CN109934060A - A kind of evaluation system and method for the Key Performance Indicator of fingerprint comparison system - Google Patents
A kind of evaluation system and method for the Key Performance Indicator of fingerprint comparison system Download PDFInfo
- Publication number
- CN109934060A CN109934060A CN201711354064.1A CN201711354064A CN109934060A CN 109934060 A CN109934060 A CN 109934060A CN 201711354064 A CN201711354064 A CN 201711354064A CN 109934060 A CN109934060 A CN 109934060A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- fingerprint
- data
- tested
- test
- 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
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The present invention provides a kind of evaluation systems of the Key Performance Indicator of fingerprint comparison system, comprising: evaluation metrics system construction module, the evaluation metrics that fingerprint comparison algorithm and engine for constructing to tested unit are tested and assessed;Data acquisition module is evaluated and tested, evaluates and tests data for obtaining the fingerprint evaluated and tested;Database interface authorization module, for providing access interface for tested unit to access the database of the evaluation system;Evaluation and test module, fingerprint modeling and template matching and concurrency performance for fingerprint comparison algorithm and engine to tested unit are tested and assessed;Evaluation result processing module, the data for being tested and assessed based on the evaluation and test module calculate the index value of the evaluation metrics, and generate corresponding evaluation result.The present invention also provides a kind of assessment methods.The present invention can provide technical standard for the Key Performance Indicator of fingerprint comparison algorithm and engine.
Description
Technical field
The present invention relates to population management fields, and in particular to a kind of assessment system of the Key Performance Indicator of fingerprint comparison system
System and method.
Background technique
It, can be effective using biological identification technologies such as face, fingerprints since biological characteristic has good irreplaceability
It was found that and screen suspicion personnel, improve authentication, the management works efficiency such as information verification and blacklist personnel quickly identify.For
The just feasibility and key technology performance indicator for objectively evaluating fingerprint comparison algorithm and engine, it is necessary to establish a set of standard
, complete evaluation metrics system and corresponding evaluating system.
It is objective there is no notarize to the feasibility and key technology performance indicator of fingerprint comparison algorithm and engine at present
The evaluation and test scheme of evaluation.
Summary of the invention
In view of the above technical problems, the present invention provide a kind of Key Performance Indicator of fingerprint comparison system evaluation system and
Method is evaluated and tested to the Key Performance Indicator to fingerprint comparison system, is each alignment algorithm and engine in practical business
Application characteristic evidences are provided, the algorithm type selecting for Exit and Entry Administration Bureau under the Minister of public Security's biological recognition system software project provides detection
Platform, the Key Performance Indicator for fingerprint comparison algorithm and engine provide technical standard.
The technical solution adopted by the present invention are as follows:
The embodiment of the present invention provides a kind of evaluation system of the Key Performance Indicator of fingerprint comparison system, comprising:
Evaluation metrics system construction module is tested and assessed for constructing the fingerprint comparison algorithm and engine to tested unit
Evaluation metrics;Data acquisition module is evaluated and tested, evaluates and tests data for obtaining the fingerprint evaluated and tested;Database interface authorization module,
For providing access interface for tested unit to access the database of the evaluation system, the database purchase has the fingerprint
Evaluate and test data;Evaluation and test module, the evaluation and test module include the first evaluation and test module and the second evaluation and test module;First evaluation and test module
Fingerprint modeling and template matching performance for fingerprint comparison algorithm and engine to tested unit are tested and assessed;Described second comments
Module is surveyed for testing and assessing to the concurrency performance of the fingerprint comparison algorithm and engine;Evaluation result processing module is used for base
The index value of the evaluation metrics is calculated in the data of evaluation and test module assessment, and generates corresponding evaluation result.
Optionally, the evaluation and test data acquisition module includes test library data capture unit and detection library data acquisition list
Member, the test library acquiring unit, for obtaining the demographic data of the first quantity from preset database;Detection library number
According to acquiring unit, for obtaining the demographic data of the second quantity from the preset database;The population of first quantity
The demographic data of data and second quantity composition evaluation and test comparison data, and the part of the demographic data of second quantity
Demographic data of the data from first quantity.
Optionally, the demographic data of second quantity passes through preset ratio parameter according to age, sex, race, nationality
It extracts.
Optionally, first evaluation and test module includes: fingerprint modeling unit, for the finger by calling the tested unit
The fingerprint modeling program of line alignment algorithm and engine carry out image modeling, to image modeling at the beginning of and the end time carry out
Record;Template matching unit, for by calling the fingerprint comparison algorithm of the tested unit and the template matching program of engine
Template comparison is carried out, is recorded at the beginning of being compared to template with the end time;The fingerprint comparison algorithm and engine are logical
It crosses the access interface and carries out fingerprint modeling and template matching using the assessment data of the database.
Optionally, second evaluation and test module includes: simulated technological process recording unit, for by calling concurrent tool to behaviour
The operating process for making the fingerprint comparison algorithm of the tested unit is recorded;Comparing unit is concurrently modeled, is called for passing through
The terminal request that concurrent quantity is preset in concurrent tool simulation executes the operating process, records the concurrent quantity and described preset
Preset the concurrent quantity corresponding response time.
Optionally, the evaluation metrics include the first evaluation metrics and the second evaluation metrics, and first evaluation metrics are used
In to fingerprint comparison algorithm and engine fingerprint modeling and template matching performance evaluate, second assessment indicator for pair
The concurrency performance of fingerprint comparison algorithm and engine is evaluated.
Another embodiment of the present invention provides a kind of assessment methods of the Key Performance Indicator of fingerprint comparison system, comprising: structure
Build the evaluation metrics tested and assessed to the fingerprint comparison algorithm and engine of tested unit;Obtain the fingerprint evaluation and test number evaluated and tested
According to;Access interface is provided for tested unit, the access interface is for accessing the fingerprint evaluation and test data;Respectively to tested unit
Fingerprint comparison algorithm and engine fingerprint modeling and template matching performance and concurrency performance test and assess, generate the first assessment
Data and the second assessment data;
Based on the first assessment data generated and the second assessment data, the index value of the evaluation metrics is counted
It calculates, and generates corresponding evaluation result.
Optionally, the acquisition is evaluated and tested fingerprint evaluation and test data specifically include: the is obtained from preset database
The demographic data of the demographic data of one quantity and the second quantity;The people of the demographic data of first quantity and second quantity
Mouth data composition evaluation and test comparison data, and the partial data of the demographic data of second quantity is from first quantity
Demographic data.
Optionally, the fingerprint modeling of the fingerprint comparison algorithm of tested unit and engine and template matching performance are surveyed
It comments, generating the first assessment data includes: to model journey by the fingerprint of the fingerprint comparison algorithm and engine that call the tested unit
Sequence carry out image modeling, to image modeling at the beginning of and the end time record;By calling the tested unit
The template matching program of fingerprint comparison algorithm and engine carry out template comparison, to template comparison at the beginning of and the end time into
Row record;At the beginning of comparing at the beginning of image modeling based on record with end time and template and the end time is raw
At the first assessment data.
Optionally, it tests and assesses to the concurrency performance of the fingerprint comparison algorithm of tested unit and engine, generates the second assessment
Data include: by calling concurrent tool to record the operating process for the fingerprint comparison algorithm for operating the tested unit;
The operating process is executed by the terminal request for calling concurrent tool simulation to preset concurrent quantity, records the default number of concurrent
Amount presets concurrent quantity corresponding response time with described;Concurrent quantity is preset based on record and described to preset concurrent quantity corresponding
Response time generate it is described second assessment data.
The evaluation system and method for the Key Performance Indicator of fingerprint comparison system provided in an embodiment of the present invention, construct first
Evaluation metrics for testing and assessing to fingerprint to alignment algorithm and engine are then based on the finger print data of acquisition, to fingerprint pair
Alignment algorithm and engine are evaluated and tested, and generate evaluation and test data, and using the evaluation and test data generated to the finger of the evaluation metrics of building
Scale value is calculated, and to obtain to fingerprint to the evaluation result of alignment algorithm and engine, can be existed for each alignment algorithm and engine
Application in practical business provides characteristic evidences, is that the algorithm of Exit and Entry Administration Bureau under the Minister of public Security's biological recognition system software project selects
Type provides detection platform, and the Key Performance Indicator for fingerprint comparison algorithm and engine provides technical standard.
Detailed description of the invention
Fig. 1 is the structural frames of the evaluation system of the Key Performance Indicator of fingerprint comparison system provided in an embodiment of the present invention
Figure;
Fig. 2 and Fig. 3 is the evaluation system of the Key Performance Indicator of fingerprint comparison system provided in an embodiment of the present invention respectively
The idiographic flow schematic diagram evaluated and tested;
Fig. 4 is the process signal of the assessment method of the Key Performance Indicator of fingerprint comparison system provided in an embodiment of the present invention
Figure.
Specific embodiment
To keep the technical problem to be solved in the present invention, technical solution and advantage clearer, below in conjunction with attached drawing and tool
Body embodiment is described in detail.
Fig. 1 is the structural frames of the evaluation system of the Key Performance Indicator of fingerprint comparison system provided in an embodiment of the present invention
Figure.As shown in Figure 1, the evaluation system of the Key Performance Indicator of fingerprint comparison system provided in an embodiment of the present invention includes: evaluation and test
Index system establishment module 1, the evaluation metrics that fingerprint comparison algorithm and engine for constructing to tested unit are tested and assessed;It comments
Measured data obtains module 2, evaluates and tests data for obtaining the fingerprint evaluated and tested;Database interface authorization module 3, for being tested
Unit provides access interface to access the database of the evaluation system, and the database purchase has the fingerprint evaluation and test data;
Evaluation and test module 4, the evaluation and test module include the first evaluation and test module and the second evaluation and test module;First evaluation and test module be used for by
The fingerprint modeling and template matching performance for surveying the fingerprint comparison algorithm and engine of unit are tested and assessed;Second evaluation and test module is used
It tests and assesses in the concurrency performance to the fingerprint comparison algorithm and engine;Evaluation result processing module 5, for being based on institute's commentary
The data for surveying module assessment calculate the index value of the evaluation metrics, and generate corresponding evaluation result.
In embodiments of the present invention, evaluation metrics system construction module 1 is predominantly defined evaluation metrics, and evaluation and test refers to
Mark is able to reflect the strengths and weaknesses of fingerprint comparison algorithm and engine, and the distribution of index weights is reasonable, and scoring calculation method meets reality
Business demand, key problem in technology point include: that evaluation metrics definition will take into account fingerprint batch performance of modeling, fingerprint duplicate checking comparison property
Energy, fingerprint interface service concurrency performance;The scoring formula of index passes through actual test, and combined standard is obtained by experts' evaluation.
In the present embodiment, evaluation metrics may include the first evaluation metrics and the second evaluation metrics, and first evaluation and test refers to
Mark is modeled for the fingerprint to fingerprint comparison algorithm and engine and template matching performance is evaluated, and second assessment indicator is used
It is evaluated in the concurrency performance to fingerprint comparison algorithm and engine.In one embodiment, the first evaluation metrics may include
The indexs such as modeling speed, the first matching rate, the rate of false alarm under preset matching rate and comparison speed.In a specific example, in advance
Rate of false alarm, matching rate 99% when rate of false alarm when if the rate of false alarm under matching rate may include matching rate 95%, matching rate 97%
When the indexs such as rate of false alarm, the second evaluation metrics may include the indexs such as the comparison response time that number of concurrent is n, in a specific example
In, it may include the comparison response that comparison response time that comparison response time that number of concurrent is 1, number of concurrent are 3, number of concurrent are 5
The indexs such as the comparison response time that time and number of concurrent are 10.Wherein, modeling speed refers in the unit time and completes in test library
The quantity of the modeling of fingerprint carries out fingerprint analysis and extracts characteristic wherein modeling refers to reads picture from fingerprint database,
According to the process of certain format storage storage;The first matching rate refers to that in fingerprint comparison result, target fingerprint ranking is
One percentage;Rate of false alarm under preset matching rate refers under preset matching rate, detects a certain sample Pi and test in library
All samples compare in library, return the result concentration and Pi is not the result of same people;It compares speed and refers to the finger in the unit time
Line compares speed;Number of concurrent is to refer to the comparison response time of n for a fingerprint comparison service, n client while or one
When a client initiates n comparison request simultaneously, the response time of the fingerprint comparison service.
In the present embodiment, the scoring formula of each evaluation metrics can be as follows:
It can be scored by following formula (1) modeling speed:
It can be scored by following formula (2) the first matching rate:
It can be scored by following formula (3) the rate of false alarm under preset matching rate:
Wherein, the wrong report number under preset matching rate is equal to similarity in preceding n (the most 5) matching results returned and is greater than
All false positive result numbers equal to threshold value T, the alarm number under preset matching rate are equal to preceding n (the most 5) matchings returned and tie
Similarity is more than or equal to all number of results of threshold value T in fruit.Wherein threshold value T is to look into minimum in middle result in the case where determining matching rate
Similarity value, look into refer to detection library in a certain sample Pi compared with samples all in test library, return the result concentration and Pi
It is the result of same people.
It can be scored by following formula (4) comparison speed:
It can be scored by following formula (5) the comparison response time that number of concurrent is n:
Data used in each scoring formula in evaluation metrics system construction module 1 are evaluation and test 2 institute of data acquisition module
The evaluation and test data of acquisition.The superiority and inferiority judgment criteria of the score value of above-mentioned each evaluation metrics can determine according to the actual situation, can join
Relevant industries standard is examined to set.
It should be noted that each assessment indicator of the embodiment of the present invention can carry out any setting according to the actual situation, without
It is confined to specific assessment indicator given by the present embodiment.
In the present embodiment, the evaluation and test data that evaluation and test data acquisition module 2 obtains should meet practical business scene, Neng Gouzhen
The key technology performance of real reaction evaluation metrics, evaluation and test data can be obtained by entry and exit clearance port.Evaluate and test data acquisition mould
Block 2 may include test library data capture unit and detection library data capture unit.The test library acquiring unit is used for from default
Database in obtain the demographic data of the first quantity;Detection library data capture unit is used for from the preset data
The demographic data of the second quantity is obtained in library;The demographic data of the demographic data of first quantity and second quantity composition
Comparison data is evaluated and tested, and the partial data of the demographic data of second quantity is from the population of first quantity
According to.In addition, the demographic data of second quantity passes through preset ratio parameter extraction according to age, sex, race, nationality.?
In the present embodiment, it can be carried out according to the actual situation really from the demographic data of the second quantity of the demographic data of the first quantity
The fixed and age, sex, race, nationality preset ratio parameter can also determines according to actual conditions, the present invention does not make spy to this
It does not limit.
In a specific example, evaluation and test data acquisition module 2 extracts 2000 in the data by each clearance port of entering and leaving the border
Ten thousand pieces of test library data, 50,000 pieces of detection library data, composition evaluation and test comparison data, wherein 50,000 pieces of friendships to 20,000,000 pieces will be completed
Fork compares, and amounts to 1,000,000,000,000 comparison number.It detects library data and the conditions such as age-based, sex, race, nationality is passed through into ratio ginseng
Number is extracted and is evenly distributed on test database server, and detecting has 40,000 piece numbers according to from 20,000,000 tests in the data of library
According to being interference data other than 20,000,000, the data of extraction meet data matter while meeting data scale for library, 10,000 piece numbers
Amount requires, with key technologies indexs such as performance, the accuracys of verifying fingerprint comparison algorithm.
Further, in this embodiment database interface authorization module 3 mainly control tested unit in test process
To the access authority of database, database connection is obtained by system interface or manual operation, it is accurate to record tested unit
Modeling start and the end time, compare start and the end time, modeling the time and comparison time be measure fingerprint comparison algorithm and
The crux index of engine main performance.
Further, first evaluation and test module can include: fingerprint modeling unit, for by calling the tested unit
Fingerprint comparison algorithm and engine fingerprint modeling program carry out image modeling, to image modeling at the beginning of and the end time
It is recorded, for measuring fingerprint comparison algorithm and the true fingerprint image modeling success rate of engine;Template matching unit, is used for
By calling the template matching program progress template comparison of the fingerprint comparison algorithm and engine of the tested unit, template is compared
At the beginning of and the end time recorded, for verifying the ratio countermeasure of fingerprint comparison algorithm and engine under large-scale data
Omit and compare accuracy rate;The fingerprint comparison algorithm and engine utilize the assessment data of the database by the access interface
Carry out fingerprint modeling and template matching.
Further, second evaluation and test module includes: simulated technological process recording unit, for by calling concurrent tool pair
The operating process for operating the fingerprint comparison algorithm of the tested unit is recorded;Comparing unit is concurrently modeled, is adjusted for passing through
The operating process is executed with the terminal request that concurrent quantity is preset in the simulation of concurrent tool, records and described presets concurrent quantity and institute
It states and presets the concurrent quantity corresponding response time.Specifically, the operating process of simulated technological process recording unit records may include clicking
User's login button completes user login operation, then clicks fingerprint comparison button, calls and compares interface service, sends single and visits
Library fingerprint is surveyed, comparison result storage, record comparison time etc. are received.Concurrently modeling comparing unit is that system calls concurrent tool,
N platform terminal is N number of concurrently carries out concurrent test for simulation, for example, the terminal that simulation number of concurrent is 1,3,5,10 requests to execute note simultaneously
The operating process of record, and the response time corresponding to each number of concurrent is recorded, concurrently comparing the response time is million people's grade fingerprint
The important indicator of test.
Further, evaluation result processing module 5 is specifically based on the evaluation and test data of the generation of evaluation and test module 4, including image is built
At the beginning of mould and at the beginning of end time, template comparison and end time and concurrent quantity and concurrent quantity pair
The response time etc. answered, the scoring formula of the evaluation metrics constructed using evaluation metrics system construction module 1 is to each assessment indicator
It is calculated, obtains the index value of each assessment indicator, the index superiority and inferiority for fingerprint comparison algorithm and engine provides analysis, type selecting
Foundation.
In one embodiment, as shown in Figures 2 and 3, the key of fingerprint comparison system provided in an embodiment of the present invention
The evaluation system of performance indicator can be completed to carry out the fingerprint comparison algorithm and engine of tested unit by following two processes
Assessment:
Algorithm evaluates and tests process: as shown in Fig. 2, evaluation and test center can be carried out in six steps algorithm evaluation and test, first step initialization evaluation and test
Environment and evaluation and test data, provide unified evaluation and test equipment and defined evaluation and test period;Second step evaluation and test is accepted, and registers tested unit
Information and evaluation and test algorithm information;The tested unit of third step prepares the deployment debugging of evaluating software environment, creates database environment;4th
It walks tested unit to start to evaluate and test, the time is started over by evaluation and test unit record evaluation and test time started, template, is compared when starting over
Between, tested unit is according to standard calling interface, storing data;5th step evaluates and tests center and backs up tested unit modeling and comparison result
Data, resetting evaluation and test environment are evaluated and tested and are serially carried out into next step;6th step evaluates and tests center after the completion of the evaluation and test of all algorithms,
Statistics calculates evaluation result.
Concurrent simulation evaluates and tests process: evaluating and testing as shown in figure 3, evaluation and test center can be carried out in six steps concurrent simulation, at the beginning of the first step
Beginningization evaluates and tests environment and evaluation and test data, provides unified evaluation and test equipment and defined evaluation and test period;Second step evaluation and test is accepted, and is registered
Tested unit information and evaluation and test algorithm information;The tested unit of third step prepares the deployment debugging of evaluating software environment, creates database
Environment;The 4th tested unit of step starts to evaluate and test, and the operation stream of simulation program is completed by concurrent tool calling interface in evaluation and test center
Journey, including user's login button is clicked, user login operation is completed, then click fingerprint comparison button, calls and compare interface service,
Single probe library fingerprint is sent, comparison result storage is received, records comparison time, the performance parameter of configuration concurrency test, starting
Tool carries out concurrent test and records test result;5th step evaluates and tests center and backs up tested unit modeling and comparison result data,
Resetting evaluation and test environment is evaluated and tested and is serially carried out into next step;6th step evaluates and tests center after the completion of the evaluation and test of all algorithms, statistics
Calculate evaluation result.
Based on the same inventive concept, the embodiment of the invention also provides a kind of Key Performance Indicators of fingerprint comparison system
Assessment method, by the evaluation system of the Key Performance Indicator of the principle and aforementioned fingerprint Compare System of the solved problem of this method
It is similar, therefore the implementation of this method may refer to the implementation of aforementioned system, overlaps will not be repeated.
Fig. 4 is the process signal of the assessment method of the Key Performance Indicator of fingerprint comparison system provided in an embodiment of the present invention
Figure.As shown in figure 4, the assessment method of the Key Performance Indicator of fingerprint comparison system provided in an embodiment of the present invention, including it is following
Step:
The evaluation metrics that S210, building test and assess to the fingerprint comparison algorithm and engine of tested unit.
