CN110598574A - Intelligent face monitoring and identifying method and system - Google Patents
Intelligent face monitoring and identifying method and system Download PDFInfo
- Publication number
- CN110598574A CN110598574A CN201910772884.5A CN201910772884A CN110598574A CN 110598574 A CN110598574 A CN 110598574A CN 201910772884 A CN201910772884 A CN 201910772884A CN 110598574 A CN110598574 A CN 110598574A
- Authority
- CN
- China
- Prior art keywords
- face image
- face
- image
- human
- recognition
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an intelligent face monitoring and identifying method and system, wherein the method comprises the following steps: acquiring a face image in real time through face image acquisition equipment, and acquiring the detection of a face area in the image through a face skin color technology; the method comprises the following steps of finishing preprocessing a face image by a light compensation technology, a gray level transformation technology, a contrast enhancement technology and a histogram processing technology; marking the characteristic parts of the face image, extracting characteristic values of the marked characteristic parts, and training to obtain a face image model; and comparing the face image model with the face models stored in the database, and if the error is within the threshold value, finishing the identification of the face image. The invention can well realize the recognition of the face image.
Description
Technical Field
The invention relates to the technical field of face image recognition, in particular to an intelligent face monitoring and recognizing method and system.
Background
With the advancement of science and technology and the development of biology, the biometric technology has received high attention in recent decades and has been developed to a great extent, and at present, the urgent need of human beings for automatic identity verification is increasingly deepened. The internal attribute-biological characteristics of people naturally have larger individual difference due to the difference among individuals, and the biological characteristics have irreplaceable status as an ideal basis for identity verification based on the stability of the human beings. The biometric technology gradually enters the visual field of people, the current mainstream biometric technology mainly comprises fingerprint identification, face identification, iris identification, retina identification, vein identification and the like, and compared with other identification technologies, the face identification technology is taken as a main research direction in the biometric identification technology and has the advantages of initiative, user friendliness, non-invasiveness and the like. With the rapid development of the world economy, the face recognition system is particularly important in such a large environment.
Disclosure of Invention
The technical problem to be solved by the embodiment of the invention is as follows: an intelligent face monitoring and recognizing method and system are provided to solve the problems in the prior art.
According to one aspect of the embodiment of the invention, an intelligent face monitoring and identifying method is disclosed, which comprises the following steps:
acquiring a face image in real time through face image acquisition equipment, and acquiring the detection of a face area in the image through a face skin color technology;
the method comprises the following steps of finishing preprocessing a face image by a light compensation technology, a gray level transformation technology, a contrast enhancement technology and a histogram processing technology;
marking the characteristic parts of the face image, extracting characteristic values of the marked characteristic parts, and training to obtain a face image model;
and comparing the face image model with the face models stored in the database, and if the error is within the threshold value, finishing the identification of the face image.
In another embodiment of the foregoing intelligent face monitoring and identifying method according to the present invention, the histogram processing technique includes: maximum method, average method, weighted average method
The average value method is that the RGB value of each pixel point is equal to the average value of the RGB values of the original pixel points;
the weighted average method is a weighted average method, the RGB weight of each pixel point is appointed according to needs, and the weighted average value is taken.
In another embodiment of the above intelligent face monitoring and recognition method, the labeling the characteristic parts of the face image, extracting characteristic values from the labeled characteristic parts, and obtaining the face image model after training includes:
detecting a skin color area, namely adopting a YCbCr color space for the acquired face image to reduce the influence of illumination on skin color;
dividing a face candidate region, and realizing the detection of the size and the position of the region of the characteristic part of the face image by combining the color and brightness mapping of the characteristic part of the face image;
and classifying the face candidate regions, performing integral image calculation on the feature parts of the face image, calculating haar features, and combining the weak classifiers into a strong classifier.
In another embodiment of the above intelligent face monitoring and recognition method according to the present invention, the comparing the face image model with the face model stored in the database, and if the error threshold is within, completing the recognition of the face image includes:
on the basis of analyzing and measuring the characteristic parts of the face image, the face image is regarded as a high-dimensional vector space;
performing space conversion on the high-dimensional vector space through a subspace algorithm, and compressing high-dimensional face image data into a low-dimensional subspace;
the human face image model is established by analyzing the pixel characteristics, segmenting visual information and combining the geometric distribution of the facial characteristics.
In another embodiment of the above intelligent face monitoring and identifying method according to the present invention, the method further includes: establishing a rule for face recognition, wherein the rule for establishing face recognition comprises the following steps:
the human face image topology information is used for classifying the characteristic parts of the human face image, a template is established by utilizing the information recorded in real time, and the human face recognition is realized according to the distribution points of the detection positions of the characteristic parts of the human face image;
the face image symmetry information is used for identifying the feature part of the face image according to the symmetry feature of the face image;
and the human face image contour information is used for detecting the edge of the human face image, extracting the edge curve of the human face image and evaluating the human face by each curve.
Based on another aspect of the embodiments of the present invention, an intelligent face monitoring and recognition system is disclosed, which includes:
the system comprises a face image acquisition and detection module, a face image preprocessing module, a face image feature extraction module and a face matching and recognition module;
the human face image acquisition and detection module is used for acquiring human face image information, processing the human face image, acquiring the accurate position of the human face image, realizing human face detection, acquiring the human face image and sending the human face image to the human face image preprocessing module;
the human face image preprocessing module receives the human face image and then performs gray correction processing on the human face image, so that information loss during image conversion is reduced;
the facial image feature extraction module identifies the feature parts of the facial image, extracts the feature values of the feature parts and stores the feature values in a local database;
and the face matching and identifying module performs retrieval matching according to the face image characteristic value extracted by the face image characteristic value extracting module and a characteristic template existing in a database, and outputs a matching result when the similarity exceeds a set threshold.
In another embodiment of the above intelligent face monitoring and recognition system according to the present invention, the face image acquisition and detection module includes a face image acquisition unit and a face image detection unit;
the human face image acquisition unit acquires image information of a human body through image acquisition equipment;
the human face image detection unit acquires useful information in the human face image through a characteristic algorithm on the human body image acquired by the human face image acquisition unit, so that the accurate capture of the position of the human face in the image is realized;
the feature algorithm adopted by the face image detection unit comprises the following steps: histogram feature, template feature and Haar feature algorithm.
In another embodiment of the above intelligent face monitoring and recognition system, the method for preprocessing the face image by the face image preprocessing module includes:
the light compensation technology is used for carrying out light compensation on the face image in a YCrCb color space of the face image so as to balance the illumination condition of the face image, wherein a Y component represents the brightness of one pixel, Cr represents a red component, and Cb represents a blue component;
the gray scale change technology is used for converting the color face image into a black-and-white face image and displaying complex color face image information by using a simple black-and-white face image;
the contrast enhancement technology processes the black and white face image again, further pulls the contrast apart, obtains different processing effects by selecting analytic formulas of different enhancement functions, and directly performs gray processing on each pixel of the original image;
binarization, namely performing black-white processing on a face image, and comprises three methods: maximum, mean, weighted mean; the average value method is that the RGB value of each pixel point is equal to the average value of the RGB values of the original pixel points; the weighted average method is to assign the RGB weight of each pixel point according to the requirement and take the weighted average value.
In another embodiment of the above intelligent face monitoring and recognition system according to the present invention, the face image feature extraction module performs face detection based on AdaBoost algorithm, and implements face detection by using Haar-like features through an integrogram, including:
detecting a skin color area, namely acquiring an image of the face area by detecting the difference of skin color brightness of the face area;
dividing a face candidate region, and realizing the detection of the size and the position of a face characteristic part by combining the color and the brightness mapping of a face image;
and (4) classifying the face candidate regions, performing integral graph calculation on the face candidate regions, calculating haar characteristics, and combining a plurality of weak classifiers into a strong classifier.
In another embodiment of the above intelligent face monitoring and recognition system, the face matching and recognition module uses a face as a high-dimensional vector through a feature of the face, performs spatial transformation by using a subspace method on the basis of analyzing and measuring features of the face feature, and compresses high-dimensional face image data into a low-dimensional subspace, and the face matching and recognition module sets a recognition rule as follows:
face image topological information, namely establishing a face template by using the face image topological information recorded in real time, and detecting position distribution points of face characteristic parts so as to realize face identification;
the human face image symmetry information detects the distribution of human face characteristic parts through the symmetry characteristics of human faces, thereby realizing human face recognition;
face image contour information, edge detection of the face image, extraction of face image edge curves, and evaluation of the face by each curve.
Compared with the prior art, the invention has the following advantages:
the intelligent face monitoring and identifying method and the intelligent face monitoring and identifying system acquire the face image in real time, then carry out face detection, carry out feature extraction on the face image through gray level transformation, gray level equalization and histogram processing, obtain a face model after training, and compare the face model with models in a database, so that face identification is realized, and the face image can be well identified.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below of the drawings used in the description of the embodiments or the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic structural diagram of an embodiment of an intelligent face monitoring and recognition system of the present invention.
Fig. 2 is a flowchart of an embodiment of the intelligent face monitoring and recognizing method of the present invention.
In the figure: the system comprises a face image acquisition and detection module 1, a face image preprocessing module 2, a face image feature extraction module 3 and a face matching and recognition module 4.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the 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.
The following describes an intelligent face monitoring and recognizing method and system provided by the invention in more detail with reference to the accompanying drawings and embodiments.
Fig. 1 is a schematic structural diagram of an embodiment of an intelligent face monitoring and recognition system of the present invention, and as shown in fig. 1, the intelligent face monitoring and recognition system of the embodiment includes:
the system comprises a face image acquisition and detection module 1, a face image preprocessing module 2, a face image feature extraction module 3 and a face matching and recognition module 4;
the human face image acquisition and detection module 1 is used for acquiring human face image information, processing the human face image, acquiring the accurate position of the human face image, realizing human face detection, acquiring the human face image and sending the human face image to the human face image preprocessing module 2;
the face image preprocessing module 2 receives the face image and then performs gray correction processing on the face image, so that information loss during image conversion is reduced;
the human face image feature extraction module 3 identifies the feature parts of the human face image, extracts the feature values of the feature parts and stores the feature values in a local database;
the face matching and identifying module 4 performs retrieval matching according to the face image characteristic value extracted by the face image characteristic value extracting module and a characteristic template existing in a database, and outputs a matching result when the similarity exceeds a set threshold.
The face image acquisition and detection module 1 comprises a face image acquisition unit and a face image detection unit;
the human face image acquisition unit acquires image information of a human body through image acquisition equipment;
the human face image detection unit acquires useful information in the human face image through a characteristic algorithm on the human body image acquired by the human face image acquisition unit, so that the accurate capture of the position of the human face in the image is realized;
the feature algorithm adopted by the face image detection unit comprises the following steps: histogram feature, template feature and Haar feature algorithm.
The method for preprocessing the face image by the face image preprocessing module 2 comprises the following steps:
the light compensation technology is used for carrying out light compensation on the face image in a YCrCb color space of the face image so as to balance the illumination condition of the face image, wherein a Y component represents the brightness of one pixel, Cr represents a red component, and Cb represents a blue component;
the gray scale change technology is used for converting the color face image into a black-and-white face image and displaying complex color face image information by using a simple black-and-white face image;
the contrast enhancement technology processes the black and white face image again, further pulls the contrast apart, obtains different processing effects by selecting analytic formulas of different enhancement functions, and directly performs gray processing on each pixel of the original image;
binarization, namely performing black-white processing on a face image, and comprises three methods: maximum, mean, weighted mean; the average value method is that the RGB value of each pixel point is equal to the average value of the RGB values of the original pixel points; the weighted average method is to assign the RGB weight of each pixel point according to the requirement and take the weighted average value.
The facial image feature extraction module 3 adopts an AdaBoost algorithm to perform facial detection, and realizes facial detection by using Haar-like features through an integrogram, and comprises the following steps:
detecting a skin color area, namely acquiring an image of the face area by detecting the difference of skin color brightness of the face area;
dividing a face candidate region, and realizing the detection of the size and the position of a face characteristic part by combining the color and the brightness mapping of a face image;
and (4) classifying the face candidate regions, performing integral graph calculation on the face candidate regions, calculating haar characteristics, and combining a plurality of weak classifiers into a strong classifier.
The face matching and recognition module 4 takes the face as a high-dimensional vector through the feature of the face, performs spatial transformation by adopting a subspace method on the basis of analyzing and measuring the features of the face feature, compresses high-dimensional face image data into a low-dimensional subspace, and sets a recognition rule as follows by the face matching and recognition module 4:
face image topological information, namely establishing a face template by using the face image topological information recorded in real time, and detecting position distribution points of face characteristic parts so as to realize face identification;
the human face image symmetry information detects the distribution of human face characteristic parts through the symmetry characteristics of human faces, thereby realizing human face recognition;
face image contour information, edge detection of the face image, extraction of face image edge curves, and evaluation of the face by each curve.
Fig. 2 is a flowchart of an embodiment of an intelligent face monitoring and recognizing method according to the present invention, and as shown in fig. 2, the intelligent face monitoring and recognizing method includes:
acquiring a face image in real time through face image acquisition equipment, and acquiring the detection of a face area in the image through a face skin color technology;
20, finishing preprocessing the face image by means of a light compensation technology, a gray level transformation technology, a contrast enhancement technology and a histogram processing technology;
30, marking the characteristic parts of the face image, extracting characteristic values of the marked characteristic parts, and training to obtain a face image model;
and 40, comparing the face image model with the face models stored in the database, and if the error is within the threshold value, finishing the identification of the face image.
The histogram processing technique includes: maximum method, average method, weighted average method
The average value method is that the RGB value of each pixel point is equal to the average value of the RGB values of the original pixel points;
the weighted average method is a weighted average method, the RGB weight of each pixel point is appointed according to needs, and the weighted average value is taken.
The method for marking the characteristic parts of the face image and extracting the characteristic values of the marked characteristic parts comprises the following steps of:
detecting a skin color area, namely adopting a YCbCr color space for the acquired face image to reduce the influence of illumination on skin color;
dividing a face candidate region, and realizing the detection of the size and the position of the region of the characteristic part of the face image by combining the color and brightness mapping of the characteristic part of the face image;
and classifying the face candidate regions, performing integral image calculation on the feature parts of the face image, calculating haar features, and combining the weak classifiers into a strong classifier.
Comparing the face image model with the face models stored in the database, and if the error threshold is within, finishing the identification of the face image comprises the following steps:
on the basis of analyzing and measuring the characteristic parts of the face image, the face image is regarded as a high-dimensional vector space;
performing space conversion on the high-dimensional vector space through a subspace algorithm, and compressing high-dimensional face image data into a low-dimensional subspace;
the human face image model is established by analyzing the pixel characteristics, segmenting visual information and combining the geometric distribution of the facial characteristics.
Further comprising: establishing a rule for face recognition, wherein the rule for establishing face recognition comprises the following steps:
the human face image topology information is used for classifying the characteristic parts of the human face image, a template is established by utilizing the information recorded in real time, and the human face recognition is realized according to the distribution points of the detection positions of the characteristic parts of the human face image;
the face image symmetry information is used for identifying the feature part of the face image according to the symmetry feature of the face image;
and the human face image contour information is used for detecting the edge of the human face image, extracting the edge curve of the human face image and evaluating the human face by each curve.
The above describes the intelligent face monitoring and recognition method and system provided by the present invention in detail, and a specific example is applied in the text to explain the principle and the implementation of the present invention, and the description of the above embodiment is only used to help understand the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.
Claims (10)
1. An intelligent face monitoring and recognizing method is characterized by comprising the following steps:
acquiring a face image in real time through face image acquisition equipment, and acquiring the detection of a face area in the image through a face skin color technology;
the method comprises the following steps of finishing preprocessing a face image by a light compensation technology, a gray level transformation technology, a contrast enhancement technology and a histogram processing technology;
marking the characteristic parts of the face image, extracting characteristic values of the marked characteristic parts, and training to obtain a face image model;
and comparing the face image model with the face models stored in the database, and if the error is within the threshold value, finishing the identification of the face image.
2. The intelligent face monitoring and recognition method according to claim 1, wherein the histogram processing technique comprises: maximum method, average method, weighted average method
The average value method is that the RGB value of each pixel point is equal to the average value of the RGB values of the original pixel points;
the weighted average method is a weighted average method, the RGB weight of each pixel point is appointed according to needs, and the weighted average value is taken.
3. The intelligent face monitoring and recognition method according to claim 2, wherein the steps of labeling the characteristic parts of the face image, extracting characteristic values from the labeled characteristic parts, and obtaining the face image model after training comprise:
detecting a skin color area, namely adopting a YCbCr color space for the acquired face image to reduce the influence of illumination on skin color;
dividing a face candidate region, and realizing the detection of the size and the position of the region of the characteristic part of the face image by combining the color and brightness mapping of the characteristic part of the face image;
and classifying the face candidate regions, performing integral image calculation on the feature parts of the face image, calculating haar features, and combining the weak classifiers into a strong classifier.
4. The intelligent face monitoring and recognition method according to claim 1, wherein the comparing the face image model with the face models stored in the database, and if the face image model is within an error threshold, completing recognition of the face image comprises:
on the basis of analyzing and measuring the characteristic parts of the face image, the face image is regarded as a high-dimensional vector space;
performing space conversion on the high-dimensional vector space through a subspace algorithm, and compressing high-dimensional face image data into a low-dimensional subspace;
the human face image model is established by analyzing the pixel characteristics, segmenting visual information and combining the geometric distribution of the facial characteristics.
5. The intelligent face monitoring and recognition method according to claim 4, further comprising: establishing a rule for face recognition, wherein the rule for establishing face recognition comprises the following steps:
the human face image topology information is used for classifying the characteristic parts of the human face image, a template is established by utilizing the information recorded in real time, and the human face recognition is realized according to the distribution points of the detection positions of the characteristic parts of the human face image;
the face image symmetry information is used for identifying the feature part of the face image according to the symmetry feature of the face image;
and the human face image contour information is used for detecting the edge of the human face image, extracting the edge curve of the human face image and evaluating the human face by each curve.
6. An intelligent face monitoring and recognition system, comprising:
the system comprises a face image acquisition and detection module, a face image preprocessing module, a face image feature extraction module and a face matching and recognition module;
the human face image acquisition and detection module is used for acquiring human face image information, processing the human face image, acquiring the accurate position of the human face image, realizing human face detection, acquiring the human face image and sending the human face image to the human face image preprocessing module;
the human face image preprocessing module receives the human face image and then performs gray correction processing on the human face image, so that information loss during image conversion is reduced;
the facial image feature extraction module identifies the feature parts of the facial image, extracts the feature values of the feature parts and stores the feature values in a local database;
and the face matching and identifying module performs retrieval matching according to the face image characteristic value extracted by the face image characteristic value extracting module and a characteristic template existing in a database, and outputs a matching result when the similarity exceeds a set threshold.
7. The intelligent face monitoring and recognition system according to claim 6, wherein the face image acquisition and detection module comprises a face image acquisition unit and a face image detection unit;
the human face image acquisition unit acquires image information of a human body through image acquisition equipment;
the human face image detection unit acquires useful information in the human face image through a characteristic algorithm on the human body image acquired by the human face image acquisition unit, so that the accurate capture of the position of the human face in the image is realized;
the feature algorithm adopted by the face image detection unit comprises the following steps: histogram feature, template feature and Haar feature algorithm.
8. The intelligent face monitoring and recognition system according to claim 6, wherein the face image preprocessing module preprocesses the face image according to a method comprising:
the light compensation technology is used for carrying out light compensation on the face image in a YCrCb color space of the face image so as to balance the illumination condition of the face image, wherein a Y component represents the brightness of one pixel, Cr represents a red component, and Cb represents a blue component;
the gray scale change technology is used for converting the color face image into a black-and-white face image and displaying complex color face image information by using a simple black-and-white face image;
the contrast enhancement technology processes the black and white face image again, further pulls the contrast apart, obtains different processing effects by selecting analytic formulas of different enhancement functions, and directly performs gray processing on each pixel of the original image;
binarization, namely performing black-white processing on a face image, and comprises three methods: maximum, mean, weighted mean; the average value method is that the RGB value of each pixel point is equal to the average value of the RGB values of the original pixel points; the weighted average method is to assign the RGB weight of each pixel point according to the requirement and take the weighted average value.
9. The intelligent face monitoring and recognizing system according to claim 6, wherein the face image feature extraction module performs face detection based on an AdaBoost algorithm, and realizes face detection by using Haar-like features through an integrogram, including:
detecting a skin color area, namely acquiring an image of the face area by detecting the difference of skin color brightness of the face area;
dividing a face candidate region, and realizing the detection of the size and the position of a face characteristic part by combining the color and the brightness mapping of a face image;
and (4) classifying the face candidate regions, performing integral graph calculation on the face candidate regions, calculating haar characteristics, and combining a plurality of weak classifiers into a strong classifier.
10. The intelligent face monitoring and recognition system of claim 6, wherein the face matching and recognition module uses the face as a high-dimensional vector through the feature of the face, performs spatial transformation by using a subspace method on the basis of analyzing and measuring the features of the face feature, and compresses the high-dimensional face image data into a low-dimensional subspace, and the face matching and recognition module sets the recognition rules as follows:
face image topological information, namely establishing a face template by using the face image topological information recorded in real time, and detecting position distribution points of face characteristic parts so as to realize face identification;
the human face image symmetry information detects the distribution of human face characteristic parts through the symmetry characteristics of human faces, thereby realizing human face recognition;
face image contour information, edge detection of the face image, extraction of face image edge curves, and evaluation of the face by each curve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910772884.5A CN110598574A (en) | 2019-08-21 | 2019-08-21 | Intelligent face monitoring and identifying method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910772884.5A CN110598574A (en) | 2019-08-21 | 2019-08-21 | Intelligent face monitoring and identifying method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110598574A true CN110598574A (en) | 2019-12-20 |
Family
ID=68854998
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910772884.5A Pending CN110598574A (en) | 2019-08-21 | 2019-08-21 | Intelligent face monitoring and identifying method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110598574A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111712021A (en) * | 2020-06-16 | 2020-09-25 | 深圳市千百辉照明工程有限公司 | Intelligent adjusting method, device and system for lamplight of art gallery |
| CN111950409A (en) * | 2020-07-31 | 2020-11-17 | 江苏大学 | Intelligent identification method and system for road marking line |
| CN112861781A (en) * | 2021-03-06 | 2021-05-28 | 同辉电子科技股份有限公司 | Subpixel arrangement mode for intelligent illumination |
| CN116363736A (en) * | 2023-05-31 | 2023-06-30 | 山东农业工程学院 | Big data user information acquisition method based on digitalization |
| CN118230395A (en) * | 2024-05-13 | 2024-06-21 | 广东电网有限责任公司 | Human face recognition method and device based on INSIGHTFACE and LIS file management |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103258191A (en) * | 2013-05-15 | 2013-08-21 | 苏州福丰科技有限公司 | Community access control system based on face recognition |
| CN107220624A (en) * | 2017-05-27 | 2017-09-29 | 东南大学 | A kind of method for detecting human face based on Adaboost algorithm |
-
2019
- 2019-08-21 CN CN201910772884.5A patent/CN110598574A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103258191A (en) * | 2013-05-15 | 2013-08-21 | 苏州福丰科技有限公司 | Community access control system based on face recognition |
| CN107220624A (en) * | 2017-05-27 | 2017-09-29 | 东南大学 | A kind of method for detecting human face based on Adaboost algorithm |
Non-Patent Citations (3)
| Title |
|---|
| 梁毅雄: "基于子空间分析的人脸特征提取及识别研究", 《万方数据》 * |
| 王雷: "人脸识别系统在山海关船厂边防检查中的应用", 《中国优秀博硕士学位论文全文数据库（硕土）信息科技辑》 * |
| 陈晓宾: "基于肤色和AdaBoost算法的人脸检测方法研究", 《中国优秀博硕士位论文全文数据库（硕士） 信息科技辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111712021A (en) * | 2020-06-16 | 2020-09-25 | 深圳市千百辉照明工程有限公司 | Intelligent adjusting method, device and system for lamplight of art gallery |
| CN111950409A (en) * | 2020-07-31 | 2020-11-17 | 江苏大学 | Intelligent identification method and system for road marking line |
| CN111950409B (en) * | 2020-07-31 | 2024-05-14 | 江苏大学 | Intelligent identification method and system for road marking line |
| CN112861781A (en) * | 2021-03-06 | 2021-05-28 | 同辉电子科技股份有限公司 | Subpixel arrangement mode for intelligent illumination |
| CN112861781B (en) * | 2021-03-06 | 2023-06-30 | 同辉电子科技股份有限公司 | Sub-pixel arrangement mode for intelligent illumination |
| CN116363736A (en) * | 2023-05-31 | 2023-06-30 | 山东农业工程学院 | Big data user information acquisition method based on digitalization |
| CN116363736B (en) * | 2023-05-31 | 2023-08-18 | 山东农业工程学院 | Big data user information acquisition method based on digitalization |
| CN118230395A (en) * | 2024-05-13 | 2024-06-21 | 广东电网有限责任公司 | Human face recognition method and device based on INSIGHTFACE and LIS file management |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109389074B (en) | Facial feature point extraction-based expression recognition method | |
| CN103632132B (en) | Face detection and recognition method based on skin color segmentation and template matching | |
| CN111126240B (en) | Three-channel feature fusion face recognition method | |
| CN110598574A (en) | Intelligent face monitoring and identifying method and system | |
| CN103839042B (en) | Face identification method and face identification system | |
| CN106845328B (en) | A kind of Intelligent human-face recognition methods and system based on dual camera | |
| Skodras et al. | An unconstrained method for lip detection in color images | |
| CN104598888B (en) | A kind of recognition methods of face gender | |
| CN105160331A (en) | Hidden Markov model based face geometrical feature identification method | |
| Vishwakarma et al. | Simple and intelligent system to recognize the expression of speech-disabled person | |
| Hao et al. | An optimized face detection based on adaboost algorithm | |
| Fernando et al. | Novel approach to use HU moments with image processing techniques for real time sign language communication | |
| CN111832405A (en) | Face recognition method based on HOG and depth residual error network | |
| Sahu et al. | Study on face recognition techniques | |
| Fernando et al. | Low cost approach for real time sign language recognition | |
| Paul et al. | Rotation invariant multiview face detection using skin color regressive model and support vector regression | |
| Mahalingam et al. | Is the eye region more reliable than the face? A preliminary study of face-based recognition on a transgender dataset | |
| Nuraisha et al. | Implementation of K-NN based on histogram at image recognition for pornography detection | |
| Chen et al. | Robust gender recognition for uncontrolled environment of real-life images | |
| El Maghraby et al. | Hybrid face detection system using combination of viola-jones method and skin detection | |
| Das et al. | Human face detection in color images using HSV color histogram and WLD | |
| CN106548130A (en) | A kind of video image is extracted and recognition methods and system | |
| Dwivedi et al. | A new hybrid approach on face detection and recognition | |
| Liang et al. | Applying Image Processing Technology to Face Recognition. | |
| CN111428670B (en) | Face detection method, face detection device, storage medium and equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191220 |