CN112232302A - Face recognition method - Google Patents
Face recognition method Download PDFInfo
- Publication number
- CN112232302A CN112232302A CN202011281345.0A CN202011281345A CN112232302A CN 112232302 A CN112232302 A CN 112232302A CN 202011281345 A CN202011281345 A CN 202011281345A CN 112232302 A CN112232302 A CN 112232302A
- Authority
- CN
- China
- Prior art keywords
- picture
- face recognition
- face
- recognition method
- server
- 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- Withdrawn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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 10
- 238000011161 development Methods 0.000 claims description 13
- 230000006835 compression Effects 0.000 claims description 12
- 238000007906 compression Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 13
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
- G06T9/001—Model-based coding, e.g. wire frame
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a face recognition method, which is executed by a server and comprises the steps of judging whether pictures needing face recognition exist or not, compressing and coding the pictures, extracting feature values related to faces, storing the feature values in a database and building a training model, wherein the model is trained by adopting a large number of face pictures of children; the method is executed by a client and comprises the steps of capturing dynamic video stream, grabbing faces in the dynamic video stream, initializing engine configuration, extracting characteristic values and matching the characteristic values, and finding out corresponding information. The invention carries out personalized customization by combining a general face recognition technology with a specific application scene, and is particularly applied to the face recognition scene of children, so that the recognition speed and the recognition precision under the specific scene are maximized, the face recognition operation can be finished off-line only by storing the database of the server in the local, the real off-line face recognition is realized, the recognition operation can be finished under the off-line state, a plurality of platform application scenes are provided, and the compatibility is strong.
Description
Technical Field
The invention relates to the technical field of cable production, in particular to a face recognition method.
Background
Face recognition is a biometric technology for identity recognition based on facial feature information of a person. A series of related technologies, also commonly called face recognition and face recognition, are used to collect images or video streams containing faces by using a camera or a video camera, automatically detect and track the faces in the images, and then perform face recognition on the detected faces.
The research of the face recognition system starts in the 60 s of the 20 th century, and is improved along with the development of computer technology and optical imaging technology after the 80 s, and really enters the early application stage at the later stage of 90 s; the key to the success of the face recognition system is whether the face recognition system has a core algorithm with a sharp end or not, and the recognition result has practical recognition rate and recognition speed; the face recognition system integrates various professional technologies such as artificial intelligence, machine recognition, machine learning, model theory, expert system, video image processing and the like, and simultaneously needs to combine the theory and realization of intermediate value processing, is the latest application of biological feature recognition, realizes the core technology of the face recognition system, and shows the conversion from weak artificial intelligence to strong artificial intelligence.
With the development of scientific technology, the appearance of face recognition in various fields is seen everywhere in our lives. In a specific field, face recognition also undergoes relatively long continuous optimization development from early face geometric feature comparison to later local texture feature comparison and finally to the current common deep learning mode.
At present, the technology of face recognition tends to mature, the mature face recognition algorithms are model training for the face of an adult, and the models are not ideal for face recognition of children in kindergarten scenes.
Disclosure of Invention
The invention aims to provide a face recognition method, which combines a general face recognition technology with a specific application scene for personalized customization, and is particularly applied to the face recognition scene of children, so that the recognition speed and the recognition precision under the specific scene are maximized, the face recognition operation can be completed under the offline condition only by storing a database of a server in the local, the real offline face recognition is realized, the recognition operation can be completed under the offline condition, a plurality of platform application scenes are provided, and the compatibility is strong, so that the problems in the background technology are solved.
In order to achieve the above object, the present invention provides a face recognition method, executed by a server, comprising:
judging whether a client end in communication connection with the server end has a picture needing face recognition, wherein the picture is an image of a living body face;
compressing the picture;
encoding the picture;
extracting feature values related to the face in the picture;
storing the characteristic value in a database for being obtained by a client matched with the characteristic value;
and (4) building a training model, and training the model by adopting a large number of face pictures of children.
Preferably, the method further comprises preprocessing the picture.
Preferably, the preprocessing the picture includes:
performing histogram equalization on the picture;
gamma calibration is carried out on the pictures;
and carrying out backlight compensation on the picture.
Preferably, the development languages used by the server are php and java.
Preferably, the compressing the picture includes:
acquiring picture entity information of the picture;
setting compression configuration information of the picture;
and compressing the picture into a target picture according to the picture entity information and the compression configuration information.
Preferably, the setting of the compression configuration information of the picture includes:
determining the picture category to which the picture belongs according to the picture entity information;
and setting the compression configuration information according to the picture category.
Preferably, the encoding the picture includes:
inputting the picture into a picture coding model which is trained in advance;
and determining the coding information of the picture based on the characteristic information output by the picture coding model.
Meanwhile, the invention provides a face recognition method, which is executed by a client and comprises the following steps:
capturing a dynamic video stream through a face recognition camera on the client side which is in communication connection with the server side, and capturing image information;
starting a face detection engine, and capturing a face in the dynamic video stream;
starting a face recognition engine and initializing engine configuration;
extracting face-related feature values captured in the dynamic video stream;
and matching the characteristic values stored in the database of the server to find out corresponding information.
Preferably, the development languages used by the client are java and nodejs, respectively.
Preferably, the client extracts feature values related to the faces captured in the dynamic video stream and feature values matched and stored in the database of the server in a multithread calling manner.
Compared with the prior art, the invention has the beneficial effects that:
1. the universal face recognition technology is combined with a specific application scene to carry out personalized customization, and is particularly applied to the face recognition scene of children, so that the recognition speed and the recognition precision under the specific scene are maximized;
2. the face recognition operation can be completed in an off-line condition only by storing the database of the server locally, so that the real off-line face recognition is realized, and the recognition operation can be completed in an off-line state;
3. the platform has multiple application scenes and strong compatibility.
Drawings
Fig. 1 is a first schematic flow chart of a face recognition method according to the present invention;
fig. 2 is a schematic flow chart of a face recognition method according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the following embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
As shown in fig. 1, the present invention provides a face recognition method, which is executed by a server, wherein the development languages used by the server are php and java, and the method includes:
and judging whether a client end in communication connection with the server end has a picture needing face recognition, wherein the picture is an image of a living body face.
Preprocessing the picture:
performing histogram equalization on the picture;
gamma calibration is carried out on the picture;
and carrying out backlight compensation on the picture.
Compressing the picture:
acquiring picture entity information of a picture;
determining the picture category to which the picture belongs according to the picture entity information, and setting compression configuration information according to the picture category;
and compressing the picture into a target picture according to the picture entity information and the compression configuration information.
Encoding a picture:
inputting the picture into a picture coding model which is trained in advance;
and determining the coding information of the picture based on the characteristic information output by the picture coding model.
And extracting the characteristic value related to the face in the picture.
And storing the characteristic value in a database for the client matched with the characteristic value to obtain.
And (4) building a training model, and training the model by adopting a large number of face pictures of children.
Example 2
As shown in fig. 2, the present invention provides a face recognition method, which is executed by a client, wherein the development languages used by the client are java and nodejs, respectively, and the method includes:
and capturing dynamic video stream through a face recognition camera on a client side in communication connection with the server side, and capturing image information.
And starting a face detection engine and capturing a face in the dynamic video stream.
And starting a face recognition engine and initializing engine configuration.
And extracting the face-related characteristic values captured in the dynamic video stream by adopting a multithread calling mode.
And matching the characteristic values stored in the database of the server side by adopting a multithread calling mode to find out corresponding information.
Example 3
As shown in fig. 1 and 2, the present invention provides a face recognition method, which is executed by both a server and a client, wherein the development languages used by the server are php and java, and the development languages used by the client are java and nodejs, respectively, and the method includes:
and judging whether a client end in communication connection with the server end has a picture needing face recognition, wherein the picture is an image of a living body face.
Preprocessing the picture:
performing histogram equalization on the picture;
gamma calibration is carried out on the picture;
and carrying out backlight compensation on the picture.
Compressing the picture:
acquiring picture entity information of a picture;
determining the picture category to which the picture belongs according to the picture entity information, and setting compression configuration information according to the picture category;
and compressing the picture into a target picture according to the picture entity information and the compression configuration information.
Encoding a picture:
inputting the picture into a picture coding model which is trained in advance;
and determining the coding information of the picture based on the characteristic information output by the picture coding model.
And extracting the characteristic value related to the face in the picture.
And storing the characteristic value in a database for the client matched with the characteristic value to obtain.
And (4) building a training model, and training the model by adopting a large number of face pictures of children.
And capturing dynamic video stream through a face recognition camera on a client side in communication connection with the server side, and capturing image information.
And starting a face detection engine and capturing a face in the dynamic video stream.
And starting a face recognition engine and initializing engine configuration.
And extracting the face-related characteristic values captured in the dynamic video stream by adopting a multithread calling mode.
And matching the characteristic values stored in the database of the server side by adopting a multithread calling mode to find out corresponding information.
When the software development system is used, firstly, the open-source iris soft SDK is downloaded, then the corresponding SDK is introduced into a service end project and a client end project, the development languages used by the client end of the project are java and nodejs respectively, and the development languages used by the server end are php and java. Finally, the feature extraction and the face feature comparison are realized through java, and nodejs and php communicate with java to show a required result to a user or store the required result in a database.
In conclusion, the invention combines the general face recognition technology with the specific application scene to carry out personalized customization, in particular to the face recognition scene of the children, so that the recognition speed and the recognition precision under the specific scene are maximized; the face recognition operation can be completed in an off-line condition only by storing the database of the server locally, so that the real off-line face recognition is realized, and the recognition operation can be completed in an off-line state; the platform has multiple application scenes and strong compatibility.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A face recognition method is executed by a server side, and is characterized by comprising the following steps:
judging whether a client end in communication connection with the server end has a picture needing face recognition, wherein the picture is an image of a living body face;
compressing the picture;
encoding the picture;
extracting feature values related to the face in the picture;
storing the characteristic value in a database for being obtained by a client matched with the characteristic value;
and (4) building a training model, and training the model by adopting a large number of face pictures of children.
2. The face recognition method of claim 1, further comprising preprocessing the picture.
3. The face recognition method of claim 2, wherein the pre-processing the picture comprises:
performing histogram equalization on the picture;
gamma calibration is carried out on the pictures;
and carrying out backlight compensation on the picture.
4. The face recognition method of claim 1, wherein the development languages used by the server are php and java.
5. The face recognition method of claim 1, wherein the compressing the picture comprises:
acquiring picture entity information of the picture;
setting compression configuration information of the picture;
and compressing the picture into a target picture according to the picture entity information and the compression configuration information.
6. The face recognition method of claim 5, wherein the setting of the compression configuration information of the picture comprises:
determining the picture category to which the picture belongs according to the picture entity information;
and setting the compression configuration information according to the picture category.
7. The face recognition method of claim 1, wherein the encoding the picture comprises:
inputting the picture into a picture coding model which is trained in advance;
and determining the coding information of the picture based on the characteristic information output by the picture coding model.
8. A face recognition method, executed by a client, comprising:
capturing a dynamic video stream through a face recognition camera on the client side which is in communication connection with the server side, and capturing image information;
starting a face detection engine, and capturing a face in the dynamic video stream;
starting a face recognition engine and initializing engine configuration;
extracting face-related feature values captured in the dynamic video stream;
and matching the characteristic values stored in the database of the server to find out corresponding information.
9. The face recognition method of claim 8, wherein the development languages used by the client are java and nodejs, respectively.
10. The face recognition method of claim 8, wherein the client uses a multi-threaded calling method to extract face-related feature values captured in the dynamic video stream and match feature values stored in the database of the server.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011281345.0A CN112232302A (en) | 2020-11-17 | 2020-11-17 | Face recognition method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011281345.0A CN112232302A (en) | 2020-11-17 | 2020-11-17 | Face recognition method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112232302A true CN112232302A (en) | 2021-01-15 |
Family
ID=74123488
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011281345.0A Withdrawn CN112232302A (en) | 2020-11-17 | 2020-11-17 | Face recognition method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112232302A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115134425A (en) * | 2022-06-20 | 2022-09-30 | 北京京东乾石科技有限公司 | Message processing method and device |
-
2020
- 2020-11-17 CN CN202011281345.0A patent/CN112232302A/en not_active Withdrawn
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115134425A (en) * | 2022-06-20 | 2022-09-30 | 北京京东乾石科技有限公司 | Message processing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111370020B (en) | Method, system, device and storage medium for converting voice into lip shape | |
CN109472198B (en) | Gesture robust video smiling face recognition method | |
US6792144B1 (en) | System and method for locating an object in an image using models | |
CN108920640B (en) | Context obtaining method and device based on voice interaction | |
CN102271241A (en) | Image communication method and system based on facial expression/action recognition | |
CN110598580A (en) | Human face living body detection method | |
CN108921032B (en) | Novel video semantic extraction method based on deep learning model | |
CN116825365B (en) | Mental health analysis method based on multi-angle micro-expression | |
CN113570689B (en) | Portrait cartoon method, device, medium and computing equipment | |
CN111639580A (en) | Gait recognition method combining feature separation model and visual angle conversion model | |
CN113361489A (en) | Decoupling representation-based face orthogonalization model construction method and training method | |
CN115131405A (en) | Speaker tracking method and system based on multi-mode information | |
CN112232302A (en) | Face recognition method | |
WO2022041182A1 (en) | Method and device for making music recommendation | |
CN117095471A (en) | Face counterfeiting tracing method based on multi-scale characteristics | |
CN116883900A (en) | Video authenticity identification method and system based on multidimensional biological characteristics | |
Wei et al. | Three-dimensional joint geometric-physiologic feature for lip-reading | |
CN112183727A (en) | Countermeasure generation network model, and shot effect rendering method and system based on countermeasure generation network model | |
CN113435248A (en) | Mask face recognition base enhancement method, device, equipment and readable storage medium | |
CN113254713A (en) | Multi-source emotion calculation system and method for generating emotion curve based on video content | |
CN111950447B (en) | Emotion recognition method and system based on walking gesture and storage medium | |
CN115063892B (en) | Examination room abnormal behavior detection method and system | |
CN117612551A (en) | Lip synchronous video generation method, device, equipment and medium | |
CN113313096B (en) | Multi-dimensional data generation method based on micro-expression and facies and related equipment thereof | |
CN112101102A (en) | Method for acquiring 3D limb movement in RGB video based on artificial intelligence |
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: 20210115 |
|
WW01 | Invention patent application withdrawn after publication |