CN111079704A - Face recognition method and device based on quantum computation - Google Patents
Face recognition method and device based on quantum computation Download PDFInfo
- Publication number
- CN111079704A CN111079704A CN201911410739.9A CN201911410739A CN111079704A CN 111079704 A CN111079704 A CN 111079704A CN 201911410739 A CN201911410739 A CN 201911410739A CN 111079704 A CN111079704 A CN 111079704A
- Authority
- CN
- China
- Prior art keywords
- quantum
- face
- vector
- operating system
- computing cloud
- 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.)
- Withdrawn
Links
Images
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
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N10/00—Quantum computing, i.e. information processing based on quantum-mechanical phenomena
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Abstract
The invention relates to a face recognition method and a face recognition device based on quantum computation, wherein the face recognition method comprises the following steps: providing face acquisition equipment and a quantum computing cloud platform, wherein the quantum computing cloud platform comprises three layers of software and hardware architectures, the bottommost layer is a quantum computer, the middle layer is a quantum computing cloud operating system, and the uppermost layer is a classical computer; acquiring a plurality of face images through face acquisition equipment; the method comprises the steps that after image preprocessing is carried out on a human face image on a classical computer, the human face image is sent to a quantum computing cloud operating system; performing parallel feature extraction on the face image through a deep learning network by a quantum computing cloud operating system through quantum preparation and quantum measurement and quantum computer interaction, and correspondingly obtaining a plurality of feature vectors to be classified; carrying out dissimilarity measurement on the plurality of feature vectors and the category vectors; and identifying a plurality of feature vectors to be classified according to the dissimilarity measure to obtain an identification result. The invention can enhance the parallel processing capability for face recognition.
Description
Technical Field
The invention relates to the technical field of quantum computation and computer vision, in particular to a face recognition method and device based on quantum computation.
Background
Compared with the classical computer, the quantum computer carries out calculation in a completely different mode, thereby bringing a new revolution to the calculation technology. The concept of quantum computers was introduced in the 80's of the 20 th century and since then was in the category of basic research for a long time. At present, quantum computing is being shifted from basic research to application research and engineering realization. Quantum computing is distributed by scientific and technological macros and scientific research institutions in the world, and quantum computers of different physical systems are released by D-Wave company, Google, IBM, China and China, Zhejiang university, Ali baba and the like.
Face recognition is one of the important tasks for computer vision applications, and identity verification or identification is performed by converting facial images acquired by using a camera into data which can be calculated and has identity distinguishing capability. The face recognition technology has extremely important application value in application scenes such as security protection, criminal investigation and authorization, and is an important technology for protecting lives and properties of people from being invaded and facilitating development of work by functional departments. With the wide application of face recognition technology, the large amount of accumulation of face data makes the calculation task of the classic computer become heavy. Moreover, with the improvement of the informatization degree and the wide application of the artificial intelligence technology, the requirements of functional departments on the face recognition technology are higher and higher, and the quantum face recognition technology with low time delay, low energy consumption, high performance and high precision is produced.
Disclosure of Invention
The invention aims to provide a face recognition method and a face recognition device based on quantum computing so as to realize a quantum face recognition technology with low time delay, low energy consumption, high performance and high precision. Therefore, the invention adopts the following specific technical scheme:
according to an aspect of the present invention, a face recognition method based on quantum computation is provided, wherein the face recognition method comprises the following steps:
providing face acquisition equipment and a quantum computing cloud platform, wherein the quantum computing cloud platform comprises three layers of software and hardware architectures, the bottommost layer is a quantum computer, the middle layer is a quantum computing cloud operating system, and the uppermost layer is a classical computer;
acquiring a plurality of face images through face acquisition equipment;
the method comprises the steps that after image preprocessing is carried out on a human face image on a classical computer, the human face image is sent to a quantum computing cloud operating system;
performing parallel feature extraction on the face image through a deep learning network by a quantum computing cloud operating system through quantum preparation and quantum measurement and quantum computer interaction, and correspondingly obtaining a plurality of feature vectors to be classified;
performing a dissimilarity measure on the plurality of feature vectors and a category vector;
and identifying the plurality of feature vectors to be classified according to the dissimilarity measure to obtain an identification result.
