CN108596057B - Information security management system based on face recognition - Google Patents
Information security management system based on face recognition Download PDFInfo
- Publication number
- CN108596057B CN108596057B CN201810319072.0A CN201810319072A CN108596057B CN 108596057 B CN108596057 B CN 108596057B CN 201810319072 A CN201810319072 A CN 201810319072A CN 108596057 B CN108596057 B CN 108596057B
- Authority
- CN
- China
- Prior art keywords
- module
- face image
- face
- image
- boundary
- 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
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Collating Specific Patterns (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of face recognition, and discloses an information security management system based on face recognition, which comprises: the system comprises a camera module, a face image extraction module, a central control module, a face recognition module, a storage module, an operation recording module, an early warning module and a display module. According to the invention, the face image is identified by the face identification module through histogram matching, the calculation speed is high, and the sensitivity to the posture, illumination, expression and environmental change can be reduced; meanwhile, the face characteristics, the operation process, the operation content and the operation time of the face decryption loser can be continuously recorded after the face decryption loser performs early warning in the early warning subsystem through the early warning module, the identity of the intruder and specific leaked information can be acquired, and accordingly, follow-up remedial measures are guaranteed.
Description
Technical Field
The invention belongs to the technical field of face recognition, and particularly relates to an information security management system based on face recognition.
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 capture an image or video stream containing a face with a camera or a video camera, automatically detect and track the face in the image, and then perform face recognition on the detected face. However, the existing human face recognition has low data processing speed and is easily influenced by posture and environmental factors; meanwhile, if decryption fails, early warning cannot be timely carried out, and the safety is low.
In summary, the problems of the prior art are as follows: the existing human face recognition has low data processing speed and is easily influenced by posture and environmental factors; meanwhile, if decryption fails, early warning cannot be timely carried out, and the safety is low.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an information safety management system based on face recognition.
The invention is realized in this way, an information security management system based on face recognition includes:
the system comprises a camera module, a face image extraction module, a central control module, a face recognition module, a storage module, an operation recording module, an early warning module and a display module;
the camera module is connected with the face image extraction module and used for collecting the user image through the camera;
the camera module adopts a saliency detection method to preprocess the query face image and the target face image, extracts a target area in the face image and filters a background area. Therefore, irrelevant information components in the face image are greatly inhibited, and a main body target part playing a key role in retrieval is highlighted, so that the situation that the face image is inquired to be retrieved to be the target face image background is effectively prevented.
(1a) Firstly, the face image is subjected to superpixelization processing, and the face image is divided into a plurality of small areas. Then calculating the distance of all super-pixel regions adjacent to the region p to obtain the accumulated boundary weight d of the shortest pathgeo(p,pi) Further, the span area (p) of each super pixel region p can be calculated;
(1b) the boundary length of each region is calculated. Calculating a boundary connection value BndCon (p) of the region according to the boundary length and the span area of the region; the connection degree of the region and the boundary is reflected, and the background part is often larger than the target region;
(1c) derived from the boundary connection value mapping
The background difference weight wctr (p) for each region is calculated. Thus, the target area obtains a larger weight value than the background area, thereby highlighting the target area;
(1d) then the target significance problem is converted into the optimization of significance values of all super pixels in the face image; designing a target loss function to limit the background part to highlight the foreground part, and then minimizing the loss function to obtain a significant value image of the face image;
(1e) extracting main body components of the significant value image obtained in the step (1d), setting a threshold value according to the range of the significant value and experimental analysis, and only keeping a main body area of the original face image; obtaining a main body component image of the face image;
the face image extraction module is connected with the camera module and the central control module and is used for extracting face characteristic parts from the image acquired by the camera module;
the central control module is connected with the camera module, the face image extraction module, the face recognition module, the storage module, the operation recording module, the early warning module and the display module and is used for controlling each module to work normally;
the central control module performs polar coordinate transformation on the image by taking the current visual attention focus as an origin point, and searches in a polar coordinate space;
let P denote the set of all pixels in the polar boundary map, and L ═ {0,1} is the set of possible labels for each pixel in the polar boundary map;
a label function is sought on the probability boundary graph from the set P to the set L, which satisfies the following energy equation:
in the formula, delta (l)p,lq) Is a Kronecker symbol, Up(lp) Is an energy function data item;
the position of the focus is obtained by an Itti visual attention model, polar coordinate transformation is carried out on the probability boundary graph by taking the focus as a coordinate origin to obtain a polar coordinate probability boundary graph, an optimal boundary is obtained according to the formula, and inverse polar coordinate transformation is carried out on the optimal boundary to obtain a closed region, namely a current focus region;
the face recognition module is connected with the central control module and is used for recognizing the face features;
the storage module is connected with the central control module and used for storing the acquired face data;
the operation recording module is connected with the central control module and is used for recording the operation history of face login;
the early warning module is connected with the operation recording module and used for warning illegal image login;
and the display module is connected with the central control module and is used for displaying the face recognition login information.
Further, the face recognition module recognition method comprises the following steps:
firstly, acquiring a face image to be recognized, and carrying out Gaussian difference filtering processing on the face image to be recognized to obtain a filtered face image to be recognized;
secondly, carrying out LBP operation on the face image to be recognized, and obtaining a histogram from the result of the LBP operation;
then, comparing the filtered face image to be recognized with a prestored registered face image training set which is subjected to Gaussian difference filtering by utilizing histogram matching, and finding out the registered face image corresponding to the face image to be recognized from the registered face image training set;
then, calculating to obtain the total reconstruction coefficient dispersion degree SCI of the filtered face image to be recognized and the corresponding registered face image;
and finally, judging whether the face image to be recognized is a registered face image or not according to the SCI.
The invention has the advantages and positive effects that: according to the invention, the face image is identified by the face identification module through histogram matching, the calculation speed is high, and the sensitivity to the posture, illumination, expression and environmental change can be reduced; meanwhile, the face characteristics, the operation process, the operation content and the operation time of the face decryption loser can be continuously recorded after the face decryption loser performs early warning in the early warning subsystem through the early warning module, the identity of the intruder and specific leaked information can be acquired, and accordingly, follow-up remedial measures are guaranteed.
Drawings
Fig. 1 is a block diagram of an information security management system based on face recognition according to an embodiment of the present invention.
In the figure: 1. a camera module; 2. a face image extraction module; 3. a central control module; 4. a face recognition module; 5. a storage module; 6. an operation recording module; 7. an early warning module; 8. and a display module.
Detailed Description
In order to further understand the contents, features and effects of the present invention, the following embodiments are illustrated and described in detail with reference to the accompanying drawings.
The structure of the present invention will be described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the information security management system based on face recognition provided by the present invention includes: the system comprises a camera module 1, a face image extraction module 2, a central control module 3, a face recognition module 4, a storage module 5, an operation recording module 6, an early warning module 7 and a display module 8.
The camera module 1 is connected with the face image extraction module 2 and is used for collecting a user image through a camera;
the face image extraction module 2 is connected with the camera module 1 and the central control module 3 and is used for extracting face characteristic parts from the image acquired by the camera module 1;
the central control module 3 is connected with the camera module 1, the face image extraction module 2, the face recognition module 4, the storage module 5, the operation recording module 6, the early warning module 7 and the display module 8 and is used for controlling each module to work normally;
the face recognition module 4 is connected with the central control module 3 and used for recognizing the face features;
the storage module 5 is connected with the central control module 3 and used for storing the acquired face data;
the operation recording module 6 is connected with the central control module 3 and is used for recording the operation history of face login;
the early warning module 7 is connected with the operation recording module 6 and used for alarming illegal image login;
and the display module 8 is connected with the central control module 3 and is used for displaying the face recognition login information.
The camera module adopts a saliency detection method to preprocess the query face image and the target face image, extracts a target area in the face image and filters a background area. Therefore, irrelevant information components in the face image are greatly inhibited, and a main body target part playing a key role in retrieval is highlighted, so that the situation that the face image is inquired to be retrieved to be the target face image background is effectively prevented.
(1a) Firstly, the face image is subjected to superpixelization processing, and the face image is divided into a plurality of small areas. Then calculating the distance of all super-pixel regions adjacent to the region p to obtain the accumulated boundary weight d of the shortest pathgeo(p,pi) Further, the span area (p) of each super pixel region p can be calculated;
(1b) the boundary length of each region is calculated. Calculating a boundary connection value BndCon (p) of the region according to the boundary length and the span area of the region; the connection degree of the region and the boundary is reflected, and the background part is often larger than the target region;
(1c) derived from the boundary connection value mapping
The background difference weight wctr (p) for each region is calculated. Thus, the target area obtains a larger weight value than the background area, thereby highlighting the target area;
(1d) then the target significance problem is converted into the optimization of significance values of all super pixels in the face image; designing a target loss function to limit the background part to highlight the foreground part, and then minimizing the loss function to obtain a significant value image of the face image;
(1e) extracting main body components of the significant value image obtained in the step (1d), setting a threshold value according to the range of the significant value and experimental analysis, and only keeping a main body area of the original face image; obtaining a main body component image of the face image;
the central control module performs polar coordinate transformation on the image by taking the current visual attention focus as an origin point, and searches in a polar coordinate space;
let P denote the set of all pixels in the polar boundary map, and L ═ {0,1} is the set of possible labels for each pixel in the polar boundary map;
a label function is sought on the probability boundary graph from the set P to the set L, which satisfies the following energy equation:
in the formula, delta (l)p,lq) Is a Kronecker symbol, Up(lp) Is an energy function data item;
the position of the focus is obtained by an Itti visual attention model, polar coordinate transformation is carried out on the probability boundary graph by taking the focus as a coordinate origin to obtain a polar coordinate probability boundary graph, an optimal boundary is obtained according to the formula, and inverse polar coordinate transformation is carried out on the optimal boundary to obtain a closed region, namely a current focus region;
the recognition method of the face recognition module 4 provided by the invention comprises the following steps:
firstly, acquiring a face image to be recognized, and carrying out Gaussian difference filtering processing on the face image to be recognized to obtain a filtered face image to be recognized;
secondly, carrying out LBP operation on the face image to be recognized, and obtaining a histogram from the result of the LBP operation;
then, comparing the filtered face image to be recognized with a prestored registered face image training set which is subjected to Gaussian difference filtering by utilizing histogram matching, and finding out the registered face image corresponding to the face image to be recognized from the registered face image training set;
then, calculating to obtain the total reconstruction coefficient dispersion degree SCI of the filtered face image to be recognized and the corresponding registered face image;
and finally, judging whether the face image to be recognized is a registered face image or not according to the SCI.
When the invention works, the user image is collected through the camera module 1; the collected image is sent to a face image extraction module 2 to extract the face characteristic part; the central control module 3 dispatches the face recognition module 4 to recognize the face features; the collected face data is stored through a storage module 5; when the human face is identified and logged in, the operation history of the human face login is recorded through the operation recording module 6; if so, judging that the illegal image login gives an alarm through the early warning module 7; and finally, displaying the face recognition login information through the display module 8.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications, equivalent changes and modifications made to the above embodiment according to the technical spirit of the present invention are within the scope of the technical solution of the present invention.
Claims (1)
1. An information security management system based on face recognition, characterized in that the information security management system based on face recognition comprises:
the system comprises a camera module, a face image extraction module, a central control module, a face recognition module, a storage module, an operation recording module, an early warning module and a display module;
the camera module is connected with the face image extraction module and used for collecting the user image through the camera;
the camera module adopts a saliency detection method to preprocess the query face image and the target face image, extracts a target area in the face image and filters a background area; therefore, irrelevant information components in the face image are greatly inhibited, and a main body target part playing a key role in retrieval is highlighted, so that the situation that the face image is inquired to be retrieved as the background of the target face image is effectively prevented;
(1a) firstly, performing superpixelation processing on a face image, and dividing the face image into a plurality of small areas; then calculating the distance of all super-pixel regions adjacent to the region p to obtain the accumulated boundary weight d of the shortest pathgeo(p,pi) And then the span area Ar of each super pixel region p can be calculatedea(p)；
(1b) Calculating the boundary length of each region; calculating a boundary connection value BndCon (p) of the region according to the boundary length and the span area of the region; the connection degree of the region and the boundary is reflected, and the background part is often larger than the target region;
(1c) derived from the boundary connection value mapping
Calculating a background difference weight wctr (p) of each region; thus, the target area obtains a larger weight value than the background area, thereby highlighting the target area;
(1d) then the target significance problem is converted into the optimization of significance values of all super pixels in the face image;
designing a target loss function to limit the background part to highlight the foreground part, and then minimizing the loss function to obtain a significant value image of the face image;
(1e) extracting main body components of the significant value image obtained in the step (1d), setting a threshold value according to the range of the significant value and experimental analysis, and only keeping a main body area of the original face image; obtaining a main body component image of the face image;
the face image extraction module is connected with the camera module and the central control module and is used for extracting face characteristic parts from the image acquired by the camera module;
the central control module is connected with the camera module, the face image extraction module, the face recognition module, the storage module, the operation recording module, the early warning module and the display module and is used for controlling each module to work normally;
the central control module performs polar coordinate transformation on the image by taking the current visual attention focus as an origin point, and searches in a polar coordinate space;
let P denote the set of all pixels in the polar boundary map, and L ═ {0,1} is the set of possible labels for each pixel in the polar boundary map;
a label function is sought on the probability boundary graph from the set P to the set L, which satisfies the following energy equation:
in the formula, delta (l)p,lq) Is a Kronecker symbol, Up(lp) Is an energy function data item;
the position of the focus is obtained by an Itti visual attention model, polar coordinate transformation is carried out on the probability boundary graph by taking the focus as a coordinate origin to obtain a polar coordinate probability boundary graph, an optimal boundary is obtained according to the formula, and inverse polar coordinate transformation is carried out on the optimal boundary to obtain a closed region, namely a current focus region;
the face recognition module is connected with the central control module and is used for recognizing the face features;
the storage module is connected with the central control module and used for storing the acquired face data;
the operation recording module is connected with the central control module and is used for recording the operation history of face login;
the early warning module is connected with the operation recording module and used for warning illegal image login;
the display module is connected with the central control module and used for displaying the face recognition login information;
the face recognition module recognition method comprises the following steps:
firstly, acquiring a face image to be recognized, and carrying out Gaussian difference filtering processing on the face image to be recognized to obtain a filtered face image to be recognized;
secondly, carrying out LBP operation on the face image to be recognized, and obtaining a histogram from the result of the LBP operation;
then, comparing the filtered face image to be recognized with a prestored registered face image training set which is subjected to Gaussian difference filtering by utilizing histogram matching, and finding out the registered face image corresponding to the face image to be recognized from the registered face image training set;
then, calculating to obtain the total reconstruction coefficient dispersion degree SCI of the filtered face image to be recognized and the corresponding registered face image;
finally, judging whether the face image to be recognized is a registered face image or not according to the SCI;
the face recognition module recognizes the face image by using histogram matching, has high calculation speed and can reduce the sensitivity to the posture, illumination, expression and environmental change; the early warning module can continue to record the facial features, the operation process, the operation content and the operation time of the face decryption loser after the early warning is carried out on the early warning subsystem, and can acquire the identity of the intruder and specific leaked information, so that the follow-up remedial measures are guaranteed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810319072.0A CN108596057B (en) | 2018-04-11 | 2018-04-11 | Information security management system based on face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810319072.0A CN108596057B (en) | 2018-04-11 | 2018-04-11 | Information security management system based on face recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108596057A CN108596057A (en) | 2018-09-28 |
| CN108596057B true CN108596057B (en) | 2022-04-05 |
Family
ID=63621593
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810319072.0A Active CN108596057B (en) | 2018-04-11 | 2018-04-11 | Information security management system based on face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108596057B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110189447B (en) * | 2019-05-31 | 2022-03-22 | 安徽无界万禾传媒科技有限公司 | Intelligent community gate control system based on face identity recognition |
| CN110766580A (en) * | 2019-10-25 | 2020-02-07 | 重庆第二师范学院 | Classroom quality monitoring system based on human face characteristics |
| CN113297920A (en) * | 2021-04-29 | 2021-08-24 | 广东白云学院 | Face image information processing management system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105959653A (en) * | 2016-07-12 | 2016-09-21 | 湖北誉恒科技有限公司 | Video monitoring system for pedestrian crosswalk |
| CN106339701A (en) * | 2016-10-31 | 2017-01-18 | 黄建文 | Face image recognition method and system |
| CN106687991A (en) * | 2014-07-16 | 2017-05-17 | 索尼公司 | System and method for setting focus of digital image based on social relationship |
| CN106815323A (en) * | 2016-12-27 | 2017-06-09 | 西安电子科技大学 | A kind of cross-domain vision search method based on conspicuousness detection |
| CN106821425A (en) * | 2017-01-13 | 2017-06-13 | 贵定县人民医院 | A kind of binary channels bladder lithotriptoscepe system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8693780B2 (en) * | 2009-06-22 | 2014-04-08 | Technion Research & Development Foundation Limited | Automated collage formation from photographic images |
-
2018
- 2018-04-11 CN CN201810319072.0A patent/CN108596057B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106687991A (en) * | 2014-07-16 | 2017-05-17 | 索尼公司 | System and method for setting focus of digital image based on social relationship |
| CN105959653A (en) * | 2016-07-12 | 2016-09-21 | 湖北誉恒科技有限公司 | Video monitoring system for pedestrian crosswalk |
| CN106339701A (en) * | 2016-10-31 | 2017-01-18 | 黄建文 | Face image recognition method and system |
| CN106815323A (en) * | 2016-12-27 | 2017-06-09 | 西安电子科技大学 | A kind of cross-domain vision search method based on conspicuousness detection |
| CN106821425A (en) * | 2017-01-13 | 2017-06-13 | 贵定县人民医院 | A kind of binary channels bladder lithotriptoscepe system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108596057A (en) | 2018-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145742B (en) | Pedestrian identification method and system | |
| CN109558810B (en) | Target person identification method based on part segmentation and fusion | |
| CN105844128B (en) | Identity recognition method and device | |
| CN105825176A (en) | Identification method based on multi-mode non-contact identity characteristics | |
| CN104751136B (en) | A kind of multi-camera video event back jump tracking method based on recognition of face | |
| CN107230267B (en) | Intelligence In Baogang Kindergarten based on face recognition algorithms is registered method | |
| CN101587485B (en) | Face information automatic login method based on face recognition technology | |
| CN108596057B (en) | Information security management system based on face recognition | |
| CN108171138B (en) | Biological characteristic information acquisition method and device | |
| WO2018040306A1 (en) | Method for detecting frequent passers-by in monitoring video | |
| CN106295524A (en) | A kind of human motion recognition method of view-based access control model word bag | |
| Shirsat et al. | Proposed system for criminal detection and recognition on CCTV data using cloud and machine learning | |
| KR101515214B1 (en) | Identification method using face recognition and entrance control system and method thereof using the identification method | |
| Xia et al. | Face occlusion detection using deep convolutional neural networks | |
| Selvaraj et al. | Raspberry Pi based automatic door control system | |
| Hsiao et al. | EfficientNet based iris biometric recognition methods with pupil positioning by U-net | |
| Cho et al. | Thermal imprint feature analysis for face recognition | |
| Yimyam et al. | Development of heat stroke detection system using image processing techniques | |
| CN112069898A (en) | Method and device for recognizing human face group attribute based on transfer learning | |
| CN109670435B (en) | Method for identifying identity based on human gait characteristics | |
| Rodrigues et al. | A simple approach for biometrics: Finger-knuckle prints recognition based on a sobel filter and similarity measures | |
| CN107657201A (en) | NEXT series of products characteristics of image identifying systems and its recognition methods | |
| CN115396591A (en) | Intelligent double-light camera image processing method and device, camera and medium | |
| Aydoğdu et al. | A study on liveness analysis for palmprint recognition system | |
| Bozed et al. | Detection of facial expressions based on Morphological face features and Minimum Distance Classifier |
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 |