CN110533002B - Big data processing method based on face recognition - Google Patents
Big data processing method based on face recognition Download PDFInfo
- Publication number
- CN110533002B CN110533002B CN201910842286.0A CN201910842286A CN110533002B CN 110533002 B CN110533002 B CN 110533002B CN 201910842286 A CN201910842286 A CN 201910842286A CN 110533002 B CN110533002 B CN 110533002B
- Authority
- CN
- China
- Prior art keywords
- face
- feature block
- face image
- face feature
- block
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- 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
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Library & Information Science (AREA)
- Human Computer Interaction (AREA)
- Medical Informatics (AREA)
- Bioethics (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention provides a big data processing method based on face recognition, which comprises the following steps: acquiring a face image through a camera; preprocessing the face image to obtain a clear face image; extracting a face feature block from a clear face image; storing the human face feature block, the clear human face image and the corresponding identity information in a platform; transmitting the face feature block to a face recognition terminal; the face recognition terminal receives the face feature block and stores the face feature block in a face feature block library; and the face recognition terminal periodically updates the issued face feature block and stores the face feature block in a face feature block library.
Description
Technical Field
The invention relates to a big data processing method based on face recognition.
Background
At present, a face recognition terminal can be divided into online recognition or offline recognition, human faces are compared after the face is collected by a face brushing terminal in the online recognition, the influence of a network is large, and the customer experience is poor. And (4) off-line identification, wherein a general platform issues all face information to a face identification terminal, and the face identification terminal performs comparison.
However, the problem that the face information is directly issued from the back-end platform to the face recognition terminal is that the information is safe, and the face information may leak, for example, after the face recognition terminal is cracked, the face information of all the people may leak.
Disclosure of Invention
The invention provides a big data processing method based on face recognition, which can effectively solve the problems.
The invention is realized by the following steps:
a big data processing method based on face recognition comprises the following steps:
acquiring a face image through a camera;
preprocessing the face image to obtain a clear face image;
extracting a face feature block from the clear face image, wherein the face feature block comprises at least one of an eye block, a jaw block, a lip block, an eyebrow block and a nose block;
storing the human face feature block, the clear human face image and the corresponding identity information in a platform, binding the human face feature block, the clear human face image and the corresponding identity information, and establishing a unique mapping relation;
transmitting the face feature block to a face recognition terminal;
the face recognition terminal receives the face feature block and stores the face feature block in a face feature block library;
and the face recognition terminal periodically updates the issued face feature block and stores the face feature block in a face feature block library.
As a further improvement, the step of preprocessing the face image to obtain a clear face image includes:
recognizing the collected face image through a face recognition frame on the camera;
setting the coordinate of a self-exposure window of the recognized face image to be consistent with the coordinate of a face recognition frame of the camera, wherein the self-exposure window is larger than the face recognition frame;
and adaptively configuring the exposure value of the corresponding self-exposure window according to the intensity of the background light, so as to perform corresponding exposure and finally obtain a clear face image.
As a further improvement, the step of preprocessing the face image to obtain a clear face image includes:
recognizing the collected face image through a face recognition frame on the camera;
setting the coordinate of a self-exposure window of the recognized face image to be consistent with the coordinate of a face recognition frame of the camera, wherein the self-exposure window is larger than the face recognition frame;
and adaptively configuring the exposure value of the corresponding self-exposure window according to the intensity of the background light, so as to perform corresponding exposure and finally obtain a clear face image.
As a further improvement, the self-exposure window is 1.1-2 times of the face recognition frame.
As a further improvement, the length of the self-exposure window is greater than the length of the face recognition frame, so as to obtain a chin picture.
As a further improvement, the step of transmitting the face feature block to the face recognition terminal includes:
and periodically transmitting and updating the face feature block to a face recognition terminal, wherein the face feature block is transmitted in a single direction through an optical gate.
