CN112800922A - Face recognition method and device, electronic equipment and storage medium - Google Patents
Face recognition method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112800922A CN112800922A CN202110086359.5A CN202110086359A CN112800922A CN 112800922 A CN112800922 A CN 112800922A CN 202110086359 A CN202110086359 A CN 202110086359A CN 112800922 A CN112800922 A CN 112800922A
- Authority
- CN
- China
- Prior art keywords
- face
- user
- characteristic information
- identified
- library
- 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
- 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
- G06V40/168—Feature extraction; Face representation
-
- 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
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention provides a face recognition method, a face recognition device and a storage medium, wherein the method comprises the following steps: registering face feature information extracted from a face image of a user with a shielding object into a first face library, and/or registering face feature information extracted from a face image of a user without a shielding object into a second face library; the method comprises the steps of collecting a face image of a user to be identified, extracting face feature information of the user to be identified from the face image of the user to be identified, and detecting whether the face of the user to be identified is provided with a shielding object; and selecting to search the face characteristic information matched with the face characteristic information of the user to be identified in the first face library and/or the second face library according to the detection result, if the face characteristic information is searched, determining that the identification of the user to be identified is successful, and if the face characteristic information is not searched, determining that the identification of the user to be identified is failed. The invention can improve the accuracy of face recognition when the face has the shielding object.
Description
Technical Field
The present invention relates to the field of face recognition technologies, and in particular, to a face recognition method, a face recognition device, and a storage medium.
Background
The face recognition technology is a process of matching a face to be recognized with a face with a known identity to realize identity verification by taking identity verification as a target.
The existing face recognition method mainly relies on face frames, face information such as key points (eyes, ears, mouth and nose) of a face and the like to model to obtain a face model, then the face model is used for similarity comparison to recognize the face, the face is required to be clear and free of shielding, the face recognition effect is good, if the face has shielding objects such as a mask and the like, part of the key points of the face can not be obtained during face recognition, and therefore the modeled face model is inaccurate and the recognition accuracy is reduced.
Disclosure of Invention
In view of this, the present invention provides a face recognition method, a face recognition device, an electronic device, and a storage medium, which can improve the face recognition accuracy when a face has an obstruction.
In order to achieve the purpose, the invention provides the following technical scheme:
a face recognition method, comprising:
registering face feature information extracted from a face image of a user with a shielding object into a first face library, and/or registering face feature information extracted from a face image of a user without a shielding object into a second face library;
the method comprises the steps of collecting a face image of a user to be identified, extracting face feature information of the user to be identified from the face image of the user to be identified, and detecting whether the face of the user to be identified is provided with a shielding object;
and selecting to search the face characteristic information matched with the face characteristic information of the user to be recognized in the first face library and/or the second face library according to the detection result, and determining whether the face recognition of the user to be recognized is successful according to the search result.
A face recognition apparatus comprising: a processor, and a non-transitory computer readable storage medium connected to the processor by a bus;
the non-transitory computer readable storage medium storing one or more computer programs executable by the processor; the processor, when executing the one or more computer programs, implements the steps of:
registering face feature information extracted from a face image of a user with a shielding object into a first face library, and/or registering face feature information extracted from a face image of a user without a shielding object into a second face library;
the method comprises the steps of collecting a face image of a user to be identified, extracting face feature information of the user to be identified from the face image of the user to be identified, and detecting whether the face of the user to be identified is provided with a shielding object;
and selecting to search the face characteristic information matched with the face characteristic information of the user to be recognized in the first face library and/or the second face library according to the detection result, and determining whether the face recognition of the user to be recognized is successful according to the search result.
A non-transitory computer readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the steps in the face recognition method as described above.
According to the technical scheme, in the invention, the face characteristic information with the shielding object is registered in the first face library, and the face characteristic information without the shielding object is registered in the second face library; when the face identification is carried out, whether the face of the user to be identified is provided with a shielding object or not is detected, and the face characteristic information matched with the face characteristic information of the user to be identified is selected to be searched in the first face library and/or the second face library, so that the user to be identified is determined to be successfully identified when the face characteristic information is searched, and the user to be identified is determined to be failed to be identified when the face characteristic information is not searched. The face identification method and the face identification device can improve the face identification accuracy rate when the face has the shielding object by matching the first face library and the second face library.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a flowchart of a face recognition method according to an embodiment of the present invention;
fig. 2 is a flowchart of a face recognition method according to a second embodiment of the present invention;
fig. 3 is a flowchart of a face recognition method according to a third embodiment of the present invention;
fig. 4 is a flowchart of a face recognition method according to a fourth embodiment of the present invention;
fig. 5 is a flowchart of a face recognition method according to a fifth embodiment of the present invention;
fig. 6 is a flowchart of a face recognition method according to a sixth embodiment of the present invention;
fig. 7 is a schematic structural diagram of a face recognition apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. 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 application.
