CN107944344A - Power supply enterprise's construction mobile security supervision platform - Google Patents
Power supply enterprise's construction mobile security supervision platform Download PDFInfo
- Publication number
- CN107944344A CN107944344A CN201711032274.9A CN201711032274A CN107944344A CN 107944344 A CN107944344 A CN 107944344A CN 201711032274 A CN201711032274 A CN 201711032274A CN 107944344 A CN107944344 A CN 107944344A
- Authority
- CN
- China
- Prior art keywords
- msub
- mrow
- mtd
- mtr
- mover
- 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
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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/20—Individual registration on entry or exit involving the use of a pass
- G07C9/22—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder
- G07C9/25—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition
Abstract
The present invention discloses a kind of power supply enterprise's construction mobile security supervision platform, cloud platform including intelligent mobile terminal and with intelligent mobile terminal communication connection, the cloud platform is equipped with the face sample unit of the facial image of storage power supply enterprise on-site personnel and the personnel safety access unit of personnel's access information is sent to intelligent terminal, the intelligent mobile terminal is equipped with face recognition module, the face recognition module is used to identify whether the access facial image sent with personnel safety access unit matches the personnel for entering scene, to determine whether to allow the personnel to enter scene.The present invention further strengthens construction site safety supervision management and control dynamics, standard construction operation, guarantees personal safety using state-of-the-art technologies such as 4G wireless networks, intelligent mobile terminal, cloud computing, recognitions of face.
Description
Technical field
The present invention relates to power construction safety supervision technical field, specifically for entering the personnel of construction site into pedestrian
Face identifies.
Background technology
In recent years, in management of power supply enterprise's pay attention to day by day to external coordination personnel's identity, to avoid external coordination personnel
Security risk caused by frequently replacing, mainly using following several ways:
1st, Quick Response Code:By Quick Response Code and photo unique mark external coordination personnel, when checking, by scanning the two-dimensional code
Identification is carried out, it is low there are efficiency, the problems such as easily forgery.
2nd, passive RFID technology:By passive RFID card come unique mark external coordination personnel, when checking, by hand-held
The non-contact scanning of terminal carries out identification, and efficiency is higher, but blocks inconsistent situation there may be people, and needs handheld terminal
With rfid read functions.
3rd, active RFID technology:External coordination personnel is uniquely indicated by active RFID, check when, can at a distance,
Identity is identified in batch, efficient, but active rfid cards and end of scan cost are higher.
4th, fingerprint identification technology:Identification is carried out to external coordination personnel based on fingerprint recognition, it is efficient, but need to hold
Fingerprint identification module is separately configured in terminal.
Currently, face recognition products be widely used to finance, the administration of justice, army, public security, frontier inspection, government, space flight, electric power,
The fields such as factory, education, medical treatment and numerous enterprises and institutions.Therefore, face recognition technology is promoted the use of into power supply enterprise, it is right
The management of external coordination personnel's identity, has realistic meaning.
Face identification system extracts the face for inputting either statically or dynamically image, so that it is determined that the body of people by recognizer
Part, it is with a wide range of applications.Typical automatic human face recognition system (Face RecognitionSystem, FRS) is general
It is made of following basic link:Pre-process link, Face datection link, feature extraction step and Classification and Identification link:
1st, pretreatment input facial image.Wherein preprocess method is returned including image filtering, region segmentation, gray scale and scale
One change, face alignment, histogram equalization and local binary pattern etc..
2nd, whether face is included to image detection after pretreatmentization, from background separation and determines face if detecting
Its quantity, position and size.According to the difference of the mode of extraction detection feature, existing method for detecting human face can be roughly divided into three
Class:Method for detecting human face based on statistical learning, Knowledge based engineering method for detecting human face and the Face datection based on stencil matching
Method, the former becomes popular method for detecting human face because of its adaptability and stability.
3rd, extract the feature that face essence is represented in facial image to be identified, and require extracted feature expression, block,
There is preferable robustness under the conditions of visual angle and illumination etc..The common method of face characteristic extraction mainly includes based on geometric space
Face feature extraction method, the face feature extraction method based on subspace, the face feature extraction method based on neutral net,
Face feature extraction method based on elastic graph matching and the face feature extraction method based on recessive Markov.
4th, face characteristic to be identified is compared with the feature of known face in database, matching draws recognition result.Often
Grader has the grader based on arest neighbors, the grader based on support vector machines, grader based on neutral net etc..
Current face's recognizer is high to shooting environmental, angle requirement, and recognition efficiency is low, using construction tube at the scene
There are larger technical difficulty in reason.
The content of the invention
The technical problems to be solved by the invention are, high to shooting environmental, angle requirement for current face's recognizer,
Recognition efficiency is low, there is provided a kind of power supply enterprise's construction mobile security supervision platform, improves the accurate of complex environment human face identification
Rate and efficiency.
In order to solve the above technical problems, the present invention adopts the following technical scheme that:Power supply enterprise's construction mobile security supervision is flat
Platform, including intelligent mobile terminal and the cloud platform with intelligent mobile terminal communication connection, the cloud platform are equipped with storage and power
The face sample unit of the facial image of enterprise's on-site personnel and the personnel that personnel's access information is sent to intelligent terminal
Safety permission unit, the intelligent mobile terminal are equipped with face recognition module, and the face recognition module is used to identify and enters now
Whether the access facial image sent with personnel safety access unit matches the personnel of field, to determine whether to allow the personnel to enter
Scene;Wherein, the method for face recognition module progress recognition of face includes the following steps,
Step 1, according to face training sample, constructs super complete dictionary
Step 2, by test image sequentially vector x arranged in columns;
Step 3, according to super complete dictionary ψ design calculation matrix Φ;
Step 4, x projects to obtain measure vectorial y under Φ, and tries to achieve
Step 5, by what is tried to achieveSubstitution formula
So as to try to achieve the differentiation result of input test sample.
Preferably, in step 1, it is assumed that have the different face of K classes, every width training facial image sequentially pulls into what N × 1 was tieed up
Column vector ψ, and l is carried out respectively2Norm normalized, i.e. ψ ∈ RN×1And | | ψ | |2=1, an atom is denoted as, from every class people
L different training samples are all selected to form such face sample matrix by row in face training sampleI=1,2 ..., K, obtains the training sample sum n=KL of selection, these matrixes is pressed
Sequence is merged into super complete dictionary:
Preferably, to the test face sample arbitrarily inputted, it is sequentially pulled into column vector x ∈ RN×1, then x is in dictionary Ψ
Under be expressed as:
X=Ψ α+z (4.2)
Wherein α ∈ Rn×1For rarefaction representation vector, z ∈ RN×1It is to represent error.
Preferably, it is theoretical based on CS, test sample x is compressed projection and obtains projection vector y ∈ RM×1(M < N), i.e.,
Y=Φ x=Φ Ψ α+Φ z=D α+e (4.3)
Wherein Φ ∈ RM×NFor the designed calculation matrix with certain property, D=Φ Ψ ∈ RM×nRepresent equivalent word
Allusion quotation, e=Φ z ∈ RM×1For projection domain error, definitionTo any i, αi∈RL×1, so that by formula
(4.3) it is restated as:
Y=Φ (ψ1α1+ψ2α2+…+ψkαk)+e (4.4)。
Preferably, for some i, D is madei=Φ Ψi∈RM×L, formula (4.5) cost function is converted into:
If DiSingular value decomposition be shown below:
WhereinFormula (4.8) is substituted into (4.7), is obtained
Order
WhereinWithSize beFormula (4.9) expands into:
Section 2 and α on the right of above formula equal signiIt is unrelated, therefore work as
When, formula (4.10) is minimized, and at this time, the solution of formula (4.5) is:
Wherein Vi、∑iWithTried to achieve respectively by calculation matrix, dictionary and input test sample projection value,For arbitrary dimension
ForVector.
Preferably, i is tried to achieve all from 1 traversal to KAfterwards, test sample classification can be tried to achieve by formula (4.6)
Preferably, according to the test sample for differentiating result reconstruct inputSo as to which reconstructed image is tried to achieve in permutatation.
Preferably, for the personnel for needing to enter scene temporarily, the personnel safety access unit is to intelligent mobile terminal
Interim access license is sent, and sets interim access number in 1 year and is not to be exceeded 2 times.
Preferably, for needing to cancel the personnel of access qualification, the personnel safety access unit is to intelligent mobile terminal
Send the information for cancelling access.
The present invention is further added using state-of-the-art technologies such as 4G wireless networks, intelligent mobile terminal, cloud computing, recognitions of face
Strong construction site safety supervision management and control dynamics, standard construction operation, guarantees personal safety.
Recognition of face to field operation construction personnel, administrative staff is realized by face recognition technology, is on the one hand passed through
Calculation matrix projects, and reduces the data of transmission and calculating, improves computational efficiency, reduce storage consumption, on the other hand, can
Improve the accuracy rate and efficiency of complex environment human face identification.
Embodiment
The present invention solves the problem of current face's recognizer is high to shooting environmental, angle requirement, and recognition efficiency is low, improves
The accuracy rate and efficiency of complex environment human face identification, realize the recognition of face to field operation construction personnel, administrative staff.From
And prevent that external coordination construction personnel from arbitrarily changing, prevent the external coordination construction personnel that there is serious historical record violating the regulations from carrying out live work
Industry, function verify construction personnel's condition of going on duty, prevent the situation generation that " work director, security official " does not arrive scene.
Power supply enterprise construction mobile security supervision platform, including intelligent mobile terminal and with intelligent mobile terminal communicate connect
The cloud platform connect, the cloud platform be equipped with the facial image of storage power supply enterprise on-site personnel face sample unit and
The personnel safety access unit of personnel's access information is sent to intelligent terminal, the intelligent mobile terminal is equipped with recognition of face mould
Block, the face recognition module be used for identify enter scene personnel whether with personnel safety access unit send access face
Images match, to determine whether to allow the personnel to enter scene.
Wherein, (3) personnel safety access:Safety is participated in all Manufacturing Workers for being engaged in the work of power generation relevant speciality
Safety code is general examines by grade of skill evaluation examination and outsourcing unit key post personnel (work ticket signed by, work director)
Afterwards, by project organization unit by the Message Entry System for the personnel of passing the examination, pedestrian's face of going forward side by side collection.
(4) temporary staff's access:Need temporarily into the outsourcing unit of construction operation in company's production and operation region, by work
Journey organization unit is by outsourcing unit company information, engineering project information input system, engineered tissue unit or equipment operation management
Unit carries out safety examination to its operating personnel, by the interim access of key post personal information, input system, system after passing the examination
Make temporary construction operation licence IC card, interim access number is not to be exceeded 2 times in same work director 1 year.
(5) personnel's access dynamic adjusts:With reference to Manufacturing Worker, the site safety situation of outsourcing working unit director, day
Often situation violating the regulations etc., is adjusted its Safety skill grade, or even cancels access qualification.
For the personnel for needing to enter scene temporarily, the personnel safety access unit sends interim to intelligent mobile terminal
Access is permitted, and is set interim access number in 1 year and be not to be exceeded 2 times.Personnel for needing cancellation access qualification, it is described
Personnel safety access unit sends the information for cancelling access to intelligent mobile terminal.
Super complete dictionary is formed based on the face recognition algorithms of compressed sensing with identified good face training sample.
Assuming that there is the different face of K classes, every width training facial image sequentially pulls into the column vector ψ that N × 1 is tieed up, and carries out l respectively2Norm
Normalized, i.e. ψ ∈ RN×1And | | ψ | |2=1, it is denoted as an atom.L difference is all selected from every class face training sample
Training sample forms such face sample matrix by rowI=1,2 ..., K.It can obtain
The training sample sum n=KL of selection.These matrixes are sequentially merged into super complete dictionary:
To the test face sample arbitrarily inputted, it is sequentially pulled into column vector x ∈ RN×1, then x can be with table under dictionary Ψ
It is shown as:
X=Ψ α+z (4.2)
Wherein α ∈ Rn×1For rarefaction representation vector, z ∈ RN×1It is to represent error.It is theoretical based on CS, test sample x is carried out
Compression projection obtains projection vector y ∈ RM×1(M < N), i.e.,
Y=Φ x=Φ Ψ α+Φ z=D α+e (4.3)
Wherein Φ ∈ RM×NFor the designed calculation matrix with certain property, D=Φ Ψ ∈ RM×nRepresent equivalent word
Allusion quotation, e=Φ z ∈ RM×1For projection domain error.DefinitionTo any i, αi∈RL×1, so that by formula
(4.3) it is restated as:
Y=Φ (ψ1α1+ψ2α2+…+ψkαk)+e (4.4)
Theoretical according to CS, in the ideal case, nonzero term is present in a certain α in rarefaction representation vector αiIn, and other
It is zero.Therefore, α will be solved to be converted into:
Try to achieve { αiAfter, recognition of face classification is used it for, forms following problem:
Try to achieveThat is the differentiation result of input test sample x.
In the case of given calculation matrix Φ, the difficult point of the above problem is how accurately to solve formula (4.5).For
Some i, makes Di=Φ Ψi∈RM×L, formula (4.5) cost function is converted into:
If DiSingular value decomposition (Singular Value Decomposition, SVD) it is as follows:
WhereinFormula (4.8) is substituted into (4.7), is obtained
Order
WhereinWithSize beFormula (4.9) can expand into:
It can be seen that Section 2 and α on the right of above formula equal signiIt is unrelated, therefore work as
Up-to-date style (4.10) is minimized.At this time, the solution of formula (4.5) is:
Wherein Vi、∑iWithTried to achieve respectively by calculation matrix, dictionary and input test sample projection value,For arbitrary dimension
ForVector.
By i from 1 traversal to K, try to achieve allAfterwards, test sample classification can be tried to achieve by formula (4.6)According to need
Asking can also be according to the test sample for differentiating result reconstruct inputSo as to which reconstructed image is tried to achieve in permutatation.
Generally speaking, the face recognition algorithms based on compressed sensing, are on the one hand projected by calculation matrix, make transmission and meter
The data of calculation are reduced, and are improved computational efficiency, are reduced storage consumption;On the other hand, the accuracy rate of recognition of face can be improved.
Claims (9)
1. power supply enterprise's construction mobile security supervision platform, it is characterised in that including intelligent mobile terminal and and intelligent mobile
The cloud platform of terminal called connection, the cloud platform are equipped with the face sample of the facial image of storage power supply enterprise on-site personnel
This unit and the personnel safety access unit that personnel's access information is sent to intelligent terminal, the intelligent mobile terminal are equipped with people
Face identification module, the face recognition module are used to identify what whether the personnel for entering scene sent with personnel safety access unit
Access facial image matches, to determine whether to allow the personnel to enter scene;Wherein, face recognition module carries out recognition of face
Method includes the following steps,
Step 1, according to face training sample, constructs super complete dictionary
Step 2, by test image sequentially vector x arranged in columns;
Step 3, according to super complete dictionary ψ design calculation matrix Φ;
Step 4, x projects to obtain measure vectorial y under Φ, and tries to achieve
Step 5, by what is tried to achieveSubstitution formula
So as to try to achieve the differentiation result of input test sample.
2. power supply enterprise's construction mobile security supervision platform according to claim 1, it is characterised in that false in step 1
Equipped with the different face of K classes, every width training facial image sequentially pulls into the column vector ψ that N × 1 is tieed up, and carries out l respectively2Norm is returned
One change is handled, i.e. ψ ∈ RN×1And | | ψ | |2=1, an atom is denoted as, L different instruction is all selected from every class face training sample
Practice sample and form such face sample matrix by rowObtain selection
These matrixes are sequentially merged into super complete dictionary by training sample sum n=KL:
3. power supply enterprise's construction mobile security supervision platform according to claim 2, it is characterised in that to what is arbitrarily inputted
Face sample is tested, it is sequentially pulled into column vector x ∈ RN×1, then x be expressed as under dictionary Ψ:
X=Ψ α+z (4.2)
Wherein α ∈ Rn×1For rarefaction representation vector, z ∈ RN×1It is to represent error.
4. power supply enterprise's construction mobile security supervision platform according to claim 3, it is characterised in that it is theoretical based on CS,
Test sample x is compressed projection and obtains projection vector y ∈ RM×1(M < N), i.e.,
Y=Φ x=Φ Ψ α+Φ z=D α+e (4.3)
Wherein Φ ∈ RM×NFor the designed calculation matrix with certain property, D=Φ Ψ ∈ RM×nRepresent equivalent dictionary, e=
Φz∈RM×1For projection domain error, definitionTo any i, αi∈RL×1, so that formula (4.3) is heavy
Newly it is expressed as:
Y=Φ (ψ1α1+ψ2α2+…+ψkαk)+e (4.4)。
5. power supply enterprise according to claim 4 construction mobile security supervision platform, it is characterised in that for some i,
Make Di=Φ Ψi∈RM×L, formula (4.5) cost function is converted into:
<mrow>
<mo>|</mo>
<mo>|</mo>
<mi>y</mi>
<mo>-</mo>
<msub>
<mi>D</mi>
<mi>i</mi>
</msub>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mo>|</mo>
<msubsup>
<mo>|</mo>
<mn>2</mn>
<mn>2</mn>
</msubsup>
<mo>=</mo>
<mi>&xi;</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4.7</mn>
<mo>)</mo>
</mrow>
</mrow>
If DiSingular value decomposition be shown below:
<mrow>
<msub>
<mi>D</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<msub>
<mi>U</mi>
<mi>I</mi>
</msub>
<mfenced open = "|" close = "|">
<mtable>
<mtr>
<mtd>
<msub>
<mi>&Sigma;</mi>
<mi>i</mi>
</msub>
</mtd>
<mtd>
<mn>0</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0</mn>
</mtd>
<mtd>
<mn>0</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
<msubsup>
<mi>V</mi>
<mi>i</mi>
<mi>T</mi>
</msubsup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4.8</mn>
<mo>)</mo>
</mrow>
</mrow>
WhereinFormula (4.8) is substituted into (4.7), is obtained
<mrow>
<mtable>
<mtr>
<mtd>
<mrow>
<mi>&xi;</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msubsup>
<mrow>
<mo>||</mo>
<mrow>
<mi>y</mi>
<mo>-</mo>
<msub>
<mi>U</mi>
<mi>i</mi>
</msub>
<mfenced open = "|" close = "|">
<mtable>
<mtr>
<mtd>
<msub>
<mo>&Sigma;</mo>
<mi>i</mi>
</msub>
</mtd>
<mtd>
<mn>0</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0</mn>
</mtd>
<mtd>
<mn>0</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
<msubsup>
<mi>V</mi>
<mi>i</mi>
<mi>T</mi>
</msubsup>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
</mrow>
<mo>||</mo>
</mrow>
<mn>2</mn>
<mn>2</mn>
</msubsup>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>=</mo>
<msubsup>
<mrow>
<mo>||</mo>
<mrow>
<msubsup>
<mi>U</mi>
<mi>i</mi>
<mi>T</mi>
</msubsup>
<mi>y</mi>
<mo>-</mo>
<mfenced open = "|" close = "|">
<mtable>
<mtr>
<mtd>
<msub>
<mo>&Sigma;</mo>
<mi>i</mi>
</msub>
</mtd>
<mtd>
<mn>0</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0</mn>
</mtd>
<mtd>
<mn>0</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
<msubsup>
<mi>V</mi>
<mi>i</mi>
<mi>T</mi>
</msubsup>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
</mrow>
<mo>||</mo>
</mrow>
<mn>2</mn>
<mn>2</mn>
</msubsup>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>=</mo>
<msubsup>
<mrow>
<mo>||</mo>
<mrow>
<mover>
<mi>y</mi>
<mo>~</mo>
</mover>
<mo>-</mo>
<mfenced open = "|" close = "|">
<mtable>
<mtr>
<mtd>
<msub>
<mo>&Sigma;</mo>
<mi>i</mi>
</msub>
</mtd>
<mtd>
<mn>0</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0</mn>
</mtd>
<mtd>
<mn>0</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
<mover>
<mi>&alpha;</mi>
<mo>~</mo>
</mover>
</mrow>
<mo>||</mo>
</mrow>
<mn>2</mn>
<mn>2</mn>
</msubsup>
</mrow>
</mtd>
</mtr>
</mtable>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4.9</mn>
<mo>)</mo>
</mrow>
</mrow>
Order
<mrow>
<mover>
<mi>y</mi>
<mo>~</mo>
</mover>
<mo>=</mo>
<mfenced open = "|" close = "|">
<mtable>
<mtr>
<mtd>
<msub>
<mover>
<mi>y</mi>
<mo>~</mo>
</mover>
<mn>1</mn>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mover>
<mi>y</mi>
<mo>~</mo>
</mover>
<mn>2</mn>
</msub>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>,</mo>
<mover>
<mi>&alpha;</mi>
<mo>~</mo>
</mover>
<mo>=</mo>
<mfenced open = "|" close = "|">
<mtable>
<mtr>
<mtd>
<msub>
<mover>
<mi>&alpha;</mi>
<mo>~</mo>
</mover>
<mn>1</mn>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mover>
<mi>a</mi>
<mo>~</mo>
</mover>
<mn>2</mn>
</msub>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
WhereinWithSize beFormula (4.9) expands into:
<mrow>
<mi>&xi;</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mo>|</mo>
<mo>|</mo>
<msub>
<mover>
<mi>y</mi>
<mo>~</mo>
</mover>
<mi>i</mi>
</msub>
<mo>-</mo>
<msub>
<mi>&Sigma;</mi>
<mi>i</mi>
</msub>
<msub>
<mover>
<mi>&alpha;</mi>
<mo>~</mo>
</mover>
<mi>i</mi>
</msub>
<mo>|</mo>
<msubsup>
<mo>|</mo>
<mn>2</mn>
<mn>2</mn>
</msubsup>
<mo>+</mo>
<mo>|</mo>
<mo>|</mo>
<msub>
<mover>
<mi>y</mi>
<mo>~</mo>
</mover>
<mn>2</mn>
</msub>
<mo>|</mo>
<msubsup>
<mo>|</mo>
<mn>2</mn>
<mn>2</mn>
</msubsup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4.10</mn>
<mo>)</mo>
</mrow>
</mrow>
Section 2 and α on the right of above formula equal signiIt is unrelated, therefore work as
<mrow>
<msub>
<mover>
<mi>&alpha;</mi>
<mo>~</mo>
</mover>
<mn>1</mn>
</msub>
<mo>=</mo>
<msubsup>
<mi>&Sigma;</mi>
<mi>i</mi>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<msub>
<mover>
<mi>y</mi>
<mo>~</mo>
</mover>
<mi>i</mi>
</msub>
</mrow>
When, formula (4.10) is minimized, and at this time, the solution of formula (4.5) is:
<mrow>
<msub>
<mover>
<mi>&alpha;</mi>
<mo>^</mo>
</mover>
<mi>i</mi>
</msub>
<mo>=</mo>
<msub>
<mi>V</mi>
<mi>i</mi>
</msub>
<mfenced open = "|" close = "|">
<mtable>
<mtr>
<mtd>
<mrow>
<msubsup>
<mo>&Sigma;</mo>
<mi>i</mi>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<msub>
<mover>
<mi>y</mi>
<mo>~</mo>
</mover>
<mn>1</mn>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mover>
<mi>&alpha;</mi>
<mo>~</mo>
</mover>
<mn>2</mn>
</msub>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4.11</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein Vi、∑iWithTried to achieve respectively by calculation matrix, dictionary and input test sample projection value,For arbitrary dimension for (Vector.
6. power supply enterprise according to claim 5 construction mobile security supervision platform, it is characterised in that by i from 1 traversal to
K, is tried to achieve allAfterwards, test sample classification can be tried to achieve by formula (4.6)
7. power supply enterprise's construction mobile security supervision platform according to claim 6, it is characterised in that according to differentiation result
Reconstruct the test sample of inputSo as to which reconstructed image is tried to achieve in permutatation.
8. power supply enterprise's construction mobile security supervision platform according to claim 1, it is characterised in that interim for needing
Into the personnel at scene, the personnel safety access unit sends interim access to intelligent mobile terminal and permits, and sets 1 year
Interior interim access number is not to be exceeded 2 times.
9. power supply enterprise's construction mobile security supervision platform according to claim 1, it is characterised in that for needing to cancel
The personnel of access qualification, the personnel safety access unit send the information for cancelling access to intelligent mobile terminal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711032274.9A CN107944344A (en) | 2017-10-30 | 2017-10-30 | Power supply enterprise's construction mobile security supervision platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711032274.9A CN107944344A (en) | 2017-10-30 | 2017-10-30 | Power supply enterprise's construction mobile security supervision platform |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107944344A true CN107944344A (en) | 2018-04-20 |
Family
ID=61936641
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711032274.9A Pending CN107944344A (en) | 2017-10-30 | 2017-10-30 | Power supply enterprise's construction mobile security supervision platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107944344A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109274107A (en) * | 2018-11-05 | 2019-01-25 | 河海大学 | The oscillating signal identification model and its parameter identification method of meter and singular value |
CN109446890A (en) * | 2018-09-11 | 2019-03-08 | 浙江大有集团有限公司 | Collective-owned enterprise's encased column base site operation personnel's face identification device |
CN109636973A (en) * | 2018-12-11 | 2019-04-16 | 国网河北省电力有限公司保定供电分公司 | The engineering site personnel of gate and video interlink pass in and out course management system and method |
CN112528693A (en) * | 2020-12-09 | 2021-03-19 | 浙江水木物联技术有限公司 | Movable material checking machine for electric power construction site and checking method thereof |
CN113379947A (en) * | 2021-05-25 | 2021-09-10 | 广州朗国电子科技有限公司 | Intelligent door lock based on face recognition |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1744494A (en) * | 2005-09-30 | 2006-03-08 | 广东省电信有限公司研究院 | Access authentication system and method by verifying safety of accessing host |
US7147246B2 (en) * | 1995-06-07 | 2006-12-12 | Automotive Technologies International, Inc. | Method for airbag inflation control |
CN1983312A (en) * | 2005-12-26 | 2007-06-20 | 余羡鸣 | Urban digital total item supporting system |
CN101976352A (en) * | 2010-10-29 | 2011-02-16 | 上海交通大学 | Various illumination face identification method based on small sample emulating and sparse expression |
WO2014175082A1 (en) * | 2013-04-25 | 2014-10-30 | 京セラ株式会社 | User terminal, base station, and processor |
CN104951756A (en) * | 2015-06-08 | 2015-09-30 | 浙江科技学院 | Face recognition method based on compressed sensing |
WO2015151155A1 (en) * | 2014-03-31 | 2015-10-08 | 株式会社日立国際電気 | Personal safety verification system and similarity search method for data encrypted for confidentiality |
CN106296925A (en) * | 2016-08-16 | 2017-01-04 | 成都鼎昊科技有限公司 | A kind of video monitoring safety access system |
CN106503716A (en) * | 2016-09-13 | 2017-03-15 | 中国电力科学研究院 | A kind of safety cap recognition methods that is extracted based on color and contour feature and system |
CN106570464A (en) * | 2016-10-31 | 2017-04-19 | 华南理工大学 | Human face recognition method and device for quickly processing human face shading |
US20170309093A1 (en) * | 2014-11-11 | 2017-10-26 | Chunkui FENG | Vehicle operation monitoring, overseeing, data processing and overload monitoring method and system |
-
2017
- 2017-10-30 CN CN201711032274.9A patent/CN107944344A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7147246B2 (en) * | 1995-06-07 | 2006-12-12 | Automotive Technologies International, Inc. | Method for airbag inflation control |
CN1744494A (en) * | 2005-09-30 | 2006-03-08 | 广东省电信有限公司研究院 | Access authentication system and method by verifying safety of accessing host |
CN1983312A (en) * | 2005-12-26 | 2007-06-20 | 余羡鸣 | Urban digital total item supporting system |
CN101976352A (en) * | 2010-10-29 | 2011-02-16 | 上海交通大学 | Various illumination face identification method based on small sample emulating and sparse expression |
WO2014175082A1 (en) * | 2013-04-25 | 2014-10-30 | 京セラ株式会社 | User terminal, base station, and processor |
WO2015151155A1 (en) * | 2014-03-31 | 2015-10-08 | 株式会社日立国際電気 | Personal safety verification system and similarity search method for data encrypted for confidentiality |
US20170309093A1 (en) * | 2014-11-11 | 2017-10-26 | Chunkui FENG | Vehicle operation monitoring, overseeing, data processing and overload monitoring method and system |
CN104951756A (en) * | 2015-06-08 | 2015-09-30 | 浙江科技学院 | Face recognition method based on compressed sensing |
CN106296925A (en) * | 2016-08-16 | 2017-01-04 | 成都鼎昊科技有限公司 | A kind of video monitoring safety access system |
CN106503716A (en) * | 2016-09-13 | 2017-03-15 | 中国电力科学研究院 | A kind of safety cap recognition methods that is extracted based on color and contour feature and system |
CN106570464A (en) * | 2016-10-31 | 2017-04-19 | 华南理工大学 | Human face recognition method and device for quickly processing human face shading |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109446890A (en) * | 2018-09-11 | 2019-03-08 | 浙江大有集团有限公司 | Collective-owned enterprise's encased column base site operation personnel's face identification device |
CN109274107A (en) * | 2018-11-05 | 2019-01-25 | 河海大学 | The oscillating signal identification model and its parameter identification method of meter and singular value |
CN109274107B (en) * | 2018-11-05 | 2022-01-28 | 河海大学 | Low-frequency oscillation signal parameter identification method considering singular values |
CN109636973A (en) * | 2018-12-11 | 2019-04-16 | 国网河北省电力有限公司保定供电分公司 | The engineering site personnel of gate and video interlink pass in and out course management system and method |
CN112528693A (en) * | 2020-12-09 | 2021-03-19 | 浙江水木物联技术有限公司 | Movable material checking machine for electric power construction site and checking method thereof |
CN113379947A (en) * | 2021-05-25 | 2021-09-10 | 广州朗国电子科技有限公司 | Intelligent door lock based on face recognition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107944344A (en) | Power supply enterprise's construction mobile security supervision platform | |
CN101558431B (en) | Face authentication device | |
US9064145B2 (en) | Identity recognition based on multiple feature fusion for an eye image | |
CN105447441B (en) | Face authentication method and device | |
CN103679158A (en) | Face authentication method and device | |
CN105335722A (en) | Detection system and detection method based on depth image information | |
CN102629320B (en) | Ordinal measurement statistical description face recognition method based on feature level | |
US11194997B1 (en) | Method and system for thermal infrared facial recognition | |
CN102567993B (en) | Fingerprint image quality evaluation method based on main component analysis | |
CN104636730A (en) | Method and device for face verification | |
CN107798308B (en) | Face recognition method based on short video training method | |
CN110287787B (en) | Image recognition method, image recognition device and computer-readable storage medium | |
CN205247468U (en) | Intelligence safety inspection is equipment of being open to custom by oneself and system thereof | |
CN108108760A (en) | A kind of fast human face recognition | |
CN103839042A (en) | Human face recognition method and human face recognition system | |
CN113449704B (en) | Face recognition model training method and device, electronic equipment and storage medium | |
CN112052731A (en) | Intelligent portrait recognition card punching attendance system and method | |
CN109376717A (en) | Personal identification method, device, electronic equipment and the storage medium of face comparison | |
CN112949468A (en) | Face recognition method and device, computer equipment and storage medium | |
CN103246880A (en) | Human face recognizing method based on multi-level local obvious mode characteristic counting | |
CN114821725A (en) | Miner face recognition system based on neural network | |
CN113192028B (en) | Quality evaluation method and device for face image, electronic equipment and storage medium | |
CN107766832A (en) | A kind of face identification method for field operation construction management | |
CN101894154B (en) | Method for extracting key pattern from image file | |
Piekarczyk et al. | Hierarchical Graph-Grammar Model for Secure and Efficient Handwritten Signatures Classification. |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180420 |
|
RJ01 | Rejection of invention patent application after publication |