CN110472400B - Trusted computer system based on face recognition and implementation method - Google Patents
Trusted computer system based on face recognition and implementation method Download PDFInfo
- Publication number
- CN110472400B CN110472400B CN201910776696.XA CN201910776696A CN110472400B CN 110472400 B CN110472400 B CN 110472400B CN 201910776696 A CN201910776696 A CN 201910776696A CN 110472400 B CN110472400 B CN 110472400B
- Authority
- CN
- China
- Prior art keywords
- face recognition
- layer
- trusted
- neural network
- convolutional neural
- 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
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/70—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer
- G06F21/71—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer to assure secure computing or processing of information
- G06F21/72—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer to assure secure computing or processing of information in cryptographic circuits
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/70—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer
- G06F21/81—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer by operating on the power supply, e.g. enabling or disabling power-on, sleep or resume operations
-
- 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)
- Computer Hardware Design (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a trusted computer system based on face recognition and an implementation method, belonging to the field of information security, aiming at solving the technical problems of how to realize intelligent protection of the trusted computer system based on face recognition, reducing the Ukey authentication process and reducing the management cost, and adopting the technical scheme that: the system comprises a general computer system, face recognition equipment and a trusted chip, wherein the general computer system recognizes a user through integrated face recognition equipment, the face recognition equipment sends a control signal to control the trusted chip to supply power and issue a protection key component, and the trusted chip decrypts a trusted root after synthesizing the component and measures BIOS to start a normal boot process. The invention discloses a trusted computer implementation method based on face recognition.
Description
Technical Field
The invention relates to the field of information security, in particular to a trusted computer system based on face recognition and an implementation method.
Background
Trusted Computing, Trusted Computing (TC), is a technology that is pushed and developed by the Trusted Computing Group (formerly TCPA). This term is derived from Trusted systems (Trusted systems) and has its specific meaning. From a technical point of view, "Trusted" (Trusted) does not necessarily mean "Trustworthy" to the user. Rather, it means that it is well believed that its behavior will follow the design more fully with a low probability of performing behaviors that designers and software writers prohibit.
The English name of Face recognition is Human Face recognition, and an AVS03A image processor is used by a Face recognition product; the system can be used for detecting the brightness of the human face, automatically adjusting dynamic exposure compensation, tracking and detecting the human face and automatically adjusting image amplification. The generalized face recognition actually comprises a series of related technologies for constructing a face recognition system, including face image acquisition, face positioning, face recognition preprocessing, identity confirmation, identity search and the like; the narrow-sense face recognition refers to a technique or system for identity confirmation or identity search through a face.
The convolutional neural network algorithm is widely applied to the artificial intelligence field, and is widely applied to the fields of security protection, automatic driving, computer vision, face recognition and the like. The CNN is essentially a multilayer perceptron, and the key reason for the success of the CNN is the local connection and weight sharing mode adopted by the CNN, so that the number of the reduced weights enables the network to be easily optimized, and the risk of overfitting is reduced. The CNN is one of the neural networks, and the weight sharing network structure of the CNN is more similar to a biological neural network, so that the complexity of a network model is reduced, and the number of weights is reduced. The advantage is more obvious when the input of the network is a multi-dimensional image, so that the image can be directly used as the input of the network, and the complex characteristic extraction and data reconstruction process in the traditional recognition algorithm is avoided.
In summary, how to realize intelligent protection of a trusted computer system based on face recognition, reduce the Ukey authentication process, and reduce the management cost is a technical problem which is urgently needed to be solved in the prior art.
Disclosure of Invention
The technical task of the invention is to provide a trusted computer system based on face recognition and an implementation method thereof, so as to solve the problems of how to implement intelligent protection of the trusted computer system based on face recognition, reduce the Ukey authentication process and reduce the management cost.
The technical task of the invention is realized in the following way, the system comprises a general computer system, a face recognition device and a trusted chip, wherein the general computer system recognizes a user by integrating the face recognition device, the face recognition device sends a control signal to control the trusted chip to supply power and issue a protection key component, and the trusted chip decrypts a trusted root after synthesizing the component and measures a BIOS to start a normal boot process.
Preferably, the face recognition device is independently powered by a Standby power supply, is independent of a trusted computer power supply system, and can not be modified by an operating system and a trusted chip COS (chip operating system), so that the information security of a user is ensured.
Preferably, the algorithm adopted by the face recognition device is a 12-layer convolutional neural network model.
