CN109948718B - System and method based on multi-algorithm fusion - Google Patents
System and method based on multi-algorithm fusion Download PDFInfo
- Publication number
- CN109948718B CN109948718B CN201910233316.8A CN201910233316A CN109948718B CN 109948718 B CN109948718 B CN 109948718B CN 201910233316 A CN201910233316 A CN 201910233316A CN 109948718 B CN109948718 B CN 109948718B
- Authority
- CN
- China
- Prior art keywords
- algorithm
- biological characteristic
- data
- algorithm system
- recognition algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a system and a method based on multi-algorithm fusion, wherein the system comprises: an access layer and a storage layer; the storage layer comprises a source data database, an algorithm system and a biological characteristic database; the algorithm system comprises at least one biological characteristic recognition algorithm system and a dispatching center; the access layer is used for receiving data and carrying out standardized operation on the data; the source data database is used for receiving and storing the data of the access layer; the dispatching center is used for extracting the biological characteristic information of the data in the source data database through a biological characteristic recognition algorithm system and generating a biological characteristic database for storing the biological characteristic information; the dispatching center is also used for integrating the recognition results output by the biological characteristic recognition algorithm system and outputting a comprehensive result. The technical problem that a single biological characteristic recognition algorithm system in the market is in a transition period from being incapable of meeting actual combat requirements to meeting the actual combat requirements is effectively solved by means of multi-algorithm fusion.
Description
Technical Field
The present application relates to the field of recognition algorithm technology, and in particular, to a system and method based on multi-algorithm fusion.
Background
In the current information age, how to quickly and accurately identify and identify the identity of a person becomes a key problem for protecting information security and social public security. The traditional identity authentication is very easy to forge and lose, and is more and more difficult to meet the existing requirements. The advent of biometric identification technology has become the most convenient and secure solution to this need.
The biometric technology is a technology for performing identity authentication by using human biometric features. The personal identity is identified by closely combining a computer with high-tech means such as optics, acoustics, biosensors and biometrics and utilizing the inherent physiological and behavioral characteristics of a human body.
A biometric identification system is a feature template that samples biometric features, extracts their unique features and converts them into digital codes, and further combines these codes. When the individual interacts with the biometric identification system for identity authentication, the identification system obtains its characteristics and compares them with the characteristics of the sample it has registered to determine if there is a match, thereby deciding whether to accept or reject the individual.
Physiological characteristics which have been widely used for biometric identification include fingerprints, voice prints, faces, irises, veins, and the like, and behavioral characteristics include signatures, gait, and the like.
However, in the current market, the identification accuracy of a certain biometric algorithm or a certain biometric algorithm for a certain special scene generally cannot meet the actual combat requirement.
Disclosure of Invention
The application provides a system and a method based on multi-algorithm fusion, which integrate output results of a plurality of algorithm systems through scientific and reasonable algorithm rules by performing multi-algorithm fusion on the existing biological characteristic recognition algorithm systems in the market, and improve the overall recognition accuracy so as to meet the requirement of actual combat.
The application provides a system based on multi-algorithm fusion in a first aspect, including: an access layer and a storage layer;
the storage layer comprises a source data database, an algorithm system and a biological characteristic database;
the algorithm system comprises at least one biological characteristic recognition algorithm system and a dispatching center;
the access layer is used for receiving data and carrying out standardized operation on the data;
the source data database is used for receiving and storing the data of the access layer;
the dispatching center is used for extracting biological characteristic information of data in the source data database through the biological characteristic recognition algorithm system and generating the biological characteristic database for storing the biological characteristic information;
the dispatching center is also used for integrating the recognition results output by the biological characteristic recognition algorithm system and outputting a comprehensive result.
Preferably, the dispatch center is specifically configured to obtain an identification result output by the biometric identification algorithm system; and sorting according to the occurrence times in the identification result.
Preferably, the scheduling center is further configured to sort the results with the largest occurrence number from small to large according to the ranking sum of the biometric recognition algorithm system.
Preferably, the dispatch center is further configured to sort the results of the total ranking of the biometric algorithm systems according to the minimum ranking of the rankings of the biometric algorithm systems.
Preferably, the dispatch center is further configured to randomly sort among the least ranked same results ranked by the biometric recognition algorithm system.
The system also comprises an application layer and a service layer;
the service layer comprises services such as system service, data service, application service, message queue service and data storage service, and serves as the application layer.
The application layer provides various service applications for the customer to use.
A second aspect of the present application provides a system based on multi-algorithm fusion, including: an access layer and a storage layer;
the storage layer comprises a source data database, an algorithm system and a biological characteristic database;
the algorithm system comprises at least one biological characteristic recognition algorithm system and a dispatching center;
the access layer is used for receiving data and carrying out standardized operation on the data;
the source data database is used for receiving and storing the data of the access layer;
the dispatching center is used for extracting biological characteristic information of data in the source data database through the biological characteristic recognition algorithm system and generating the biological characteristic database for storing the biological characteristic information;
the scheduling center is specifically used for acquiring the identification result output by the biological characteristic identification algorithm system; calculating according to the current ranking result integral of the biological feature recognition algorithm system and the weight of the biological feature recognition algorithm system to obtain a weight integral; and sorting according to the sum of the weight integrals from large to small.
Preferably, the weight of the scheduling center used for the biometric algorithm is equal to the integral of the biometric algorithm divided by the sum of the integrals of all the biometric algorithms.
Preferably, the scheduling center is further configured to obtain a correct result, and obtain an updated integral of the biometric algorithm system by adding the integral of the biometric algorithm system to the current ranking result integral corresponding to the correct result.
The system also comprises an application layer and a service layer;
the service layer comprises services such as system service, data service, application service, message queue service and data storage service, and serves as the application layer.
The application layer provides various service applications for the customer to use.
A third aspect of the present application provides a method based on multi-algorithm fusion, which performs calculation based on a system based on multi-algorithm fusion as in the first aspect or performs calculation based on a system based on multi-algorithm fusion as in the second aspect, including:
importing material detection data;
after the access layer carries out standardized operation on the data, the data is stored in a source data database;
the dispatching center obtains the material to be detected from the source data database, issues the material to at least one biological characteristic recognition algorithm system and submits a comparison request;
the biological characteristic recognition algorithm system compares the detected material with the samples in the sample library and returns a recognition result;
and the dispatching center collects the identification results returned by the biological characteristic identification algorithm system, integrates all the results through a fusion algorithm and then displays the integrated results.
Preferably, before importing the material inspection data, the method further comprises:
importing sample data;
after the access layer carries out standardized operation on the data, the data is stored in a source data database;
the dispatching center obtains samples from the source data database, issues the samples to at least one biological characteristic recognition algorithm system and submits a registration request;
extracting biological characteristic data of the sample by a biological characteristic identification algorithm system;
the dispatching center stores the generated biological characteristic data into a biological characteristic database corresponding to the biological characteristic recognition algorithm system, and associates the identity information of the sample.
According to the technical scheme, the method has the following advantages:
the application provides a system based on multi-algorithm fusion, including: an access layer and a storage layer; the storage layer comprises a source data database, an algorithm system and a biological characteristic database; the algorithm system comprises at least one biological characteristic recognition algorithm system and a dispatching center; the access layer is used for receiving data and carrying out standardized operation on the data; the source data database is used for receiving and storing the data of the access layer; the dispatching center is used for extracting biological characteristic information of data in the source data database through the biological characteristic recognition algorithm system and generating the biological characteristic database for storing the biological characteristic information; the dispatching center is also used for integrating the recognition results output by the biological characteristic recognition algorithm system and outputting a comprehensive result. The technical problem that a single biological characteristic recognition algorithm system in the market is in a transition period from being incapable of meeting actual combat requirements to meeting the actual combat requirements is effectively solved by means of multi-algorithm fusion.
Drawings
In order to illustrate the embodiments of the present application more clearly, the drawings that are needed for describing the embodiments or prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive exercise.
FIG. 1 is a schematic diagram of one embodiment of a system based on multi-algorithm fusion provided herein;
FIG. 2 is a schematic diagram of one embodiment of a method for multi-algorithm fusion based on the present application;
FIG. 3 is a schematic diagram of another embodiment of a method based on multi-algorithm fusion provided by the present application.
Detailed Description
The application provides a system and a method based on multi-algorithm fusion, which integrate output results of a plurality of algorithm systems through scientific and reasonable algorithm rules by performing multi-algorithm fusion on the existing biological characteristic recognition algorithm systems in the market, and improve the overall recognition accuracy so as to meet the requirement of actual combat.
In order to make the objects, features and advantages of the present invention more apparent and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the embodiments described below 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.
Referring to fig. 1, the present application provides an embodiment of a system based on multi-algorithm fusion, comprising: an access layer 12 and a storage layer 13;
the storage layer 13 comprises a source data database 16, an algorithm system 17 and a biological characteristic database 19;
the algorithm system 17 comprises at least one biometric algorithm system and a dispatch center;
the access layer 12 is used for receiving data and performing standardization operation on the data;
the source data database 16 is used for receiving and storing data of the access layer 12;
the dispatching center is used for extracting the biological characteristic information of the data in the source data database 16 through a biological characteristic recognition algorithm system and generating a biological characteristic database 19 for storing the biological characteristic information;
the dispatching center is also used for integrating the recognition results output by the biological characteristic recognition algorithm system and outputting a comprehensive result.
The biometric algorithm system corresponds to the biometric database 19.
The application provides a system and a method based on multi-algorithm fusion, which integrate the output results of a plurality of algorithm systems 17 through scientific and reasonable algorithm rules by carrying out multi-algorithm fusion on the existing biological characteristic recognition algorithm systems in the market, and improve the overall recognition accuracy so as to meet the requirement of actual combat.
The algorithm 17 incorporates a plurality of biometric algorithms. The system is divided into an access layer 12, a storage layer 13, a service layer 14 and an application layer 15 on the software architecture. In the storage layer there are included a source data database 16, an algorithm system 17, a further database 18 and a biometric database 19. In addition there is an external data source 11.
The external data source 11 refers to data containing biometric information, such as audio, pictures and video containing human faces, and the like. The access layer 12 is mainly composed of a data management bus, and is responsible for uniformly accessing data, performing standardized operation on the data, and preparing for subsequent use of the system. The storage layer 13 contains a source data database 16, an algorithm system 17 (consisting of the same kind of biometric algorithm system, for example both a voiceprint recognition algorithm system or a face recognition algorithm system), a biometric database 19 and other databases 18. After being processed by the access layer 12, the data enters the storage layer 13 and is stored in the source data database 16 to form a database such as an audio library, a face picture library and the like. The algorithm system 17 schedules each biometric algorithm system through the scheduling center, extracts biometric information of data in the source data database 16, and stores the biometric information in the biometric database 19 to form databases such as a voiceprint database and a face database. The corresponding biometric database generated by each biometric algorithm is included, for example, the biometric database a generated by the biometric algorithm a is correspondingly included. When the user submits the comparison request, the algorithm system 17 issues the request to each biometric algorithm system through the dispatch center, and then integrates the results output by the plurality of biometric algorithm systems based on a certain fusion algorithm (a fusion algorithm based on frequency statistics, a fusion algorithm based on integral statistics, or other fusion algorithms) to output a comprehensive result.
Further, the dispatching center is specifically used for acquiring the identification result output by the biological characteristic identification algorithm system; and sorting according to the occurrence times in the identification result.
Further, the scheduling center is also used for sorting the results with the largest occurrence number from small to large according to the ranking sum of the biometric recognition algorithm system.
Further, the scheduling center is also used for sorting according to the minimum ranking of the biometric algorithm system in the result that the total ranking of the biometric algorithm system is the same.
Further, the dispatching center is also used for randomly ordering in the result with the same minimum ranking ranked by the biometric recognition algorithm system.
Also includes an application layer 15 and a service layer 14;
the service layer 14 includes services such as system services, data services, application services, message queue services, and data storage services, and serves the application layer 15.
The application layer 15 provides various business applications for use by customers.
The scheduling center of this embodiment integrates the recognition results output by the biometric recognition algorithm system according to a fusion algorithm based on the frequency statistics, and outputs a comprehensive result, where the fusion algorithm is executed by the scheduling center, and specifically includes:
each biometric algorithm system returns N results for each comparison, and the results are sorted and output according to the sequence from Top1 to Top N. For example, the number of the biometric algorithm systems participating in the fusion is 3, which are respectively an algorithm system a, an algorithm system B, and an algorithm system C. When the number N of output results is 10, it is shown in table 1.
TABLE 1
The results are output to a multi-algorithm fusion system, and the fusion system integrates and outputs the results according to set rules.
And the multi-algorithm fusion system counts the results output by the plurality of biological characteristic recognition algorithm systems based on the occurrence times, calculates the comprehensive ranking according to the rule and outputs the comprehensive ranking.
The statistical table is shown in table 2;
TABLE 2
The composite ranking is reordered according to the following rules:
1. and sorting according to the occurrence times from large to small. If the two are the same, 2 is reached;
2. if the occurrence times are the same, sequencing the results from small to large according to the ranking sum of the multiple algorithm systems; for example, person _1 and person _10, the results in the three algorithmic systems are Top1+ Top1+ Top2 and Top4+ Top5+ Top7, respectively, then the total rankings are 4 and 16, respectively, so person _1 is ranked ahead of person _ 10. If the total ranking sum is the same, 3 is reached;
3. if the ranking sums of the algorithm systems are the same, ranking is carried out from small to large according to the minimum terms of the ranking in each algorithm system. For example: the occurrence times and the total ranking in the algorithm systems of the person _26 and the person _9 are the same, but the ranking in each algorithm system is Top3+ Top10 and Top6+ Top7 respectively, the minimum ranking obtained by the person _26 in the algorithm system is Top3, the minimum ranking obtained by the person _9 in the algorithm system is Top6, so that the person _26 is ranked in front of the person _9 (if the 1 st minimum ranking is the same, the 2 nd ranking is taken, and the rest is done by traversing all the results for comparison). If the ranks in the algorithm system are the same, 4 is reached;
4. and if the occurrence times, the total ranking in the algorithm systems and the ranking in each algorithm system are the same, randomly sequencing.
The result output by the dispatching center is a sequencing result, and an algorithm can be added to set a threshold value, for example, the result of x names before ranking is an output result. Or manually selected from the sorted results.
The above is a detailed description of an embodiment of a system based on multi-algorithm fusion provided by the present application, and another embodiment of a system based on multi-algorithm fusion provided by the present application is described in detail below.
Referring to fig. 1, another embodiment of a system based on multi-algorithm fusion provided by the present application includes: an access layer 12 and a storage layer 13;
the storage layer 13 comprises a source data database 16, an algorithm system 17 and a biological characteristic database 19;
the algorithm system 17 comprises at least one biometric algorithm system and a dispatch center;
the access layer 12 is used for receiving data and performing standardization operation on the data;
the source data database 16 is used for receiving and storing data of the access layer 12;
the dispatching center is used for extracting the biological characteristic information of the data in the source data database 16 through a biological characteristic recognition algorithm system and generating a biological characteristic database 19 for storing the biological characteristic information;
the scheduling center is specifically used for acquiring the identification result output by the biological characteristic identification algorithm system; calculating according to the current ranking result integral of the biological feature recognition algorithm system and the weight of the biological feature recognition algorithm system to obtain a weight integral; and sorting according to the sum of the weight integrals from large to small.
Further, the weight of the scheduling center used for the biometric algorithm is equal to the integral of the biometric algorithm divided by the sum of the integrals of all the biometric algorithms.
And further, the scheduling center is also used for obtaining a correct result, and the updated integral of the biological feature recognition algorithm system is obtained by adding the integral of the current ranking result corresponding to the correct result to the integral of the biological feature recognition algorithm system.
Also includes an application layer 15 and a service layer 14;
the service layer 14 includes services such as system services, data services, application services, message queue services, and data storage services, and serves the application layer 15.
The application layer 15 provides various business applications for use by customers.
Each biometric algorithm system returns N results for each comparison, and the results are sorted and output according to the sequence from Top1 to Top N. For example, the number of the biometric algorithm systems participating in the fusion is 3, which are respectively an algorithm system a, an algorithm system B, and an algorithm system C. When the number N of output results is 10, it is shown in table 1.
In this embodiment, the scheduling center executes a fusion algorithm based on integral statistics, and as shown in table 3, the weights of the algorithm systems are obtained according to the integrals of the algorithm systems (the integrals are obtained by evaluating the algorithm systems by users, and the integral calculation mode will be mentioned later). The weight of the biometric algorithm is equal to the integral of the biometric algorithm divided by the sum of the integrals of all the biometric algorithms. For example, the weight of the biometric algorithm a is equal to 2600/6400-0.40625.
TABLE 3
As shown in table 4, the multi-algorithm fusion system calculates the weight integral of the result according to the integral of each algorithm system. The weight integral is the current ranking result integral which is determined by the result ranking, and if each algorithm system only outputs 10 results, the weight integral is decreased from 10 points of Top1 to 1 point of Top 10. If each algorithm outputs only 100 results, it decrements from 100 points of Top1 to 1 point of Top 100. The current ranking result integral can be set according to the actual combat use condition, and the descending with smaller span or the descending with larger span can be selected.
TABLE 4
As shown in table 5, after the weight integrals of the results in the respective algorithm systems are calculated, the weight integrals of the same result are added to obtain the sum of the weight integrals. And the comprehensive ranking reorders all the results from large to small according to the sum of the weight integrals to obtain a fused result.
TABLE 5
As shown in table 6, after verification (manual verification or computer intelligent verification), the user finds that the person _1 and the material to be tested are the same person, that is, the person _1 is the correct result, the multi-algorithm fusion system provides a function of receiving user feedback, and scores the algorithm systems according to the current ranking algorithm score after obtaining the feedback. If each algorithm outputs only 10 results, the current ranking algorithm score is decremented from 10 points of Top1 to 1 point of Top 10. If each algorithm outputs only 100 results, it decrements from 100 points of Top1 to 1 point of Top 100. The integral of the current ranking algorithm can be set according to the use condition of actual combat, and the decrement with smaller span or the decrement with larger span can be selected.
TABLE 6
As shown in table 7, after the multi-algorithm fusion system scores each algorithm system, the integral of each algorithm system is updated. The initial integral for each algorithm can be set.
TABLE 7
The result output by the dispatching center is the sequencing result, and an algorithm can be added to set a threshold, for example, the result with the sum of weight integrals larger than y is the output result. Or manually selected from the sorted results.
The foregoing is a detailed description of another embodiment of a system based on multi-algorithm fusion provided in the present application, and the following is a detailed description of an embodiment of a method based on multi-algorithm fusion provided in the present application.
Referring to fig. 2, the present application provides an embodiment of a method based on multi-algorithm fusion, which performs calculation based on a system based on multi-algorithm fusion as described in the above embodiments, including:
201. importing sample data;
202. after the access layer carries out standardized operation on the data, the data is stored in a source data database;
203. the dispatching center obtains samples from the source data database, issues the samples to at least one biological characteristic recognition algorithm system and submits a registration request;
204. extracting biological characteristic data of the sample by a biological characteristic identification algorithm system;
205. the dispatching center stores the generated biological characteristic data into a biological characteristic database corresponding to the biological characteristic recognition algorithm system, and associates the identity information of the sample.
The above is a detailed description of an embodiment of a method based on multi-algorithm fusion provided by the present application, and another embodiment of the method based on multi-algorithm fusion provided by the present application is described in detail below.
Referring to fig. 3, another embodiment of a method based on multi-algorithm fusion provided by the present application, which performs calculation based on a system based on multi-algorithm fusion as described in the foregoing embodiment, includes:
301. importing material detection data;
302. after the access layer carries out standardized operation on the data, the data is stored in a source data database;
303. the dispatching center obtains the material to be detected from the source data database, issues the material to at least one biological characteristic recognition algorithm system and submits a comparison request;
304. the biological characteristic recognition algorithm system compares the detected material with the samples in the sample library and returns a recognition result;
305. and the dispatching center collects the identification results returned by the biological characteristic identification algorithm system, integrates all the results through a fusion algorithm and then displays the integrated results.
The above is a detailed description of another embodiment of the method based on multi-algorithm fusion provided by the present application, and the following is a detailed description of another embodiment of the method based on multi-algorithm fusion provided by the present application.
Another embodiment of a method based on multi-algorithm fusion provided by the present application, which performs calculation based on a system based on multi-algorithm fusion as described in the above embodiments, includes:
importing sample data;
after the access layer carries out standardized operation on the data, the data is stored in a source data database;
the dispatching center obtains samples from the source data database, issues the samples to at least one biological characteristic recognition algorithm system and submits a registration request;
extracting biological characteristic data of the sample by a biological characteristic identification algorithm system;
the dispatching center stores the generated biological characteristic data into a biological characteristic database corresponding to the biological characteristic recognition algorithm system and associates the identity information of the sample;
importing material detection data;
after the access layer carries out standardized operation on the data, the data is stored in a source data database;
the dispatching center obtains the material to be detected from the source data database, issues the material to at least one biological characteristic recognition algorithm system and submits a comparison request;
the biological characteristic recognition algorithm system compares the detected material with the samples in the sample library and returns a recognition result;
and the dispatching center collects the identification results returned by the biological characteristic identification algorithm system, integrates all the results through a fusion algorithm and then displays the integrated results.
The method combines the steps of sample registration and material checking comparison, realizes the training and operation of the system, and solves the problem that the existing recognition algorithm cannot realize low recognition accuracy.
The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (5)
1. A system based on multi-algorithm fusion, comprising: an access layer and a storage layer;
the storage layer comprises a source data database, an algorithm system and a biological characteristic database;
the algorithm system comprises at least one biological characteristic recognition algorithm system and a dispatching center; when the algorithm system comprises a plurality of biological feature recognition algorithm systems, the biological feature recognition algorithm systems are all biological feature recognition algorithm systems of the same kind;
the access layer is used for receiving data and carrying out standardized operation on the data;
the source data database is used for receiving and storing the data of the access layer;
the dispatching center is used for extracting biological characteristic information of data in the source data database through the biological characteristic recognition algorithm system and generating the biological characteristic database for storing the biological characteristic information;
the dispatching center is also used for integrating the recognition results output by the biological characteristic recognition algorithm system and outputting a comprehensive result;
the scheduling center is specifically used for acquiring the identification result output by the biological characteristic identification algorithm system; sorting according to the occurrence times in the identification result;
the scheduling center is also used for sequencing from small to large according to the ranking sum of the biological feature recognition algorithm system in the result with the largest occurrence frequency;
or, the dispatching center is specifically configured to obtain an identification result output by the biometric identification algorithm system; calculating according to the current ranking result integral of the biological feature recognition algorithm system and the weight of the biological feature recognition algorithm system to obtain a weight integral; sorting according to the sum of the weight integrals from large to small; the calculation method of the weight integral is as follows: the weight integral is the integral of the current ranking result and the weight of the algorithm system;
the dispatching center is also used for the weight of the biological feature recognition algorithm system to be equal to the integral of the biological feature recognition algorithm system divided by the sum of the integrals of all the biological feature recognition algorithm systems;
the scheduling center is further used for obtaining a correct result, and obtaining an updated integral of the biological feature recognition algorithm system by adding the integral of the biological feature recognition algorithm system to the integral of the current ranking result corresponding to the correct result.
2. The system of claim 1, wherein the dispatch center is further configured to sort the results of the sum of the rankings of the biometric algorithm systems according to a minimum ranking of the rankings of the biometric algorithm systems.
3. The system based on multi-algorithm fusion as claimed in claim 2, wherein the dispatch center is further configured to randomly sort the least ranked results ranked by the biometric algorithm system.
4. A method based on multi-algorithm fusion, which is based on a system based on multi-algorithm fusion according to any one of claims 1 to 3, and comprises:
importing material detection data;
after the access layer carries out standardized operation on the data, the data is stored in a source data database;
the dispatching center obtains the material to be detected from the source data database, issues the material to at least one biological characteristic recognition algorithm system and submits a comparison request;
the biological characteristic recognition algorithm system compares the detected material with the samples in the sample library and returns a recognition result;
and the dispatching center collects the identification results returned by the biological characteristic identification algorithm system, integrates all the results through a fusion algorithm and then displays the integrated results.
5. The method based on multi-algorithm fusion according to claim 4, wherein before importing the material inspection data, the method further comprises:
importing sample data;
after the access layer carries out standardized operation on the data, the data is stored in a source data database;
the dispatching center obtains samples from the source data database, issues the samples to at least one biological characteristic recognition algorithm system and submits a registration request;
extracting biological characteristic data of the sample by a biological characteristic identification algorithm system;
the dispatching center stores the generated biological characteristic data into a biological characteristic database corresponding to the biological characteristic recognition algorithm system, and associates the identity information of the sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910233316.8A CN109948718B (en) | 2019-03-26 | 2019-03-26 | System and method based on multi-algorithm fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910233316.8A CN109948718B (en) | 2019-03-26 | 2019-03-26 | System and method based on multi-algorithm fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109948718A CN109948718A (en) | 2019-06-28 |
| CN109948718B true CN109948718B (en) | 2022-03-15 |
Family
ID=67011535
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910233316.8A Active CN109948718B (en) | 2019-03-26 | 2019-03-26 | System and method based on multi-algorithm fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109948718B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113542142B (en) * | 2020-04-14 | 2024-03-22 | 中国移动通信集团浙江有限公司 | Portrait anti-fake detection method and device and computing equipment |
| CN111444377A (en) * | 2020-04-15 | 2020-07-24 | 厦门快商通科技股份有限公司 | Voiceprint identification authentication method, device and equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022043A (en) * | 2016-05-23 | 2016-10-12 | 南京甄视智能科技有限公司 | System architecture of biological characteristic recognition business processing platform and implementation method |
| CN107153811A (en) * | 2017-03-20 | 2017-09-12 | 中国建设银行股份有限公司 | Know method for distinguishing, apparatus and system for multi-modal biological characteristic |
| CN107294730A (en) * | 2017-08-24 | 2017-10-24 | 北京无线电计量测试研究所 | A kind of multi-modal biological characteristic identity identifying method, apparatus and system |
| CN108921191A (en) * | 2018-05-25 | 2018-11-30 | 北方工业大学 | Multi-biological-feature fusion recognition method based on image quality evaluation |
-
2019
- 2019-03-26 CN CN201910233316.8A patent/CN109948718B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022043A (en) * | 2016-05-23 | 2016-10-12 | 南京甄视智能科技有限公司 | System architecture of biological characteristic recognition business processing platform and implementation method |
| CN107153811A (en) * | 2017-03-20 | 2017-09-12 | 中国建设银行股份有限公司 | Know method for distinguishing, apparatus and system for multi-modal biological characteristic |
| CN107294730A (en) * | 2017-08-24 | 2017-10-24 | 北京无线电计量测试研究所 | A kind of multi-modal biological characteristic identity identifying method, apparatus and system |
| CN108921191A (en) * | 2018-05-25 | 2018-11-30 | 北方工业大学 | Multi-biological-feature fusion recognition method based on image quality evaluation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109948718A (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109766872B (en) | Image recognition method and device | |
| CN107423613B (en) | Method and device for determining device fingerprint according to similarity and server | |
| CN108197532A (en) | The method, apparatus and computer installation of recognition of face | |
| US20070174272A1 (en) | Facial Recognition in Groups | |
| CN106604051A (en) | Live channel recommending method and device | |
| CN110210194A (en) | Electronic contract display methods, device, electronic equipment and storage medium | |
| CN108510396B (en) | Method and device for insurance verification, computer equipment and storage medium | |
| CN109948718B (en) | System and method based on multi-algorithm fusion | |
| US10997609B1 (en) | Biometric based user identity verification | |
| CN109858344A (en) | Love and marriage object recommendation method, apparatus, computer equipment and storage medium | |
| CN111861748A (en) | Financial big data analysis platform based on artificial intelligence | |
| CN109896374B (en) | Elevator screen display method and system | |
| CN109886239B (en) | Portrait clustering method, device and system | |
| CN115222443A (en) | Client group division method, device, equipment and storage medium | |
| CN112988848B (en) | Data processing method, device, equipment and storage medium | |
| CN108073567B (en) | Feature word extraction processing method, system and server | |
| CN111354013A (en) | Target detection method and device, equipment and storage medium | |
| CN114466214B (en) | Live broadcasting room people counting method and device | |
| CN113344124B (en) | Track analysis method and device, storage medium and system | |
| CN113448876B (en) | Service testing method, device, computer equipment and storage medium | |
| CN113010664B (en) | Data processing method and device and computer equipment | |
| KR101716748B1 (en) | Call classification system and method for managing quality of call center | |
| CN109902545B (en) | User feature analysis method and system | |
| WO2019141039A1 (en) | Account information grouping method and apparatus and payment method and device | |
| CN112528140A (en) | Information recommendation method, device, equipment, system and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |