CN105046234B - Facial image secret recognition methods in cloud environment based on rarefaction representation - Google Patents
Facial image secret recognition methods in cloud environment based on rarefaction representation Download PDFInfo
- Publication number
- CN105046234B CN105046234B CN201510472454.3A CN201510472454A CN105046234B CN 105046234 B CN105046234 B CN 105046234B CN 201510472454 A CN201510472454 A CN 201510472454A CN 105046234 B CN105046234 B CN 105046234B
- Authority
- CN
- China
- Prior art keywords
- client
- vector
- euclidean distance
- server
- rarefaction representation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Collating Specific Patterns (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses facial image secret recognition methods in a kind of cloud environment based on rarefaction representation, it can be carried out under the mode of safety, while protect the privacy of picture and the crypticity of database.The in store image data base of server in high in the clouds, client obtain facial image and need server to be confirmed whether that the more information of both sides will not be obtained by matching at the same time server with suspect.Rarefaction representation is applied to concealed recognition of face security protocol by the present invention first, and describe a kind of safe Euclidean distance algorithm, then Paillier homomorphic cryptographies and Oblivious Transfer algorithm are utilized, concealed comparison terminal and the rarefaction representation coefficient vector of high in the clouds face, the dimension for which reducing face representation vector it also avoid the attack based on image block.And this method is easy to realize by software, the present invention can extensively using be generalized to cloud computing, safety certification, suspect tracking etc. in.
Description
Technical field
The invention belongs to cryptography, computer vision field, the method for particularly concealed recognition of face, specifically base
The facial image secret recognition methods in the cloud environment of rarefaction representation.
Background technology
Recognition of face plays important role in video monitoring and safety.With the fast development of computer technology,
Cloud computing has changed the mode of traditional face identification system.Video and facial image big data and powerful recognition of face
System is stored beyond the clouds and run beyond the clouds, this provides one and is widely applied such as face search, suspect's search.
However, largely in the distribution in public places of detection camera, the privacy of people is completely exposed undoubtedly.Suspect searches application can
It can be utilized by criminal and go to search the people that they want to find.Once face identification system is connected to a general database
The removal search common people that can be made one's wish fulfilled such as identity card, some people.Another aspect suspect database may also expose
Even cause more crimes.
Paillier systems be it is a kind of there is Semantic Security plus homomorphism common key cryptosystem, so being usually used in construction safety
It is multi-party to calculate basic agreement, such as scalar product protocol, 0T agreements.If cryptographic operation in cipher system is denoted as Epk(), decryption behaviour
It is denoted as Dpk(), then if semantic security refers to any message m0、m1, there is no the differentiation of any polynomial time algorithm
Epk(m0) and Epk(m1), add isomorphism to refer to Epk(x, r1)·Epk(y, r2)=Epk(x+y, r1·r2), r1, r2It is random number, root
It is easily verified that Paillier systems have semantic security and plus isomorphism according to the knowwhy of Paillier algorithms.
Oblivious transfer protocol is a kind of cipher protocol for protecting privacy, is also a kind of intercommunication for protecting privacy
Agreement, can make communicating pair transmit message in a manner of a kind of selection blurring.Can simply it be interpreted as, Oblivious Transfer energy
Enough so that communicating pair by it is a kind of it is casual in a manner of transmit message.Under specific occasion and needs, for the hidden of protection user
Private Oblivious Transfer provides a kind of real selection.
The content of the invention
The invention solves technical problem to be：Overcome the deficiencies of the prior art and provide a kind of cloud ring based on rarefaction representation
Facial image secret recognition methods in border, this method can effectively improve the computational efficiency of safe recognition of face, and can have
Effect resistance recovers the attack of image based on image block.
The technical solution adopted by the present invention is：Facial image secret identification side in a kind of cloud environment based on rarefaction representation
Method, realizes that step is as follows：
(1) totally 100 width facial images train face dictionary to training sample；
(2) client and server end calculates the rarefaction representation vector of its image respectively；
(3) client will be sent to server after the face vector encryption of calculating, and server calculates received vector and itself
The ciphertext of the Euclidean distance of any one image vector in picture library, and ciphertext is sent back into client, client solve Euclidean away from
From in plain text；
(4) client recycles oblivious transfer protocol to be interacted with server end according to Euclidean distance；
(5) server end calculates the threshold value of each facial image Euclidean distance of database by many experiments in advance,
In Oblivious Transfer can by the Euclidean distance calculated compared with corresponding threshold value to determine whether client and clothes
The face matching at business device end.
Wherein, the image face dictionary and coefficient vector of the step (1) and (2) take following steps：
(11) training sample of training face dictionary is 5 different facial images of 20 people, totally 100 width training sample；
(12) after image compression in advance processing, such a matrix can be obtained：Each row represent all of piece image
Pixel (being 18 pixel values after compression) order arranges, 100 width facial images according to 20 different peoples mode classification again successively
Arrangement, obtains the normalized matrix of one 18 × 200 afterwards by standardizing computing, that is, obtains face dictionary；
(13) facial image of k × j sizes is regarded as a column vector v ∈ Rm(m=kj).Use matrixRepresent all training samples in the i-th class, its each row are represented in the category
One training sample, niRepresent the number of all training samples in the category, training sample matrixTest sample y can be expressed as y=Ax ∈ R againm；
(14) finally solve most sparse solution and obtain rarefaction representation vector.
Wherein, the method for the calculating Euclidean distance described in step (3) takes following steps：
(21) client carries out square operation by turn to vector first, then former vector sum square vector is carried out by turn respectively
Encryption, encrypted result are sent to server end；
(22) received server-side to secret two vectors after, using homomorphism plus property and Euclidean distance formula calculate
The Euclidean distance of both sides' coefficient vector, this is carried out under the conditions of ciphertext, and is sent to visitor plus a random number to result
Family end；
(23) client by the Euclidean distance under ciphertext state and random number and be decrypted, just obtain under plaintext state
Euclidean distance and random number and.
Wherein, step (4) client interacts process using oblivious transfer protocol and server end and takes following step
Suddenly：
(31) client generates the private key of symmetrical secret key, and server end generates the public private key pair of multiple asymmetric secret keys, visitor
Family end selects a public key that its private key is encrypted and is sent to server end；
(32) server is decrypted ciphertext with its all private key, and is used as secret key pair matching result by the use of decrypted result
Multiple encrypted results are returned to client by encryption；
(33) ciphertext that client selects it with symmetrical secret key and can decrypt decrypt to obtain whether matched information.
The principle of the present invention is：
According to the defects of current concealed face recognition scheme and deficiency, secret of the design based on rarefaction representation can be summed up
Some rules of face recognition algorithms, as described below：
(1) as any biometric data, as same between the image acquired in terminal and existing list image
In individual, it is impossible to matching completely.Therefore, it is necessary to use a highly practical face recognition algorithms.
(2) the matching work of face must be completed under the mode of a secret protection.That is, high in the clouds and terminal all without
Any information in addition to whether the input of terminal matches with face in the list of high in the clouds known.Realize that this target needs to find
One people's face recognition algorithms, the algorithm can show to identify robustness well under the conditions of different illumination, expression etc., and
And it can also support to calculate agreement safely；
(3) the defects of safety of structure of concealed face recognition scheme is extremely important, some structures can expose face figure
The information of picture, public database are exposed are also possible that completely；
(4) the usually used data of face recognition algorithms are represented in real number field, and security protocol is operated in finite field, existing
Face identification method be transformed into finite field and may result in degeneration.The mathematical operation that can be realized in existing Encryption Algorithm
It is very conditional.
According to above-mentioned rule, the present invention utilizes rarefaction representation, Paillier homomorphic cryptographies, Euclidean distance and Oblivious Transfer
(OT), a kind of new concealed face recognition scheme is devised.In this scenario, rarefaction representation be used for generate facial image represent to
Amount, then generation is vectorial adds the Euclidean distance calculated between vector using homomorphism, finally returns result to visitor by OT operations
Family end.In order to strengthen the robustness of identification, face representation vector is generated by rarefaction representation, then carries out similarity system design fortune
Calculate, this can effectively shorten the dimension of vector and improve encrypted efficiency.The realization of Oblivious Transfer is added using symmetrical
Close and asymmetric encryption.Experimental analysis shows concealed rarefaction representation recognition of face, can be adapted to actual face recognition application.
The present invention compared with prior art, it is advantageous that：
(1) algorithm can show to identify robustness well under the conditions of different illumination, expression etc., and can also prop up
Hold safety and calculate agreement；
(2) represented using face sparse and Euclidean distance has been broken under the conditions of only binary vector can do secret
The final conclusion of recognition of face, improves the efficiency of algorithm, reduces the dimension of face representation vector, and program shortens test
Time, it is possibility to have effect resistance recovers the attack of original image based on image block.
(3) face recognition scheme has the advantages of simple structure and easy realization.
Brief description of the drawings
Fig. 1 is application scenario diagram of the present invention；
Fig. 2 is the present invention program flow chart.
Embodiment：
The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
The adduction number of Paillier homomorphisms multiplies property and is described by formula (1) and formula (2)：
E(km1)≡E(m1)k (2)
Wherein m1, m2Represent two plaintexts, E () homomorphism equation, N=pq, p and q are two Big prime N ∈ Z, at random
Numberm∈ZN, G is mould n2Multiplicative group, i.e.,Randomly choose g ∈ G so that g meets
gcd(L(gemod N2), N)=1, then the public key of the encryption system is (g, n), and private key is e (N).E (N) and L () definition is such as
Under：
ZN=x | x ∈ Z, 0≤x≤N },
E (N)=1cm (p-1, q-1), (3)
S={ x ＜ N2| x=1mod N },
Refering to Fig. 2 protocol procedures figures, ciphering process of the present invention can be divided into step in detail below：
Input step：
Client inputs one-dimensional face vector s=(s0, s1..., sl-1), l=200 in the present invention, among other experiments
It can be changed according to actual conditions.Client inputs one group of Q one-dimensional face vector { s1, s2..., sQAnd random number (t1,
t2..., tQCorrespond to each si, both sides are to Euclidean distance upper limit dmax。
Export step：
Client knows index i, Euclidean distance ED (s, si)≤ti, and server end does not know more information.
(1) client bitwise encryption face vector s=(s0, s1..., sl-1) and it is vectorial square (s)2=((s0)2, (s1
)2..., (sl-1)2, it is sent to server, received server-side to encrypted result (Epk(s0), Epk(s1) ..., Epk(sl-1))
(Epk((s0)2), Epk((s1)2) ..., Epk((sl-1)2)), below every face of one group of suspect of server end
Step is to repeat；
(2) E is calculated for j-th of element in i-th of face vector in server, cloud serverpk(vj) wherein：
(3) can be passed through according to the property of homomorphism, the server in high in the cloudsCalculate dE=(ED
(s, si)2, dE∈ [0, dmax].Then a random number r is selected to each faceiAnd calculateHair
Give client；
(4) client receives Epk((ED (s, si))2+ri) and decrypted；
(5) both sides useAgreement goes to judge whether (dE)i＜ ti, in client result of calculation Ri
(6) draw whether match, 1 represents matching, and 0 represents to mismatch.
In short, the concealed face sparse proposed in the present invention represent recognition methods can under the agreement of a safety into
OK, the Information Security of client and server end both sides can at the same time be protected.The present invention is first by rarefaction representation application
Into the security protocol of concealed recognition of face, this not only lowers face representation vector dimension and can resist and be based on image block
Recover the attack of image information.In addition, we talk of the Euclidean distance algorithm of safety, solves nonbinary vector not
It can carry out the problem of safe computing.Show that method proposed by the present invention can effectively shorten vectorial dimension and carry by experiment
The efficiency of high encryption and decryption, reduces calculation amount, improves recognition efficiency and shorten recognition time.And the encryption method is easy to lead to
Software realization is crossed, during the present invention can be encrypted extensively using recognition of face secure storage is generalized to transmission.
The foregoing is merely some basic explanations of the present invention, any equivalent change done according to technical scheme
Change, be within the scope of protection of the invention.
Claims (3)
1. facial image secret recognition methods in a kind of cloud environment based on rarefaction representation, it is characterised in that realize step：
(1) totally 100 width facial images train face dictionary to training sample；
(2) client and server end calculates the rarefaction representation vector of its image respectively；
(3) client will be sent to server after the face vector encryption of calculating, and server calculates received vector and itself picture library
In any one image vector Euclidean distance ciphertext, and ciphertext is sent back into client, it is bright that client solves Euclidean distance
Text；
(4) client recycles oblivious transfer protocol to be interacted with server end according to Euclidean distance；
(5) server end calculates the threshold value of each facial image Euclidean distance of database by many experiments in advance, not
In careful transmission by the Euclidean distance calculated compared with corresponding threshold value to determine whether client and server
Face matches；
Wherein, step (1) and (2) described image face dictionary and rarefaction representation vector take following steps：
(11) training sample of training face dictionary is 5 different facial images of 20 people, totally 100 width training sample；
(12) after image compression in advance processing, such a matrix can be obtained：Each row represent all pixels of piece image
Order arranges, and is 18 pixel values after all pixels compression, 100 width facial images according to 20 different peoples mode classification again
It is arranged in order, obtains the normalized matrix of one 18 × 200 afterwards by standardizing computing, that is, obtain face dictionary；
(13) facial image of k × j sizes is regarded as a column vector v ∈ Rm, m=kj, uses matrixRepresent all training samples in the i-th class, its each row are represented in the category
One training sample, niRepresent the number of all training samples in the category, training sample matrixTest sample y can be expressed as y=Ax ∈ R againm；
(14) finally solve most sparse solution and obtain rarefaction representation vector.
2. facial image secret recognition methods in the cloud environment according to claim 1 based on rarefaction representation, its feature exist
In：The method of calculating Euclidean distance described in step (3) takes following steps：
(21) client carries out square operation by turn to vector first, then former vector sum square vector is added by turn respectively
Close, encrypted result is sent to server end；
(22) received server-side is to after encrypted two vectors, using homomorphism plus property and Euclidean distance formula calculate both sides
The Euclidean distance of coefficient vector, this is carried out under the conditions of ciphertext, and is sent to client plus a random number to result；
(23) client by the Euclidean distance under ciphertext state and random number and be decrypted, just obtain the Europe under plaintext state
Family name's distance and random number and.
3. facial image secret recognition methods in the cloud environment according to claim 1 based on rarefaction representation, its feature exist
In：Step (4) client interacts process using oblivious transfer protocol and server end and takes following steps：
(31) private key of client generation symmetric cryptography, server end generate the public private key pair of multiple asymmetric encryption, client
Its private key, which is encrypted, in one public key of selection is sent to server end；
(32) server is decrypted ciphertext with its whole private key, and adds by the use of decrypted result as secret key pair matching result
It is close, multiple encrypted results are returned into client；
(33) ciphertext that client selects it with symmetrical secret key and can decrypt decrypts to obtain the information of matching result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510472454.3A CN105046234B (en) | 2015-08-04 | 2015-08-04 | Facial image secret recognition methods in cloud environment based on rarefaction representation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510472454.3A CN105046234B (en) | 2015-08-04 | 2015-08-04 | Facial image secret recognition methods in cloud environment based on rarefaction representation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105046234A CN105046234A (en) | 2015-11-11 |
| CN105046234B true CN105046234B (en) | 2018-05-11 |
Family
ID=54452763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510472454.3A Active CN105046234B (en) | 2015-08-04 | 2015-08-04 | Facial image secret recognition methods in cloud environment based on rarefaction representation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105046234B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105721140B (en) * | 2016-01-27 | 2019-03-15 | 北京航空航天大学 | N takes the Oblivious Transfer method and system of k |
| CN106096548B (en) * | 2016-06-12 | 2019-05-24 | 北京电子科技学院 | A kind of shared face secret recognition methods of more intelligent terminals based on cloud environment |
| CN106127666B (en) * | 2016-06-12 | 2019-02-19 | 北京电子科技学院 | It is a kind of based on random subgraph indicate cloud environment in subject image secret detection method |
| CN108171262A (en) * | 2017-12-22 | 2018-06-15 | 珠海习悦信息技术有限公司 | The recognition methods of ciphertext picture/mb-type, device, storage medium and processor |
| CN109359210A (en) * | 2018-08-09 | 2019-02-19 | 中国科学院信息工程研究所 | The face retrieval method and system of double blind secret protection |
| US10713544B2 (en) | 2018-09-14 | 2020-07-14 | International Business Machines Corporation | Identification and/or verification by a consensus network using sparse parametric representations of biometric images |
| CN111241514B (en) * | 2020-01-14 | 2022-05-31 | 浙江理工大学 | Safety face verification method based on face verification system |
| CN112215158B (en) * | 2020-10-13 | 2022-10-18 | 中山大学 | Face recognition method fusing fully homomorphic encryption and discrete wavelet transform in cloud environment |
| CN112287375A (en) * | 2020-11-21 | 2021-01-29 | 上海同态信息科技有限责任公司 | Method for calculating dense state Euclidean distance |
| CN113946858B (en) * | 2021-12-20 | 2022-03-18 | 湖南丰汇银佳科技股份有限公司 | Identity security authentication method and system based on data privacy calculation |
| CN115865391A (en) * | 2022-08-04 | 2023-03-28 | ***股份有限公司 | Data matching method, device, system, equipment and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101674299A (en) * | 2009-10-16 | 2010-03-17 | 西安电子科技大学 | Method for generating key based on amalgamation of multiple features in encryption area |
| CN101753304A (en) * | 2008-12-17 | 2010-06-23 | 中国科学院自动化研究所 | Method for binding biological specificity and key |
| CN101976321A (en) * | 2010-09-21 | 2011-02-16 | 北京工业大学 | Generated encrypting method based on face feature key |
-
2015
- 2015-08-04 CN CN201510472454.3A patent/CN105046234B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101753304A (en) * | 2008-12-17 | 2010-06-23 | 中国科学院自动化研究所 | Method for binding biological specificity and key |
| CN101674299A (en) * | 2009-10-16 | 2010-03-17 | 西安电子科技大学 | Method for generating key based on amalgamation of multiple features in encryption area |
| CN101976321A (en) * | 2010-09-21 | 2011-02-16 | 北京工业大学 | Generated encrypting method based on face feature key |
Non-Patent Citations (1)
| Title |
|---|
| 基于稀疏表示的云环境中人脸图像隐秘识别方法;刘妍等;《***仿真学报》;20151008;第27卷(第10期);第2291-2298页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105046234A (en) | 2015-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105046234B (en) | Facial image secret recognition methods in cloud environment based on rarefaction representation | |
| CN105631296B (en) | A kind of safe face authentication system design method based on CNN feature extractors | |
| Ma et al. | A secure face-verification scheme based on homomorphic encryption and deep neural networks | |
| CN109145829A (en) | A kind of safe and efficient face identification method based on deep learning and homomorphic cryptography | |
| Guo et al. | Towards efficient privacy-preserving face recognition in the cloud | |
| CN109086615A (en) | A kind of support multiple key search public key encryption method of anti-keyword guessing attack | |
| Kulshrestha et al. | Identifying harmful media in {End-to-End} encrypted communication: Efficient private membership computation | |
| CN106096548B (en) | A kind of shared face secret recognition methods of more intelligent terminals based on cloud environment | |
| CN106130716A (en) | Cipher key exchange system based on authentication information and method | |
| CN109543434A (en) | Block chain information encryption method, decryption method, storage method and device | |
| Guo et al. | A quantum image encryption algorithm based on the Feistel structure | |
| Zeroual et al. | Lightweight deep learning model to secure authentication in Mobile Cloud Computing | |
| Im et al. | Privacy-preserving palm print authentication using homomorphic encryption | |
| Jin et al. | Privacy preserving face identification in the cloud through sparse representation | |
| Huang et al. | Efficient privacy-preserving face verification scheme | |
| Bentafat et al. | Towards real-time privacy-preserving video surveillance | |
| CN112380404B (en) | Data filtering method, device and system | |
| Shankar et al. | Secure image transmission in wireless sensor network (WSN) applications | |
| Ahmad et al. | A pixel-based encryption method for privacy-preserving deep learning models | |
| Khan et al. | Secure facial recognition in the encrypted domain using a local ternary pattern approach | |
| Patsakis et al. | Privacy-preserving biometric authentication and matching via lattice-based encryption | |
| Jin et al. | Efficient blind face recognition in the cloud | |
| CN116341000A (en) | Information protection enhanced tagged privacy set intersection method | |
| Hu et al. | Security and privacy protocols for perceptual image hashing | |
| Vanitha et al. | Enhanced Security using Advanced Encryption Standards in Face Recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20191106 Address after: 311800 no.30-1 and no.30-2, Likai Road, Jiyang street, Zhuji City, Shaoxing City, Zhejiang Province Patentee after: Zhejiang Jun Kai Electromechanical Technology Co. Ltd. Address before: 100070 Beijing city Fengtai District Fung Fu Road Beijing Electronics Science and Technology Institute No. 7 Building 413 Patentee before: Beijing Electronic Science and Technology Institute |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20191225 Address after: Room 302-9, Qunxian road 2003, Keqiao street, Keqiao District, Shaoxing City, Zhejiang Province Patentee after: Zhejiang shaoding intelligent robot Co., Ltd Address before: 311800 no.30-1 and no.30-2, Likai Road, Jiyang street, Zhuji City, Shaoxing City, Zhejiang Province Patentee before: Zhejiang Jun Kai Electromechanical Technology Co. Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200826 Address after: 610-2, floor 6, No. 8, caihefang Road, Haidian District, Beijing 100000 Patentee after: Shaoding Artificial Intelligence Technology Co.,Ltd. Address before: Room 302-9, Qunxian road 2003, Keqiao street, Keqiao District, Shaoxing City, Zhejiang Province Patentee before: Zhejiang shaoding intelligent robot Co.,Ltd. |