Further, the image preprocessing includes image enhancement processing for performing enhancement processing on a dark picture taken at evening or night.
Further, the image enhancement processing adopts a logarithmic computation enhancement method, and the specific process is as follows:
storing the log values of 0-255 pixel values as a table;
and quickly looking up a table from the storage table to obtain the pixel value corresponding to the darker image pixel point.
Further, the method also comprises the following steps:
training a deep learning network, specifically, constructing a face vector and a parameter vector in a cloud operating system, and initializing the parameter vector; the face vector is transmitted to a deep learning network for training, a gradient vector is formed by a comparison result through similarity comparison with a target class vector in the training process, and the gradient vector is transmitted in the reverse direction to correct the parameter vector; the training process is completed by a quantum computing cloud operating system through preparation and measurement of quanta and interactive parallel computing of a quantum computer.
Further, the dissimilarity measure includes a euclidean distance measure and a cosine distance measure.
Further, the face acquisition equipment comprises a camera and terminal equipment with the camera.
According to another aspect of the invention, a face recognition device based on quantum computing is provided, and the face recognition device can comprise face acquisition equipment and a quantum computing cloud platform, wherein the quantum computing cloud platform comprises three layers of software and hardware architectures, the bottommost layer is a quantum computer, the middle layer is a quantum computing cloud operating system, and the topmost layer is a classical computer;
the face acquisition equipment is used for acquiring a face image;
the classical computer is used for carrying out image preprocessing on the face images so as to improve the definition of the face images;
the quantum cloud operating system interacts with a quantum computer through quantum preparation and quantum measurement, and is provided with:
the characteristic extraction module is used for carrying out quantum computation on the face image, carrying out characteristic extraction in parallel and correspondingly obtaining a plurality of characteristic vectors to be identified;
the dissimilarity measurement module is used for performing dissimilarity measurement on the plurality of feature vectors and the category vectors;
and the identification module is used for identifying the plurality of feature vectors to be classified according to the dissimilarity measure to obtain an identification result.
Further, the quantum cloud operating system is further provided with a parameter training module for training the deep learning network to obtain deep learning network parameters, specifically, a face vector and a parameter vector are constructed in the cloud operating system, and the parameter vector is initialized; the face vector is transmitted to a deep learning network for training, a gradient vector is formed by a comparison result through similarity comparison with a target class vector in the training process, and the gradient vector is transmitted in the reverse direction to correct the parameter vector.
Further, the face acquisition equipment comprises a camera and terminal equipment with the camera.
Further, the quantum computer comprises a quantum processor or quantum chip, the quantum processor comprising a quantum wire and a quantum gate, the quantum wire consisting of initialization of quantum bits, a set of quantum gates and a final information reading; the quantum gate comprises a Hadmard gate (H), a pi/4 phase gate (S), a pi/8 phase gate (T) and a controlled NOT gate (CNOT).
By adopting the technical scheme, the invention has the beneficial effects that: the quantum computing cloud platform is a parallel computing platform based on a quantum computer, and the training of the human face parameter vector and the recognition of the human face are both based on the quantum computing cloud platform, so that the parallel processing capability of the human face recognition can be enhanced and the recognition speed is increased by adopting the method and the system.
Drawings
To further illustrate the various embodiments, the invention provides the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the embodiments. Those skilled in the art will appreciate still other possible embodiments and advantages of the present invention with reference to these figures. Elements in the figures are not drawn to scale and like reference numerals are generally used to indicate like elements.
Fig. 1 is a flowchart of a face recognition method based on quantum computation according to a first embodiment of the present invention;
fig. 2 is a block diagram of a face recognition apparatus based on quantum computation according to a first embodiment of the present invention;
FIG. 3 is a block diagram of the quantum computer shown in FIG. 2;
fig. 4 is a comparison diagram before and after face image preprocessing.