Preferably, the 12-layer convolutional neural network model specifically includes:
the convolutional neural network model establishing module is used for replacing the convolutional layer with the convolutional layer for adjusting the step length of the convolutional kernel with the pooling layer to establish a 12-layer convolutional neural network model and reduce the complexity of the face recognition equipment;
the convolutional neural network model training module is used for carrying out model training on the 12-layer convolutional neural network model;
the network quantization module is used for carrying out network quantization on the 12-layer convolutional neural network model;
the over-training module is used for performing over-training on the 12-layer convolutional neural network model and outputting a final model;
and the face recognition equipment loading module is used for disassembling the final model into operation instructions of multiplication, step length, accumulation, input and output through a compiler and loading the operation instructions into the face recognition equipment.
Preferably, the network quantization on the 12-layer convolutional neural network model specifically includes: the weight, the input and the output are subjected to 8-bit shaping quantization by a 32-bit floating point, the accumulation part is subjected to 32-bit floating point to 9-bit shaping quantization, and the multiplication part is subjected to 32-bit floating point to 12-bit shaping quantization, so that the model parameter calculation amount is reduced and the precision is kept.
Preferably, the training the 12-layer convolutional neural network model and outputting the final model specifically includes: and carrying out binarization on the 4-layer network in the 12-layer network, further compressing network parameters, and outputting a final model after carrying out overtraining again.
A trusted computer implementation method based on face recognition comprises the following steps:
s1, establishing a 12-layer convolutional neural network model and loading the 12-layer convolutional neural network model into face recognition equipment;
s2, recognizing the human face by the human face recognition equipment;
s3, after the face recognition equipment recognizes the face, the trusted chip power supply circuit is opened, and a communication key is negotiated through the trusted chip interconnection interface;
s4, encrypting the system protection key component and sending the encrypted system protection key component to a trusted chip;
s5, the trusted chip synthesizes the received system protection key component and the chip self-storage component into a system protection key through displacement;
and S6, decrypting the trusted root and measuring the BIOS of the trusted computer, and entering a normal trusted computer starting process.
Preferably, the specific steps of establishing the 12-layer convolutional neural network model in step S1 and loading the 12-layer convolutional neural network model into the face recognition device are as follows:
s101, establishing a 12-layer convolutional neural network model, and replacing a pooling layer with a convolutional layer for adjusting the step length of a convolutional kernel to reduce the complexity of face recognition equipment;
s102, performing model training on the 12-layer convolutional neural network model;
s103, carrying out network quantization on the 12-layer convolutional neural network model;
s104, performing over-retraining on the 12-layer convolutional neural network model and outputting a final model;
and S105, disassembling the final model into operation instructions of multiplication, step length, accumulation, input and output through a compiler, and loading the operation instructions into the face recognition equipment.
Preferably, the network quantization on the 12-layer convolutional neural network model in step S103 specifically includes: the weight, the input and the output are subjected to 8-bit shaping quantization by a 32-bit floating point, the accumulation part is subjected to 32-bit floating point to 9-bit shaping quantization, and the multiplication part is subjected to 32-bit floating point to 12-bit shaping quantization, so that the model parameter calculation amount is reduced and the precision is kept.
Preferably, the step S104 of performing the retraining on the 12-layer convolutional neural network model and outputting the final model specifically includes binarizing the 4-layer network in the 12-layer network, further compressing the network parameters, and outputting the final model after performing the retraining again.
The trusted computer system based on face recognition and the implementation method have the following advantages:
the face recognition process is added, so that the intelligent protection of a trusted computer system is realized, the Ukey authentication process is reduced, and the management cost is reduced;
the face recognition equipment independently supplies power to the Standby power supply, is independent of a trusted computer power supply system, and can not be modified by an operating system and a trusted chip COS (chip operating system), so that the safety of user information is ensured;
the algorithm of the face recognition equipment adopts a customized 12-layer convolutional neural network, and adopts a convolutional layer for adjusting the step length of a convolutional kernel to replace a pooling layer, so that the complexity of face recognition hardware is reduced;
and fourthly, performing network quantization on the convolutional neural network model, wherein the weight, the input and the output are subjected to 8-bit shaping quantization by a 32-bit floating point, the accumulation part is subjected to 32-bit floating point to 9-bit shaping quantization, and the multiplication part is subjected to 32-bit floating point to 12-bit shaping quantization, so that the model parameter calculation amount is reduced and the precision is kept.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a block diagram of a trusted computer system based on face recognition;
fig. 2 is a flow chart of a trusted computer based on face recognition.
Detailed Description
The trusted computer system based on face recognition and the implementation method of the present invention are described in detail below with reference to the drawings and the specific embodiments of the specification.
Example 1:
as shown in fig. 1, the trusted computer system based on face recognition of the present invention includes a general computer system, a face recognition device and a trusted chip, wherein the general computer system recognizes a user by integrating the face recognition device, the face recognition device sends a control signal to control the trusted chip to supply power and issue a protected key component, and the trusted chip decrypts a trusted root after synthesizing the component and measures a BIOS to start a normal boot process. The face recognition device is independently powered by a Standby power supply, is independent of a trusted computer power supply system, and can not be modified by an operating system and a trusted chip COS (chip operating system), so that the safety of user information is ensured.
The algorithm adopted by the face recognition device is a 12-layer convolutional neural network model. The 12-layer convolutional neural network model specifically comprises:
the convolutional neural network model establishing module is used for replacing the convolutional layer with the convolutional layer for adjusting the step length of the convolutional kernel with the pooling layer to establish a 12-layer convolutional neural network model and reduce the complexity of the face recognition equipment;
the convolutional neural network model training module is used for carrying out model training on the 12-layer convolutional neural network model;
the network quantization module is used for performing network quantization on the 12-layer convolutional neural network model, wherein the weight, the input and the output are subjected to 8-bit shaping quantization by a 32-bit floating point, the accumulation part is subjected to 32-bit floating point to 9-bit shaping quantization, and the multiplication part is subjected to 32-bit floating point to 12-bit shaping quantization, so that the model parameter calculation amount is reduced and the precision is kept;
the over-retraining module is used for performing over-retraining on the 12-layer convolutional neural network model and outputting a final model, binarizing the 4-layer network in the 12-layer network, further compressing network parameters, and outputting the final model after performing over-retraining again;
and the face recognition equipment loading module is used for disassembling the final model into operation instructions of multiplication, step length, accumulation, input and output through a compiler and loading the operation instructions into the face recognition equipment.
Example 2:
as shown in fig. 2, the trusted computer implementation method based on face recognition of the present invention includes the following steps:
s1, establishing a 12-layer convolutional neural network model and loading the 12-layer convolutional neural network model into face recognition equipment;
s2, recognizing the human face by the human face recognition equipment;
s3, after the face recognition equipment recognizes the face, the trusted chip power supply circuit is opened, and a communication key is negotiated through the trusted chip interconnection interface;
s4, encrypting the system protection key component and sending the encrypted system protection key component to a trusted chip;
s5, the trusted chip synthesizes the received system protection key component and the chip self-storage component into a system protection key through displacement;
and S6, decrypting the trusted root and measuring the BIOS of the trusted computer, and entering a normal trusted computer starting process.
The specific steps of establishing the 12-layer convolutional neural network model in step S1 and loading the 12-layer convolutional neural network model into the face recognition device are as follows:
s101, establishing a 12-layer convolutional neural network model, and replacing a pooling layer with a convolutional layer for adjusting the step length of a convolutional kernel to reduce the complexity of face recognition equipment;
s102, performing model training on the 12-layer convolutional neural network model;
s103, carrying out network quantization on the 12-layer convolutional neural network model, wherein the weight, the input and the output are subjected to 8-bit shaping quantization by a 32-bit floating point, the accumulation part is subjected to 32-bit floating point to 9-bit shaping quantization, and the multiplication part is subjected to 32-bit floating point to 12-bit shaping quantization, so that the calculation amount of the model parameters is reduced, and the precision is kept;
s104, performing over-retraining on the 12-layer convolutional neural network model and outputting a final model, binarizing the 4-layer network in the 12-layer network, further compressing network parameters, performing over-retraining again, and outputting the final model;
and S105, disassembling the final model into operation instructions of multiplication, step length, accumulation, input and output through a compiler, and loading the operation instructions into the face recognition equipment.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (3)