The fingerprint evaluation and test data that S220, acquisition are evaluated and tested.
S230, access interface is provided for tested unit, the access interface is for accessing the fingerprint evaluation and test data.
S240, respectively to the modeling of the fingerprint of the fingerprint comparison algorithm of tested unit and engine and template matching performance and simultaneously
Volatility is tested and assessed, and the first assessment data and the second assessment data are generated.
S250, based on the first assessment data generated and the second assessment data, to the index values of the evaluation metrics into
Row calculates, and generates corresponding evaluation result.
Further, the evaluation metrics of the building in step S210 include the first evaluation metrics and the second evaluation metrics, institute
The first evaluation metrics are stated for evaluating the modeling of the fingerprint of fingerprint comparison algorithm and engine and template matching performance, described the
Two assessment indicators are for evaluating the concurrency performance of fingerprint comparison algorithm and engine.
Further, step S220 may particularly include: obtained from preset database the first quantity demographic data and
The demographic data of second quantity;The composition evaluation and test of the demographic data of the demographic data of first quantity and second quantity compares
Data, and the partial data of the demographic data of second quantity is from the demographic data of first quantity.And institute
The demographic data for stating the second quantity passes through preset ratio parameter extraction according to age, sex, race, nationality.
Further, step S240 may particularly include:
The fingerprint modeling program of S241, the fingerprint comparison algorithm by calling the tested unit and engine carry out image and build
Mould, to image modeling at the beginning of and the end time record;By the fingerprint comparison algorithm for calling the tested unit
And the template matching program of engine carries out template comparison, records at the beginning of comparing to template with the end time;It is based on
It generates first at the beginning of the image modeling of record and with the end time at the beginning of end time and template comparison and tests and assesses
Data.
S242, the operating process for the fingerprint comparison algorithm for operating the tested unit is remembered by the concurrent tool of calling
Record;The operating process is executed by the terminal request for calling concurrent tool simulation to preset concurrent quantity, records described preset simultaneously
Hair quantity and described preset the concurrent quantity corresponding response time;Concurrent quantity is preset based on record and described presets concurrent quantity
The corresponding response time generates the second assessment data.
Further, step S250 is specifically included: the evaluation and test data generated based on step S240, opening including image modeling
Sound corresponding with end time and concurrent quantity and concurrent quantity at the beginning of time beginning and end time, template comparison
Between seasonable etc., the calculation formula of the evaluation metrics of step S210 building calculates each assessment indicator, is fingerprint comparison algorithm
And the index superiority and inferiority of engine provides analysis, selection ground.
Method in the present embodiment can use system provided by the above embodiment to realize, the executing subject of method can be with
For each module in system, concrete implementation principle and process are referred to previous embodiment, and details are not described herein again.
Embodiment described above, only a specific embodiment of the invention, to illustrate technical solution of the present invention, rather than
It is limited, scope of protection of the present invention is not limited thereto, although having carried out with reference to the foregoing embodiments to the present invention detailed
Illustrate, those skilled in the art should understand that: anyone skilled in the art the invention discloses
In technical scope, it can still modify to technical solution documented by previous embodiment or variation can be readily occurred in, or
Person's equivalent replacement of some of the technical features;And these modifications, variation or replacement, do not make corresponding technical solution
Essence is detached from the spirit and scope of technical solution of the embodiment of the present invention, should be covered by the protection scope of the present invention.Therefore,
The protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. a kind of evaluation system of the Key Performance Indicator of fingerprint comparison system characterized by comprising
Evaluation metrics system construction module, the evaluation and test that fingerprint comparison algorithm and engine for constructing to tested unit are tested and assessed
Index;
Data acquisition module is evaluated and tested, evaluates and tests data for obtaining the fingerprint evaluated and tested;
Database interface authorization module, for providing access interface for tested unit to access the database of the evaluation system,
The database purchase has the fingerprint evaluation and test data;
Evaluation and test module, the evaluation and test module include the first evaluation and test module and the second evaluation and test module;
First evaluation and test module is used for fingerprint modeling and template matching to the fingerprint comparison algorithm and engine of tested unit
It can be carried out assessment;
Second evaluation and test module is for testing and assessing to the concurrency performance of the fingerprint comparison algorithm and engine;
Evaluation result processing module, the data for being tested and assessed based on the evaluation and test module carry out the index value of the evaluation metrics
It calculates, and generates corresponding evaluation result.
2. evaluation system according to claim 1, which is characterized in that the evaluation and test data acquisition module includes test library number
According to acquiring unit and library data capture unit is detected,
The test library acquiring unit, for obtaining the demographic data of the first quantity from preset database;
Detection library data capture unit, for obtaining the demographic data of the second quantity from the preset database;
The demographic data of the demographic data of first quantity and second quantity composition evaluation and test comparison data, and described the
Demographic data of the partial data of the demographic data of two quantity from first quantity.
3. evaluation system according to claim 2, which is characterized in that the demographic data of second quantity according to the age,
Sex, race, nationality pass through preset ratio parameter extraction.
4. evaluation system according to claim 1, which is characterized in that first evaluation and test module includes:
Fingerprint modeling unit, for by call the tested unit fingerprint comparison algorithm and engine fingerprint modeling program into
Row image modeling, to image modeling at the beginning of and the end time record;
Template matching unit, for by call the tested unit fingerprint comparison algorithm and engine template matching program into
The comparison of row template, records at the beginning of comparing to template with the end time;
The fingerprint comparison algorithm and engine carry out fingerprint using the assessment data of the database by the access interface and build
Mould and template matching.
5. evaluation system according to claim 1, which is characterized in that second evaluation and test module includes:
Simulated technological process recording unit, for by calling behaviour of the concurrent tool to the fingerprint comparison algorithm for operating the tested unit
It is recorded as process;
Comparing unit is concurrently modeled, executes the behaviour for the terminal request by calling concurrent tool simulation to preset concurrent quantity
Make process, records and described preset concurrent quantity and described preset the concurrent quantity corresponding response time.
6. evaluation system according to claim 1, which is characterized in that the evaluation metrics include the first evaluation metrics and the
Two evaluation metrics, first evaluation metrics be used for the modeling of the fingerprint of fingerprint comparison algorithm and engine and template matching performance into
Row evaluation, second assessment indicator is for evaluating the concurrency performance of fingerprint comparison algorithm and engine.
7. a kind of assessment method of the Key Performance Indicator of fingerprint comparison system characterized by comprising
Construct the evaluation metrics tested and assessed to the fingerprint comparison algorithm and engine of tested unit;
Obtain the fingerprint evaluation and test data evaluated and tested;
Access interface is provided for tested unit, the access interface is for accessing the fingerprint evaluation and test data;
Respectively to the modeling of the fingerprint of the fingerprint comparison algorithm of tested unit and engine and template matching performance and concurrency performance into
Row assessment generates the first assessment data and the second assessment data;
Based on the first assessment data generated and the second assessment data, the index value of the evaluation metrics is calculated, and
Generate corresponding evaluation result.
8. the method according to the description of claim 7 is characterized in that the fingerprint evaluation and test data that the acquisition is evaluated and tested specifically are wrapped
It includes:
The demographic data of the first quantity and the demographic data of the second quantity are obtained from preset database;
The demographic data of the demographic data of first quantity and second quantity composition evaluation and test comparison data, and described the
Demographic data of the partial data of the demographic data of two quantity from first quantity.
9. the method according to the description of claim 7 is characterized in that the fingerprint comparison algorithm of tested unit and the fingerprint of engine
Modeling and template matching performance are tested and assessed, and are generated the first assessment data and are included:
By calling the fingerprint comparison algorithm of the tested unit and the fingerprint modeling program progress image modeling of engine, to image
It is recorded at the beginning of modeling with the end time;
By calling the template matching program progress template comparison of the fingerprint comparison algorithm and engine of the tested unit, to template
It is recorded at the beginning of comparison with the end time;
It is generated at the beginning of image modeling based on record and with the end time at the beginning of end time and template comparison
First assessment data.
10. the method according to the description of claim 7 is characterized in that fingerprint comparison algorithm and engine to tested unit and
Volatility is tested and assessed, and is generated the second assessment data and is included:
By calling concurrent tool to record the operating process for the fingerprint comparison algorithm for operating the tested unit;
The operating process is executed by the terminal request for calling concurrent tool simulation to preset concurrent quantity, records described preset simultaneously
Hair quantity and described preset the concurrent quantity corresponding response time;
Concurrent quantity is preset based on record and described preset concurrent quantity corresponding response time and is generated the second assessment data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711354064.1A CN109934060A (en) | 2017-12-15 | 2017-12-15 | A kind of evaluation system and method for the Key Performance Indicator of fingerprint comparison system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711354064.1A CN109934060A (en) | 2017-12-15 | 2017-12-15 | A kind of evaluation system and method for the Key Performance Indicator of fingerprint comparison system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109934060A true CN109934060A (en) | 2019-06-25 |
Family
ID=66980651
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711354064.1A Pending CN109934060A (en) | 2017-12-15 | 2017-12-15 | A kind of evaluation system and method for the Key Performance Indicator of fingerprint comparison system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109934060A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104331477A (en) * | 2014-11-04 | 2015-02-04 | 哈尔滨工业大学 | Method for testing concurrency property of cloud platform based on federated research |
CN106067043A (en) * | 2016-06-01 | 2016-11-02 | 重庆中科云丛科技有限公司 | A kind of performance test methods and system |
CN106874306A (en) * | 2015-12-14 | 2017-06-20 | 公安部户政管理研究中心 | People information portrait Compare System Key Performance Indicator evaluating method |
-
2017
- 2017-12-15 CN CN201711354064.1A patent/CN109934060A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104331477A (en) * | 2014-11-04 | 2015-02-04 | 哈尔滨工业大学 | Method for testing concurrency property of cloud platform based on federated research |
CN106874306A (en) * | 2015-12-14 | 2017-06-20 | 公安部户政管理研究中心 | People information portrait Compare System Key Performance Indicator evaluating method |
CN106067043A (en) * | 2016-06-01 | 2016-11-02 | 重庆中科云丛科技有限公司 | A kind of performance test methods and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Canzian et al. | Trajectories of depression: unobtrusive monitoring of depressive states by means of smartphone mobility traces analysis | |
CN107133265B (en) | Method and device for identifying user with abnormal behavior | |
CN109617910B (en) | Vulnerability risk assessment method and device, storage medium and server | |
CN104392221B (en) | A kind of diverse identities identifying system and multidimensional diverse identities recognition methods | |
WO2017071126A1 (en) | Touch-screen user key-press behavior pattern construction and analysis system and identity recognition method thereof | |
JPH10510385A (en) | Method and system for software quality architecture based analysis | |
CN112884092A (en) | AI model generation method, electronic device, and storage medium | |
CN104866763A (en) | Permission-based Android malicious software hybrid detection method | |
CN114117311B (en) | Data access risk detection method and device, computer equipment and storage medium | |
CN111783663A (en) | Algorithm evaluation system and detection method for performance detection of human evidence verification equipment | |
CN109886709B (en) | Intelligent lock management method, system, computer equipment and storage medium | |
CN110069411A (en) | Client performance quality report generation method, device, medium and electronic equipment | |
CN109165153A (en) | A kind of performance test methods of high emulation securities business transaction class system | |
KR20070080313A (en) | Method and system for analyzing performance of providing services to client terminal | |
CN110349015A (en) | The anti-fake system tuning operation loading method and device held up based on three pass | |
CN106874306B (en) | Method for evaluating key performance index of population information portrait comparison system | |
CN109871676A (en) | Three identity identifying methods and system based on mouse behavior | |
CN109871673A (en) | Based on the lasting identity identifying method and system in different context environmentals | |
CN110008101A (en) | Client performance evaluation method, device, storage medium and electronic equipment | |
KhudaBukhsh et al. | Detecting non-adversarial collusion in crowdsourcing | |
CN107168844A (en) | A kind of method and device of performance monitoring | |
CN109033205B (en) | Aerospace test data checking device based on data input behavior analysis | |
CN110138638A (en) | A kind of processing method and processing device of network flow | |
US11144773B2 (en) | System for characterizing biometric station metrics with genericized biometric information | |
CN109242658A (en) | Suspicious transaction reporting generation method, system, computer equipment 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190625 |
|
RJ01 | Rejection of invention patent application after publication |