In the embodiment of the invention, in order to improve the face recognition accuracy when the face has the shielding object, a first face library used for storing face characteristic information extracted from a face image with the shielding object and a second face library used for storing face characteristic information extracted from a face image without the shielding object are arranged. The user can select to register the face image with the shielding object when registering the face, can select to register the face image without the shielding object, and can select to register the face image with the shielding object and the face image without the shielding object, so that the influence of the face shielding object on face identification can be reduced, and the face identification accuracy when the face has the shielding object is improved.
The following is a detailed description with reference to specific examples.
Referring to fig. 1, fig. 1 is a flowchart of a face recognition method according to an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
102, acquiring a face image of a user to be identified, extracting face characteristic information of the user to be identified from the face image of the user to be identified, and detecting whether the face of the user to be identified is provided with a blocking object;
and 103, selecting to search the face feature information matched with the face feature information of the user to be recognized in the first face library and/or the second face library according to the detection result, and determining whether the face recognition of the user to be recognized is successful according to the search result.
As can be seen from the method shown in fig. 1, in this embodiment, the first face library is used to store the face feature information of the user with the blocking object, and the second face library is used to store the face feature information of the user without the blocking object; when the face recognition is carried out, whether the face of the user to be recognized is provided with a shelter or not is detected, the face feature information matched with the face feature information of the user to be recognized is selected to be searched in the first face library and/or the second face library, and whether the user to be recognized is successfully recognized or not is determined according to the searching. The face identification method and the face identification device can improve the face identification accuracy rate when the face is provided with the shielding object by matching the first face library with the second face library.
Referring to fig. 2, fig. 2 is a flowchart of a face recognition method according to a second embodiment of the present invention, and as shown in fig. 2, the method includes the following steps:
in this embodiment, in the process of registering a face of a user, an image of the user including the face may be collected and preprocessed to obtain a face image, for example, a face position in the image is detected and determined, and the face image in the image is extracted according to the face position.
In this embodiment, the user can perform face registration under the condition that the face has the blocking object. In this case, a face image with a mask of the user is acquired.
In this embodiment, the user can perform face registration without the face having a blocking object. In this case, a face image of the user without the blocking object is acquired.
In this embodiment, the user can also register the face under two conditions that the face has a blocking object and the face does not have the blocking object, and under such a condition, the face image with the blocking object of the user and the face image without the blocking object of the user can be respectively collected.
In this embodiment, the blocking object may be a mask, an eye mask, or other objects capable of partially blocking a human face.
The above steps 2011 to 2012 are detailed refinements of the step 101 shown in fig. 1.
202, acquiring a face image of a user to be identified, extracting face characteristic information of the user to be identified from the face image of the user to be identified, and detecting whether the face of the user to be identified is provided with a shielding object;
and 203, selecting to search the face feature information matched with the face feature information of the user to be recognized in the first face library and/or the second face library according to the detection result, and determining whether the face recognition of the user to be recognized is successful according to the search result.
As can be seen from the method shown in fig. 2, in the embodiment, in the process of performing face registration by a user, a face image with a blocking object and/or a face image without a blocking object of the user are/is acquired, so that the face feature information of the user with the blocking object is stored in a first face library, and the face feature information of the user without the blocking object is stored in a second face library; when the face recognition is carried out, whether the face of the user to be recognized is provided with a shelter or not is detected, the face feature information matched with the face feature information of the user to be recognized is selected to be searched in the first face library and/or the second face library, and whether the user to be recognized is successfully recognized or not is determined according to the searching. The face identification method and the face identification device can improve the face identification accuracy rate when the face is provided with the shielding object by matching the first face library with the second face library.
Referring to fig. 3, fig. 3 is a flowchart of a face recognition method according to a third embodiment of the present invention, and as shown in fig. 3, the method includes the following steps:
And step 3033, determining whether the face recognition of the user to be recognized is successful according to the search result.
The above steps 3031 to 3033 are specific refinements of the step 103 shown in fig. 1.
As can be seen from the method shown in fig. 3, in this embodiment, the first face library is used to store the face feature information of the user with the blocking object, and the second face library is used to store the face feature information of the user without the blocking object; when the face recognition is carried out, face feature information matched with the face feature information of the user to be recognized is searched in the two face libraries by adopting different searching sequences according to whether the face of the user to be recognized has a shielding object or not, and whether the user to be recognized is successfully recognized or not is determined according to the searching sequence or not. In the embodiment, the searching speed is increased by the difference of the searching sequence, and the face identification accuracy rate when the face has the shielding object can be increased by the matched use of the first face library and the second face library.
Referring to fig. 4, fig. 4 is a flowchart of a face recognition method according to a fourth embodiment of the present invention, and as shown in fig. 4, the method mainly includes the following steps:
step 4031a, if the face detection result indicates that the face of the user to be identified has a blocking object, searching face feature information of which the matching degree with the face feature information of the user to be identified exceeds a preset first threshold value in a first face library, if the face feature information is searched, executing step 4031b, and if the face feature information is not searched, executing step 4031 c;
4031b, determining the face feature information matched with the face feature information of the user to be identified, and turning to 4033;
4031d, determining that the face feature information matched with the face feature information of the user to be identified is not found, and turning to 4033;
in this embodiment, the preset first threshold may be greater than the preset second threshold.
The above steps 4031a to 4031d are a detailed refinement of step 3031 shown in fig. 3.
4032b, determining the face feature information matched with the face feature information of the user to be identified, and turning to 4033;
step 4032c, searching the face feature information of which the matching degree with the face feature information of the user to be identified exceeds a preset fourth threshold value in the first face library, if the face feature information is searched, turning to step 4032b, and if the face feature information is not searched, executing step 4032 d;
4032d, determining that the face feature information matched with the face feature information of the user to be identified is not found, and turning to 4033;
in this embodiment, the preset third threshold may be greater than the preset fourth threshold.
The above steps 4032a to 4032d are a detailed refinement of step 3032 shown in fig. 3.
Step 4033, if the face feature information matched with the face feature information of the user to be recognized is found, determining that the face recognition of the user to be recognized is successful, otherwise, determining that the face recognition of the user to be recognized is failed.
Step 4033 above is a detailed refinement of step 101 shown in fig. 1;
the above steps 4031a to 4033 are a detailed refinement of step 103 shown in fig. 1.
As can be seen from the method shown in fig. 4, in this embodiment, the first face library is used to store the face feature information of the user with the blocking object, and the second face library is used to store the face feature information of the user without the blocking object; when the face recognition is carried out, face feature information of which the matching degree with the face feature information of the user to be recognized exceeds a certain threshold value is searched in two face libraries in different sequences according to the fact that whether the face of the user to be recognized is provided with the shielding object, and whether the user to be recognized is successfully recognized is determined according to the fact that whether the face of the user to be recognized is searched. In the embodiment, the searching speed is increased by the difference of the searching sequence, and the face identification accuracy rate when the face has the shielding object can be increased by the matched use of the first face library and the second face library.
Referring to fig. 5, fig. 5 is a flowchart of a face recognition method according to a fifth embodiment of the present invention, and as shown in fig. 5, the method includes the following steps:
502, acquiring a face image of a user to be identified, extracting face characteristic information of the user to be identified from the face image of the user to be identified, and detecting whether the face of the user to be identified is provided with a shielding object;
The above steps 5031 to 5033 are detailed refinements of the step 103 shown in fig. 1.
As can be seen from the method shown in fig. 5, in this embodiment, the first face library is used to store the face feature information of the user with the blocking object, and the second face library is used to store the face feature information of the user without the blocking object; when the face recognition is carried out, face feature information matched with the face feature information of the user to be recognized is searched in different face libraries respectively according to whether the face of the user to be recognized is provided with a shielding object, and whether the user to be recognized is successfully recognized is determined according to the searching condition. In the embodiment, the first face library and the second face library are matched, so that the face identification accuracy rate when the face has the shielding object can be improved.
Referring to fig. 6, fig. 6 is a flowchart of a face recognition method according to a sixth embodiment of the present invention, and as shown in fig. 6, the method mainly includes the following steps:
601, registering face characteristic information extracted from a face image of a user with a shelter in a first face library, and/or registering face characteristic information extracted from a face image of a user without a shelter in a second face library;
step 6031a, if the face detection result shows that the face of the user to be identified has a blocking object, searching face feature information of which the matching degree with the face feature information of the user to be identified exceeds a preset fifth threshold value in a first face library, if the face feature information is searched, executing step 6031b, and if the face feature information is not searched, executing step 6031 c;
step 6031b, determining the face feature information matched with the face feature information of the user to be identified, and turning to step 6033;
the above steps 6031a to 6031c are a detailed refinement of the step 3031 shown in fig. 3.
in this embodiment, the preset third threshold may be greater than the preset fourth threshold.
The above steps 6032a to 6032c are a detailed refinement of the step 3032 shown in fig. 3.
Step 6033, if the face feature information matched with the face feature information of the user to be recognized is found, determining that the face recognition of the user to be recognized is successful, otherwise, determining that the face recognition of the user to be recognized is failed.
The above step 6033 is a detailed refinement of step 101 shown in fig. 1;
the above steps 6031a to 6033 are a detailed refinement of step 103 shown in fig. 1.
The face recognition method provided by the embodiment of the invention is explained in detail above, and the embodiment of the invention also provides a face recognition device, which is explained in detail below with reference to fig. 7.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a face recognition apparatus according to an embodiment of the present invention, and as shown in fig. 7, the apparatus includes: a processor 701, and a non-transitory computer-readable storage medium 702 connected to the processor 701 through a bus;
the non-transitory computer readable storage medium 702 storing one or more computer programs executable by the processor 701; the processor 701, when executing the one or more computer programs, implements the steps of:
registering face characteristic information extracted from a face image with a shelter to a first face library, and/or registering face characteristic information extracted from a face image without a shelter to a second face library;
the method comprises the steps of collecting a face image of a user to be identified, extracting face feature information of the user to be identified from the face image of the user to be identified, and detecting whether the face of the user to be identified is provided with a shielding object;
and selecting to search the face characteristic information matched with the face characteristic information of the user to be recognized in the first face library and/or the second face library according to the detection result, and determining whether the face recognition of the user to be recognized is successful according to the search result.
In the arrangement shown in figure 7 of the drawings,
the processor 701 registers, to a first face library, face feature information extracted from a face image of a user with a blocking object, and/or registers, to a second face library, face feature information extracted from a face image of a user without a blocking object, including:
in the process of registering the face of a user, acquiring a face image with a shelter and/or a face image without the shelter of the user;
extracting face characteristic information from the collected face image, and detecting whether the face of the user has a shelter;
if the face of the user has a shelter, the extracted face feature information is registered in a first face library;
and if the face of the user does not carry the obstruction, registering the extracted face feature information into a second face library.
In the arrangement shown in figure 7 of the drawings,
the processor 701 selects, according to the detection result, to search the face feature information matched with the face feature information of the user to be identified in the first face library and the second face library, and includes:
if the detection result shows that the face of the user to be identified has a shielding object, searching face feature information matched with the face feature information of the user to be identified in the face library according to the sequence of the first face library and the second face library;
and if the detection result shows that the face of the user to be identified does not have the shielding object, searching the face characteristic information matched with the face characteristic information of the user to be identified in the face library according to the sequence of the second face library and the first face library.
In the arrangement shown in figure 7 of the drawings,
the processor 701 searches the face feature information matched with the face feature information of the user to be recognized in the face library according to the sequence of the first face library and the second face library, and includes:
searching the face characteristic information of which the matching degree with the face characteristic information of the user to be identified exceeds a preset first threshold value in a first face library, and if the face characteristic information is searched, determining that the face characteristic information matched with the face characteristic information of the user to be identified is searched; if the face feature information is not found, the face feature information of which the matching degree with the face feature information of the user to be identified exceeds a preset second threshold value is found in a second face library, if the face feature information is found, the face feature information matched with the face feature information of the user to be identified is determined to be found, and if the face feature information is not found, the face feature information matched with the face feature information of the user to be identified is determined not to be found; wherein the preset first threshold is larger than the preset second threshold;
according to the sequence of the second face library and the first face library, searching the face feature information matched with the face feature information of the user to be identified in the face library, wherein the method comprises the following steps:
searching the face feature information of which the matching degree with the face feature information of the user to be recognized exceeds a preset third threshold value in a second face library, and if the face feature information is searched, determining that the face feature information matched with the face feature information of the user to be recognized is searched; if the face characteristic information is not found, searching the face characteristic information of which the matching degree with the face characteristic information of the user to be identified exceeds a preset fourth threshold value in the first face library, if the face characteristic information is found, determining the face characteristic information matched with the face characteristic information of the user to be identified, and if the face characteristic information is not found, determining the face characteristic information matched with the face characteristic information of the user to be identified; and the preset third threshold is greater than the preset fourth threshold.
In the arrangement shown in figure 7 of the drawings,
the processor 701, according to the detection result, selects to search the face feature information matched with the face feature information of the user to be identified in the first face library or the second face library, including:
if the detection result shows that the face of the user to be identified is provided with a blocking object, searching face characteristic information matched with the face characteristic information of the user to be identified in a first face library;
and if the detection result shows that the face of the user to be identified does not carry the obstruction, searching the face characteristic information matched with the face characteristic information of the user to be identified in the second face library.
In the arrangement shown in figure 7 of the drawings,
the processor 701 searches for the face feature information matched with the face feature information of the user to be identified in the first face library, and includes:
searching the face characteristic information of which the matching degree with the face characteristic information of the user to be identified exceeds a preset fifth threshold value in a first face library, if the face characteristic information is searched, determining that the face characteristic information matched with the face characteristic information of the user to be identified is searched, and if the face characteristic information is not searched, determining that the face characteristic information matched with the face characteristic information of the user to be identified is not searched;
searching the face characteristic information matched with the face characteristic information of the user to be identified in a second face library, wherein the face characteristic information comprises the following steps:
and searching the face characteristic information of which the matching degree with the face characteristic information of the user to be identified exceeds a preset sixth threshold value in the second face library, if the face characteristic information is searched, determining that the face characteristic information matched with the face characteristic information of the user to be identified is searched, and if the face characteristic information is not searched, determining that the face characteristic information matched with the face characteristic information of the user to be identified is not searched.
In the arrangement shown in figure 7 of the drawings,
the processor 701, determining whether the face recognition of the user to be recognized is successful according to the search result, includes:
and if the face characteristic information matched with the face characteristic information of the user to be recognized is found, determining that the face recognition of the user to be recognized is successful, otherwise, determining that the face recognition of the user to be recognized is failed.
In the device shown in fig. 7, the shield includes a mask and an eyecup.
Embodiments of the present invention also provide a non-transitory computer readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the steps in the face recognition method as shown in any of the flowcharts of fig. 1-6.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A face recognition method is characterized by comprising the following steps:
registering face feature information extracted from a face image of a user with a shielding object into a first face library, and/or registering face feature information extracted from a face image of a user without a shielding object into a second face library;
the method comprises the steps of collecting a face image of a user to be identified, extracting face feature information of the user to be identified from the face image of the user to be identified, and detecting whether the face of the user to be identified is provided with a shielding object;
and selecting to search the face characteristic information matched with the face characteristic information of the user to be recognized in the first face library and/or the second face library according to the detection result, and determining whether the face recognition of the user to be recognized is successful according to the search result.
2. The method of claim 1,
registering face feature information extracted from a face image of a user with an obstruction to a first face library, and/or registering face feature information extracted from a face image of a user without an obstruction to a second face library, comprising:
in the process of registering the face of a user, acquiring a face image with a shelter and/or a face image without the shelter of the user;
extracting face characteristic information from the collected face image, and detecting whether the face of the user has a shelter;
if the face of the user has a shelter, the extracted face feature information is registered in a first face library;
and if the face of the user does not carry the obstruction, registering the extracted face feature information into a second face library.
3. The method of claim 1,
according to the detection result, the face feature information matched with the face feature information of the user to be identified is selected to be searched in the first face library and the second face library, and the method comprises the following steps:
if the detection result shows that the face of the user to be identified has a shielding object, searching face feature information matched with the face feature information of the user to be identified in the face library according to the sequence of the first face library and the second face library;
and if the detection result shows that the face of the user to be identified does not have the shielding object, searching the face characteristic information matched with the face characteristic information of the user to be identified in the face library according to the sequence of the second face library and the first face library.
4. The method of claim 3,
searching the face characteristic information matched with the face characteristic information of the user to be identified in the face library according to the sequence of the first face library and the second face library, wherein the face characteristic information comprises the following steps:
searching the face characteristic information of which the matching degree with the face characteristic information of the user to be identified exceeds a preset first threshold value in a first face library, and if the face characteristic information is searched, determining that the face characteristic information matched with the face characteristic information of the user to be identified is searched; if the face feature information is not found, the face feature information of which the matching degree with the face feature information of the user to be identified exceeds a preset second threshold value is found in a second face library, if the face feature information is found, the face feature information matched with the face feature information of the user to be identified is determined to be found, and if the face feature information is not found, the face feature information matched with the face feature information of the user to be identified is determined not to be found; wherein the preset first threshold is larger than the preset second threshold;
according to the sequence of the second face library and the first face library, searching the face feature information matched with the face feature information of the user to be identified in the face library, wherein the method comprises the following steps:
searching the face feature information of which the matching degree with the face feature information of the user to be recognized exceeds a preset third threshold value in a second face library, and if the face feature information is searched, determining that the face feature information matched with the face feature information of the user to be recognized is searched; if the face characteristic information is not found, searching the face characteristic information of which the matching degree with the face characteristic information of the user to be identified exceeds a preset fourth threshold value in the first face library, if the face characteristic information is found, determining the face characteristic information matched with the face characteristic information of the user to be identified, and if the face characteristic information is not found, determining the face characteristic information matched with the face characteristic information of the user to be identified; and the preset third threshold is greater than the preset fourth threshold.
5. The method of claim 1,
selecting to search the face characteristic information matched with the face characteristic information of the user to be identified in the first face library or the second face library according to the detection result, wherein the face characteristic information comprises the following steps:
if the detection result shows that the face of the user to be identified is provided with a blocking object, searching face characteristic information matched with the face characteristic information of the user to be identified in a first face library;
and if the detection result shows that the face of the user to be identified does not carry the obstruction, searching the face characteristic information matched with the face characteristic information of the user to be identified in the second face library.
6. The method of claim 5,
searching the face characteristic information matched with the face characteristic information of the user to be identified in the first face library, wherein the face characteristic information comprises:
searching the face characteristic information of which the matching degree with the face characteristic information of the user to be identified exceeds a preset fifth threshold value in a first face library, if the face characteristic information is searched, determining that the face characteristic information matched with the face characteristic information of the user to be identified is searched, and if the face characteristic information is not searched, determining that the face characteristic information matched with the face characteristic information of the user to be identified is not searched;
searching the face characteristic information matched with the face characteristic information of the user to be identified in a second face library, wherein the face characteristic information comprises the following steps:
and searching the face characteristic information of which the matching degree with the face characteristic information of the user to be identified exceeds a preset sixth threshold value in the second face library, if the face characteristic information is searched, determining that the face characteristic information matched with the face characteristic information of the user to be identified is searched, and if the face characteristic information is not searched, determining that the face characteristic information matched with the face characteristic information of the user to be identified is not searched.
7. The method of claim 1,
determining whether the face recognition of the user to be recognized is successful according to the search result, wherein the determining step comprises the following steps:
and if the face characteristic information matched with the face characteristic information of the user to be recognized is found, determining that the face recognition of the user to be recognized is successful, otherwise, determining that the face recognition of the user to be recognized is failed.
8. The method according to any one of claims 1 to 7,
the shielding object comprises a mask and an eye mask.
9. A face recognition apparatus, comprising: a processor, and a non-transitory computer readable storage medium connected to the processor by a bus;
the non-transitory computer readable storage medium storing one or more computer programs executable by the processor; the processor, when executing the one or more computer programs, implements the steps of:
registering face characteristic information extracted from a face image with a shelter to a first face library, and/or registering face characteristic information extracted from a face image without a shelter to a second face library;
the method comprises the steps of collecting a face image of a user to be identified, extracting face feature information of the user to be identified from the face image of the user to be identified, and detecting whether the face of the user to be identified is provided with a shielding object;
and selecting to search the face characteristic information matched with the face characteristic information of the user to be recognized in the first face library and/or the second face library according to the detection result, and determining whether the face recognition of the user to be recognized is successful according to the search result.
10. A non-transitory computer readable storage medium storing instructions which, when executed by a processor, cause the processor to perform the steps in the face recognition method of any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110086359.5A CN112800922A (en) | 2021-01-22 | 2021-01-22 | Face recognition method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110086359.5A CN112800922A (en) | 2021-01-22 | 2021-01-22 | Face recognition method and device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112800922A true CN112800922A (en) | 2021-05-14 |
Family
ID=75811160
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110086359.5A Pending CN112800922A (en) | 2021-01-22 | 2021-01-22 | Face recognition method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112800922A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115471944A (en) * | 2022-08-08 | 2022-12-13 | 国网河北省电力有限公司建设公司 | Warehouse access lock control method, device and system and readable storage medium |
CN116092228A (en) * | 2023-01-05 | 2023-05-09 | 厦门科拓通讯技术股份有限公司 | Access control processing method and device for face shielding, access control equipment and medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110363047A (en) * | 2018-03-26 | 2019-10-22 | 普天信息技术有限公司 | Method, apparatus, electronic equipment and the storage medium of recognition of face |
CN112115866A (en) * | 2020-09-18 | 2020-12-22 | 北京澎思科技有限公司 | Face recognition method and device, electronic equipment and computer readable storage medium |
CN112241689A (en) * | 2020-09-24 | 2021-01-19 | 北京澎思科技有限公司 | Face recognition method and device, electronic equipment and computer readable storage medium |
-
2021
- 2021-01-22 CN CN202110086359.5A patent/CN112800922A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110363047A (en) * | 2018-03-26 | 2019-10-22 | 普天信息技术有限公司 | Method, apparatus, electronic equipment and the storage medium of recognition of face |
CN112115866A (en) * | 2020-09-18 | 2020-12-22 | 北京澎思科技有限公司 | Face recognition method and device, electronic equipment and computer readable storage medium |
CN112241689A (en) * | 2020-09-24 | 2021-01-19 | 北京澎思科技有限公司 | Face recognition method and device, electronic equipment and computer readable storage medium |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115471944A (en) * | 2022-08-08 | 2022-12-13 | 国网河北省电力有限公司建设公司 | Warehouse access lock control method, device and system and readable storage medium |
CN116092228A (en) * | 2023-01-05 | 2023-05-09 | 厦门科拓通讯技术股份有限公司 | Access control processing method and device for face shielding, access control equipment and medium |
CN116092228B (en) * | 2023-01-05 | 2024-05-14 | 厦门科拓通讯技术股份有限公司 | Access control processing method and device for face shielding, access control equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11107225B2 (en) | Object recognition device and computer readable storage medium | |
EP3826317B1 (en) | Method and device for identifying key time point of video, computer apparatus and storage medium | |
CN109325964B (en) | Face tracking method and device and terminal | |
US11270108B2 (en) | Object tracking method and apparatus | |
CN105938622B (en) | Method and apparatus for detecting object in moving image | |
KR101557376B1 (en) | Method for Counting People and Apparatus Therefor | |
WO2015165365A1 (en) | Facial recognition method and system | |
JP5554984B2 (en) | Pattern recognition method and pattern recognition apparatus | |
US9208375B2 (en) | Face recognition mechanism | |
WO2018099268A1 (en) | Method and device for tracking target, and storage medium | |
CN110610127B (en) | Face recognition method and device, storage medium and electronic equipment | |
CN112016353B (en) | Method and device for carrying out identity recognition on face image based on video | |
KR102132722B1 (en) | Tracking method and system multi-object in video | |
US20200193146A1 (en) | Method and device for recognizing identity of human target | |
CN101408929A (en) | Multiple-formwork human face registering method and apparatus for human face recognition system | |
CN107305693B (en) | Information processing apparatus, information processing method, and storage medium | |
JP5557189B2 (en) | Position estimation apparatus, position estimation method and program | |
CN111444817B (en) | Character image recognition method and device, electronic equipment and storage medium | |
CN108596079B (en) | Gesture recognition method and device and electronic equipment | |
CN113837006B (en) | Face recognition method and device, storage medium and electronic equipment | |
CN112800922A (en) | Face recognition method and device, electronic equipment and storage medium | |
Mathur et al. | Sign language gesture recognition using Zernike moments and DTW | |
CN115527168A (en) | Pedestrian re-identification method, storage medium, database editing method, and storage medium | |
JP2007334810A (en) | Image area tracking device and method therefor | |
KR20130056170A (en) | Real-time detection method of human abnormality using motion sequence and apparatus thereof |
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 |