FIG. 5 is a flow chart of the quantum computation based face recognition deep network training according to the second embodiment of the present invention;
fig. 6 is a flow chart of face recognition based on quantum computation according to a third embodiment of the present invention.
Detailed Description
The invention will now be further described with reference to the accompanying drawings and detailed description.
Example one
As shown in fig. 1 to 3, a face recognition method based on quantum computation, wherein the face recognition method comprises the following steps:
s100, providing a face acquisition device 1 and a quantum computing cloud platform 2. The face acquisition device 1 is a terminal device with a camera, such as a smart phone, a tablet computer, an access control system, a classic computer, and the like. The quantum computing cloud platform 2 comprises three layers of software and hardware architectures, wherein the bottommost layer is a quantum computer 21, the middle layer is a quantum computing cloud operating system 22, the topmost layer is a classical computer 23, and the three parts are closely cooperated to complete the whole process. The quantum cloud operating system is computer software, runs on a classic computer server, and provides an interactive interface between the classic computer 23 and the quantum computer 21. Quantum computer 21 may include, among other things, a quantum chip or quantum processor 211, a power supply component 212, a quantum memory 213, a quantum preparation interface 214, and a quantum measurement interface 215. The quantum processor comprises a quantum wire and a quantum gate, wherein the quantum wire is composed of initialization of quantum bits, a group of quantum gates and final information reading; the quantum gate comprises a Hadmard gate (H), a pi/4 phase gate (S), a pi/8 phase gate (T), a controlled NOT gate (CNOT) and the like. The quantum computer 21 interacts with the quantum cloud operating system 22 through two interfaces of quantum preparation and quantum measurement.
S102, a plurality of face images are collected through the face collecting equipment 1 (such as a mobile phone). The mobile phone sends the collected human face collection equipment 1 to a classical computer 21 of the quantum computing cloud platform 2.
And S104, preprocessing the face image on a classical computer, and sending the face image to a quantum computing cloud operating system. Specifically, the image preprocessing comprises enhancement processing of human faces, and detection and alignment of the human faces; the method not only comprises the pretreatment of a single face, but also comprises the pretreatment of a plurality of faces. The preprocessing is to increase the definition of the face image and the consistency of the face size. The enhancement processing of the human face adopts a logarithmic function to carry out rapid processing. As shown in fig. 3, the contrast between the face image before enhancement and the face image after enhancement increases the sharpness of the face image. Preferably, the enhancement processing of the human face adopts a logarithm calculation enhancement method: storing the log values of 0-255 pixel values as a table; and quickly looking up a table from the storage table to obtain the pixel value corresponding to the darker image pixel point. The table lookup method can realize rapid enhancement processing of the face image. The detection and alignment of the human face are realized by finding out the characteristic points of the human face, so that the human face is cut into a square frame, and the alignment of the human face is carried out by taking the eye center point of the human face as a standard.
And S106, performing parallel feature extraction on the face image through quantum preparation and quantum measurement and quantum computer interaction by a quantum computing cloud operating system through a deep learning network, and correspondingly obtaining a plurality of feature vectors (face vectors) to be classified. The feature extraction process of the deep learning network is well known to those skilled in the art and will not be further described here.
And S108, carrying out dissimilarity measurement on the plurality of feature vectors and the category vectors. Wherein the dissimilarity measure includes a Euclidean distance measure and a cosine distance measure. This process is well known to those skilled in the art and will not be described further herein.
And S110, identifying the plurality of feature vectors to be classified according to the dissimilarity measure to obtain an identification result.
That is, the face recognition process is: and constructing a face vector in a quantum computing cloud operating system, transmitting the face vector to a deep learning network for computing, and comparing the face vector with a target class vector so as to identify the identity of the face. Meanwhile, the identification process interacts with a quantum computer, and the two processes of preparation and measurement of the quantum are carried out; thereby participating in the high-speed parallel computing process of the quantum computer.
In addition, the face recognition method may further include the steps of: training a deep learning network, specifically, constructing a face vector and a parameter vector in a quantum computing cloud operating system, and initializing the parameter vector; the face vector is transmitted to a deep learning network for training, a gradient vector is formed by a comparison result through similarity comparison with a target class vector in the training process, and the gradient vector is transmitted in the reverse direction to correct the parameter vector; the training process is completed by a quantum computing cloud operating system through preparation and measurement of quanta and interactive parallel computing of a quantum computer.
Because the quantum computing cloud platform is a parallel computing platform based on a quantum computer, and the training of the human face parameter vector and the recognition of the human face are both based on the quantum computing cloud platform, the parallel processing capability of the human face recognition can be enhanced and the recognition speed is increased by adopting the method and the system.
Example two
In this embodiment, a training process of a deep learning network for quantum face recognition is required, as shown in fig. 5. The acquisition of the face images is started, as shown in S201, which includes the acquisition of a plurality of face images. Next, face image preprocessing is performed, as shown in S202, and the specific processing procedure is described above and will not be repeated here. Both steps are handled by the terminal computer. Then, transmitting the preprocessed face images to a quantum cloud operating system, constructing face vectors and parameter vectors in the quantum cloud operating system, and initializing the parameter vectors, as shown in S203; the vectors are transmitted to a deep learning network for training, the similarity between the vectors and the target class vectors is compared in the training process, the comparison result forms gradient vectors, and the gradient vectors are transmitted in the reverse direction to correct the parameter vectors, as shown in S204. Meanwhile, the training process interacts with the quantum computer, and the two processes of quantum preparation and measurement are carried out, such as S205; thereby participating in the high-speed parallel computing process of the quantum computer, as shown in S206. And the interactive process is parallel processing, a plurality of face vectors can be trained simultaneously, and the deep learning network parameters can be corrected.
EXAMPLE III
In this embodiment, a face recognition process of quantum computing deep learning is included, as shown in fig. 6. First, a face image is collected, as shown in S301, which includes collecting a plurality of face images. Next, face image preprocessing is performed, as shown in S302, and the specific processing procedure is described above and will not be repeated here. Both steps are handled by the terminal computer. Then, transmitting the preprocessed face images to a quantum cloud operating system, and constructing face vectors in the quantum cloud operating system, as shown in S303; the face vector is transmitted to the deep learning network for calculation, and is compared with the target category vector, so as to identify the identity of the face, as shown in S304. Meanwhile, the identification process interacts with the quantum computer, and the two processes of quantum preparation and measurement are carried out, such as S305; thereby participating in the high-speed parallel computing process of the quantum computer, as shown in S306.
While the invention has been particularly shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A face recognition method based on quantum computation is characterized by comprising the following steps:
providing face acquisition equipment and a quantum computing cloud platform, wherein the quantum computing cloud platform comprises three layers of software and hardware architectures, the bottommost layer is a quantum computer, the middle layer is a quantum computing cloud operating system, and the uppermost layer is a classical computer;
acquiring a plurality of face images through face acquisition equipment;
the method comprises the steps that after image preprocessing is carried out on a human face image on a classical computer, the human face image is sent to a quantum computing cloud operating system;
performing parallel feature extraction on the face image through a deep learning network by a quantum computing cloud operating system through quantum preparation and quantum measurement and quantum computer interaction, and correspondingly obtaining a plurality of feature vectors to be classified;
performing a dissimilarity measure on the plurality of feature vectors and a category vector;
and identifying the plurality of feature vectors to be classified according to the dissimilarity measure to obtain an identification result.
2. The face recognition method according to claim 1, wherein the image preprocessing includes image enhancement processing for a dark picture taken at evening or night.
3. The face recognition method according to claim 2, wherein the image enhancement processing adopts a logarithmic computation enhancement method, and the specific process is as follows:
storing the log values of 0-255 pixel values as a table;
and quickly looking up a table from the storage table to obtain the pixel value corresponding to the darker image pixel point.
4. The face recognition method of claim 1, further comprising the steps of:
training a deep learning network, specifically, constructing a face vector and a parameter vector in a quantum computing cloud operating system, and initializing the parameter vector; the face vector is transmitted to a deep learning network for training, a gradient vector is formed by a comparison result through similarity comparison with a target class vector in the training process, and the gradient vector is transmitted in the reverse direction to correct the parameter vector; the training process is completed by a quantum computing cloud operating system through preparation and measurement of quanta and interactive parallel computing of a quantum computer.
5. The method of claim 4, wherein the dissimilarity measure comprises a Euclidean distance measure and a cosine distance measure.
6. The face recognition method according to claim 1, wherein the face acquisition device is a terminal device with a camera.
7. A face recognition device based on quantum computing is characterized by comprising face acquisition equipment and a quantum computing cloud platform, wherein the quantum computing cloud platform comprises three layers of software and hardware architectures, the bottommost layer is a quantum computer, the middle layer is a quantum computing cloud operating system, and the uppermost layer is a classical computer;
the face acquisition equipment is used for acquiring a face image;
the classical computer is used for carrying out image preprocessing on the face images so as to improve the definition of the face images;
the quantum cloud operating system interacts with a quantum computer through quantum preparation and quantum measurement, and is provided with:
the characteristic extraction module is used for carrying out quantum computation on the face image, carrying out characteristic extraction in parallel and correspondingly obtaining a plurality of characteristic vectors to be identified;
the dissimilarity measurement module is used for performing dissimilarity measurement on the plurality of feature vectors and the category vectors;
and the identification module is used for identifying the plurality of feature vectors to be classified according to the dissimilarity measure to obtain an identification result.
8. The face recognition device according to claim 7, wherein the quantum cloud operating system is further provided with a parameter training module, configured to train a deep learning network to obtain deep learning network parameters, specifically, construct a face vector and a parameter vector in the cloud operating system, and initialize the parameter vector; the face vector is transmitted to a deep learning network for training, a gradient vector is formed by a comparison result through similarity comparison with a target class vector in the training process, and the gradient vector is transmitted in the reverse direction to correct the parameter vector.
9. The face recognition apparatus according to claim 7, wherein the face acquisition device is a terminal device with a camera.
10. The face recognition device of claim 7, wherein the quantum computer comprises a quantum processor or quantum chip, the quantum processor comprising quantum wires and quantum gates, the quantum wires consisting of initialization of quantum bits, a set of quantum gates, and a final information read; the quantum gate comprises a Hadmard gate (H), a pi/4 phase gate (S), a pi/8 phase gate (T) and a controlled NOT gate (CNOT).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911410739.9A CN111079704A (en) | 2019-12-31 | 2019-12-31 | Face recognition method and device based on quantum computation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911410739.9A CN111079704A (en) | 2019-12-31 | 2019-12-31 | Face recognition method and device based on quantum computation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111079704A true CN111079704A (en) | 2020-04-28 |
Family
ID=70321137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911410739.9A Withdrawn CN111079704A (en) | 2019-12-31 | 2019-12-31 | Face recognition method and device based on quantum computation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111079704A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112651418A (en) * | 2020-05-25 | 2021-04-13 | 腾讯科技（深圳）有限公司 | Data classification method, classifier training method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109213603A (en) * | 2018-05-31 | 2019-01-15 | 合肥本源量子计算科技有限责任公司 | A kind of cloud platform and platform operation method for docking quantum computer and user |
| US20190102220A1 (en) * | 2017-09-29 | 2019-04-04 | International Business Machines Corporation | Job processing in quantum computing enabled cloud environments |
| CN208766679U (en) * | 2018-09-05 | 2019-04-19 | 深圳太古计算机系统有限公司 | A kind of face identification system based on quantum calculation |
| CN109934047A (en) * | 2017-12-15 | 2019-06-25 | 浙江舜宇智能光学技术有限公司 | Face identification system and its face identification method based on deep learning |
| CN110069385A (en) * | 2019-04-26 | 2019-07-30 | 济南浪潮高新科技投资发展有限公司 | Quantum cloud monitoring system and method based on Internet of Things |
| CN110309692A (en) * | 2018-03-27 | 2019-10-08 | 杭州海康威视数字技术股份有限公司 | Face identification method, apparatus and system, model training method and device |
-
2019
- 2019-12-31 CN CN201911410739.9A patent/CN111079704A/en not_active Withdrawn
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190102220A1 (en) * | 2017-09-29 | 2019-04-04 | International Business Machines Corporation | Job processing in quantum computing enabled cloud environments |
| CN109934047A (en) * | 2017-12-15 | 2019-06-25 | 浙江舜宇智能光学技术有限公司 | Face identification system and its face identification method based on deep learning |
| CN110309692A (en) * | 2018-03-27 | 2019-10-08 | 杭州海康威视数字技术股份有限公司 | Face identification method, apparatus and system, model training method and device |
| CN109213603A (en) * | 2018-05-31 | 2019-01-15 | 合肥本源量子计算科技有限责任公司 | A kind of cloud platform and platform operation method for docking quantum computer and user |
| CN208766679U (en) * | 2018-09-05 | 2019-04-19 | 深圳太古计算机系统有限公司 | A kind of face identification system based on quantum calculation |
| CN110069385A (en) * | 2019-04-26 | 2019-07-30 | 济南浪潮高新科技投资发展有限公司 | Quantum cloud monitoring system and method based on Internet of Things |
Non-Patent Citations (1)
| Title |
|---|
| 吕相文: "高性能计算云环境下GPU并行计算技术及应用研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112651418A (en) * | 2020-05-25 | 2021-04-13 | 腾讯科技（深圳）有限公司 | Data classification method, classifier training method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109558832B (en) | Human body posture detection method, device, equipment and storage medium | |
| CN111738244B (en) | Image detection method, image detection device, computer equipment and storage medium | |
| CN111460968B (en) | Unmanned aerial vehicle identification and tracking method and device based on video | |
| CN110503076B (en) | Video classification method, device, equipment and medium based on artificial intelligence | |
| WO2021139324A1 (en) | Image recognition method and apparatus, computer-readable storage medium and electronic device | |
| US20220222918A1 (en) | Image retrieval method and apparatus, storage medium, and device | |
| WO2015149534A1 (en) | Gabor binary pattern-based face recognition method and device | |
| CN110765860A (en) | Tumble determination method, tumble determination device, computer apparatus, and storage medium | |
| EP4085369A1 (en) | Forgery detection of face image | |
| WO2021218238A1 (en) | Image processing method and image processing apparatus | |
| Gupta et al. | Advanced security system in video surveillance for COVID-19 | |
| JP2022133378A (en) | Face biological detection method, device, electronic apparatus, and storage medium | |
| Xu et al. | Multi‐pyramid image spatial structure based on coarse‐to‐fine pyramid and scale space | |
| CN110008922A (en) | Image processing method, unit, medium for terminal device | |
| CN112464873A (en) | Model training method, face living body recognition method, system, device and medium | |
| CN111079704A (en) | Face recognition method and device based on quantum computation | |
| CN111881803A (en) | Livestock face recognition method based on improved YOLOv3 | |
| CN113723310B (en) | Image recognition method and related device based on neural network | |
| CN116188956A (en) | Method and related equipment for detecting deep fake face image | |
| CN113033305B (en) | Living body detection method, living body detection device, terminal equipment and storage medium | |
| CN114913339A (en) | Training method and device of feature map extraction model | |
| CN113869253A (en) | Living body detection method, living body training device, electronic apparatus, and medium | |
| CN117036658A (en) | Image processing method and related equipment | |
| US11087121B2 (en) | High accuracy and volume facial recognition on mobile platforms | |
| CN114067394A (en) | Face living body detection method and device, electronic equipment and storage medium |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200428 |
|
| WW01 | Invention patent application withdrawn after publication |