CN109145813A - A kind of image matching algorithm test method and device - Google Patents
A kind of image matching algorithm test method and device Download PDFInfo
- Publication number
- CN109145813A CN109145813A CN201810947655.8A CN201810947655A CN109145813A CN 109145813 A CN109145813 A CN 109145813A CN 201810947655 A CN201810947655 A CN 201810947655A CN 109145813 A CN109145813 A CN 109145813A
- Authority
- CN
- China
- Prior art keywords
- image
- test
- test sample
- matching algorithm
- script
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of image matching algorithm test method and devices, are related to field of computer technology.One specific embodiment of this method includes: to crawl image and video flowing is made in the image crawled using crawling script automatically, and each test sample image is intercepted from video flowing using automatic interception image script；Each reference sample image is read using automatic reading image script and each test sample image, permutation and combination obtain test sample；Test sample is for testing image matching algorithm.The embodiment acquires each reference sample image and video flowing using script, intercepts each test sample image from video flowing automatically, time saving and energy saving, and testing efficiency is high；Permutation and combination is carried out to each reference sample image and each test sample image and obtains test sample so that for test image matching algorithm, amount of test data is huge, and the accuracy of test result is good, can comprehensively be tested algorithm.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of image matching algorithm test method and devices.
Background technique
The test of testimony of a witness alignment algorithm based on recognition of face need a large amount of face and identity card picture compare sample into
Row test, the test method of the prior art is that the photo that tester organizes departmental staff as much as possible to carry out respectively on the spot is adopted
Collection is tested, everyone needs existing identity card sample once to be compared when test, calculates its misclassification rate and its
Accuracy rate.
In realizing process of the present invention, at least there are the following problems in the prior art for inventor's discovery:
(1) amount of test data is smaller, and the accuracy of test result is poor；
(2) testimony of a witness photo comparison sample is single, can not comprehensively be tested algorithm, can not also be continued to algorithm
Property, robustness testing；
(3) participant is numerous, takes time and effort, inefficiency.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of image matching algorithm test method and device, acquired using script
Each reference sample image and video flowing intercept each test sample image, time saving and energy saving, testing efficiency from video flowing automatically
It is high；Permutation and combination is carried out to each reference sample image and each test sample image and obtains test sample for test image
Matching algorithm, amount of test data is huge, and the accuracy of test result is good, can comprehensively be tested algorithm.
According to an aspect of an embodiment of the present invention, a kind of image matching algorithm test method is provided.
A kind of image matching algorithm test method according to an embodiment of the present invention includes:
It crawls image using script is crawled automatically and video flowing is made in the image crawled, utilize automatic interception image foot
This intercepts each test sample image from video flowing；
Each reference sample image and each test sample image are read using the automatic image script that reads, to each reference
Sample image and each test sample image carry out permutation and combination and obtain test sample；Each test sample includes one and refers to sample
This image and a test sample image；
Test sample is for testing image matching algorithm.
Optionally, the test result tested image matching algorithm includes: that test passes through and tests and do not pass through；
After obtaining the test result of each test sample, further includes: using automatically analyzing script according to the test of each test sample
As a result the current percent of pass of image matching algorithm is determined.
Optionally it is determined that after the current percent of pass of image matching algorithm, further includes: worked as using script judgement is automatically analyzed
Whether preceding percent of pass is more than or equal to percent of pass threshold value；If so, test terminates；Otherwise, using automatically analyzing script adjustment figure
As the algorithm parameter of matching algorithm, the test result tested using test sample image matching algorithm is then reacquired
To determine the percent of pass of image matching algorithm, until the percent of pass of image matching algorithm is more than or equal to percent of pass threshold value.
Optionally, reference sample image is identity card picture, and test sample image is the human face photo of acquisition.
Optionally, each reference sample image and each test sample image are read using the automatic image script that reads, it is right
Each reference sample image and each test sample image carry out permutation and combination and obtain test sample, comprising: are read using automatic
Image script reads each identity card picture and each human face photo, arranges each identity card picture and each human face photo
Column combination obtains test sample；The method also includes: it calls and is passed test sample using the interface of Flask Web framework encapsulation
Image matching algorithm is handed to be tested.
Another aspect according to an embodiment of the present invention provides a kind of image matching algorithm test device.
Image matching algorithm test device according to an embodiment of the present invention includes:
Acquisition module crawls image and video flowing is made in the image crawled using script is crawled automatically, using automatic
Interception image script intercepts each test sample image from video flowing；
Read module reads each reference sample image and each test sample image using the automatic image script that reads,
Permutation and combination is carried out to each reference sample image and each test sample image and obtains test sample；Each test sample includes
One reference sample image and a test sample image；
Test sample is for testing image matching algorithm.
Optionally, the test result tested image matching algorithm includes: that test passes through and tests and do not pass through；
The image matching algorithm test device of the embodiment of the present invention further include: analysis module is used for: the test of each test sample is obtained
As a result after, passed through using automatically analyzing script and determining that image matching algorithm is current according to the test result of each test sample
Rate.
Optionally, analysis module is also used to: after determining the current percent of pass of image matching algorithm, using automatically analyzing foot
This judges whether current percent of pass is more than or equal to percent of pass threshold value；If so, test terminates；Otherwise, analysis module utilizes certainly
The algorithm parameter of dynamic analysis script adjustment image matching algorithm, then reacquire using test sample to image matching algorithm into
The test result of row test to determine the percent of pass of image matching algorithm, until the percent of pass of image matching algorithm be more than or equal to it is logical
Cross rate threshold value.
Optionally, reference sample image is identity card picture, and test sample image is the human face photo of acquisition.
Optionally, read module reads each reference sample image and each test sample using the automatic image script that reads
Image carries out permutation and combination to each reference sample image and each test sample image and obtains test sample, comprising: using certainly
The dynamic image script that reads reads each identity card picture and each human face photo, to each identity card picture and each human face photo
It carries out permutation and combination and obtains test sample；Read module is also used to: calling will be tested using the interface of Flask Web framework encapsulation
Sample is transferred to image matching algorithm and is tested.
Other side according to an embodiment of the present invention provides a kind of image matching algorithm test electronic equipment.
Image matching algorithm according to an embodiment of the present invention tests electronic equipment, comprising:
One or more processors；
Storage device, for storing one or more programs,
When the one or more program is executed by the one or more processors, so that the one or more processors are realized
The image matching algorithm test method that first aspect of the embodiment of the present invention provides.
Still another aspect according to an embodiment of the present invention provides a kind of computer-readable medium.
Computer-readable medium according to an embodiment of the present invention, is stored thereon with computer program, and the program is by processor
The image matching algorithm test method that first aspect of the embodiment of the present invention provides is realized when execution.
One embodiment in foregoing invention has the following advantages that or the utility model has the advantages that acquires each reference sample using script
Image and video flowing intercept each test sample image from video flowing automatically, time saving and energy saving, and testing efficiency is high；To each ginseng
It examines sample image and each test sample image carries out permutation and combination and obtains test sample to survey for test image matching algorithm
Examination data volume is huge, and the accuracy of test result is good, can comprehensively be tested algorithm.It is determined using script is automatically analyzed
The percent of pass of image matching algorithm, and based on this adjustment image matching algorithm algorithm parameter, can to algorithm carry out duration,
Robustness testing.
Further effect possessed by above-mentioned non-usual optional way adds hereinafter in conjunction with specific embodiment
With explanation.
Detailed description of the invention
Attached drawing for a better understanding of the present invention, does not constitute an undue limitation on the present invention.Wherein:
Fig. 1 is the schematic diagram of the main flow of image matching algorithm test method according to an embodiment of the present invention；
Fig. 2 is the schematic diagram of the main modular of image matching algorithm test device according to an embodiment of the present invention；
Fig. 3 is that the embodiment of the present invention can be applied to exemplary system architecture figure therein；
Fig. 4 is adapted for the structural representation of the computer system for the terminal device or server of realizing the embodiment of the present invention
Figure.
Specific embodiment
Below in conjunction with attached drawing, an exemplary embodiment of the present invention will be described, including the various of the embodiment of the present invention
Details should think them only exemplary to help understanding.Therefore, those of ordinary skill in the art should recognize
It arrives, it can be with various changes and modifications are made to the embodiments described herein, without departing from scope and spirit of the present invention.Together
Sample, for clarity and conciseness, descriptions of well-known functions and structures are omitted from the following description.
According to an aspect of an embodiment of the present invention, a kind of image matching algorithm test method is provided.
Fig. 1 is the schematic diagram of the main flow of image matching algorithm test method according to an embodiment of the present invention.Such as Fig. 1 institute
Show, image matching algorithm test method includes: step S101 and step S102.
Step S101, it crawls image and video flowing is made in the image crawled using crawling script automatically, using automatic
Interception image script intercepts each test sample image from video flowing.
Automatically crawling script is the script for referring to crawl image from network.Automatic interception image script be refer to from
Script of at least part image as test sample image is intercepted in each frame image of video flowing.
The picture material of test sample image can be configured according to the actual situation.For example, being surveyed when being used for recognition of face
Trying sample image can be the human face photo of acquisition.When for goods matching, test sample image can shine for the commodity of acquisition
Piece.The each image crawled is converted into video flowing, intercepts each test sample image, number convenient for automatic interception image script
It is big and accurate according to amount, it is with a high credibility.
When carrying out recognition of face in the prior art, tester organizes departmental staff as much as possible to carry out respectively on the spot
Photo acquisition is tested, and is taken time and effort.Script is automatic and automatic interception image script obtains automatically using crawling automatically by the present invention
Each test sample image is taken, is participated in without artificial, it is time saving and energy saving, it is high-efficient.
Step S102, each reference sample image and each test sample image are read using the automatic image script that reads,
Permutation and combination is carried out to each reference sample image and each test sample image and obtains test sample；Each test sample includes
One reference sample image and a test sample image；Test sample is for testing image matching algorithm.
The automatic image script that reads is to refer to will to be stored in each reference sample image of some position and each automatically
Test sample image reads out the script for obtaining test sample.The automatic calling interface pair of image script is read using automatic
Different parameters are arranged, carry out automation biography ginseng test to algorithm, instead of manual testing, improve testing efficiency.
Reference sample image and test sample image are all the images of object to be matched.For example, being surveyed when being used for recognition of face
Identity card picture can be can be for the human face photo of acquisition, reference sample image by trying sample image.For another example knowing for fingerprint
When other, test sample image can be the fingerprint pre-saved for the fingerprint of acquisition, reference sample image.
In some embodiments, each reference sample image and each test sample are read using the automatic image script that reads
Image carries out permutation and combination to each reference sample image and each test sample image and obtains test sample, comprising: using certainly
The dynamic image script that reads reads each identity card picture and each human face photo, to each identity card picture and each human face photo
It carries out permutation and combination and obtains test sample；The method of the embodiment of the present invention further include: (one is based on calling using Flask Web
The miniature Web frame of Python) test sample is transferred to image matching algorithm and tests by the interface of framework encapsulation.
Assuming that the quantity of reference sample image is m, then the quantity of test sample image is n, then obtains after permutation and combination
The quantity of test sample is m*n.Amount of test data is huge, have diversity, the accuracy of test result is good, can to algorithm into
The comprehensive test of row.
The embodiment of the present invention is used for test image matching algorithm, and why not the algorithm model of the image matching algorithm is as influenced this
The implementation of the test method of inventive embodiments.
The test result tested image matching algorithm includes: that test passes through and tests and do not pass through；It obtains each
It can also include: to utilize the test knot for automatically analyzing script according to each test sample after the test result of a test sample
Fruit determines the current percent of pass of image matching algorithm.
Assuming that the quantity of reference sample image is m, then the quantity of test sample image is n, then obtains after permutation and combination
The quantity of test sample is m*n.Using the m*n test sample as the input of image matching algorithm, m*n test knot is obtained
Fruit.Assuming that: having a test result in the m*n test result is that test passes through, i.e. has a test specimens in m*n test result
This test sample image and reference sample image through image matching algorithm confirmation be it is matched, then the image matching algorithm is logical
Crossing rate is a/m*n.
Due to more than test result and complicated, automatically analyzed using script, calculate its percent of pass, improve test result confidence level
Optionally it is determined that after the current percent of pass of image matching algorithm, further includes: worked as using script judgement is automatically analyzed
Whether preceding percent of pass is more than or equal to percent of pass threshold value；If so, test terminates；Otherwise, using automatically analyzing script adjustment figure
As the algorithm parameter of matching algorithm, the test result tested using test sample image matching algorithm is then reacquired
To determine the percent of pass of image matching algorithm, until the percent of pass of image matching algorithm is more than or equal to percent of pass threshold value.
The algorithm model of image matching algorithm is different, and corresponding algorithm parameter is not necessarily identical.In trained and test image
During the algorithm model of matching algorithm, algorithm parameter can be continued to optimize by adjusting algorithm parameter.
For example, this parameter of similarity threshold in image matching algorithm, then when being outputed test result according to test sample, figure
As matching algorithm calculates the similarity of test sample image and reference sample image in each test sample, if the similarity is greater than
Equal to similarity threshold, then the test result of the test sample is that test passes through；Otherwise, test result is that test does not pass through.If
The percent of pass that test result based on each test sample obtains is more than or equal to percent of pass threshold value, then test terminates；Otherwise, it utilizes
Automatically analyze script adjustment image matching algorithm similarity threshold, then re-use test sample to image matching algorithm into
Row test, the percent of pass for determining image matching algorithm, until the percent of pass of image matching algorithm is more than or equal to percent of pass threshold value.
It is illustrated below with image matching algorithm of the specific embodiment to the embodiment of the present invention.
Step 1: identity card picture is put in as sample identity license piece after department's identity card picture is taken pictures
In IdentityCard_images file, a kind of image script Python (explanation type meter of object-oriented is crawled using automatic
Calculation machine programming language) multiple human face photos are crawled from network is fabricated to video flowing, utilize automatic interception image script
Ffmpeg (it is a set of can be used to record, converted digital audio, video, and the open source computer program of stream can be translated into) will
It stores from the human face photo being truncated in video flowing into human face photo Face_images file；With ffmpeg by multiple figures
Piece is converted to video flowing, human face photo is intercepted convenient for automatic interception image script, for calculating human face photo and identity card picture
Misclassification rate, data volume is big and accurate with a high credibility.
Step 2: using Flask Web framework encapsulation Rest, (Rest describes client and server end in HTTP layers
Data interaction rule) (can also use other frames, easy to use using this frame) interface, calls testimony of a witness alignment algorithm (i.e.
Image matching algorithm as mentioned in the embodiments of the present invention), it is read under Face_images file using the automatic image script that reads
Human face photo, the identity card picture under IdentityCard_images file, post (HTTP will be called after photo transcoding
A kind of request interface of layer) interface, to pass ginseng.
It needs to call in a kind of Comparator (comparator) module using Flask Web framework encapsulation Rest interface
The compare_offline_raw method of comparator class.It needs to carry out biography ginseng in business, calls tester to write and connect
Mouthful, test whether its testimony of a witness is consistent, parameter is the human face photo and identity card picture of step 1, if identity card picture quantity is n,
Human face photo quantity is m, combines identity card picture and human face photo, that is, has m*n kind combined result, result is compared,
Similarity is found out using people's alignment algorithm.
Step 3: the automatic image script that reads calls Rest interface pass ginseng test (for example, recycling using for automatically
Read an identity card picture and a human face photo respectively, using the imencode method coded image of cv2 module, and by its
Switch to byte vector, the b64encode method for recalling base64 module switchs to base64 coded format, by encoded two
As a result Rest interface is transmitted to as parameter), parameter is the face and identity card picture in step 1, and different parameters are arranged,
Testimony of a witness comparison is persistently carried out, is outputed test result.Specifically, entering ginseng is that an encoded identity card picture and a face shine
Identity card picture and human face photo are all compared using double for circulation and are completed by piece；Ginseng is that photo compares matching value out, to
Test report is exported after all comparings, includes comparing human face photo, comparing identity card picture, test in test report
As a result, spent time for automatically analyzing script to its interpretation of result, while can also be supplied to tester's analysis and summary.It surveys
It is more to try data volume, as a result more acurrate more convincingness.
Step 4: the test result after execution is automatically analyzed using script is automatically analyzed, calculates and passes through automatically
Rate, using percent of pass ask its accidentally know (should test pass through be judged to testing by algorithm and do not pass through or should test obstructed
Cross be judged to testing by algorithm passes through) rate and its corresponding percent of pass threshold value.For example, by my human face photo and my identity
The comparison result of license piece is put into a list, will be put in my human face photo and the comparison result of other people identity card pictures
Into another list, be compared respectively at a certain similarity threshold, it can be deduced that percent of pass under this similarity threshold and
Misclassification rate.Similarity threshold, which can use, is incremented by the different value of setting, compare obtain percent of pass under different similarity thresholds and
Misclassification rate.After automatically analyzing script execution, there can be a directive sending, send relevant people for test result automatically
Member's mailbox reduces if problematic can at the first time be handled problem and links up cost.
The specific embodiment of above-mentioned steps one to step 4 is as follows:
Using PyCharm, (a kind of Python IDE can help user using Python with a whole set of first
The tool of its efficiency is improved when exploitation) complete that Python obtains multiple human face photos from network automatically crawl image foot automatically
This, the human face photo that will acquire is stored in local c disk file sample_faceImages, using ffmpeg tool by c
The human face photo crawled in disk sample_faceImages command statement synthetic video stream is convenient for automatic interception image foot
This interception photo.Automatic interception image script realizes automatic identification face by Python third party library cv2 module and will interception
The human face photo arrived saves, key step are as follows: 1) VideoConverter (a kind of video converter) reading video flowing, 2)
CascadeClassifier (cascade classifier for doing Face datection) identification face, 3) detectMultiScale (one kind
Can be used for the function of Face datection) Face datection, 4) save picture.The face being truncated to by automatic interception image script is shone
Piece is stored in Face_Images file, to enter ginseng test.
Secondly, needing to call the comparator class in Comparator module using Flask framework encapsulation Rest interface
Compare_offline_raw method.Rest interface is deployed on arithmetic server.
Matching algorithm is finally called according to the Rest interface that tester independently encapsulates, reads image script certainly using automatic
The human face photo parameter in identity card picture and Face_Images file in dynamic transmitting Identity_Images file,
Testimony of a witness comparison is carried out to human face photo and identity card picture combination using double for circulation, is calculated using certification alignment algorithm
Similarity is output in result file, and similarity number is smaller, illustrates that its matching degree is higher, on the contrary then lower.
Finally the number of pictures passed through is tested using the Cacul_Function method for automatically analyzing comparison result script
Percent of pass is calculated automatically divided by whole number of pictures, asks its misclassification rate and its corresponding percent of pass threshold value using percent of pass, is surveyed
Examination automatically sends test result in the mailbox of related personnel after completing, to handle problem at the first time.
The embodiment of the present invention has the advantages that intercepts human face photo using script automatically, and the face being truncated to shines
Piece is made as video flowing using script, to intercept photo automatically, saves manpower, substantially reduces the time of true man's test, mention
High efficiency.Then carry out biography ginseng using script, the testimony of a witness compares, output as a result, automatically analyze result calculate its percent of pass and
Misclassification rate substantially reduces the testing time, ensure that the diversity of data, reduces the time of waste each department's manpower.By with
The testing efficiency of software project can be improved in upper method.
The embodiment of the present invention has used 4 scripts to carry out automatic test, eliminates the complexity of manual testing, mentions significantly
High testing efficiency, realizes the full-range automatic test of algorithm.
Another aspect according to an embodiment of the present invention provides a kind of image matching algorithm test device.
Fig. 2 is the schematic diagram of the main modular of image matching algorithm test device according to an embodiment of the present invention.Such as Fig. 2 institute
Show, image matching algorithm test device 200 according to an embodiment of the present invention includes:
Acquisition module 201 crawls image and video flowing is made in the image crawled using script is crawled automatically, utilize from
Dynamic interception image script intercepts each test sample image from video flowing；
Read module 202 reads each reference sample image and each test sample figure using the automatic image script that reads
Picture carries out permutation and combination to each reference sample image and each test sample image and obtains test sample；Each test sample
Including a reference sample image and a test sample image；
Test sample is for testing image matching algorithm.
Optionally, the test result tested image matching algorithm includes: that test passes through and tests and do not pass through；
The image matching algorithm test device of the embodiment of the present invention further include: analysis module (not shown) is used for: obtaining each survey
After the test result of sample sheet, determine that images match is calculated according to the test result of each test sample using script is automatically analyzed
The current percent of pass of method.
Optionally, analysis module is also used to: after determining the current percent of pass of image matching algorithm, using automatically analyzing foot
This judges whether current percent of pass is more than or equal to percent of pass threshold value；If so, test terminates；Otherwise, analysis module utilizes certainly
The algorithm parameter of dynamic analysis script adjustment image matching algorithm, then reacquire using test sample to image matching algorithm into
The test result of row test to determine the percent of pass of image matching algorithm, until the percent of pass of image matching algorithm be more than or equal to it is logical
Cross rate threshold value.
Optionally, reference sample image is identity card picture, and test sample image is the human face photo of acquisition.
Optionally, read module reads each reference sample image and each test sample using the automatic image script that reads
Image carries out permutation and combination to each reference sample image and each test sample image and obtains test sample, comprising: using certainly
The dynamic image script that reads reads each identity card picture and each human face photo, to each identity card picture and each human face photo
It carries out permutation and combination and obtains test sample；Read module is also used to: calling will be tested using the interface of Flask Web framework encapsulation
Sample is transferred to image matching algorithm and is tested.
Other side according to an embodiment of the present invention provides a kind of image matching algorithm test electronic equipment.
Image matching algorithm according to an embodiment of the present invention tests electronic equipment, comprising:
One or more processors；
Storage device, for storing one or more programs,
When the one or more program is executed by the one or more processors, so that the one or more processors are realized
The image matching algorithm test method that first aspect of the embodiment of the present invention provides.
Fig. 3 is shown can be using image matching algorithm test method or the image matching algorithm test of the embodiment of the present invention
The exemplary system architecture 300 of device.
As shown in figure 3, system architecture 300 may include terminal device 301,302,303, network 304 and server 305.
Network 304 between terminal device 301,302,303 and server 305 to provide the medium of communication link.Network 304 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 301,302,303 and be interacted by network 304 with server 305, to receive or send out
Send message etc..Various telecommunication customer end applications, such as the application of shopping class, net can be installed on terminal device 301,302,303
(merely illustrative) such as the application of page browsing device, searching class application, instant messaging tools, mailbox client, social platform softwares.
Terminal device 301,302,303 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart phone, tablet computer, pocket computer on knee and desktop computer etc..
Server 305 can be to provide the server of various services, such as utilize terminal device 301,302,303 to user
The shopping class website browsed provides the back-stage management server (merely illustrative) supported.Back-stage management server can be to reception
To the data such as information query request analyze etc. processing, and by processing result (such as target push information, product letter
Breath -- merely illustrative) feed back to terminal device.
It should be noted that image matching algorithm test method provided by the embodiment of the present invention is generally by server 305
It executes, correspondingly, image matching algorithm test device is generally positioned in server 305.
It should be understood that the number of terminal device, network and server in Fig. 3 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
Below with reference to Fig. 4, it illustrates the computer systems 400 for the terminal device for being suitable for being used to realize the embodiment of the present invention
Structural schematic diagram.Terminal device shown in Fig. 4 is only an example, function to the embodiment of the present invention and should not use model
Shroud carrys out any restrictions.
As shown in figure 4, computer system 400 includes central processing unit (CPU) 401, it can be read-only according to being stored in
Program in memory (ROM) 402 or be loaded into the program in random access storage device (RAM) 403 from storage section 408 and
Execute various movements appropriate and processing.In RAM 403, also it is stored with system 400 and operates required various programs and data.
CPU 401, ROM 402 and RAM 403 are connected with each other by bus 404.Input/output (I/O) interface 405 is also connected to always
Line 404.
I/O interface 405 is connected to lower component: the importation 406 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 407 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 408 including hard disk etc.；
And the communications portion 409 of the network interface card including LAN card, modem etc..Communications portion 409 via such as because
The network of spy's net executes communication process.Driver 410 is also connected to I/O interface 405 as needed.Detachable media 411, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 410, in order to read from thereon
Computer program be mounted into storage section 408 as needed.
Particularly, disclosed embodiment, the process described above with reference to flow chart may be implemented as counting according to the present invention
Calculation machine software program.For example, embodiment disclosed by the invention includes a kind of computer program product comprising be carried on computer
Computer program on readable medium, the computer program include the program code for method shown in execution flow chart.?
In such embodiment, which can be downloaded and installed from network by communications portion 409, and/or from can
Medium 411 is dismantled to be mounted.When the computer program is executed by central processing unit (CPU) 401, system of the invention is executed
The above-mentioned function of middle restriction.
It should be noted that computer-readable medium shown in the present invention can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the present invention, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this
In invention, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. are above-mentioned
Any appropriate combination.
Flow chart and block diagram in attached drawing are illustrated according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
Being described in module involved in the embodiment of the present invention can be realized by way of software, can also be by hard
The mode of part is realized.Described module also can be set in the processor, for example, can be described as: a kind of processor packet
Include: acquisition module crawls each image and video flowing is made in the image crawled using script is crawled automatically, utilizes automatic cut
Image script is taken to intercept each test sample image from video flowing；Read module is read respectively using the automatic image script that reads
A reference sample image and each test sample image, arrange each reference sample image and each test sample image
Combination obtains test sample；Each test sample includes a reference sample image and a test sample image；Test sample
For testing image matching algorithm, to obtain the test result of each test sample.Wherein, the title of these modules exists
The restriction to the module itself is not constituted in the case of certain, for example, acquisition module is also described as " reading using automatic
Image script reads the module of each reference sample image and each test sample image ".
As on the other hand, the present invention also provides a kind of computer-readable medium, which be can be
Included in equipment described in above-described embodiment；It is also possible to individualism, and without in the supplying equipment.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the equipment, makes
The equipment includes: to crawl each image and video flowing is made in the image crawled using crawling script automatically, using automatic
Interception image script intercepts each test sample image from video flowing；It is read using automatic reading image script each with reference to sample
This image and each test sample image carry out permutation and combination to each reference sample image and each test sample image and obtain
Test sample；Each test sample includes a reference sample image and a test sample image；Test sample is used for figure
As matching algorithm is tested, to obtain the test result of each test sample.
Technical solution according to an embodiment of the present invention has the following advantages that or the utility model has the advantages that acquires each ginseng using script
Sample image and video flowing are examined, intercepts each test sample image from video flowing automatically, time saving and energy saving, testing efficiency is high；It is right
Each reference sample image and each test sample image carry out permutation and combination and obtain test sample to match for test image
Algorithm, amount of test data is huge, and the accuracy of test result is good, can comprehensively be tested algorithm.Using automatically analyzing
Script determines the percent of pass of image matching algorithm, and the algorithm parameter based on this adjustment image matching algorithm, can to algorithm into
Row duration, robustness testing.
Above-mentioned specific embodiment, does not constitute a limitation on the scope of protection of the present invention.Those skilled in the art should be bright
It is white, design requirement and other factors are depended on, various modifications, combination, sub-portfolio and substitution can occur.It is any
Made modifications, equivalent substitutions and improvements etc. within the spirit and principles in the present invention, should be included in the scope of the present invention
Within.
Claims (12)
1. a kind of image matching algorithm test method characterized by comprising
Crawl image using script is crawled automatically and video flowing be made in the image crawled, using automatic interception image script from
Each test sample image is intercepted in video flowing；
Each reference sample image and each test sample image are read using the automatic image script that reads, to each reference sample
Image and each test sample image carry out permutation and combination and obtain test sample；Each test sample includes a reference sample figure
Picture and a test sample image；
The test sample is for testing image matching algorithm.
2. the method as described in claim 1, which is characterized in that the test result packet tested image matching algorithm
Include: test, which passes through and tests, not to be passed through；After obtaining the test result of each test sample, further includes: using automatically analyzing foot
This determines the current percent of pass of image matching algorithm according to the test result of each test sample.
3. method according to claim 2, which is characterized in that after determining the current percent of pass of image matching algorithm, also wrap
It includes: judging whether current percent of pass is more than or equal to percent of pass threshold value using script is automatically analyzed；If so, test terminates；It is no
Then, using the algorithm parameter for automatically analyzing script adjustment image matching algorithm, the test sample is then re-used to image
Matching algorithm is tested, until the percent of pass of image matching algorithm is more than or equal to percent of pass threshold value.
4. the method as described in claim 1, which is characterized in that reference sample image is identity card picture, test sample image
For the human face photo of acquisition.
5. method as claimed in claim 4, which is characterized in that read each reference sample figure using the automatic image script that reads
Picture and each test sample image carry out permutation and combination to each reference sample image and each test sample image and are tested
Sample, comprising: read each identity card picture and each human face photo using the automatic image script that reads, each identity card is shone
Piece and each human face photo carry out permutation and combination and obtain test sample；The method also includes: the automatic image script that reads calls
The test sample image matching algorithm is transferred to using the interface of Flask Web framework encapsulation to test.
6. a kind of image matching algorithm test device characterized by comprising
Acquisition module crawls image and video flowing is made in the image crawled using script is crawled automatically, utilizes automatic interception
Image script intercepts each test sample image from video flowing；
Read module reads each reference sample image and each test sample image using the automatic image script that reads, to each
A reference sample image and each test sample image carry out permutation and combination and obtain test sample；Each test sample includes one
Reference sample image and a test sample image；
The test sample is for testing image matching algorithm.
7. device as claimed in claim 6, which is characterized in that the test result packet tested image matching algorithm
Include: test, which passes through and tests, not to be passed through；Described device further include: analysis module is used for: the test knot of each test sample is obtained
After fruit, passed through using automatically analyzing script and determining that image matching algorithm is current according to the test result of each test sample
Rate.
8. device as claimed in claim 7, which is characterized in that analysis module is also used to: determining that image matching algorithm is current
After percent of pass, judge whether current percent of pass is more than or equal to percent of pass threshold value using script is automatically analyzed；If so, test
Terminate；Otherwise, then analysis module is reacquired and is utilized using the algorithm parameter for automatically analyzing script adjustment image matching algorithm
The test result that the test sample tests image matching algorithm is to determine the percent of pass of image matching algorithm, until scheming
As the percent of pass of matching algorithm is more than or equal to percent of pass threshold value.
9. device as claimed in claim 6, which is characterized in that reference sample image is identity card picture, test sample image
For the human face photo of acquisition.
10. device as claimed in claim 9, which is characterized in that read module is read each using automatic reading image script
Reference sample image and each test sample image carry out arrangement group to each reference sample image and each test sample image
Conjunction obtains test sample, comprising: each identity card picture and each human face photo is read using the automatic image script that reads, to each
A identity card picture and each human face photo carry out permutation and combination and obtain test sample；Read module is also used to: being called and is used
The test sample is transferred to image matching algorithm and tested by the interface of Flask Web framework encapsulation.
11. a kind of image matching algorithm tests electronic equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as method as claimed in any one of claims 1 to 5.
12. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is held by processor
Such as method as claimed in any one of claims 1 to 5 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810947655.8A CN109145813B (en) | 2018-08-20 | 2018-08-20 | Image matching algorithm testing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810947655.8A CN109145813B (en) | 2018-08-20 | 2018-08-20 | Image matching algorithm testing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109145813A true CN109145813A (en) | 2019-01-04 |
| CN109145813B CN109145813B (en) | 2021-03-30 |
Family
ID=64790331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810947655.8A Active CN109145813B (en) | 2018-08-20 | 2018-08-20 | Image matching algorithm testing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109145813B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110427962A (en) * | 2019-06-20 | 2019-11-08 | 厦门网宿有限公司 | A kind of test method, electronic equipment and computer readable storage medium |
| TWI748297B (en) * | 2019-12-04 | 2021-12-01 | 瑞軒科技股份有限公司 | Automatic test method |
| TWI777552B (en) * | 2019-12-04 | 2022-09-11 | 瑞軒科技股份有限公司 | Automatic test method |
| US11489750B2 (en) | 2019-12-04 | 2022-11-01 | Amtran Technology Co., Ltd. | Automatic test system and device thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484650A (en) * | 2014-12-09 | 2015-04-01 | 北京信息科技大学 | Method and device for identifying sketch face |
| CN105389812A (en) * | 2015-10-31 | 2016-03-09 | 重庆电信研究院 | Computer vision-based vehicle-mounted information terminal function automatic test method |
| CN105868102A (en) * | 2016-03-22 | 2016-08-17 | 中国科学院软件研究所 | Computer vision based mobile terminal application testing system and method |
| CN106411633A (en) * | 2016-08-23 | 2017-02-15 | 国家电网公司 | Web application compatibility testing method based on openstack and system thereof |
| US9870520B1 (en) * | 2013-08-02 | 2018-01-16 | Intuit Inc. | Iterative process for optimizing optical character recognition |
-
2018
- 2018-08-20 CN CN201810947655.8A patent/CN109145813B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9870520B1 (en) * | 2013-08-02 | 2018-01-16 | Intuit Inc. | Iterative process for optimizing optical character recognition |
| CN104484650A (en) * | 2014-12-09 | 2015-04-01 | 北京信息科技大学 | Method and device for identifying sketch face |
| CN105389812A (en) * | 2015-10-31 | 2016-03-09 | 重庆电信研究院 | Computer vision-based vehicle-mounted information terminal function automatic test method |
| CN105868102A (en) * | 2016-03-22 | 2016-08-17 | 中国科学院软件研究所 | Computer vision based mobile terminal application testing system and method |
| CN105868102B (en) * | 2016-03-22 | 2018-06-26 | 中国科学院软件研究所 | A kind of mobile terminal application test systems and method based on computer vision |
| CN106411633A (en) * | 2016-08-23 | 2017-02-15 | 国家电网公司 | Web application compatibility testing method based on openstack and system thereof |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110427962A (en) * | 2019-06-20 | 2019-11-08 | 厦门网宿有限公司 | A kind of test method, electronic equipment and computer readable storage medium |
| TWI748297B (en) * | 2019-12-04 | 2021-12-01 | 瑞軒科技股份有限公司 | Automatic test method |
| TWI777552B (en) * | 2019-12-04 | 2022-09-11 | 瑞軒科技股份有限公司 | Automatic test method |
| US11489750B2 (en) | 2019-12-04 | 2022-11-01 | Amtran Technology Co., Ltd. | Automatic test system and device thereof |
| US11528473B2 (en) | 2019-12-04 | 2022-12-13 | Amtran Technology Co., Ltd. | Automatic test method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109145813B (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145813A (en) | A kind of image matching algorithm test method and device | |
| CN108154196B (en) | Method and apparatus for exporting image | |
| CN109002842A (en) | Image-recognizing method and device | |
| CN109308490A (en) | Method and apparatus for generating information | |
| CN109446990A (en) | Method and apparatus for generating information | |
| CN109308681A (en) | Image processing method and device | |
| CN109145828A (en) | Method and apparatus for generating video classification detection model | |
| CN109426593A (en) | The method and apparatus of automatic evaluation system performance | |
| CN107590255A (en) | Information-pushing method and device | |
| CN109447156A (en) | Method and apparatus for generating model | |
| CN109934242A (en) | Image identification method and device | |
| CN108073506A (en) | Test method and device | |
| CN107958247A (en) | Method and apparatus for facial image identification | |
| CN111008848A (en) | Fresh product tracing method and device based on block chain and storage medium | |
| CN109327887B (en) | Method and apparatus for generating information | |
| CN108388563A (en) | Information output method and device | |
| CN108960110A (en) | Method and apparatus for generating information | |
| CN110232091A (en) | Mthods, systems and devices for synchrodata | |
| CN110110666A (en) | Object detection method and device | |
| CN110084317A (en) | The method and apparatus of image for identification | |
| CN108600250A (en) | Authentication method | |
| CN109635993A (en) | Operation behavior monitoring method and device based on prediction model | |
| CN108399401A (en) | Method and apparatus for detecting facial image | |
| CN109992496A (en) | A kind of data processing method and device for automatic test | |
| CN108171167A (en) | For exporting the method and apparatus of image |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 101111 Room 221, 2nd Floor, Block C, 18 Kechuang 11th Street, Beijing Economic and Technological Development Zone Applicant after: JINGDONG DIGITAL TECHNOLOGY HOLDINGS Co.,Ltd. Address before: 101111 Room 221, 2nd Floor, Block C, 18 Kechuang 11th Street, Beijing Economic and Technological Development Zone Applicant before: BEIJING JINGDONG FINANCIAL TECHNOLOGY HOLDING Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 101111 Room 221, 2nd Floor, Block C, 18 Kechuang 11th Street, Beijing Economic and Technological Development Zone Patentee after: Jingdong Technology Holding Co.,Ltd. Address before: 101111 Room 221, 2nd Floor, Block C, 18 Kechuang 11th Street, Beijing Economic and Technological Development Zone Patentee before: Jingdong Digital Technology Holding Co.,Ltd. Address after: 101111 Room 221, 2nd Floor, Block C, 18 Kechuang 11th Street, Beijing Economic and Technological Development Zone Patentee after: Jingdong Digital Technology Holding Co.,Ltd. Address before: 101111 Room 221, 2nd Floor, Block C, 18 Kechuang 11th Street, Beijing Economic and Technological Development Zone Patentee before: JINGDONG DIGITAL TECHNOLOGY HOLDINGS Co.,Ltd. |