4, if the face recognition fails, an adjustment prompt message is output to guide the user to cooperate with the face recognition.
From the above description, the adjustment prompt information is output to guide the user to cooperate with the face recognition, so that the success rate of the face recognition is improved.
The face optimization recognition method and the terminal can be applied to scenes needing face recognition, and are explained by specific implementation modes as follows:
referring to fig. 1, a first embodiment of the present invention is:
a face optimization recognition method comprises the following steps:
s1, acquiring the face data to be recognized, comparing the face data to be recognized with the stored face data of the user to obtain a first similarity, if the first similarity exceeds a recognition threshold, successfully recognizing the face, otherwise, executing the step S2;
the stored user face data is standard face data entered by the user after authentication. In this embodiment, the similarity comparison between the face data to be recognized and the stored user face data is performed by using the existing mature algorithm, that is, normal recognition is performed according to the existing face recognition, and if the recognition is not successful, the subsequent steps are performed.
S2, judging whether the first similarity exceeds an approximate threshold, if so, calling the user face data to carry out three-dimensional reconstruction to obtain a user face three-dimensional model;
where, for example, the recognition threshold is 80%, the approximation threshold may be set to 60%, i.e. the approximation threshold is necessarily smaller than the recognition threshold.
The three-dimensional model of the user face is generated by three-dimensional reconstruction when the user face data is input, and then the three-dimensional model is directly called.
S3, obtaining a first face orientation, first environment information and first shielding object information corresponding to face data to be recognized, adjusting a user face three-dimensional model according to the first face orientation, simulating the space where the user face three-dimensional model is located according to the first environment information, adding first shielding object information to the position where the user face three-dimensional model is located corresponding to the first shielding object information, removing face data of a shielded area, and obtaining a simulated current user face three-dimensional model;
acquiring auxiliary face data of which the face orientation difference value with face data to be recognized exceeds an orientation threshold value in real time, acquiring a second face orientation, second environment information and second shelter information corresponding to the auxiliary face data, adjusting a user face three-dimensional model according to the second face orientation, simulating the space where the user face three-dimensional model is located according to the second environment information, adding first shelter information to the user face three-dimensional model at a position corresponding to the second shelter information, removing face data of a sheltered area, and obtaining a simulated auxiliary user face three-dimensional model;
in this embodiment, the face orientation, the environment information and the shelter information can be acquired through the acquisition camera, wherein the face orientation is the steering direction of the user relative to the acquisition camera, the environment information includes illumination, weather, brightness and the like which can affect the facial feature expression, and the shelter information is an object which is trained in advance and can affect the facial feature, such as the change of a hair style, a cosmetic product with obvious expression on a part, a wearing mask and the like.
The face orientation difference between the face data to be recognized and the auxiliary face data exceeds an orientation threshold, the orientation threshold can be 30 degrees or other angles, the primary face orientations are all right, so that the face front information is relatively complete, and when the face orientations are different from the acquisition camera, the face features on the edge can be further acquired so as to obtain more face features to make up the face features missing due to the environment or the obstruction.
In this embodiment, if the occlusion ratio of the first occlusion information exceeds the occlusion threshold, it is directly determined that the face recognition fails.
And S4, comparing the similarity of the face data to be recognized with the three-dimensional face model of the current user to obtain a second similarity, wherein if the second similarity exceeds a recognition threshold, the face recognition is successful, otherwise, the face recognition fails.
In this embodiment, step S4 specifically includes the following steps:
s41, comparing the similarity of the face data to be recognized with the face three-dimensional model of the current user to obtain a second similarity;
s42, carrying out similarity comparison on the auxiliary face data and the auxiliary user face three-dimensional model to obtain a third similarity;
and S43, if the second similarity and the third similarity both exceed the recognition threshold, the face recognition is successful, otherwise, the face recognition is failed.
In this embodiment, if the face recognition fails, the adjustment prompt information is output to guide the user to cooperate with the face recognition.
Referring to fig. 2, the second embodiment of the present invention is:
a face optimization recognition terminal 1 comprises a memory 3, a processor 2 and a computer program stored on the memory 3 and capable of running on the processor 2, wherein the processor 2 realizes the steps of the first embodiment when executing the computer program.