The invention has the beneficial effects that: the face feature block, not the whole face information, is transmitted to the face recognition terminal and stored in the face feature block library, and even if the face recognition terminal is cracked, the whole face cannot be restored, so that the safety of the face information can be effectively ensured, and in addition, the leakage of the personnel information corresponding to the face image can be avoided. In addition, the coordinate setting of the self-exposure window of the recognized face image is consistent with the coordinate setting of the face recognition frame of the camera, and the self-exposure window is larger than the face recognition frame, so that a complete face image, particularly an image of a mandible block, can be obtained; in addition, the exposure value of the corresponding self-exposure window is configured in a self-adaptive manner according to the intensity of the background light, so that corresponding exposure is carried out, and finally a clear face image is obtained.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a flowchart of a big data processing method based on face recognition according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a face recognition frame and a self-exposure window in the big data processing method based on face recognition according to the embodiment of the present invention.
Fig. 3 is a schematic diagram illustrating a face recognition frame and a self-exposure window in a big data processing method based on face recognition according to another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings of the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Referring to fig. 1, an embodiment of the present invention provides a big data processing method based on face recognition, including the following steps:
a big data processing method based on face recognition comprises the following steps:
s1, acquiring a face image through a camera;
s2, preprocessing the face image to obtain a clear face image;
s3, extracting a face feature block from the clear face image, wherein the face feature block comprises at least one of an eye block, a jaw block, a lip block, an eyebrow block and a nose block;
s4, storing the face feature block, the clear face image and the corresponding identity information in a platform, binding the face feature block, the clear face image and the corresponding identity information, and establishing a unique mapping relation;
s5, transmitting the face feature block to a face recognition terminal;
s6, the face recognition terminal receives the face feature block and stores the face feature block in a face feature block library;
and S7, the face recognition terminal periodically updates the issued face feature blocks and stores the face feature blocks in a face feature block library.
In step S2, as a further improvement, the step of preprocessing the face image to obtain a sharp face image includes:
s21, recognizing the collected face image through a face recognition frame on the camera;
s22, setting the coordinate of a self-exposure window of the recognized face image to be consistent with the coordinate of a face recognition frame of the camera, wherein the self-exposure window is larger than the face recognition frame;
and S23, adaptively configuring the exposure value of the corresponding self-exposure window according to the intensity of the background light, so as to perform corresponding exposure and finally obtain a clear face image.
In step S21, the size of the general face recognition frame is difficult to cover the entire face, particularly the chin portion.
In step S22, the coordinates of the self-exposure window of the recognized face image are set to be consistent with the coordinates of the face recognition frame of the camera, that is, the self-exposure window and the face recognition frame share the same origin, the X axis and the Y axis. As a further improvement, the self-exposure window can be 1.1-2 times of the face recognition frame. Referring to fig. 2, in this embodiment, the self-exposure window is 1.69 times that of the face recognition frame, that is, the length and the style of the self-exposure window are correspondingly enlarged by 1.3 times. Referring to fig. 3, in other embodiments, in order to obtain a clear chin picture, it is preferable to enlarge the length of the self-exposure window by 1.3 times.
In step S23, the method of automatic exposure is not described in detail again for the prior art.
In step S3, the face feature block is preferably an eye block, because the eye block is the most recognizable block and has the most features. In addition, a lip region may also be selected. In the present embodiment, only the eye block is selected.
In step S4, the facial feature blocks are bound with the clear facial image and the corresponding identity information, and a unique mapping relationship is established, so that the clear facial image and the corresponding identity information can be quickly acquired, and the error rate is reduced.
In step S5, the facial feature block may be periodically updated to the face recognition terminal through a wireless communication module or a wired communication module. The face feature blocks are periodically transmitted and updated to the face recognition terminal to be in a single-direction issuing behavior, and the face feature blocks can be transmitted by arranging a single-direction optical shutter.
After step S7, the method may further include:
and S8, the face recognition terminal extracts the face feature blocks of the face image to be recognized, compares the face feature blocks of the face image to be recognized with the face feature blocks in the face feature block library respectively, and acquires a clear face image matched with the face image to be recognized and corresponding identity information thereof when the comparison is successful.
In step S8, as a further improvement, the step of comparing the face feature blocks of the to-be-recognized face image with the face feature blocks in the face feature block library respectively includes:
and S81, comparing the eye blocks of the face image to be recognized with the eye blocks in the face feature block library respectively.
In one embodiment, the step of comparing the face feature blocks of the face image to be recognized with the face feature blocks in the face feature block library, and when the comparison is successful, acquiring a clear face image matched with the face image to be recognized and identity information corresponding to the clear face image includes:
s82-1, when at least one face feature block in the face image to be recognized is successfully compared with at least one face feature block in the face feature block library, controlling the face recognition terminal to send a first request to the platform;
s82-2, when the platform receives the first request, the platform issues a corresponding clear face image to the face recognition terminal;
s82-3, the face recognition terminal compares the issued clear face image with the face image to be recognized, when the comparison is successful, the face recognition terminal is controlled to send a second request to the platform, and when the platform receives the second request, the platform issues corresponding identity information to the face recognition terminal; otherwise, the face recognition terminal continuously compares the face feature blocks of the face image to be recognized with other face feature blocks in the face feature block library respectively.
In step S82-3, the method for comparing the face feature blocks of the to-be-recognized face image with other face feature blocks in the face feature block library further includes:
and S82-4, deleting the issued clear face image from the face recognition terminal.
In another embodiment, the step of comparing the face feature blocks of the face image to be recognized with the face feature blocks in the face feature block library, and when the comparison is successful, acquiring a clear face image matched with the face image to be recognized and identity information corresponding to the clear face image includes:
s83-1, when at least one face feature block in the face image to be recognized is successfully compared with at least one face feature block in the face feature block library, the face recognition terminal sends the face image to be recognized and the successfully compared face feature block to the platform;
s83-2, the platform acquires a corresponding clear face image according to the successfully compared face feature blocks;
s83-3, the platform further compares the corresponding clear face image with the face image to be recognized, and issues the clear face image matched with the face image to be recognized and the corresponding identity information thereof to the face recognition terminal after the comparison is successful; and otherwise, issuing a command for continuously comparing the face feature blocks of the face image to be recognized with other face feature blocks in the face feature block library to the face recognition terminal.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A big data processing method based on face recognition is characterized by comprising the following steps:
acquiring a face image through a camera;
preprocessing the face image to obtain a clear face image;
extracting a face feature block from the clear face image, wherein the face feature block comprises at least one of an eye block, a jaw block, a lip block, an eyebrow block and a nose block;
storing the human face feature block, the clear human face image and the corresponding identity information in a platform, binding the human face feature block, the clear human face image and the corresponding identity information, and establishing a unique mapping relation;
transmitting the face feature block to a face recognition terminal;
the face recognition terminal receives the face feature block and stores the face feature block in a face feature block library;
the face recognition terminal periodically updates the issued face feature block and stores the face feature block in a face feature block library; further comprising:
the face recognition terminal extracts a face feature block of a face image to be recognized, compares the face feature block of the face image to be recognized with face feature blocks in the face feature block library respectively, and acquires a clear face image matched with the face image to be recognized and identity information corresponding to the clear face image when the comparison is successful, and the face recognition terminal specifically comprises:
when at least one face feature block in the face image to be recognized is successfully compared with at least one face feature block in the face feature block library, the face recognition terminal sends the face image to be recognized and the successfully compared face feature block to the platform;
the platform acquires a corresponding clear face image according to the successfully compared face feature blocks;
the platform further compares the corresponding clear face image with the face image to be recognized, and issues the clear face image matched with the face image to be recognized and the identity information corresponding to the clear face image to be recognized to the face recognition terminal after the comparison is successful; and otherwise, issuing a command for continuously comparing the face feature blocks of the face image to be recognized with other face feature blocks in the face feature block library to the face recognition terminal.
2. The big data processing method based on face recognition according to claim 1, wherein the step of preprocessing the face image to obtain a clear face image comprises:
recognizing the collected face image through a face recognition frame on the camera;
setting the coordinate of a self-exposure window of the recognized face image to be consistent with the coordinate of a face recognition frame of the camera, wherein the self-exposure window is larger than the face recognition frame;
and adaptively configuring the exposure value of the corresponding self-exposure window according to the intensity of the background light, so as to perform corresponding exposure and finally obtain a clear face image.
3. The big data processing method based on face recognition according to claim 2, wherein the self-exposure window is 1.1-2 times of the face recognition frame.
4. The big data processing method based on face recognition according to claim 2, wherein the length of the self-exposure window is greater than the length of the face recognition frame, so as to obtain a chin picture.
5. The big data processing method based on face recognition according to claim 1, wherein the step of transmitting the face feature block to the face recognition terminal comprises:
and periodically transmitting and updating the face feature block to a face recognition terminal, wherein the face feature block is transmitted in a single direction through an optical gate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910842286.0A CN110533002B (en) | 2019-09-06 | 2019-09-06 | Big data processing method based on face recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910842286.0A CN110533002B (en) | 2019-09-06 | 2019-09-06 | Big data processing method based on face recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110533002A CN110533002A (en) | 2019-12-03 |
CN110533002B true CN110533002B (en) | 2022-04-12 |
Family
ID=68667493
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910842286.0A Active CN110533002B (en) | 2019-09-06 | 2019-09-06 | Big data processing method based on face recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110533002B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109214310A (en) * | 2018-08-16 | 2019-01-15 | 安徽超清科技股份有限公司 | Improve the method and face identification system of recognition of face efficiency |
CN111614638A (en) * | 2020-05-08 | 2020-09-01 | 快猪侠信息技术(杭州)有限公司 | Face recognition data distribution system and method based on big data platform |
CN112232206B (en) * | 2020-10-16 | 2021-05-18 | 天津天权教育科技有限公司 | Face recognition method and face recognition platform based on big data and artificial intelligence |
CN114998979B (en) * | 2022-08-01 | 2022-11-18 | 中国通信建设第三工程局有限公司 | Intelligent Internet of vehicles system |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107967458A (en) * | 2017-12-06 | 2018-04-27 | 宁波亿拍客网络科技有限公司 | A kind of face identification method |
CN110084207A (en) * | 2019-04-30 | 2019-08-02 | 惠州市德赛西威智能交通技术研究院有限公司 | Automatically adjust exposure method, device and the storage medium of face light exposure |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105095881B (en) * | 2015-08-21 | 2023-04-07 | 小米科技有限责任公司 | Face recognition method, face recognition device and terminal |
-
2019
- 2019-09-06 CN CN201910842286.0A patent/CN110533002B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107967458A (en) * | 2017-12-06 | 2018-04-27 | 宁波亿拍客网络科技有限公司 | A kind of face identification method |
CN110084207A (en) * | 2019-04-30 | 2019-08-02 | 惠州市德赛西威智能交通技术研究院有限公司 | Automatically adjust exposure method, device and the storage medium of face light exposure |
Also Published As
Publication number | Publication date |
---|---|
CN110533002A (en) | 2019-12-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110533002B (en) | Big data processing method based on face recognition | |
CN110533001B (en) | Big data face recognition method based on face recognition | |
CN111428581B (en) | Face shielding detection method and system | |
WO2021072673A1 (en) | User identity identification method and apparatus, and electronic device | |
CN107818308A (en) | A kind of recognition of face intelligence comparison method, electronic installation and computer-readable recording medium | |
CN108447159B (en) | Face image acquisition method and device and entrance and exit management system | |
CN108171032A (en) | A kind of identity identifying method, electronic device and computer readable storage medium | |
WO2021174880A1 (en) | Feature extraction model training method, facial recognition method, apparatus, device and medium | |
CN108829900A (en) | A kind of Research on face image retrieval based on deep learning, device and terminal | |
CN116110100B (en) | Face recognition method, device, computer equipment and storage medium | |
CN107766785A (en) | A kind of face recognition method | |
CN111444862A (en) | Face recognition method and device | |
CN104778392A (en) | Privilege validation method and system on basis of biological identification | |
CN108734092A (en) | Personage's authentication device | |
CN111839455A (en) | Eye sign identification method and equipment for thyroid-associated ophthalmopathy | |
CN109544384A (en) | Subsidy distribution method, device, terminal, storage medium based on bio-identification | |
US20230036338A1 (en) | Method and apparatus for generating image restoration model, medium and program product | |
CN115240262A (en) | Face recognition method, system, computer device and medium based on end-side cooperation | |
CN115147261A (en) | Image processing method, device, storage medium, equipment and product | |
CN110443577A (en) | A kind of campus attendance checking system based on recognition of face | |
US10929984B2 (en) | Systems and methods for shaking action recognition based on facial feature points | |
KR20220038877A (en) | Individual facial recognition method and system using artificial intelligence | |
CN108334821B (en) | Image processing method and electronic equipment | |
CN114445528B (en) | Virtual image generation method and device, electronic equipment and storage medium | |
CN113158744A (en) | Security protection management system based on face recognition |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |