CN112488078A - Face comparison method and device and readable storage medium - Google Patents
Face comparison method and device and readable storage medium Download PDFInfo
- Publication number
- CN112488078A CN112488078A CN202011533409.1A CN202011533409A CN112488078A CN 112488078 A CN112488078 A CN 112488078A CN 202011533409 A CN202011533409 A CN 202011533409A CN 112488078 A CN112488078 A CN 112488078A
- Authority
- CN
- China
- Prior art keywords
- face
- database
- target
- time period
- priority
- 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 74
- 230000001815 facial effect Effects 0.000 claims abstract description 50
- 238000004590 computer program Methods 0.000 claims description 15
- 238000010586 diagram Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000697 sensory organ Anatomy 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
- 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)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention provides a face comparison method, a face comparison device and a readable storage medium, wherein the face comparison method comprises the following steps: at a first moment, acquiring a face image to be recognized; determining a target time period of the first moment; determining a target feature library group corresponding to the face database in the target time period according to a corresponding relation between the pre-stored time period of the face database and the feature library group, wherein the target feature library group comprises a plurality of database link lists, and each database link list in the plurality of database link lists comprises a plurality of face images with the same priority; and comparing the facial image to be recognized with the plurality of facial images in the corresponding target database chain tables in the plurality of database chain tables according to the sequence of the priorities from high to low to obtain a comparison result. The face comparison and recognition efficiency is improved.
Description
Technical Field
The present invention relates to the field of face recognition technologies, and in particular, to a face comparison method, an apparatus, and a readable storage medium.
Background
With the development of artificial intelligence and electronic payment, large-scale human face identity confirmation becomes a key technical means. In the field of current face recognition, with the increase of the capacity of a registration comparison library, for example, in the hundred thousand level and the million level, the face recognition calculation amount is very large, and at the moment, how to improve the face comparison efficiency is more and more important.
Disclosure of Invention
The embodiment of the invention provides a face comparison method, a face comparison device and a readable storage medium, which are used for improving the face comparison and identification efficiency.
In a first aspect, an embodiment of the present invention provides a face comparison method, including:
at a first moment, acquiring a face image to be recognized;
determining a target time period of the first moment;
determining a target feature library group corresponding to the face database in the target time period according to a corresponding relation between the pre-stored time period of the face database and the feature library group, wherein the target feature library group comprises a plurality of database link lists, and each database link list in the plurality of database link lists comprises a plurality of face images with the same priority;
and comparing the facial image to be recognized with the plurality of facial images in the corresponding target database chain tables in the plurality of database chain tables according to the sequence of the priorities from high to low to obtain a comparison result.
In a possible implementation manner, before the obtaining of the face image to be recognized, the method further includes:
the method comprises the steps of establishing a face database in advance, wherein each face image in the face database is provided with corresponding time period information and priority information except face characteristic information, wherein the face database corresponds to different characteristic base groups in different time periods, and the face images with the same priority information form the same database linked list of the same characteristic base group.
In one possible implementation, after the pre-establishing the face database, the method further includes:
counting the recognition time of each face image in the face database within a preset time period;
determining the recognition times of each face image in the face database in the preset time period according to the recognition time;
and at a second moment after the preset time period, updating the priority information of each face image in the face database according to the identification times, and updating the time period information of each face image in the face database according to the identification time to obtain an updated face database.
In a possible implementation manner, the updating the priority information of each face image in the face database according to the identification times includes:
at a second moment after the preset time period, if the identification times are greater than preset times, adjusting the current priority of the corresponding face image to a target priority greater than the current priority;
and updating the priority information of the corresponding face image in the face database according to the target priority.
In a possible implementation manner, the comparing, according to the order of priority from high to low, the facial image to be recognized with a plurality of facial images in a target database chain table corresponding to the plurality of database chain tables to obtain a comparison result includes:
determining a target database link table with the highest priority in the plurality of database link tables;
comparing the face image to be recognized with a plurality of face images in the target database linked list, and determining a target face image with the face characteristics of the face image to be recognized larger than a preset characteristic threshold value;
and taking the target face image as a comparison result of the face image to be recognized.
In one possible implementation, after the determining a target database link table with a highest priority in the plurality of database link tables, the method further includes:
if the target database linked list does not contain the target face image, determining another database linked list with the priority lower than that of the target database linked list from the plurality of database linked lists;
and comparing the facial image to be recognized with the plurality of facial images in the other database chain table, and determining a target facial image with the facial features of the facial image to be recognized larger than a preset feature threshold value.
In a second aspect, an embodiment of the present invention provides a face comparison apparatus, including:
the acquiring unit is used for acquiring a face image to be recognized at a first moment;
a first determining unit, configured to determine a target time period at which the first time is located;
a second determining unit, configured to determine, according to a correspondence between a time period of a pre-stored face database and a feature library group, a target feature library group corresponding to the face database in the target time period, where the target feature library group includes a plurality of database links, and each of the plurality of database links includes a plurality of face images with the same priority;
and the comparison unit is used for comparing the facial image to be recognized with the plurality of facial images in the corresponding target database chain tables in the plurality of database chain tables according to the sequence of the priorities from high to low to obtain a comparison result.
In one possible implementation, the apparatus further includes:
the establishing unit is used for establishing the face database in advance, each face image in the face database is provided with corresponding time period information and priority information except face characteristic information, wherein in different time periods, the face database corresponds to different characteristic base groups, and the face images with the same priority information form the same database linked list of the same characteristic base group.
In a third aspect, an embodiment of the present invention further provides a computer apparatus, where the computer apparatus includes a processor, and the processor is configured to implement the steps of the human face comparison method as described above when executing the computer program stored in the memory.
In a fourth aspect, the embodiment of the present invention further provides a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the human face comparison method as described above.
The invention has the following beneficial effects:
the embodiment of the invention provides a face comparison method, a face comparison device and a readable storage medium, which comprises the steps of firstly, obtaining a face image to be recognized at a first moment, then determining a target time period of the first moment, then determining a target characteristic library group corresponding to the face database at the target time period according to a corresponding relation between the pre-stored time period of the face database and a characteristic library group, wherein the target characteristic library group comprises a plurality of database chain lists, each database chain list in the plurality of database chain lists comprises a plurality of face images with the same priority, and then comparing the face image to be recognized with the plurality of face images in the corresponding target chain lists in the plurality of database chain lists according to the sequence from high priority to low priority to obtain a comparison result. That is to say, when a facial image to be recognized is recognized, a time period of time at which the facial image to be recognized is determined, then a plurality of database chain tables in a feature library group corresponding to the time period are determined, and the facial image to be recognized is compared with a plurality of facial images in a target database chain table according to the sequence of the priorities of the plurality of database chain tables from high to low, so that the rapid recognition of the facial image to be recognized is realized, and the recognition efficiency of facial comparison is improved.
Drawings
Fig. 1 is a flowchart of a method for comparing human faces according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a feature library group a in the face comparison method according to the embodiment of the present invention;
fig. 3 is a schematic structural diagram of a feature library group B in the face comparison method according to the embodiment of the present invention;
fig. 4 is a schematic structural diagram of a data structure of a face database in the face comparison method according to the embodiment of the present invention;
fig. 5 is a flowchart of another method after a face database is pre-established in a face comparison method according to an embodiment of the present invention;
fig. 6 is a flowchart of a method in step S202 of a face comparison method according to an embodiment of the present invention;
fig. 7 is a flowchart of a method in step S104 of a face comparison method according to an embodiment of the present invention;
fig. 8 is a flowchart of a method after step S401 in the face comparison method according to the embodiment of the present invention;
fig. 9 is a schematic structural diagram of a face comparison device according to an embodiment of the present invention.
Detailed Description
The terms "first," "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "comprises" and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to better understand the technical solutions of the present invention, the technical solutions of the present invention are described in detail below with reference to the drawings and the specific embodiments, and it should be understood that the specific features in the embodiments and the embodiments of the present invention are detailed descriptions of the technical solutions of the present invention, and are not limitations of the technical solutions of the present invention, and the technical features in the embodiments and the embodiments of the present invention may be combined with each other without conflict.
The existing face comparison usually adopts 1: the comparison of N takes longer time for more than 10W human face base libraries. In the prior art, a face database is mainly divided into a plurality of databases, the face databases are established in points, and the capacity of a comparison database is reduced, so that the comparison speed is increased. The method has the disadvantages that the management cost of a plurality of databases is high, comparison needs to be carried out in each database, and the number of invalid comparisons is large. Therefore, the technical problem of low recognition efficiency exists in the existing face comparison.
In view of this, embodiments of the present invention provide a face comparison method, a face comparison device and a readable storage medium, which are used to improve face comparison efficiency.
As shown in fig. 1, an embodiment of the present invention provides a face comparison method, including:
s101: at a first moment, acquiring a face image to be recognized;
in the embodiment of the present invention, the face image to be recognized may be an image collected by an image collector in the face recognition system, or may also be an image sent to the face recognition system by other devices, which is not limited herein. In addition, the first moment is the moment when the face image to be recognized is acquired.
S102: determining a target time period of the first moment;
in the embodiment of the present invention, a division principle of a time period may be set according to actual application requirements, for example, when a time period is divided by one hour, after a first time point at which a face image to be recognized is obtained is determined, a time period at which the face image to be recognized is located may be determined according to an hour interval at which the first time point is located. Of course, in practical application, other time interval division principles may also be adopted, and are not described herein again.
S103: determining a target feature library group corresponding to the face database in the target time period according to a corresponding relation between the pre-stored time period of the face database and the feature library group, wherein the target feature library group comprises a plurality of database link lists, and each database link list in the plurality of database link lists comprises a plurality of face images with the same priority;
in the embodiment of the invention, the face database corresponds to different feature database groups in different time periods, only one face database is used in the whole face comparison process, and the difference is that different feature database groups correspond to different time periods. In a specific implementation process, according to a corresponding relation between a time period of a face database and a feature library group which are stored in advance, a target feature library group corresponding to the face database in a target time period is determined, and then a plurality of database link lists included in the target feature library group are determined, wherein each database link list in the plurality of database link lists comprises a plurality of face images with the same priority. As a specific example, only two time slots including time slot 1 and time slot 2 are provided, and only database link tables with 2 priorities are provided, the schematic structure of the feature library group a corresponding to time slot 1 is shown in fig. 2, the feature library group a includes database link table a1 with priority 1 and database link table a2 with priority 2, where a1, a2, … …, am represent m face images included in database link table a1, a11, a22, … …, ann represent n face images included in database link table a2, where n and m are integers greater than 1, the schematic structure of the feature library group B corresponding to time slot 2 is shown in fig. 3, the feature library group B includes database link table B1 with priority 1 and database link table B2 with priority 2, where B1, B2, … …, and bj represent j face images included in database link table B1, b11, B22, … … and bkk represent k individual face images included in the database chain table B2, wherein j and k are integers greater than 1. In a specific implementation process, the database linked lists in different time periods can be the same linked list, and the difference is that due to different time periods, the sequence of the face images in the database linked lists is different correspondingly. Still taking the above example as an example, in the database link table a1 in time slot 1, the face image ap is included, and in time slot 2, the database link table B1 does not include the face image ap, because any one face image is unique in the face database, the same face image does not exist in both the database link table a1 and the database link table a2, and thus, each face image in the same database link table is continuously updated along with the change of time slot, and the whole face comparison is more flexible.
S104: and comparing the facial image to be recognized with the plurality of facial images in the corresponding target database chain tables in the plurality of database chain tables according to the sequence of the priorities from high to low to obtain a comparison result.
In the embodiment of the present invention, the to-be-recognized face images are compared with the plurality of face images in the corresponding target database chain tables in the plurality of database chain tables in the order from high priority to low priority, still taking the above example as an example, if the priority of 1 is higher than the priority of 2, the to-be-recognized face images may be compared with the m face images in the database chain table a1, and if the to-be-recognized face is confirmed, the n face images in the database chain table a2 do not need to be compared. In the embodiment of the invention, the face images to be recognized are recognized through the priority order, so that the recognition speed of face comparison is improved, and the face images with higher priority are preferentially compared, so that the accuracy of face comparison is ensured, and the recognition efficiency of face comparison is further ensured.
In the embodiment of the present invention, in step S101: before the face image to be recognized is acquired at the first moment, the method further comprises the following steps:
the method comprises the steps of establishing a face database in advance, wherein each face image in the face database is provided with corresponding time period information and priority information except face characteristic information, wherein the face database corresponds to different characteristic base groups in different time periods, and the face images with the same priority information form the same database linked list of the same characteristic base group.
In the embodiment of the invention, before the face image to be recognized is recognized, a face database is established in advance, and correspondingly, the corresponding relation between the time period of the face database and the characteristic library group is stored in advance. In a specific implementation process, the data structure of the face database may be one of the schematic structures shown in fig. 4, specifically, the data structure of each face image in the face database includes a database ID, a face image ID, priority information, time period information, and facial feature information, where the facial feature information may include skin tone, five sense organs, hair style, expression, and the like. The database ID can uniquely identify the ID of the face database, and the rapid index of the face database can be realized. The face image ID is used as a unique ID for application of the identification service process. The priority information may be a comparison priority for representing the face images, and the priority of each face image in the face database may be set to be the lowest level under the initial setting. In practical applications, the level of the priority information may be configured as [1,5], and it may be that the smaller the number, the higher the priority, and accordingly, the priority is compared. In addition, in the implementation, the higher the number, the higher the priority. Of course, those skilled in the art can set the priority value and the level of the priority level according to the actual application requirement, and the setting is not limited herein.
In the embodiment of the invention, the data structure of each face image in the face database is provided with corresponding time period information and priority information except the face characteristic information, so that once the time period information and/or the priority information are/is changed, the face image in the face database is also correspondingly changed, thereby ensuring the real-time property of the face database and further improving the face recognition efficiency. In the specific implementation process, the face database corresponds to different feature library groups in different time periods, and in the same time period, the face images with the same priority information form the same database chain table of the same feature library group. In the same time period, when the human face is compared, the human face images with the same priority information can be compared.
In this embodiment of the present invention, as shown in fig. 5, after the face database is pre-established, the method further includes:
s201: counting the recognition time of each face image in the face database within a preset time period;
s202: determining the recognition times of each face image in the face database in the preset time period according to the recognition time;
s203: and at a second moment after the preset time period, updating the priority information of each face image in the face database according to the identification times, and updating the time period information of each face image in the face database according to the identification time to obtain an updated face database.
In the specific implementation process, the specific implementation process of step S201 to step S203 is as follows:
firstly, counting the recognition time of each face image in the face database within a preset time period, where the preset time period may be a fixed time period, for example, the preset time period may be two consecutive days, which is not limited herein. The recognition time of each face image in the face database may be the time of the corresponding face image. Then, according to the recognition time, the recognition times of each face image in the face database in a preset time period are determined, and the recognition times can be the times of successful recognition. And then, at a second moment after the preset time period, updating the priority information of each face image in the face database according to the identification times, and updating the time period information of each face image in the face database according to the identification time to obtain the updated face database. In a specific implementation, after the preset time period, the second time may be a starting time after the preset time period, for example, two consecutive days later, morning 8: 00, or may be a time after the start time after a preset time period, for example, 2:00 in the morning after two consecutive days. In practical application, the update time may be set at a time when the face recognition system is less operated, for example, most people are in the white class, the update time may be set at night, and of course, a person skilled in the art may set the second time according to practical application needs, which is not described in detail herein. In the specific implementation process, the identification time and the identification times of each face image in the face database are regularly counted, and then the priority information and the time period information of each face image are regularly updated, so that the face database is updated in real time, and the identification efficiency of face identification is ensured.
In the embodiment of the present invention, as shown in fig. 6, step S202: updating the priority information of each face image in the face database according to the identification times, wherein the updating comprises the following steps:
s301: at a second moment after the preset time period, if the identification times are greater than preset times, adjusting the current priority of the corresponding face image to a target priority greater than the current priority;
s302: and updating the priority information of the corresponding face image in the face database according to the target priority.
In the specific implementation process, the specific implementation process from step S301 to step S302 is as follows:
firstly, at a second moment after a preset time period, if the identification times are greater than the preset times, the current priority of the face image is adjusted to a target priority greater than the current priority. The specific value of the preset number may be a value set by a person skilled in the art according to the actual application requirement, and is not limited herein. For example, if the average recognition frequency of the face image c in the face database exceeds 2 times per day, the current priority of the face image c is upgraded, for example, the current priority of the face image c is 4, and the adjusted target priority is 3. And then updating the priority information of the corresponding face image in the face database according to the target priority. In the specific implementation process, the priority information is updated according to the recognition times, so that the face recognition efficiency can be further improved. In addition, at a second time after the preset time period, if the recognition times are less than or equal to the preset times, the current priority of the corresponding face image is adjusted to a target priority less than the current priority, for example, if the recognition times of the face image d in the face database for two consecutive days are less than the preset times, the current priority of the face image d is subjected to degradation processing, for example, the current priority of the face image d is 2, and the adjusted target priority is 3. In the specific implementation process, after the priority information of the face images in the face database is updated, the database link lists in the feature library groups corresponding to the face database are correspondingly updated, so that the real-time performance of the face database is ensured, and the face comparison efficiency is improved.
In the embodiment of the present invention, as shown in fig. 7, step S104: comparing the facial image to be recognized with the plurality of facial images in the corresponding target database chain tables in the plurality of database chain tables according to the sequence of the priorities from high to low to obtain comparison results, wherein the comparison results comprise:
s401: determining a target database link table with the highest priority in the plurality of database link tables;
s402: comparing the face image to be recognized with a plurality of face images in the target database linked list, and determining a target face image with the face characteristics of the face image to be recognized larger than a preset characteristic threshold value;
s403: and taking the target face image as a comparison result of the face image to be recognized.
In the specific implementation process, the specific implementation process of steps S401 to S403 is as follows:
firstly, determining a target database chain table with the highest priority in a plurality of database chain tables in a target feature library group, then comparing the face image to be recognized with a plurality of face images in the target database chain table, determining a target face image with the face feature of the face image to be recognized larger than a preset feature threshold value, taking the example shown in fig. 2 as an example, the target database chain table is database chain table a1, comparing the face image to be recognized with m face images of a1, a2, … … and am in database chain table a1, and determining the target face image with the face feature of the face image to be recognized larger than the preset feature threshold value. In the specific implementation process, the facial images to be recognized are recognized through the plurality of facial images in the target database chain table with the highest priority, once the recognition is successful, the comparison is not needed, and the whole recognition efficiency is high. In addition, the specific method for performing face feature recognition on the faces to be recognized and a plurality of faces in the target database linked list is the same as the face feature recognition in the prior art, and is not repeated herein.
In the embodiment of the present invention, as shown in fig. 8, in step S401: after determining the highest priority target database linked list of the plurality of database linked lists, the method further comprises:
s501: if the target database linked list does not contain the target face image, determining another database linked list with the priority lower than that of the target database linked list from the plurality of database linked lists;
s502: and comparing the facial image to be recognized with the plurality of facial images in the other database chain table, and determining a target facial image with the facial features of the facial image to be recognized larger than a preset feature threshold value.
In the specific implementation process, the specific implementation process of steps S501 to S502 is as follows:
firstly, if there is no target face image in the target database chain table with the highest priority, determining another database chain table with the priority only second to the target database chain table from the target feature library group, then comparing the face image to be recognized with a plurality of face images in the another database chain table, taking the example shown in fig. 2 as an example, if the face image to be recognized is not recognized after feature comparison with m face images in the database chain table a1, comparing the face image to be recognized with n face images in the database chain table a2 with the priority lower than the database chain table a1, and determining the target image with the face feature larger than the preset feature threshold value. In the specific implementation process, in the same target time period, the face image to be recognized and the plurality of face images in the target database linked list can be sequentially compared from high to low according to the priority of the database linked list until the face image to be recognized is recognized, so that the face recognition efficiency is improved while the face recognition speed is ensured.
Based on the same inventive concept, as shown in fig. 9, an embodiment of the present invention provides a face comparison apparatus, including:
the acquiring unit 10 is used for acquiring a face image to be recognized at a first moment;
a first determining unit 20, configured to determine a target time period at the first time;
a second determining unit 30, configured to determine, according to a correspondence between a time period of a pre-stored face database and a feature library group, a target feature library group corresponding to the face database in the target time period, where the target feature library group includes a plurality of database links, and each of the plurality of database links includes a plurality of face images with the same priority;
and the comparison unit 40 is configured to compare the facial image to be recognized with the plurality of facial images in the corresponding target database chain tables in the plurality of database chain tables in the order from high priority to low priority, so as to obtain a comparison result.
In an embodiment of the present invention, the apparatus further includes:
the establishing unit is used for establishing the face database in advance, each face image in the face database is provided with corresponding time period information and priority information except face characteristic information, wherein in different time periods, the face database corresponds to different characteristic base groups, and the face images with the same priority information form the same database linked list of the same characteristic base group.
In an embodiment of the present invention, the apparatus further includes an updating unit, where the updating unit is configured to:
counting the recognition time of each face image in the face database within a preset time period;
determining the recognition times of each face image in the face database in the preset time period according to the recognition time;
and at a second moment after the preset time period, updating the priority information of each face image in the face database according to the identification times, and updating the time period information of each face image in the face database according to the identification time to obtain an updated face database.
In an embodiment of the present invention, the update unit is configured to:
at a second moment after the preset time period, if the identification times are greater than preset times, adjusting the current priority of the corresponding face image to a target priority greater than the current priority;
and updating the priority information of the corresponding face image in the face database according to the target priority.
In the embodiment of the present invention, the comparing unit 40 is configured to:
determining a target database link table with the highest priority in the plurality of database link tables;
comparing the face image to be recognized with a plurality of face images in the target database linked list, and determining a target face image with the face characteristics of the face image to be recognized larger than a preset characteristic threshold value;
and taking the target face image as a comparison result of the face image to be recognized.
In the embodiment of the present invention, the comparing unit 40 is further configured to:
if the target database linked list does not contain the target face image, determining another database linked list with the priority lower than that of the target database linked list from the plurality of database linked lists;
and comparing the facial image to be recognized with the plurality of facial images in the other database chain table, and determining a target facial image with the facial features of the facial image to be recognized larger than a preset feature threshold value.
Based on the same inventive concept, an embodiment of the present invention further provides a computer apparatus, where the computer apparatus includes a processor, and the processor is configured to implement the steps of the above-described face comparison method when executing a computer program stored in a memory.
Based on the same inventive concept, the embodiment of the present invention further provides a readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the above-mentioned face comparison method.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (10)
1. A face comparison method is characterized by comprising the following steps:
at a first moment, acquiring a face image to be recognized;
determining a target time period of the first moment;
determining a target feature library group corresponding to the face database in the target time period according to a corresponding relation between the pre-stored time period of the face database and the feature library group, wherein the target feature library group comprises a plurality of database link lists, and each database link list in the plurality of database link lists comprises a plurality of face images with the same priority;
and comparing the facial image to be recognized with the plurality of facial images in the corresponding target database chain tables in the plurality of database chain tables according to the sequence of the priorities from high to low to obtain a comparison result.
2. The method of claim 1, wherein prior to said obtaining the image of the face to be recognized, the method further comprises:
the method comprises the steps of establishing a face database in advance, wherein each face image in the face database is provided with corresponding time period information and priority information except face characteristic information, wherein the face database corresponds to different characteristic base groups in different time periods, and the face images with the same priority information form the same database linked list of the same characteristic base group.
3. The method of claim 2, wherein after said pre-building said face database, said method further comprises:
counting the recognition time of each face image in the face database within a preset time period;
determining the recognition times of each face image in the face database in the preset time period according to the recognition time;
and at a second moment after the preset time period, updating the priority information of each face image in the face database according to the identification times, and updating the time period information of each face image in the face database according to the identification time to obtain an updated face database.
4. The method of claim 3, wherein said updating the priority information of each face image in the face database according to the recognition times comprises:
at a second moment after the preset time period, if the identification times are greater than preset times, adjusting the current priority of the corresponding face image to a target priority greater than the current priority;
and updating the priority information of the corresponding face image in the face database according to the target priority.
5. The method according to claim 1, wherein the comparing the facial image to be recognized with the plurality of facial images in the corresponding target database lists in the plurality of database lists in the order of priority from high to low to obtain a comparison result comprises:
determining a target database link table with the highest priority in the plurality of database link tables;
comparing the face image to be recognized with a plurality of face images in the target database linked list, and determining a target face image with the face characteristics of the face image to be recognized larger than a preset characteristic threshold value;
and taking the target face image as a comparison result of the face image to be recognized.
6. The method of claim 5, wherein after said determining a highest priority target database linked list of said plurality of database linked lists, said method further comprises:
if the target database linked list does not contain the target face image, determining another database linked list with the priority lower than that of the target database linked list from the plurality of database linked lists;
and comparing the facial image to be recognized with the plurality of facial images in the other database chain table, and determining a target facial image with the facial features of the facial image to be recognized larger than a preset feature threshold value.
7. A face comparison apparatus, comprising:
the acquiring unit is used for acquiring a face image to be recognized at a first moment;
a first determining unit, configured to determine a target time period at which the first time is located;
a second determining unit, configured to determine, according to a correspondence between a time period of a pre-stored face database and a feature library group, a target feature library group corresponding to the face database in the target time period, where the target feature library group includes a plurality of database links, and each of the plurality of database links includes a plurality of face images with the same priority;
and the comparison unit is used for comparing the facial image to be recognized with the plurality of facial images in the corresponding target database chain tables in the plurality of database chain tables according to the sequence of the priorities from high to low to obtain a comparison result.
8. The apparatus of claim 7, wherein the apparatus further comprises:
the establishing unit is used for establishing the face database in advance, each face image in the face database is provided with corresponding time period information and priority information except face characteristic information, wherein in different time periods, the face database corresponds to different characteristic base groups, and the face images with the same priority information form the same database linked list of the same characteristic base group.
9. A computer arrangement, characterized in that the computer arrangement comprises a processor for implementing the steps of the face comparison method according to any one of claims 1-6 when executing a computer program stored in a memory.
10. A readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the face comparison method according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011533409.1A CN112488078A (en) | 2020-12-23 | 2020-12-23 | Face comparison method and device and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011533409.1A CN112488078A (en) | 2020-12-23 | 2020-12-23 | Face comparison method and device and readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112488078A true CN112488078A (en) | 2021-03-12 |
Family
ID=74915362
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011533409.1A Pending CN112488078A (en) | 2020-12-23 | 2020-12-23 | Face comparison method and device and readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112488078A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113344132A (en) * | 2021-06-30 | 2021-09-03 | 成都商汤科技有限公司 | Identity recognition method, system, device, computer equipment and storage medium |
CN113688712A (en) * | 2021-08-18 | 2021-11-23 | 上海浦东发展银行股份有限公司 | Portrait identification method and device, electronic equipment and storage medium |
CN114613056A (en) * | 2022-03-17 | 2022-06-10 | 深圳创维-Rgb电子有限公司 | Gate control method, device, equipment and computer readable storage medium |
CN115050079A (en) * | 2022-06-30 | 2022-09-13 | 北京瑞莱智慧科技有限公司 | Face recognition method, face recognition device and storage medium |
CN117523638A (en) * | 2023-11-28 | 2024-02-06 | 广州视声智能科技有限公司 | Face recognition method and system based on priority screening |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107292228A (en) * | 2017-05-05 | 2017-10-24 | 珠海数字动力科技股份有限公司 | A kind of method for accelerating face recognition search speed |
CN108446692A (en) * | 2018-06-08 | 2018-08-24 | 南京擎华信息科技有限公司 | Face comparison method, device and system |
CN111368620A (en) * | 2019-08-14 | 2020-07-03 | 杭州海康威视***技术有限公司 | Method and device for identifying target attention object and storage medium |
-
2020
- 2020-12-23 CN CN202011533409.1A patent/CN112488078A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107292228A (en) * | 2017-05-05 | 2017-10-24 | 珠海数字动力科技股份有限公司 | A kind of method for accelerating face recognition search speed |
CN108446692A (en) * | 2018-06-08 | 2018-08-24 | 南京擎华信息科技有限公司 | Face comparison method, device and system |
CN111368620A (en) * | 2019-08-14 | 2020-07-03 | 杭州海康威视***技术有限公司 | Method and device for identifying target attention object and storage medium |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113344132A (en) * | 2021-06-30 | 2021-09-03 | 成都商汤科技有限公司 | Identity recognition method, system, device, computer equipment and storage medium |
CN113688712A (en) * | 2021-08-18 | 2021-11-23 | 上海浦东发展银行股份有限公司 | Portrait identification method and device, electronic equipment and storage medium |
CN114613056A (en) * | 2022-03-17 | 2022-06-10 | 深圳创维-Rgb电子有限公司 | Gate control method, device, equipment and computer readable storage medium |
CN114613056B (en) * | 2022-03-17 | 2024-03-12 | 深圳创维-Rgb电子有限公司 | Gate control method, device, equipment and computer readable storage medium |
CN115050079A (en) * | 2022-06-30 | 2022-09-13 | 北京瑞莱智慧科技有限公司 | Face recognition method, face recognition device and storage medium |
CN117523638A (en) * | 2023-11-28 | 2024-02-06 | 广州视声智能科技有限公司 | Face recognition method and system based on priority screening |
CN117523638B (en) * | 2023-11-28 | 2024-05-17 | 广州视声智能科技有限公司 | Face recognition method and system based on priority screening |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112488078A (en) | Face comparison method and device and readable storage medium | |
CN108512650A (en) | Dynamic Hash calculation method, apparatus, node and storage medium towards block chain | |
CN109255342B (en) | Image region-of-interest extraction method and system based on two-step clustering of eye movement trajectory data | |
CN109086139B (en) | Dynamic fragmentation method, device and computer storage medium | |
CN111949666B (en) | Identification generation method and device, electronic equipment and storage medium | |
CN110334152A (en) | A kind of method of data synchronization, device and server | |
CN106055630A (en) | Log storage method and device | |
CN111698094A (en) | Consensus method based on block chain system and block chain system | |
CN112333342A (en) | Intelligent voice calling method, device, equipment and storage medium | |
CN110876072B (en) | Batch registered user identification method, storage medium, electronic device and system | |
CN113254701A (en) | Video data index construction method and system based on FOV model | |
CN106327251A (en) | Model training system and model training method | |
CN108073408B (en) | System updating method and device of self-service terminal | |
CN108833133A (en) | Network configuration management method, apparatus and storage medium based on system for cloud computing | |
CN111128233A (en) | Recording detection method and device, electronic equipment and storage medium | |
CN115988001A (en) | Consensus voting processing method, device, equipment and medium for block chain system | |
CN108984790A (en) | A kind of data branch mailbox method and device | |
CN109597804A (en) | Client's merging method and device, electronic equipment and storage medium based on big data | |
CN108365962B (en) | Certificate revocation list query method and device | |
CN111124672A (en) | Data distribution method based on Redis cluster and related equipment | |
JP2000069165A (en) | Method and device for traffic prediction using time series data conversion | |
CN113065323B (en) | Method, device and equipment for importing contract template data and storage medium | |
CN114912627A (en) | Recommendation model training method, system, computer device and storage medium | |
CN116303418A (en) | Mass rule processing method, system and storage medium based on Internet of things platform | |
CN114139008A (en) | Image clustering processing method, computer equipment and storage device |
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 |