In summary, according to the face optimization identification method and the terminal provided by the invention, when normal face identification fails, the approximate threshold is used as a judgment basis for whether the face is likely to be a user, on the premise that the face is likely to be the user, the current face orientation, the environmental information and the blocking object information of the user are subjected to three-dimensional simulation, and then further secondary face identification is performed, so that different environments can be adapted and the behavior of the user for blocking the face features can be adapted on the basis of ensuring the accuracy of face identification, and the flexibility, the safety and the accuracy of face identification are improved.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent changes made by using the contents of the present specification and the drawings, or applied directly or indirectly to the related technical fields, are included in the scope of the present invention.
Claims (10)
1. A face optimization recognition method is characterized by comprising the following steps:
s1, acquiring face data to be recognized, comparing the face data to be recognized with stored user face data to obtain a first similarity, if the first similarity exceeds a recognition threshold, successfully recognizing the face, otherwise, executing the step S2;
s2, judging whether the first similarity exceeds an approximate threshold, if so, calling the user face data to carry out three-dimensional reconstruction to obtain a user face three-dimensional model;
s3, obtaining a first face orientation, first environment information and first obstruction information corresponding to face data to be recognized, adjusting the user face three-dimensional model according to the first face orientation, simulating the space where the user face three-dimensional model is located according to the first environment information, adding the first obstruction information to the user face three-dimensional model at the position corresponding to the first obstruction information, removing the face data of an obstructed area, and obtaining a simulated current user face three-dimensional model;
s4, comparing the similarity of the face data to be recognized with the face three-dimensional model of the current user to obtain a second similarity, if the second similarity exceeds a recognition threshold, the face recognition is successful, otherwise, the face recognition is failed.
2. The method for optimal face recognition according to claim 1, wherein the step S3 further comprises the steps of:
acquiring auxiliary face data of which the face orientation difference value with face data to be recognized exceeds an orientation threshold value in real time, acquiring a second face orientation, second environment information and second shelter information corresponding to the auxiliary face data, adjusting the user face three-dimensional model according to the second face orientation, simulating the space where the user face three-dimensional model is located according to the second environment information, adding first shelter information to the user face three-dimensional model at a position corresponding to the second shelter information, removing face data of a sheltered area, and acquiring a simulated auxiliary user face three-dimensional model;
the step S4 specifically includes the following steps:
comparing the similarity of the face data to be recognized with the face three-dimensional model of the current user to obtain a second similarity;
comparing the similarity of the auxiliary face data with the three-dimensional face model of the auxiliary user to obtain a third similarity;
if the second similarity and the third similarity both exceed the recognition threshold, the face recognition is successful, otherwise, the face recognition is failed.
3. The method for face optimization recognition according to claim 1, wherein in step S2, the three-dimensional model of the user face is generated by three-dimensional reconstruction when the user face data is entered.
4. The method according to claim 1, wherein in step S3, if the occlusion ratio of the first occlusion information exceeds an occlusion threshold, the face recognition is directly considered to have failed.
5. The method according to claim 1, wherein in step S4, if the face recognition fails, an adjustment prompt message is output to guide the user to cooperate with the face recognition.
6. A face optimization recognition terminal, comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor implements the following steps when executing the computer program:
s1, acquiring face data to be recognized, comparing the face data to be recognized with stored user face data to obtain a first similarity, if the first similarity exceeds a recognition threshold, successfully recognizing the face, otherwise, executing the step S2;
s2, judging whether the first similarity exceeds an approximate threshold, if so, calling the user face data to carry out three-dimensional reconstruction to obtain a user face three-dimensional model;
s3, obtaining a first face orientation, first environment information and first obstruction information corresponding to face data to be recognized, adjusting the user face three-dimensional model according to the first face orientation, simulating the space where the user face three-dimensional model is located according to the first environment information, adding the first obstruction information to the user face three-dimensional model at the position corresponding to the first obstruction information, removing the face data of an obstructed area, and obtaining a simulated current user face three-dimensional model;
s4, comparing the similarity of the face data to be recognized with the face three-dimensional model of the current user to obtain a second similarity, if the second similarity exceeds a recognition threshold, the face recognition is successful, otherwise, the face recognition is failed.
7. The terminal according to claim 6, wherein the step S3 further comprises the steps of:
acquiring auxiliary face data of which the face orientation difference value with face data to be recognized exceeds an orientation threshold value in real time, acquiring a second face orientation, second environment information and second shelter information corresponding to the auxiliary face data, adjusting the user face three-dimensional model according to the second face orientation, simulating the space where the user face three-dimensional model is located according to the second environment information, adding first shelter information to the user face three-dimensional model at a position corresponding to the second shelter information, removing face data of a sheltered area, and acquiring a simulated auxiliary user face three-dimensional model;
the step S4 specifically includes the following steps:
comparing the similarity of the face data to be recognized with the face three-dimensional model of the current user to obtain a second similarity;
comparing the similarity of the auxiliary face data with the three-dimensional face model of the auxiliary user to obtain a third similarity;
if the second similarity and the third similarity both exceed the recognition threshold, the face recognition is successful, otherwise, the face recognition is failed.
8. The terminal according to claim 6, wherein in step S2, the three-dimensional model of the user face is generated by three-dimensional reconstruction when inputting the data of the user face.
9. The terminal according to claim 6, wherein in step S3, if the occlusion ratio of the first occlusion information exceeds an occlusion threshold, the face recognition is directly considered to have failed.
10. The terminal according to claim 6, wherein in step S4, if the face recognition fails, an adjustment prompt message is output to guide the user to cooperate with the face recognition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210093644.4A CN114241584A (en) | 2022-01-26 | 2022-01-26 | Face optimization identification method and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210093644.4A CN114241584A (en) | 2022-01-26 | 2022-01-26 | Face optimization identification method and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114241584A true CN114241584A (en) | 2022-03-25 |
Family
ID=80747283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210093644.4A Pending CN114241584A (en) | 2022-01-26 | 2022-01-26 | Face optimization identification method and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114241584A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115810214A (en) * | 2023-02-06 | 2023-03-17 | 广州市森锐科技股份有限公司 | Verification management method, system, equipment and storage medium based on AI face recognition |
| CN116503289A (en) * | 2023-06-20 | 2023-07-28 | 北京天工异彩影视科技有限公司 | Visual special effect application processing method and system |
-
2022
- 2022-01-26 CN CN202210093644.4A patent/CN114241584A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115810214A (en) * | 2023-02-06 | 2023-03-17 | 广州市森锐科技股份有限公司 | Verification management method, system, equipment and storage medium based on AI face recognition |
| CN116503289A (en) * | 2023-06-20 | 2023-07-28 | 北京天工异彩影视科技有限公司 | Visual special effect application processing method and system |
| CN116503289B (en) * | 2023-06-20 | 2024-01-09 | 北京天工异彩影视科技有限公司 | Visual special effect application processing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jain et al. | Can soft biometric traits assist user recognition? | |
| KR101998112B1 (en) | Method for recognizing partial obscured face by specifying partial area based on facial feature point, recording medium and apparatus for performing the method | |
| Kumar et al. | Real time face recognition using adaboost improved fast PCA algorithm | |
| JP3337988B2 (en) | Individual identification device | |
| CN114241584A (en) | Face optimization identification method and terminal | |
| CN108960103B (en) | Identity authentication method and system with face and lip language integrated | |
| KR101743927B1 (en) | Method and apparatus for generating an objected descriptor using extended curvature gabor filter | |
| Yin et al. | A proposed approach for biometric-based authentication using of face and facial expression recognition | |
| Paul et al. | Extraction of facial feature points using cumulative histogram | |
| Yin et al. | Fusion of face recognition and facial expression detection for authentication: a proposed model | |
| Shang et al. | Face and lip-reading authentication system based on android smart phones | |
| Quintiliano et al. | Face recognition based on eigeneyes | |
| Amjed et al. | Noncircular iris segmentation based on weighted adaptive hough transform using smartphone database | |
| Mattar | Principal components analysis based iris recognition and identification system | |
| Jonsson et al. | Learning salient features for real-time face verification | |
| Paul et al. | Automatic adaptive facial feature extraction using CDF analysis | |
| Quintiliano et al. | Face recognition based on eigenfeatures | |
| Ivanova et al. | Generalized net model of a biometric authentication system based on palm geometry and palm vein matching using intuitionistic fuzzy evaluations | |
| De Marsico et al. | A new data normalization function for multibiometric contexts: A case study | |
| Ozkaya et al. | Intelligent face border generation system from fingerprints | |
| Garud et al. | Fingerprint and Palmprint Recognition using neighborhood operation and FAST features | |
| Ozkaya et al. | Intelligent face mask prediction system | |
| Gulhane et al. | A review on surgically altered face images recognition using multimodal bio-metric features | |
| Findling | Pan shot face unlock: Towards unlocking personal mobile devices using stereo vision and biometric face information from multiple perspectives | |
| Rafi | A Secured Biometric Authentication with Hybrid Face Detection and Recognition Model. |
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 |