1. A trusted computer system based on face recognition is characterized by comprising a general computer system, face recognition equipment and a trusted chip, wherein the general computer system recognizes a user by integrating the face recognition equipment, the face recognition equipment sends a control signal to control the trusted chip to supply power and issue a protection key component, and the trusted chip decrypts a trusted root after synthesizing the component and measures a BIOS (basic input output System) to start a normal boot process;
the face recognition equipment adopts an algorithm of a 12-layer convolutional neural network model; the 12-layer convolutional neural network model specifically comprises:
the convolutional neural network model establishing module is used for replacing the convolutional layer with the convolutional layer for adjusting the step length of the convolutional kernel with the pooling layer to establish a 12-layer convolutional neural network model and reduce the complexity of the face recognition equipment;
the convolutional neural network model training module is used for carrying out model training on the 12-layer convolutional neural network model;
the network quantization module is used for carrying out network quantization on the 12-layer convolutional neural network model; the method specifically comprises the following steps: the weight, the input and the output are subjected to 8-bit shaping quantization by a 32-bit floating point, the accumulation part is subjected to 32-bit floating point to 9-bit shaping quantization, and the multiplication part is subjected to 32-bit floating point to 12-bit shaping quantization;
the over-training module is used for performing over-training on the 12-layer convolutional neural network model and outputting a final model; the method specifically comprises the following steps: carrying out binarization on a 4-layer network in a 12-layer network, further compressing network parameters, and outputting a final model after carrying out overtraining again;
and the face recognition equipment loading module is used for disassembling the final model into operation instructions of multiplication, step length, accumulation, input and output through a compiler and loading the operation instructions into the face recognition equipment.
2. The trusted computer system based on face recognition of claim 1, wherein the face recognition device is powered solely by a Standby power supply.
3. A trusted computer implementation method based on face recognition is characterized by comprising the following steps:
s1, establishing a 12-layer convolutional neural network model and loading the 12-layer convolutional neural network model into face recognition equipment; the method comprises the following specific steps:
s101, establishing a 12-layer convolutional neural network model, and replacing a pooling layer with a convolutional layer for adjusting the step length of a convolutional kernel to reduce the complexity of face recognition equipment;
s102, performing model training on the 12-layer convolutional neural network model;
s103, carrying out network quantization on the 12-layer convolutional neural network model; the method specifically comprises the following steps: the weight, the input and the output are subjected to 8-bit shaping quantization by a 32-bit floating point, the accumulation part is subjected to 32-bit floating point to 9-bit shaping quantization, and the multiplication part is subjected to 32-bit floating point to 12-bit shaping quantization;
s104, performing over-retraining on the 12-layer convolutional neural network model and outputting a final model; the method specifically comprises the steps of carrying out binarization on a 4-layer network in a 12-layer network, further compressing network parameters, carrying out retraining again, and outputting a final model;
s105, disassembling the final model into operation instructions of multiplication, step length, accumulation, input and output through a compiler, and loading the operation instructions into face recognition equipment;
s2, recognizing the human face by the human face recognition equipment;
s3, after the face recognition equipment recognizes the face, the trusted chip power supply circuit is opened, and a communication key is negotiated through the trusted chip interconnection interface;
s4, encrypting the system protection key component and sending the encrypted system protection key component to a trusted chip;
s5, the trusted chip synthesizes the received system protection key component and the chip self-storage component into a system protection key through displacement;
and S6, decrypting the trusted root and measuring the BIOS of the trusted computer, and entering a normal trusted computer starting process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910776696.XA CN110472400B (en) | 2019-08-22 | 2019-08-22 | Trusted computer system based on face recognition and implementation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910776696.XA CN110472400B (en) | 2019-08-22 | 2019-08-22 | Trusted computer system based on face recognition and implementation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110472400A CN110472400A (en) | 2019-11-19 |
| CN110472400B true CN110472400B (en) | 2021-06-01 |
Family
ID=68512736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910776696.XA Active CN110472400B (en) | 2019-08-22 | 2019-08-22 | Trusted computer system based on face recognition and implementation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110472400B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6763400B2 (en) * | 2000-09-12 | 2004-07-13 | Kabushiki Kaisha Toshiba | Computer having control means for determining an operation state of an audio sources selecting switch when the computer is powered on/off, in a standby and a pause states |
| CN205377891U (en) * | 2016-01-05 | 2016-07-06 | 北京神州新桥科技有限公司 | Identity authentication device and system |
| CN107247991A (en) * | 2017-06-15 | 2017-10-13 | 北京图森未来科技有限公司 | A kind of method and device for building neutral net |
| CN108572861A (en) * | 2018-04-26 | 2018-09-25 | 浪潮(北京)电子信息产业有限公司 | A kind of guard method, system, equipment and the storage medium of virtual credible root |
| CN109992973A (en) * | 2019-04-10 | 2019-07-09 | 北京可信华泰信息技术有限公司 | A kind of starting measure and device using OPROM mechanism |
| CN110008841A (en) * | 2019-03-08 | 2019-07-12 | 中国华戎科技集团有限公司 | A kind of Expression Recognition model building method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107341463B (en) * | 2017-06-28 | 2020-06-05 | 苏州飞搜科技有限公司 | Face feature recognition method combining image quality analysis and metric learning |
| CN108345856B (en) * | 2018-02-09 | 2021-01-12 | 电子科技大学 | SAR automatic target recognition method based on heterogeneous convolutional neural network integration |
-
2019
- 2019-08-22 CN CN201910776696.XA patent/CN110472400B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6763400B2 (en) * | 2000-09-12 | 2004-07-13 | Kabushiki Kaisha Toshiba | Computer having control means for determining an operation state of an audio sources selecting switch when the computer is powered on/off, in a standby and a pause states |
| CN205377891U (en) * | 2016-01-05 | 2016-07-06 | 北京神州新桥科技有限公司 | Identity authentication device and system |
| CN107247991A (en) * | 2017-06-15 | 2017-10-13 | 北京图森未来科技有限公司 | A kind of method and device for building neutral net |
| CN108572861A (en) * | 2018-04-26 | 2018-09-25 | 浪潮(北京)电子信息产业有限公司 | A kind of guard method, system, equipment and the storage medium of virtual credible root |
| CN110008841A (en) * | 2019-03-08 | 2019-07-12 | 中国华戎科技集团有限公司 | A kind of Expression Recognition model building method and system |
| CN109992973A (en) * | 2019-04-10 | 2019-07-09 | 北京可信华泰信息技术有限公司 | A kind of starting measure and device using OPROM mechanism |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110472400A (en) | 2019-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108898168B (en) | Compression method and system of convolutional neural network model for target detection | |
| US20200097651A1 (en) | Systems and methods to achieve robustness and security in medical devices | |
| CN110875093A (en) | Treatment scheme processing method, device, equipment and storage medium | |
| CN110309692B (en) | Face recognition method, device and system, and model training method and device | |
| CN101739564A (en) | System and method for fingerprint identification | |
| JP6933356B2 (en) | Image processing methods, devices, and systems | |
| CN110826420A (en) | Training method and device of face recognition model | |
| EP3382596B1 (en) | Human face model matrix training method and apparatus, and storage medium | |
| CN115512005A (en) | Data processing method and device | |
| US20230100874A1 (en) | Facial expression-based unlocking method and apparatus, computer device, and storage medium | |
| CN113990482A (en) | Health data processing system and method | |
| CN111125707A (en) | BMC (baseboard management controller) safe starting method, system and equipment based on trusted password module | |
| CN110472400B (en) | Trusted computer system based on face recognition and implementation method | |
| CN104392356A (en) | Mobile payment system and method based on three-dimensional human face recognition | |
| CN110569083B (en) | Image segmentation processing method and device, computer equipment and storage medium | |
| CN116311370A (en) | Multi-angle feature-based cow face recognition method and related equipment thereof | |
| CN109886402B (en) | Deep learning model training method, device, computer equipment and storage medium | |
| CN111738182B (en) | Identity verification method, device, terminal and storage medium based on image recognition | |
| CN113973018A (en) | Endogenous safety-based Internet of things terminal data processing method and system | |
| Benhammadi et al. | Embedded fingerprint matching on smart card | |
| CN110841143A (en) | Method and system for predicting state of infusion pipeline | |
| Ana et al. | IOT-based biometric attendance system for CRUTECH | |
| CN111753854B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN115168843A (en) | Hardware Trojan side channel detection method based on self-encoder | |
| CN112233776A (en) | Dermatosis self-learning auxiliary judgment system based on visual asymptotic cavity network |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210512 Address after: No. 1036, Shandong high tech Zone wave road, Ji'nan, Shandong Applicant after: INSPUR GROUP Co.,Ltd. Address before: North 6th floor, S05 building, Langchao Science Park, 1036 Langchao Road, hi tech Zone, Jinan City, Shandong Province, 250100 Applicant before: SHANDONG INSPUR ARTIFICIAL INTELLIGENCE RESEARCH INSTITUTE Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |