CN110162462A - Test method, system and the computer equipment of face identification system based on scene - Google Patents
Test method, system and the computer equipment of face identification system based on scene Download PDFInfo
- Publication number
- CN110162462A CN110162462A CN201910305396.3A CN201910305396A CN110162462A CN 110162462 A CN110162462 A CN 110162462A CN 201910305396 A CN201910305396 A CN 201910305396A CN 110162462 A CN110162462 A CN 110162462A
- Authority
- CN
- China
- Prior art keywords
- picture
- scene
- feature
- face
- 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
- 238000010998 test method Methods 0.000 title claims abstract description 21
- 238000012360 testing method Methods 0.000 claims abstract description 87
- 238000000034 method Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 14
- 239000000284 extract Substances 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 210000001061 forehead Anatomy 0.000 claims description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 210000000887 face Anatomy 0.000 claims description 4
- 238000003786 synthesis reaction Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 210000004209 hair Anatomy 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- HUTDUHSNJYTCAR-UHFFFAOYSA-N ancymidol Chemical compound C1=CC(OC)=CC=C1C(O)(C=1C=NC=NC=1)C1CC1 HUTDUHSNJYTCAR-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3688—Test management for test execution, e.g. scheduling of test suites
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3692—Test management for test results analysis
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a kind of test methods of face identification system based on scene, which comprises obtains test video, N number of picture including face feature is obtained from the test video；The corresponding multiple picture set of multiple classification scenes are obtained according to N number of picture including face feature, each picture set includes multiple pictures under corresponding classification scene；User is received for the selection instruction of the target scene in the multiple classification scene；Target Photo set corresponding with the target scene is selected from the multiple picture set；By Target Photo set synthetic video stream；And the video flowing is input in face identification system, to carry out system test operation to face identification system by the video flowing.By pictures symphysis, at test video, the efficiency of regression test can be improved in the embodiment of the present invention；By the combination of test scene, the coverage rate of user's scrnario testing can be improved.
Description
Technical field
The present embodiments relate to testing field more particularly to a kind of test sides of the face identification system based on scene
Method, system, computer equipment and computer readable storage medium.
Background technique
Face recognition technology is widely used in the good characteristics such as its uniqueness, concurrency, non-imposed, untouchable
The every field such as security protection, finance, education, e-commerce, internet.
Face identification system is under normal scene at present, under suitable light source, acquires the front of face, comprising normal complete
Whole facial contour, has no the face blocked, is clearly photographed equipment and photographed, and can accurately capture feature in this way,
And judge.But for test man, it is also contemplated that the performance of various scenes, i.e., any to may cause bat less than bat
It is unintelligible, can not judge it is face or incomplete performance.Existing test method needs personnel on site to carry out living body inspection
It surveys, but this test mode wanted can not quickly find the problem and validation problem.And the combined test of various abnormal scenes also without
Method is efficiently completed test.The difficulty of regression test is big, low efficiency.
Summary of the invention
In view of this, it is necessary to provide a kind of test method of face identification system based on scene, system, computers to set
Standby and computer readable storage medium can not quickly be found the problem and validation problem, various exceptions with solving current test mode
The problem of combined test of scene can not be also efficiently completed and the difficulty of regression test is big and low efficiency.
To achieve the above object, the embodiment of the invention provides the test method of the face identification system based on scene, institutes
Stating method and step includes:
Test video is obtained, the test video that obtains includes the original video number in the test video database of pre-acquired
According to, or pass through image collecting device obtain default scene under nominative testing video data；
N number of picture including face feature is obtained from the test video；
The corresponding multiple picture set of multiple classification scenes are obtained according to N number of picture including face feature, each
Picture set includes multiple pictures under corresponding classification scene；
User is received for the selection instruction of the target scene in the multiple classification scene；
Target Photo set corresponding with the target scene is selected from the multiple picture set；
By Target Photo set synthetic video stream；And
The video flowing is input in face identification system, with by the video flowing to face identification system system
System test operation.
Illustratively, the step of acquisition test video includes:
Original video according to multiple application scenarios of face identification system to be tested, from the test video database
Video corresponding with multiple application scenarios is obtained in data as the test video.
Illustratively, N number of picture for including the steps that face feature is obtained from the test video includes:
The test video sub-frame processing is obtained into multiple pictures；
Recognition of face is carried out to the multiple picture, to judge whether in each picture include face feature, the face
Portion's feature includes: forehead provincial characteristics, ocular feature, nasal area feature, mouth region feature and/or ear region；
It will not include that the picture of face feature is defined as invalid picture；And
The invalid picture is rejected from the multiple picture, obtains N number of picture including face feature.
Illustratively, the corresponding multiple pictures of multiple classification scenes are obtained according to N number of picture including face feature
The step of set, comprising:
N number of picture including face feature is sampled, multiple samples pictures set are obtained；
One of samples pictures set is selected from the multiple samples pictures set；
The image scene feature of each picture in the samples pictures set selected is extracted, and according to described selected
The image scene feature for each picture in samples pictures set selected extracts non-selected multiple samples by incremental learning method
The image scene feature of each picture in each samples pictures set in this picture set, to obtain N number of including face feature
Picture picture scene characteristic；And
According to the image scene feature of N number of picture including face feature, N number of include by described based on clustering algorithm
The picture of face feature is divided into the corresponding multiple picture set of the multiple classification scene, and each picture is located at one or more
In pictures.
Illustratively, multiple scenes corresponding to the multiple picture set include: angle tilt scene, dark field
Scape, eye block scene, face mask blocks scene and/or plurality of human faces scene.
To achieve the above object, the embodiment of the invention also provides a kind of test macros of face identification system, comprising:
Module is obtained, for obtaining test video；
Decomposing module, for the test video sub-frame processing to be obtained N number of picture including face feature；
Categorization module, for it is corresponding more to obtain multiple classification scenes by N number of picture classification including face feature
A picture set；
Receiving module, for receiving user for the selection instruction of the target scene in the multiple classification scene；
Selecting module, for selecting Target Photo collection corresponding with the target scene from the multiple picture set
It closes；
Synthesis module is used for Target Photo set synthetic video stream；And
Input module carries out the test of face identification system for the video flowing to be input in face identification system.
Illustratively, the acquisition module, is also used to:
The test video sub-frame processing is obtained into multiple pictures；
Recognition of face is carried out to the multiple picture, to judge whether in each picture include face feature, the face
Portion's feature includes: forehead provincial characteristics, ocular feature, nasal area feature, mouth region feature and/or ear region；
It will not include that the picture of the face feature is defined as invalid picture；And
The invalid picture is rejected from the multiple picture, obtains N number of picture including face feature.
Illustratively, the categorization module, is also used to:
N number of picture including face feature is sampled, multiple samples pictures set are obtained；
One of samples pictures set is selected from the multiple samples pictures set；
The image scene feature of each picture in the samples pictures set selected is extracted, and according to described selected
The image scene feature for each picture in samples pictures set selected extracts non-selected multiple samples by incremental learning method
The image scene feature of each picture in each samples pictures set in this picture set, to obtain N number of including face feature
Picture picture scene characteristic；And
According to the image scene feature of N number of picture including face feature, N number of include by described based on clustering algorithm
The picture of face feature is divided into the corresponding multiple picture set of the multiple classification scene, and each picture is located at one or more
In picture set.
To achieve the above object, the embodiment of the invention also provides a kind of computer equipment, the computer equipment is described
Computer equipment includes memory, processor and is stored in the computer that can be run on the memory and on the processor
Program, which is characterized in that such as the above-mentioned recognition of face system based on scene is realized when the computer program is executed by processor
The step of test method of system.
To achieve the above object, the embodiment of the invention also provides a kind of computer readable storage mediums, which is characterized in that
Computer program is stored in the computer readable storage medium, the computer program can be held by least one processor
Row, so as to realize when at least one described processor executes such as the test method of the above-mentioned face identification system based on scene
Step.
The test method of face identification system provided in an embodiment of the present invention based on scene, system, computer equipment and
Computer readable storage medium provides effective classification method for the test scene of face identification system；Pass through picture set
Test video is generated, the efficiency of regression test can be improved；By the combination of test scene, user's scrnario testing can be improved
Coverage rate.
Detailed description of the invention
Fig. 1 is the flow diagram of the test method of face identification system of the embodiment of the present invention based on scene.
Fig. 2 is the idiographic flow schematic diagram of step S102 in Fig. 1.
Fig. 3 is the idiographic flow schematic diagram of step S104 in Fig. 1.
Fig. 4 is that the present invention is based on the program module schematic diagrames of the test macro embodiment two of the face identification system of scene.
Fig. 5 is the hardware structural diagram of computer equipment embodiment three of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not before making creative work
Every other embodiment obtained is put, shall fall within the protection scope of the present invention.
It should be noted that the description for being related to " first ", " second " etc. in the present invention is used for description purposes only, and cannot
It is interpreted as its relative importance of indication or suggestion or implicitly indicates the quantity of indicated technical characteristic.Define as a result, " the
One ", the feature of " second " can explicitly or implicitly include at least one of the features.In addition, the skill between each embodiment
Art scheme can be combined with each other, but must be based on can be realized by those of ordinary skill in the art, when technical solution
Will be understood that the combination of this technical solution is not present in conjunction with there is conflicting or cannot achieve when, also not the present invention claims
Protection scope within.
In following embodiment, exemplary description will be carried out by executing subject of computer equipment.
Embodiment one
Refering to fig. 1, the step of showing the test method of the face identification system based on scene of embodiment of the present invention stream
Cheng Tu.The sequence for executing step is defined it is appreciated that the flow chart in this method embodiment is not used in.Below to calculate
Machine equipment is that executing subject carries out exemplary description.It is specific as follows.
Step S100 obtains test video, and the acquisition test video includes in the test video database of pre-acquired
Original video data, or pass through image collecting device obtain default scene under nominative testing video data.
Illustratively, the original video data in the test video database of the pre-acquired, by being connected to the network cloud
Storage, is downloaded multitude of video therein.These videos, some are personal self-timers；Some are that other people shoot, such as the parent of user
People, friend, colleague etc.；Also some are more people's videos；Also some are not personages, such as landscape, the scenic spots and historical sites.These videos
Have nothing in common with each other in shooting angle, shooting environmental (such as ambient light intensity, background), photographed scene etc., these with identical or
The shooting video of different photographed scene features can provide test video data source abundant for tester's face identifying system.
Illustratively, the nominative testing video data under the default scene, for example, being supervised by automobile data recorder or road
Control face scene video in collecting vehicle；Pass through cell or market monitoring collection pedestrian's face scene video etc..
Step S102 obtains N number of picture including face feature from the test video.
Specifically, as shown in Fig. 2, the step S102 may further include:
The test video sub-frame processing is obtained multiple pictures by step S102a, carries out face knowledge to the multiple picture
Not, to judge whether in each picture include face feature.The face feature may include: forehead provincial characteristics, eye
Provincial characteristics, nasal area feature, mouth region feature and/or ear region；
Step S102b will not include that the picture of the face feature is defined as invalid picture；
Step S102c rejects the invalid picture from the multiple picture, obtains described N number of including face feature
Picture.
Step S104 obtains the corresponding multiple pictures of multiple classification scenes according to N number of picture including face feature
Set, each picture set include multiple pictures under corresponding classification scene.
Specifically, as shown in figure 3, the step S104 may further include:
Step S104a is sampled N number of picture including face feature, obtains multiple samples pictures set；
Step S104b selects one of samples pictures set from the multiple samples pictures set；
Step S104c extracts the image scene feature of each picture in the samples pictures set selected, Yi Jigen
According to the image scene feature of each picture in the samples pictures set selected, it is not chosen by the extraction of incremental learning method
The image scene feature of each picture in each samples pictures set in multiple samples pictures set selected, to obtain N number of packet
Include the picture scene characteristic of the picture of face feature.
Illustratively, a function T (X) is constructed, by inputting any one facial image Ii, export a dimension and be lower than
IiVector fi, i.e. fi=T (Ii)。
Specifically, the step S104c may further include:
Step 1, it is assumed that a shared n image x in the samples pictures set selected1, x2..., xn；
Step 2, a part of picture is first extracted from n image, is denoted as x1, x2..., xm, m < n calculates this m picture
Mean valueAnd covariance matrix
Step 3, a part of picture is extracted again from N number of picture including face feature, be denoted as xm+1, xm+2..., xm+p, together
Reason, the mean value of this p picture are xp, covariance matrix is Σ p, and calculates this m+p picture x1, x2..., xm, xm+1,
xm+2..., xm+pCovariance matrix are as follows:
Step 4, part figure piece is extracted constantly from N number of picture including face feature, until N number of including face feature
Until all pictures in picture have all extracted, final calculated covariance matrix is exactly the covariance calculated in PCA method
Matrix
It should be strongly noted that T (X) can be selected according to user in feature extraction, by taking PCA as an example,
To covariance matrixFeature decomposition is carried out, is obtained: Σ=P Λ PT, for each picture xi,
Feature is exactlyI.e.When gradually extracting image scene feature by incremental learning method, for
I-th (1≤i≤n) a image Ii, provide a vector fi, and fiDimension be less than IiDimension.
Step S104d, according to the image scene feature of N number of picture including face feature, being based on clustering algorithm will
N number of picture including face feature is divided into the corresponding multiple picture set of the multiple classification scene, each picture position
In one or more picture set.
Specifically, N number of image scene feature obtained is divided into M picture set by clustering methodology, i.e. M poly-
Class, the corresponding cluster of each image scene feature, can identify cluster corresponding to image scene feature, example with class label
Such as the corresponding class label L of a image scene feature of i-th (1≤i≤n)i, LiValue range from 1 to M.
It should be noted that the embodiment of the present invention is handled feature by clustering methodology, according to N number of including face
N number of picture including face feature is divided M picture set, thus by similar by the image scene feature of the picture of feature
The picture of image scene feature is brought together, the corresponding cluster of a picture set.After end of clustering, i-th (1≤i≤n)
The feature of a image scene obtains a class label Li, LiValue range be 1 to arrive M, M cluster centre be respectivelyData in each cluster are closely gathered in around its cluster centre.When being searched, only
It needs for images to be recognized scene characteristic to be first compared with M cluster centre, finds that nearest cluster centre of distance, in
It is that images to be recognized scene characteristic may belong to the cluster, is then further matched in the cluster, so that it may obtain
Matching result finally is obtained, to reduce the time searched in the database.
It should be noted that in N number of picture including face feature the corresponding image information of each picture (such as
The archive information etc. for the people that the image is showed), image scene feature and class label record can be recorded in database.
Step S106 receives user for the selection instruction of the target scene in the multiple classification scene.
The target scene can be the combination of one of scene or several scenes in existing scene classification.
Illustratively, the target scene can be selected according to actual scene locating for face identification system to be tested,
Or the scene instruction of user preset is received to select by input interface.
Illustratively, the discrimination of examining system under relatively low, can choose light in the scene Recognition rate of dark
The corresponding Target Photo set of darker scene, or the combine scenes of dark and posture are selected to filter out pictures
It closes.The scene includes but is not limited to following several: 1. faces do not have face camera, and 2. photo environments are excessively dark or excessively black,
3. having wearing black surround glasses or sunglasses to take pictures, it includes multiple in 5. cameras that 4. hairs, which have, which obviously covers eyes or face mask,
The test of the scenes such as face.Wherein combine scenes may is that photo environment is excessively dark and face does not have face camera；In camera
Comprising multiple faces and hair has and obviously covers eyes or face mask；Face does not have face camera, and angle has inclination etc..
Step S108 selects Target Photo set corresponding with the target scene from the multiple picture set.
Illustratively, by the feature of the target scene, the cluster centre of multiple clusters corresponding with multiple picture set
It is compared, determines the classification of cluster belonging to the feature of target scene, selected according to the scene characteristic classification of target scene
Corresponding picture set.
It specifically operates and includes:
The first step extracts any one pair picture I to be matchedtFeature ft。
For example, the picture I to be matched for any one pairt, substitute into function T (x) and obtain its feature ft=T (It)。
Second step, the feature f calculated according to the first steptAnd M cluster centre in database, use arest neighbors rule
Determine the class label L of picture to be matchedt。
For example, calculating f using following formulatWith the difference d of each cluster centrei:
Wherein, i=1,2 ..., M.
Obtain M difference d1, d2..., dMAfterwards, d is determined1, d2..., dMIn minimum value, it is corresponding poly- to find out the minimum value
Class, it is assumed that k is designated as under the minimum value, then image to be matched ItJust belong to k-th of cluster, it is assumed that the classification of this k-th cluster
Label is Lt。
That is, the image scene feature of picture to be matched is matched with each image scene feature in k-th of cluster,
Corresponding cluster centre is found, to determine the classification of cluster belonging to the feature of target scene.
Step S110, by Target Photo set synthetic video stream.
Illustratively, all pictures in Target Photo set are synthesized by video flowing according to predefined test script.
The test script includes but is not limited to: the sequence such as uploading pictures time sequencing, sequence of picture pixels size is arranged.
The video flowing is input in face identification system by step S112, with by the video flowing to recognition of face
System carries out system test operation.
Illustratively, specific testing process can be such that
By the multiframe picture composition detection collection or query set in the video flowing, for inputing to face identification system；It is logical
The stock collection or object set for crossing the image composition of the people of known identities, by the every frame picture and stock collection or mesh in the video flowing
Every of mark collection prestores picture and compares, and to export comparing result, judges the face identification system according to comparing result
Discrimination.
Illustratively, the video stream data that the Target Photo set chosen synthesizes is input in face identification system, with
This can thus bypass In vivo detection come the video data for replacing camera to get, and test man does not have to simulate various complexity
Special screne, if test man is just not for example, face identification system is in the strong environment of darker environment or light
It is come out with the strong test environment of dark test environment or light is simulated respectively, can directly carry out face identification system
Test.
Embodiment two
Fig. 4 is that the present invention is based on the program module schematic diagrames of the test macro embodiment two of the face identification system of scene.
Test macro 20 may include or be divided into one or more program modules, one or more program module, which is stored in, deposits
In storage media, and as performed by one or more processors, to complete the present invention, and it can realize that the above-mentioned face based on scene is known
The test method of other system.The so-called program module of the embodiment of the present invention is the series of computation machine for referring to complete specific function
Program instruction section, the implementation procedure than program itself more suitable for description Text Classification System 20 in storage medium.It retouches below
The function of each program module of the present embodiment will specifically be introduced by stating:
Module 200 is obtained, for obtaining test video.
Decomposing module 202, for the test video sub-frame processing to be obtained N number of picture including face feature.Example
Property, the decomposing module is also used to: the test video sub-frame processing is obtained multiple pictures；The multiple picture is carried out
Recognition of face, to judge whether in each picture include face feature, and the face feature includes: forehead provincial characteristics, eye
Portion's provincial characteristics, nasal area feature, mouth region feature and/or ear region；It will not include the picture of the face feature
It is defined as invalid picture；And the invalid picture is rejected from the multiple picture, obtain N number of figure including face feature
Piece.
Categorization module 204, for it is corresponding to obtain multiple classification scenes by N number of picture classification including face feature
Multiple picture set.Illustratively, the categorization module 204 is also used to: being carried out to N number of picture including face feature
Sampling, obtains multiple samples pictures set；One of samples pictures set is selected from the multiple samples pictures set；It mentions
The image scene feature for each picture in samples pictures set for taking this to be selected, and according to the sample graph selected
The image scene feature of each picture in piece set extracts non-selected multiple samples pictures set by incremental learning method
In each samples pictures set in each picture image scene feature, to obtain the figure of N number of picture including face feature
Piece scene characteristic；And the image scene feature according to N number of picture including face feature, clustering algorithm is based on by the N
A picture including face feature is divided into the corresponding multiple picture set of the multiple classification scene, and each picture is located at one
Or in multiple picture set.
Receiving module 206, for receiving user for the selection instruction of the target scene in the multiple classification scene.
Selecting module 208, for selecting Target Photo corresponding with the target scene from the multiple picture set
Set.
Synthesis module 210 is used for Target Photo set synthetic video stream.
Input module 212 carries out the survey of face identification system for the video flowing to be input in face identification system
Examination.
Embodiment three
It is the hardware structure schematic diagram of the computer equipment of the embodiment of the present invention three refering to Fig. 5.It is described in the present embodiment
Computer equipment 2 is that one kind can be automatic to carry out numerical value calculating and/or information processing according to the instruction for being previously set or storing
Equipment.The computer equipment 2 can be rack-mount server, blade server, tower server or Cabinet-type server
(including server cluster composed by independent server or multiple servers) etc..As shown, the computer equipment
2 include at least, but are not limited to, can be in communication with each other by system bus connection memory 21, processor 22, network interface 23, with
And test macro 20.
In the present embodiment, memory 21 includes at least a type of computer readable storage medium, the readable storage
Medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory etc.), random access storage device
(RAM), static random-access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory
(EEPROM), programmable read only memory (PROM), magnetic storage, disk, CD etc..In some embodiments, memory
21 can be the internal storage unit of computer equipment 2, such as the hard disk or memory of the computer equipment 2.In other implementations
In example, memory 21 is also possible to the grafting being equipped on the External memory equipment of computer equipment 2, such as the computer equipment 2
Formula hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card
(Flash Card) etc..Certainly, memory 21 can also both including computer equipment 2 internal storage unit and also including outside it
Store equipment.In the present embodiment, memory 21 is installed on the operating system and types of applications of computer equipment 2 commonly used in storage
Software, for example, embodiment two the face identification system based on scene test macro 20 program code etc..In addition, memory
21 can be also used for temporarily storing the Various types of data that has exported or will export.
Processor 22 can be in some embodiments central processing unit (Central Processing Unit, CPU),
Controller, microcontroller, microprocessor or other data processing chips.The processor 22 is commonly used in control computer equipment 2
Overall operation.In the present embodiment, program code or processing data of the processor 22 for being stored in run memory 21, example
Test macro 20 as run the face identification system based on scene, to realize the recognition of face system based on scene of embodiment one
The test method of system.
The network interface 23 may include radio network interface or wired network interface, which is commonly used in
Communication connection is established between the computer equipment 2 and other electronic devices.For example, the network interface 23 is for passing through network
The computer equipment 2 is connected with exterior terminal, establishes data transmission between the computer equipment 2 and exterior terminal
Channel and communication connection etc..The network can be intranet (Intranet), internet (Internet), whole world movement
Communication system (Global System of Mobile communication, GSM), wideband code division multiple access (Wideband
Code Division Multiple Access, WCDMA), 4G network, 5G network, bluetooth (Bluetooth), the nothings such as Wi-Fi
Line or cable network.
It should be pointed out that Fig. 5 illustrates only the computer equipment 2 with component 20-23, it should be understood that simultaneously
All components shown realistic are not applied, the implementation that can be substituted is more or less component.
In the present embodiment, the test macro 20 for the face identification system based on scene being stored in memory 21 may be used also
To be divided into one or more program module, one or more of program modules are stored in memory 21, and
It is performed by one or more processors (the present embodiment is processor 22), to complete the present invention.
For example, Fig. 4 shows the test system of the face identification system of the realization based on scene of the embodiment of the present invention two
The program module schematic diagram of system, in the embodiment, the test macro 20 of the face identification system of the scene can be divided into
Obtain module 200, decomposing module 202, categorization module 204, receiving module 206, selecting module 208, synthesis module 210 and input
Module 212.Wherein, the so-called program module of the present invention is the series of computation machine program instruction for referring to complete specific function
Section, than program more suitable for describing the test 20 of the face identification system based on scene in the computer equipment 2
Implementation procedure.The concrete function of described program module 200-212 has had a detailed description in example 2, and details are not described herein.
Example IV
The present embodiment also provides a kind of computer readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory
(for example, SD or DX memory etc.), random access storage device (RAM), static random-access memory (SRAM), read-only memory
(ROM), electrically erasable programmable read-only memory (EEPROM), programmable read only memory (PROM), magnetic storage, magnetic
Disk, CD, server, App are stored thereon with computer program, phase are realized when program is executed by processor using store etc.
Answer function.The computer readable storage medium of the present embodiment is held for storing financial product data processing system 20 by processor
The test method of the face identification system based on scene of embodiment one is realized when row.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of test method of the face identification system based on scene, which is characterized in that the described method includes:
Test video is obtained, the test video that obtains includes the original video data in the test video database of pre-acquired,
Or the nominative testing video data under the default scene for passing through image collecting device acquisition；
N number of picture including face feature is obtained from the test video；
The corresponding multiple picture set of multiple classification scenes, each picture are obtained according to N number of picture including face feature
Set includes multiple pictures under corresponding classification scene；
User is received for the selection instruction of the target scene in the multiple classification scene；
Target Photo set corresponding with the target scene is selected from the multiple picture set；
By Target Photo set synthetic video stream；And
The video flowing is input in face identification system, to carry out system survey to face identification system by the video flowing
Examination operation.
2. the test method of the face identification system based on scene as described in claim 1, which is characterized in that obtain test view
The step of frequency includes:
Original video data according to multiple application scenarios of face identification system to be tested, from the test video database
It is middle to obtain video corresponding with multiple application scenarios as the test video.
3. the test method of the face identification system based on scene as described in claim 1, which is characterized in that from the test
N number of picture for including the steps that face feature is obtained in video, comprising:
The test video sub-frame processing is obtained into multiple pictures；
Recognition of face is carried out to the multiple picture, to judge whether in each picture include face feature, and the face is special
Sign includes: forehead provincial characteristics, ocular feature, nasal area feature, mouth region feature and/or ear region；
It will not include that the picture of the face feature is defined as invalid picture；And
The invalid picture is rejected from the multiple picture, obtains N number of picture including face feature.
4. the test method of the face identification system based on scene as described in claim 1, which is characterized in that according to the N
A picture for including the steps that face feature obtains the corresponding multiple picture set of multiple classification scenes, comprising:
N number of picture including face feature is sampled, multiple samples pictures set are obtained；
One of samples pictures set is selected from the multiple samples pictures set；
It extracts the image scene feature of each picture in the samples pictures set selected, and is selected according to described
The image scene feature of each picture in samples pictures set extracts non-selected multiple sample graphs by incremental learning method
The image scene feature of each picture in each samples pictures set in piece set, to obtain N number of figure including face feature
The picture scene characteristic of piece；And
It, will be described N number of including face based on clustering algorithm according to the image scene feature of N number of picture including face feature
The picture of feature is divided into the corresponding multiple picture set of the multiple classification scene, and each picture is located at one or more pictures
In set.
5. the test method of the face identification system based on scene as described in claim 1, which is characterized in that the multiple figure
Multiple scenes corresponding to piece set include: that angle tilt scene, dark scene, eye block scene, face mask
Block scene and/or plurality of human faces scene.
6. a kind of test macro of face identification system characterized by comprising
Module is obtained, for obtaining test video；
Decomposing module, for the test video sub-frame processing to be obtained N number of picture including face feature；
Categorization module, for obtaining the corresponding multiple figures of multiple classification scenes for N number of picture classification including face feature
Piece set；
Receiving module, for receiving user for the selection instruction of the target scene in the multiple classification scene；
Selecting module, for selecting Target Photo set corresponding with the target scene from the multiple picture set；
Synthesis module is used for Target Photo set synthetic video stream；And
Input module carries out the test of face identification system for the video flowing to be input in face identification system.
7. the test macro of face identification system as claimed in claim 6, which is characterized in that the acquisition module is also used to:
The test video sub-frame processing is obtained into multiple pictures；
Recognition of face is carried out to the multiple picture, to judge whether in each picture include face feature, and the face is special
Sign includes: forehead provincial characteristics, ocular feature, nasal area feature, mouth region feature and/or ear region；
It will not include that the picture of the face feature is defined as invalid picture；And
The invalid picture is rejected from the multiple picture, obtains N number of picture including face feature.
8. the test macro of face identification system as claimed in claim 6, which is characterized in that the categorization module is also used to:
N number of picture including face feature is sampled, multiple samples pictures set are obtained；
One of samples pictures set is selected from the multiple samples pictures set；
It extracts the image scene feature of each picture in the samples pictures set selected, and is selected according to described
The image scene feature of each picture in samples pictures set extracts non-selected multiple sample graphs by incremental learning method
The image scene feature of each picture in each samples pictures set in piece set, to obtain N number of figure including face feature
The picture scene characteristic of piece；And
It, will be described N number of including face based on clustering algorithm according to the image scene feature of N number of picture including face feature
The picture of feature is divided into the corresponding multiple picture set of the multiple classification scene, and each picture is located at one or more pictures
In set.
9. a kind of computer equipment, the computer equipment, the computer equipment includes memory, processor and is stored in institute
State the computer program that can be run on memory and on the processor, which is characterized in that the computer program is processed
The step of the test method of the face identification system based on scene as described in any one of claims 1 to 5 is realized when device executes
Suddenly.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer in the computer readable storage medium
Program, the computer program can be performed by least one processors, so that at least one described processor executes such as right
It is required that the step of test method of face identification system described in any one of 1 to 5 based on scene.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910305396.3A CN110162462A (en) | 2019-04-16 | 2019-04-16 | Test method, system and the computer equipment of face identification system based on scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910305396.3A CN110162462A (en) | 2019-04-16 | 2019-04-16 | Test method, system and the computer equipment of face identification system based on scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110162462A true CN110162462A (en) | 2019-08-23 |
Family
ID=67639622
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910305396.3A Pending CN110162462A (en) | 2019-04-16 | 2019-04-16 | Test method, system and the computer equipment of face identification system based on scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110162462A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110618943A (en) * | 2019-09-20 | 2019-12-27 | 重庆紫光华山智安科技有限公司 | Security service test method and device, electronic equipment and readable storage medium |
| CN110705651A (en) * | 2019-10-17 | 2020-01-17 | 上海眼控科技股份有限公司 | Method, device, equipment and medium for testing video identification accuracy |
| CN110781809A (en) * | 2019-10-23 | 2020-02-11 | 杭州宇泛智能科技有限公司 | Identification method and device based on registration feature update and electronic equipment |
| CN111241945A (en) * | 2019-12-31 | 2020-06-05 | 杭州艾芯智能科技有限公司 | Method and device for testing face recognition performance, computer equipment and storage medium |
| CN111339811A (en) * | 2019-08-27 | 2020-06-26 | 杭州海康威视系统技术有限公司 | Image processing method, device, equipment and storage medium |
| CN112084902A (en) * | 2020-08-26 | 2020-12-15 | 武汉普利商用机器有限公司 | Face image acquisition method and device, electronic equipment and storage medium |
| CN113495833A (en) * | 2020-04-03 | 2021-10-12 | 杭州海康威视系统技术有限公司 | Software testing method, device and system based on video event and readable storage medium |
| WO2021212725A1 (en) * | 2020-04-21 | 2021-10-28 | 烽火通信科技股份有限公司 | Method and apparatus for evaluating performance of facial recognition algorithm |
| CN115601799A (en) * | 2022-09-09 | 2023-01-13 | 广州市盛通建设工程质量检测有限公司（Cn） | Evaluation method, system, equipment and storage medium based on face recognition |
| CN115633321A (en) * | 2022-12-05 | 2023-01-20 | 北京数字众智科技有限公司 | Wireless communication network monitoring method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103136533A (en) * | 2011-11-28 | 2013-06-05 | 汉王科技股份有限公司 | Face recognition method and device based on dynamic threshold value |
| CN103605993A (en) * | 2013-12-04 | 2014-02-26 | 康江科技(北京)有限责任公司 | Image-to-video face identification method based on distinguish analysis oriented to scenes |
-
2019
- 2019-04-16 CN CN201910305396.3A patent/CN110162462A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103136533A (en) * | 2011-11-28 | 2013-06-05 | 汉王科技股份有限公司 | Face recognition method and device based on dynamic threshold value |
| CN103605993A (en) * | 2013-12-04 | 2014-02-26 | 康江科技(北京)有限责任公司 | Image-to-video face identification method based on distinguish analysis oriented to scenes |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111339811A (en) * | 2019-08-27 | 2020-06-26 | 杭州海康威视系统技术有限公司 | Image processing method, device, equipment and storage medium |
| CN111339811B (en) * | 2019-08-27 | 2024-02-20 | 杭州海康威视系统技术有限公司 | Image processing method, device, equipment and storage medium |
| CN110618943B (en) * | 2019-09-20 | 2022-08-19 | 重庆紫光华山智安科技有限公司 | Security service test method and device, electronic equipment and readable storage medium |
| CN110618943A (en) * | 2019-09-20 | 2019-12-27 | 重庆紫光华山智安科技有限公司 | Security service test method and device, electronic equipment and readable storage medium |
| CN110705651A (en) * | 2019-10-17 | 2020-01-17 | 上海眼控科技股份有限公司 | Method, device, equipment and medium for testing video identification accuracy |
| CN110781809A (en) * | 2019-10-23 | 2020-02-11 | 杭州宇泛智能科技有限公司 | Identification method and device based on registration feature update and electronic equipment |
| CN111241945A (en) * | 2019-12-31 | 2020-06-05 | 杭州艾芯智能科技有限公司 | Method and device for testing face recognition performance, computer equipment and storage medium |
| CN113495833A (en) * | 2020-04-03 | 2021-10-12 | 杭州海康威视系统技术有限公司 | Software testing method, device and system based on video event and readable storage medium |
| CN113495833B (en) * | 2020-04-03 | 2024-02-23 | 杭州海康威视系统技术有限公司 | Software testing method, device and system based on video event and storage medium |
| WO2021212725A1 (en) * | 2020-04-21 | 2021-10-28 | 烽火通信科技股份有限公司 | Method and apparatus for evaluating performance of facial recognition algorithm |
| CN112084902A (en) * | 2020-08-26 | 2020-12-15 | 武汉普利商用机器有限公司 | Face image acquisition method and device, electronic equipment and storage medium |
| CN112084902B (en) * | 2020-08-26 | 2024-05-14 | 武汉普利商用机器有限公司 | Face image acquisition method and device, electronic equipment and storage medium |
| CN115601799A (en) * | 2022-09-09 | 2023-01-13 | 广州市盛通建设工程质量检测有限公司（Cn） | Evaluation method, system, equipment and storage medium based on face recognition |
| CN115633321A (en) * | 2022-12-05 | 2023-01-20 | 北京数字众智科技有限公司 | Wireless communication network monitoring method and system |
| CN115633321B (en) * | 2022-12-05 | 2023-05-05 | 北京数字众智科技有限公司 | Wireless communication network monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110162462A (en) | Test method, system and the computer equipment of face identification system based on scene | |
| Huh et al. | Fighting fake news: Image splice detection via learned self-consistency | |
| Matern et al. | Exploiting visual artifacts to expose deepfakes and face manipulations | |
| CN109697416B (en) | Video data processing method and related device | |
| CN112215180B (en) | Living body detection method and device | |
| CN110210276A (en) | A kind of motion track acquisition methods and its equipment, storage medium, terminal | |
| CN112801057B (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN111046956A (en) | Occlusion image detection method and device, electronic equipment and storage medium | |
| CN111444744A (en) | Living body detection method, living body detection device, and storage medium | |
| Almeida et al. | Detecting face presentation attacks in mobile devices with a patch-based CNN and a sensor-aware loss function | |
| CN111598132B (en) | Portrait recognition algorithm performance evaluation method and device | |
| CN111680675B (en) | Face living body detection method, system, device, computer equipment and storage medium | |
| CN111914812A (en) | Image processing model training method, device, equipment and storage medium | |
| CN111738349B (en) | Detection effect evaluation method and device of target detection algorithm, storage medium and equipment | |
| CN113269091A (en) | Personnel trajectory analysis method, equipment and medium for intelligent park | |
| CN112633255A (en) | Target detection method, device and equipment | |
| CN115049675A (en) | Generation area determination and light spot generation method, apparatus, medium, and program product | |
| CN114565955A (en) | Face attribute recognition model training and community personnel monitoring method, device and equipment | |
| CN111597944B (en) | Living body detection method, living body detection device, computer equipment and storage medium | |
| CN113450297A (en) | Fusion model construction method and system for infrared image and visible light image | |
| CN113723310B (en) | Image recognition method and related device based on neural network | |
| CN116246200A (en) | Screen display information candid photographing detection method and system based on visual identification | |
| Kaur et al. | Deep learning: survey of environmental and camera impacts on internet of things images | |
| CN114998962A (en) | Living body detection and model training method and device | |
| CN114842411A (en) | Group behavior identification method based on complementary space-time information modeling |
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 |