CN112580541A - Clustering face recognition method and system - Google Patents
Clustering face recognition method and system Download PDFInfo
- Publication number
- CN112580541A CN112580541A CN202011549995.9A CN202011549995A CN112580541A CN 112580541 A CN112580541 A CN 112580541A CN 202011549995 A CN202011549995 A CN 202011549995A CN 112580541 A CN112580541 A CN 112580541A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- images
- dimensional
- face image
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Abstract
The invention provides a clustering face recognition method and a system, which are characterized in that face images of different face regions of a target object are obtained in a multi-angle shooting mode and then are preprocessed, image contour characteristic information in the face images is extracted and is clustered to obtain corresponding three-dimensional face images, and finally the three-dimensional face images are compared with a preset face information database to execute data acquisition authority operation matched with personnel identity information according to comparison results, so that three-dimensional face images are constructed and formed according to the contour characteristics of the different regions of the face of the target object, and therefore the accuracy of face recognition is improved and the reliability of face recognition results is improved to the maximum extent.
Description
Technical Field
The invention relates to the technical field of face recognition, in particular to a clustering face recognition method and a clustering face recognition system.
Background
The human face recognition is widely applied to data information security occasions as a security authentication means, and whether the identity information of a target object is verified or not can be quickly and accurately determined by shooting and recognizing the face image of the target object, so that the corresponding data information can be operated in different modes only by a user with preset access permission, and the security and confidentiality of the data information are improved. However, in the face recognition process of the prior art, the face image of the target object is only compared with the image data in the preset image database, which is easy to cause recognition errors due to comparison errors, and meanwhile, the face recognition process is only limited to comparison on a two-dimensional image layer, which seriously reduces the accuracy of comparison, thereby greatly reducing the reliability of the face recognition result.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a clustering face recognition method and a clustering face recognition system, wherein the face of a target object is shot in multiple angles, so that a plurality of face images of different face regions of the target object are obtained, the face images are preprocessed, the preprocessed face images are subjected to image contour feature extraction processing, so that image contour feature information of the face images is obtained, the face images are clustered according to the image contour feature information, so that corresponding three-dimensional face images are constructed, the personnel identity information corresponding to the three-dimensional face images is determined according to a preset face information database, and data acquisition permission operation matched with the personnel identity information is executed according to the personnel identity information; therefore, the clustering face recognition method and the clustering face recognition system can obtain the face images of different face regions of a target object in a multi-angle shooting mode, then preprocess the face images, then extract the image contour characteristic information in the face images, perform clustering processing on the image contour characteristic information to obtain corresponding three-dimensional face images, finally compare the three-dimensional face images with a preset face information database, and execute data acquisition permission operation matched with personnel identity information according to the comparison result, so that three-dimensional face images are constructed and formed according to the different region contour characteristics of the face of the target object, thereby improving the accuracy of face recognition and improving the reliability of the face recognition result to the maximum extent.
The invention provides a clustering face recognition method, which is characterized by comprising the following steps:
step S1, shooting the face of the target object in multiple angles, so as to obtain a plurality of face images of different face areas of the target object, and preprocessing the face images;
step S2, carrying out image contour feature extraction processing on the preprocessed face images so as to obtain image contour feature information of the face images, and carrying out clustering processing on the face images according to the image contour feature information so as to construct and obtain corresponding three-dimensional face images;
step S3, determining personnel identity information corresponding to the three-dimensional face image according to a preset face information database, and executing data acquisition permission operation matched with the personnel identity information according to the personnel identity information;
further, in step S1, the multi-angle shooting of the face of the target object is performed to obtain several face images of different face areas of the target object, and the pre-processing of the several face images specifically includes:
step S101, shooting the face of the target object in multiple angles relative to the left direction, the right direction, the dead direction, the upper direction and the lower direction, so as to correspondingly obtain a left area face image, a right area face image, a dead area face image, an upper area face image and a lower area face image;
step S102, sequentially carrying out image pixel dead pixel repairing processing, image pixel graying processing and image edge pixel sharpening processing on the left side region face image, the right side region face image and the opposite region face image, and thus realizing the preprocessing;
further, in step S2, performing image contour feature extraction processing on the preprocessed face images to obtain image contour feature information about the face images, and performing clustering processing on the face images according to the image contour feature information to construct corresponding three-dimensional face images specifically includes:
step S201, performing cutting processing on the preprocessed face image, thereby cutting the face image into a plurality of face sub-images with the same area, and acquiring image contour characteristic information corresponding to each face sub-image;
step S202, determining an image contour feature vector corresponding to each face sub-image in the face image according to the image contour feature information;
step S203, performing clustering operation on all image contour characteristic vectors contained in the face image to obtain a three-dimensional topography map corresponding to the face image, and then splicing the three-dimensional topography maps corresponding to all the face images to obtain the three-dimensional face image;
further, in step S3, determining, according to a preset face information database, person identity information corresponding to the three-dimensional face image, and executing, according to the person identity information, a data acquisition permission operation matched with the person identity information specifically includes:
step S301, determining image similarity between the three-dimensional face image and a plurality of face three-dimensional images contained in the preset face information database, and taking the face three-dimensional image with the maximum image similarity as a final identification determination image;
step S302, using the personnel identity information corresponding to the final identification confirmation image as the real personnel identity information of the target object;
step S303, determining a data acquisition level corresponding to the target object according to the identity information of the real person, and executing corresponding data reading operation and/or data modification operation according to the data acquisition level;
further, in step S3, determining, according to a preset face information database, person identity information corresponding to the three-dimensional face image, and according to the person identity information, performing a data acquisition permission operation matched with the person identity information specifically includes splitting the face image, determining an image contour feature value corresponding to each sub-image of the face image, performing a clustering operation on all image contour feature vectors included in the face image, comparing the obtained face image contour clustering operation value with preset face information database data, and according to a comparison result, performing a corresponding data reading operation and a data modification operation specifically:
firstly, the preprocessed face image is cut to obtain image contour characteristic information corresponding to each face sub-image, and an image contour characteristic value P corresponding to each face sub-image in the face image is determined by using the following formula (1),
in the above formula (1), S represents the area of the face image, n represents the total number of face sub-images that are not divided into the same area, i represents the number of lines of the face image partial image, j represents the number of columns of the face image partial image, and x represents the number of lines of the face image partial imageiRepresents the area value occupied by five sense organs in the i-th row of sub-images,
represents the ratio of the area value of five sense organs in the sub-image in the ith row in the area of the sub-image, ljDenotes the longest diagonal length value of the five sense organs in the jth column of sub-images, dis (l)j,lj-1) Representing the distance between the longest diagonal length value of the five sense organs in the jth column of the sub-image and the jth-1 column of the sub-image;
secondly, using the following formula (2), clustering operation is performed on all image contour feature vectors contained in the face image to obtain a face image contour clustering operation value K,
in the above formula (2), sum (x)i,xi-1) Representing the sum of the area value occupied by the five sense organs in the sub-image of the ith row and the area value occupied by the five sense organs in the sub-image of the (i-1) th row, wherein P' represents the derivation operation on the image contour characteristic value P;
thirdly, comparing the obtained face image contour clustering operation value with the preset face information database data by using the following formula (3) to obtain a corresponding comparison value C, and then executing corresponding data reading operation and data modification operation according to the comparison value,
in the above formula (3), m represents the total number of data in the preset face information database, K 'represents the derivation operation for the face image contour cluster operation value K, O'mRepresenting the derivation operation of the contour clustering operation value corresponding to the mth data;
and when C is larger than 1, the obtained face image contour cluster operation value is matched with the mth data in the preset face information database, so that corresponding data reading operation and data modification operation are executed.
The invention also provides a clustering face recognition system which is characterized by comprising a face image acquisition module, a face image preprocessing module, a three-dimensional face image construction module and an identity information recognition module; wherein the content of the first and second substances,
the face image acquisition module is used for shooting the face of the target object in multiple angles so as to acquire a plurality of face images of different face areas of the target object;
the face image preprocessing module is used for preprocessing a plurality of face images;
the three-dimensional face image construction module is used for extracting image contour characteristics of the preprocessed face images so as to obtain image contour characteristic information of the face images, and clustering the face images according to the image contour characteristic information so as to construct and obtain corresponding three-dimensional face images;
the identity information identification module is used for determining personnel identity information corresponding to the three-dimensional face image according to a preset face information database and executing data acquisition permission operation matched with the personnel identity information according to the personnel identity information;
further, the face image obtaining module performs multi-angle shooting on the face of the target object, so as to obtain a plurality of face images of different face areas of the target object, specifically including:
shooting the face of the target object in multiple angles relative to the left direction, the right direction, the dead direction, the upper side direction and the lower side direction so as to correspondingly obtain a left area face image, a right area face image, a dead area face image, an upper area face image and a lower area face image;
and the number of the first and second groups,
the preprocessing of the face images by the face image preprocessing module specifically comprises
Carrying out image pixel dead pixel repairing processing, image pixel graying processing and image edge pixel sharpening processing on the left side region face image, the right side region face image and the opposite region face image in sequence so as to realize the preprocessing;
further, the three-dimensional facial image constructing module performs image contour feature extraction processing on the preprocessed face images to obtain image contour feature information about the face images, and performs clustering processing on the face images according to the image contour feature information, so as to construct and obtain corresponding three-dimensional facial images specifically includes:
cutting the preprocessed face image to obtain a plurality of face sub-images with the same area, and acquiring image contour characteristic information corresponding to each face sub-image;
determining an image contour characteristic vector corresponding to each face sub-image in the face image according to the image contour characteristic information;
clustering all image contour characteristic vectors contained in the face image to obtain a three-dimensional topography map corresponding to the face image, and splicing the three-dimensional topography maps corresponding to all the face images to obtain the three-dimensional face image;
further, the identity information identification module determines the personnel identity information corresponding to the three-dimensional face image according to a preset face information database, and executes data acquisition permission operation matched with the personnel identity information according to the personnel identity information specifically comprises:
determining image similarity between the three-dimensional face image and a plurality of face three-dimensional images contained in the preset face information database, and taking the face three-dimensional image with the maximum image similarity as a final identification determination image;
and the personnel identity information corresponding to the final identification determination image is used as the real personnel identity information of the target object;
and determining a data acquisition level corresponding to the target object according to the identity information of the real personnel, and executing corresponding data reading operation and/or data modification operation according to the data acquisition level.
Compared with the prior art, the clustering face recognition method and the clustering face recognition system have the advantages that the face of the target object is shot in multiple angles, so that a plurality of face images of different face regions of the target object are obtained, the face images are preprocessed, the preprocessed face images are subjected to image contour feature extraction processing, so that image contour feature information of the face images is obtained, the face images are clustered according to the image contour feature information, so that corresponding three-dimensional face images are obtained, personnel identity information corresponding to the three-dimensional face images is determined according to a preset face information database, and data acquisition permission operation matched with the personnel identity information is executed according to the personnel identity information; therefore, the clustering face recognition method and the clustering face recognition system can obtain the face images of different face regions of a target object in a multi-angle shooting mode, then preprocess the face images, then extract the image contour characteristic information in the face images, perform clustering processing on the image contour characteristic information to obtain corresponding three-dimensional face images, finally compare the three-dimensional face images with a preset face information database, and execute data acquisition permission operation matched with personnel identity information according to the comparison result, so that three-dimensional face images are constructed and formed according to the different region contour characteristics of the face of the target object, thereby improving the accuracy of face recognition and improving the reliability of the face recognition result to the maximum extent.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of the clustering face recognition method provided by the invention.
Fig. 2 is a schematic structural diagram of the clustered face recognition system provided in the present invention.
Detailed Description
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.
Fig. 1 is a schematic flow chart of the clustering face recognition method according to the embodiment of the present invention. The clustering face recognition method comprises the following steps:
step S1, shooting the face of the target object in multiple angles, so as to obtain a plurality of face images of different face areas of the target object, and preprocessing the face images;
step S2, carrying out image contour feature extraction processing on the preprocessed face images so as to obtain image contour feature information of the face images, and carrying out clustering processing on the face images according to the image contour feature information so as to construct and obtain corresponding three-dimensional face images;
and step S3, determining the personnel identity information corresponding to the three-dimensional face image according to a preset face information database, and executing data acquisition permission operation matched with the personnel identity information according to the personnel identity information.
The beneficial effects of the above technical scheme are: the clustering face recognition method comprises the steps of obtaining face images of different face regions of a target object in a multi-angle shooting mode, preprocessing the face images, extracting image contour characteristic information in the face images, clustering the image contour characteristic information to obtain corresponding three-dimensional face images, comparing the three-dimensional face images with a preset face information database, executing data acquisition authority operation matched with personnel identity information according to a comparison result, and constructing and forming the three-dimensional face images according to the contour characteristics of the different regions of the face of the target object, so that the accuracy of face recognition is improved, and the reliability of face recognition results is improved to the maximum extent.
Preferably, in step S1, the multi-angle shooting of the face of the target object is performed to obtain several face images of different face regions of the target object, and the pre-processing of the several face images specifically includes:
step S101, shooting the face of the target object in multiple angles relative to the left direction, the right direction, the dead direction, the upper direction and the lower direction, so as to correspondingly obtain a left area face image, a right area face image, a dead area face image, an upper area face image and a lower area face image;
step S102, sequentially performing an image pixel dead pixel repairing process, an image pixel graying process and an image edge pixel sharpening process on the left side region face image, the right side region face image and the opposite region face image, respectively, so as to implement the preprocessing.
The beneficial effects of the above technical scheme are: the face of the target object is shot in multiple angles in the left direction, the right direction, the dead direction, the upper side direction and the lower side direction, so that the detail information of different areas of the face of the target object can be shot to the maximum extent, and the facial features of the target object can be comprehensively and accurately represented and analyzed; and the face image of different areas is subjected to image pixel dead pixel repairing processing, image pixel graying processing and image edge pixel sharpening processing, so that the overall quality of the face image can be improved, and the influence on the overall quality of the face image due to individual image pixels is avoided.
Preferably, in step S2, the image contour feature extraction processing is performed on the preprocessed face images to obtain image contour feature information about the face images, and the clustering processing is performed on the face images according to the image contour feature information, so as to construct corresponding three-dimensional face images specifically includes:
step S201, performing cutting processing on the preprocessed face image, thereby cutting the face image into a plurality of face sub-images with the same area, and acquiring image contour characteristic information corresponding to each face sub-image;
step S202, determining an image contour feature vector corresponding to each face sub-image in the face image according to the image contour feature information;
step S203, performing clustering operation on all image contour characteristic vectors contained in the face image to obtain a three-dimensional topography map corresponding to the face image, and then splicing the three-dimensional topography maps corresponding to all the face images to obtain the three-dimensional face image.
The beneficial effects of the above technical scheme are: the corresponding image contour characteristics of the face image at different regions are correspondingly different, the face image is cut to perform thinning analysis processing on the image contour of the face image at different regions, the image contour characteristic information is converted into an image contour characteristic vector through a corresponding image contour conversion algorithm, then the vector is subjected to clustering operation to generate a three-dimensional topography image corresponding to the face image on an image contour detail level, and therefore the three-dimensional face image obtained by subsequent splicing can comprehensively and accurately reflect the real face contour characteristics of a target object.
Preferably, in step S3, determining, according to a preset human face information database, the person identity information corresponding to the three-dimensional face image, and according to the person identity information, performing a data acquisition permission operation matched with the person identity information specifically includes:
step S301, determining image similarity between the three-dimensional face image and a plurality of face three-dimensional images contained in the preset face information database, and taking the face three-dimensional image with the maximum image similarity as a final identification determination image;
step S302, using the personnel identity information corresponding to the final identification confirmation image as the real personnel identity information of the target object;
step S303, determining a data acquisition level corresponding to the target object according to the identity information of the real person, and performing a corresponding data reading operation and/or a data modification operation according to the data acquisition level.
The beneficial effects of the above technical scheme are: by determining the image similarity between the three-dimensional face image and a plurality of face three-dimensional images contained in the preset face information database, the face recognition of the target object can be carried out on the three-dimensional image layer, so that the accuracy and the reliability of the face recognition are improved; in addition, different personnel identity information corresponds to data operation authorities of different levels, and the data acquisition level of the target object can be determined in a targeted manner by determining the real personnel identity information of the target object, so that the target object can conveniently execute corresponding data reading operation and/or data modification operation, and the safety of corresponding data information is ensured.
Preferably, in step S3, determining, according to a preset face information database, the person identity information corresponding to the three-dimensional face image, and according to the person identity information, performing a data acquisition permission operation matched with the person identity information specifically includes splitting the face image, determining an image contour feature value corresponding to each sub-image of the face image, performing a clustering operation on all image contour feature vectors included in the face image, comparing the obtained face image contour clustering operation value with preset face information database data, and according to a comparison result, performing a corresponding data reading operation and a data modification operation specifically:
firstly, the preprocessed face image is cut to obtain the image contour characteristic information corresponding to each face sub-image, and the image contour characteristic value P corresponding to each face sub-image in the face image is determined by using the following formula (1),
in the above formula (1), S represents the area of the face image, n represents the total number of face sub-images that are not divided into the same area, i represents the number of lines of the face image partial image, j represents the number of columns of the face image partial image, and x represents the number of lines of the face image partial imageiRepresents the area value occupied by five sense organs in the i-th row of sub-images,
represents the ratio of the area value of five sense organs in the sub-image in the ith row in the area of the sub-image, ljDenotes the longest diagonal length value of the five sense organs in the jth column of sub-images, dis (l)j,lj-1) Representing the distance between the longest diagonal length value of the five sense organs in the jth column of the sub-image and the jth-1 column of the sub-image;
secondly, using the following formula (2), clustering operation is performed on all image contour feature vectors contained in the face image to obtain a face image contour clustering operation value K,
in the above formula (2), sum (x)i,xi-1) Representing the sum of the area value occupied by the five sense organs in the sub-image of the ith row and the area value occupied by the five sense organs in the sub-image of the (i-1) th row, wherein P' represents the derivation operation on the image contour characteristic value P;
thirdly, comparing the obtained face image contour clustering operation value with the preset face information database data by using the following formula (3) to obtain a corresponding comparison value C, and then executing corresponding data reading operation and data modification operation according to the comparison value,
in the above formula (3), m represents the total number of data in the preset face information database, K 'represents the derivation operation for the face image contour cluster operation value K, O'mIndicating the derivation operation of the contour clustering operation value corresponding to the mth data；
And when C is larger than 1, the obtained face image contour cluster operation value is matched with the mth data in the preset face information database, so that corresponding data reading operation and data modification operation are executed.
The beneficial effects of the above technical scheme are: the face contour characteristics of each segmented subimage are determined, and clustering operation processing is carried out to improve the face recognition precision so as to support face recognition of a target object from a three-dimensional image layer, thereby improving the accuracy and reliability of the face recognition; in addition, because different personnel identity information corresponds to data operation authorities of different levels, the identity information and the operation authority of the target object are accurately determined by matching the existing data of the database, so that the target object can conveniently execute corresponding data reading operation and data modification operation, and the safety of corresponding data information is enhanced.
Fig. 2 is a schematic structural diagram of a clustered face recognition system according to an embodiment of the present invention. The clustering face recognition system comprises a face image acquisition module, a face image preprocessing module, a three-dimensional face image construction module and an identity information recognition module; wherein the content of the first and second substances,
the face image acquisition module is used for shooting the face of the target object in multiple angles so as to acquire a plurality of face images of different face areas of the target object;
the face image preprocessing module is used for preprocessing a plurality of face images;
the three-dimensional face image construction module is used for extracting image contour characteristics of the preprocessed face images so as to obtain image contour characteristic information of the face images, and clustering the face images according to the image contour characteristic information so as to construct and obtain corresponding three-dimensional face images;
the identity information identification module is used for determining personnel identity information corresponding to the three-dimensional face image according to a preset face information database, and executing data acquisition permission operation matched with the personnel identity information according to the personnel identity information.
The beneficial effects of the above technical scheme are: the clustering face recognition system obtains face images of different face regions of a target object in a multi-angle shooting mode, then carries out preprocessing on the face images, extracts image contour characteristic information in the face images, carries out clustering processing on the image contour characteristic information to obtain corresponding three-dimensional face images, and finally compares the three-dimensional face images with a preset face information database to execute data acquisition authority operation matched with personnel identity information according to comparison results, so that three-dimensional face images are constructed and formed according to the different region contour characteristics of the face of the target object, and therefore the accuracy of face recognition is improved and the reliability of face recognition results is improved to the maximum extent.
Preferably, the face image obtaining module performs multi-angle shooting on the face of the target object, so as to obtain a plurality of face images of different face regions of the target object, specifically including:
shooting the face of the target object in multiple angles relative to the left direction, the right direction, the opposite direction, the upper side direction and the lower side direction so as to correspondingly obtain a left area face image, a right area face image, an opposite area face image, an upper area face image and a lower area face image;
and the number of the first and second groups,
the preprocessing module of the face image is used for preprocessing a plurality of face images specifically comprising
And sequentially carrying out image pixel dead pixel repairing processing, image pixel graying processing and image edge pixel sharpening processing on the left side region face image, the right side region face image and the opposite region face image, and the upper side region face image and the lower side region face image so as to realize the preprocessing.
The beneficial effects of the above technical scheme are: the face of the target object is shot in multiple angles in the left direction, the right direction, the dead direction, the upper side direction and the lower side direction, so that the detail information of different areas of the face of the target object can be shot to the maximum extent, and the facial features of the target object can be comprehensively and accurately represented and analyzed; and the face image of different areas is subjected to image pixel dead pixel repairing processing, image pixel graying processing and image edge pixel sharpening processing, so that the overall quality of the face image can be improved, and the influence on the overall quality of the face image due to individual image pixels is avoided.
Preferably, the three-dimensional facial image constructing module performs image contour feature extraction processing on the preprocessed face images to obtain image contour feature information about the face images, and performs clustering processing on the face images according to the image contour feature information, so as to construct corresponding three-dimensional facial images specifically including:
cutting the preprocessed face image to obtain a plurality of face sub-images with the same area, and acquiring image contour characteristic information corresponding to each face sub-image;
determining an image contour characteristic vector corresponding to each face sub-image in the face image according to the image contour characteristic information;
and then carrying out clustering operation on all image contour characteristic vectors contained in the face image so as to obtain a three-dimensional topography map corresponding to the face image, and then splicing the three-dimensional topography maps corresponding to all the face images so as to obtain the three-dimensional face image.
The beneficial effects of the above technical scheme are: the corresponding image contour characteristics of the face image at different regions are correspondingly different, the face image is cut to perform thinning analysis processing on the image contour of the face image at different regions, the image contour characteristic information is converted into an image contour characteristic vector through a corresponding image contour conversion algorithm, then the vector is subjected to clustering operation to generate a three-dimensional topography image corresponding to the face image on an image contour detail level, and therefore the three-dimensional face image obtained by subsequent splicing can comprehensively and accurately reflect the real face contour characteristics of a target object.
Preferably, the identity information recognition module determines the person identity information corresponding to the three-dimensional face image according to a preset face information database, and executes a data acquisition permission operation matched with the person identity information according to the person identity information specifically includes:
determining image similarity between the three-dimensional face image and a plurality of face three-dimensional images contained in the preset face information database, and taking the face three-dimensional image with the maximum image similarity as a final identification determination image;
and the personnel identity information corresponding to the final identification confirmation image is used as the real personnel identity information of the target object;
and determining a data acquisition level corresponding to the target object according to the identity information of the real person, and executing corresponding data reading operation and/or data modification operation according to the data acquisition level.
The beneficial effects of the above technical scheme are: by determining the image similarity between the three-dimensional face image and a plurality of face three-dimensional images contained in the preset face information database, the face recognition of the target object can be carried out on the three-dimensional image layer, so that the accuracy and the reliability of the face recognition are improved; in addition, different personnel identity information corresponds to data operation authorities of different levels, and the data acquisition level of the target object can be determined in a targeted manner by determining the real personnel identity information of the target object, so that the target object can conveniently execute corresponding data reading operation and/or data modification operation, and the safety of corresponding data information is ensured.
As can be seen from the content of the above embodiment, the clustered face recognition method and system obtain a plurality of face images related to different face regions of a target object by performing multi-angle shooting on the face of the target object, pre-process the plurality of face images, and perform image contour feature extraction processing on the plurality of pre-processed face images, so as to obtain image contour feature information related to the face images, perform clustering processing on the plurality of face images according to the image contour feature information, so as to construct a corresponding three-dimensional face image, determine personal identity information corresponding to the three-dimensional face image according to a preset face information database, and perform data acquisition permission operation matched with the personal identity information according to the personal identity information; therefore, the clustering face recognition method and the clustering face recognition system can obtain the face images of different face regions of a target object in a multi-angle shooting mode, then preprocess the face images, then extract the image contour characteristic information in the face images, perform clustering processing on the image contour characteristic information to obtain corresponding three-dimensional face images, finally compare the three-dimensional face images with a preset face information database, and execute data acquisition permission operation matched with personnel identity information according to the comparison result, so that three-dimensional face images are constructed and formed according to the different region contour characteristics of the face of the target object, thereby improving the accuracy of face recognition and improving the reliability of the face recognition result to the maximum extent.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. The clustering face recognition method is characterized by comprising the following steps:
step S1, shooting the face of the target object in multiple angles, so as to obtain a plurality of face images of different face areas of the target object, and preprocessing the face images;
step S2, carrying out image contour feature extraction processing on the preprocessed face images so as to obtain image contour feature information of the face images, and carrying out clustering processing on the face images according to the image contour feature information so as to construct and obtain corresponding three-dimensional face images;
and step S3, determining personnel identity information corresponding to the three-dimensional face image according to a preset face information database, and executing data acquisition permission operation matched with the personnel identity information according to the personnel identity information.
2. The clustered face recognition method of claim 1, wherein:
in step S1, the multi-angle shooting of the face of the target object is performed to obtain several face images of different face areas of the target object, and the pre-processing of the several face images specifically includes:
step S101, shooting the face of the target object in multiple angles relative to the left direction, the right direction, the dead direction, the upper direction and the lower direction, so as to correspondingly obtain a left area face image, a right area face image, a dead area face image, an upper area face image and a lower area face image;
step S102, the left side region face image, the right side region face image and the right side region face image are subjected to image pixel dead pixel repairing processing, image pixel graying processing and image edge pixel sharpening processing in sequence, so that the preprocessing is realized.
3. The clustered face recognition method of claim 2, wherein:
in step S2, performing image contour feature extraction processing on the preprocessed face images to obtain image contour feature information about the face images, and performing clustering processing on the face images according to the image contour feature information to construct corresponding three-dimensional face images specifically includes:
step S201, performing cutting processing on the preprocessed face image, thereby cutting the face image into a plurality of face sub-images with the same area, and acquiring image contour characteristic information corresponding to each face sub-image;
step S202, determining an image contour feature vector corresponding to each face sub-image in the face image according to the image contour feature information;
step S203, performing clustering operation on all image contour characteristic vectors contained in the face image to obtain a three-dimensional topography map corresponding to the face image, and then splicing the three-dimensional topography maps corresponding to all the face images to obtain the three-dimensional face image.
4. The clustered face recognition method of claim 3, wherein:
in step S3, determining, according to a preset face information database, person identity information corresponding to the three-dimensional face image, and executing, according to the person identity information, a data acquisition permission operation matched with the person identity information specifically includes:
step S301, determining image similarity between the three-dimensional face image and a plurality of face three-dimensional images contained in the preset face information database, and taking the face three-dimensional image with the maximum image similarity as a final identification determination image;
step S302, using the personnel identity information corresponding to the final identification confirmation image as the real personnel identity information of the target object;
step S303, determining a data acquisition level corresponding to the target object according to the identity information of the real person, and executing corresponding data reading operation and/or data modification operation according to the data acquisition level.
5. The clustered face recognition method of claim 3, wherein:
in step S3, determining, according to a preset face information database, person identity information corresponding to the three-dimensional face image, and according to the person identity information, performing a data acquisition permission operation matched with the person identity information specifically includes splitting the face image, determining an image contour feature value corresponding to each sub-image of the face image, performing a clustering operation on all image contour feature vectors included in the face image, comparing the obtained face image contour clustering operation value with preset face information database data, and according to a comparison result, performing a corresponding data reading operation and a corresponding data modifying operation, which specifically includes:
firstly, the preprocessed face image is cut to obtain image contour characteristic information corresponding to each face sub-image, and an image contour characteristic value P corresponding to each face sub-image in the face image is determined by using the following formula (1),
in the above formula (1), S represents the area of the face image, n represents the total number of face sub-images that are not divided into the same area, i represents the number of lines of the face image partial image, j represents the number of columns of the face image partial image, and x represents the number of lines of the face image partial imageiRepresents the area value occupied by five sense organs in the i-th row of sub-images,
represents the ratio of the area value of five sense organs in the sub-image in the ith row in the area of the sub-image, ljDenotes the longest diagonal length value of the five sense organs in the jth column of sub-images, dis (l)j,lj-1) Representing the distance between the longest diagonal length value of the five sense organs in the jth column of the sub-image and the jth-1 column of the sub-image;
secondly, using the following formula (2), clustering operation is performed on all image contour feature vectors contained in the face image to obtain a face image contour clustering operation value K,
in the above formula (2), sum (x)i,xi-1) Representing five of the i-th row of sub-imagesThe sum of the area value occupied by the facial features and the area value occupied by the five facial features in the sub-image of the i-1 th line, wherein P' represents the derivation operation on the image contour characteristic value P;
thirdly, comparing the obtained face image contour clustering operation value with the preset face information database data by using the following formula (3) to obtain a corresponding comparison value C, and then executing corresponding data reading operation and data modification operation according to the comparison value,
in the above formula (3), m represents the total number of data in the preset face information database, K 'represents the derivation operation for the face image contour cluster operation value K, O'mRepresenting the derivation operation of the contour clustering operation value corresponding to the mth data;
and when C is larger than 1, the obtained face image contour cluster operation value is matched with the mth data in the preset face information database, so that corresponding data reading operation and data modification operation are executed.
6. The clustering face recognition system is characterized by comprising a face image acquisition module, a face image preprocessing module, a three-dimensional face image construction module and an identity information recognition module; wherein the content of the first and second substances,
the face image acquisition module is used for shooting the face of the target object in multiple angles so as to acquire a plurality of face images of different face areas of the target object;
the face image preprocessing module is used for preprocessing a plurality of face images;
the three-dimensional face image construction module is used for extracting image contour characteristics of the preprocessed face images so as to obtain image contour characteristic information of the face images, and clustering the face images according to the image contour characteristic information so as to construct and obtain corresponding three-dimensional face images;
the identity information identification module is used for determining personnel identity information corresponding to the three-dimensional face image according to a preset face information database, and executing data acquisition permission operation matched with the personnel identity information according to the personnel identity information.
7. The clustered face recognition system of claim 6, wherein:
the face image acquisition module carries out multi-angle shooting on the face of the target object, so as to acquire a plurality of face images of different face areas of the target object, and the method specifically comprises the following steps:
shooting the face of the target object in multiple angles relative to the left direction, the right direction, the dead direction, the upper side direction and the lower side direction so as to correspondingly obtain a left area face image, a right area face image, a dead area face image, an upper area face image and a lower area face image;
and the number of the first and second groups,
the face image preprocessing module is used for preprocessing the face images, and specifically comprises the steps of carrying out image pixel dead pixel repairing processing, image pixel graying processing and image edge pixel sharpening processing on the left side region face image, the right side region face image and the right side region face image, wherein the upper side region face image and the lower side region face image are sequentially subjected to the image pixel dead pixel repairing processing, the image pixel graying processing and the image edge pixel sharpening processing, so that the preprocessing is realized.
8. The clustered face recognition system of claim 7, wherein:
the three-dimensional facial image construction module performs image contour feature extraction processing on the preprocessed face images so as to obtain image contour feature information about the face images, and performs clustering processing on the face images according to the image contour feature information, so as to construct and obtain corresponding three-dimensional facial images, specifically comprising:
cutting the preprocessed face image to obtain a plurality of face sub-images with the same area, and acquiring image contour characteristic information corresponding to each face sub-image;
determining an image contour characteristic vector corresponding to each face sub-image in the face image according to the image contour characteristic information;
and then carrying out clustering operation on all image contour characteristic vectors contained in the face image so as to obtain a three-dimensional topography map corresponding to the face image, and then splicing the three-dimensional topography maps corresponding to all the face images so as to obtain the three-dimensional face image.
9. The clustered face recognition system of claim 8, wherein:
the identity information identification module determines personnel identity information corresponding to the three-dimensional face image according to a preset face information database, and executes data acquisition permission operation matched with the personnel identity information according to the personnel identity information, wherein the data acquisition permission operation specifically comprises the following steps:
determining image similarity between the three-dimensional face image and a plurality of face three-dimensional images contained in the preset face information database, and taking the face three-dimensional image with the maximum image similarity as a final identification determination image;
and the personnel identity information corresponding to the final identification determination image is used as the real personnel identity information of the target object;
and determining a data acquisition level corresponding to the target object according to the identity information of the real personnel, and executing corresponding data reading operation and/or data modification operation according to the data acquisition level.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011549995.9A CN112580541B (en) | 2020-12-24 | 2020-12-24 | Clustering face recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011549995.9A CN112580541B (en) | 2020-12-24 | 2020-12-24 | Clustering face recognition method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112580541A true CN112580541A (en) | 2021-03-30 |
| CN112580541B CN112580541B (en) | 2021-10-08 |
Family
ID=75140467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011549995.9A Active CN112580541B (en) | 2020-12-24 | 2020-12-24 | Clustering face recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112580541B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7221809B2 (en) * | 2001-12-17 | 2007-05-22 | Genex Technologies, Inc. | Face recognition system and method |
| US20100098301A1 (en) * | 2006-09-22 | 2010-04-22 | Xuebing Zhou | Method and Device for Recognizing a Face and Face Recognition Module |
| CN102201061A (en) * | 2011-06-24 | 2011-09-28 | 常州锐驰电子科技有限公司 | Intelligent safety monitoring system and method based on multilevel filtering face recognition |
| CN104063702A (en) * | 2014-07-16 | 2014-09-24 | 中南大学 | Three-dimensional gait recognition based on shielding recovery and partial similarity matching |
| CN106251395A (en) * | 2016-07-27 | 2016-12-21 | 中测高科（北京）测绘工程技术有限责任公司 | A kind of threedimensional model fast reconstructing method and system |
| CN107680152A (en) * | 2017-08-31 | 2018-02-09 | 太原理工大学 | Target surface topography measurement method and apparatus based on image procossing |
| CN112001360A (en) * | 2020-09-09 | 2020-11-27 | 深圳中神电子科技有限公司 | Face recognition monitoring system based on intelligent adjustment |
-
2020
- 2020-12-24 CN CN202011549995.9A patent/CN112580541B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7221809B2 (en) * | 2001-12-17 | 2007-05-22 | Genex Technologies, Inc. | Face recognition system and method |
| US20100098301A1 (en) * | 2006-09-22 | 2010-04-22 | Xuebing Zhou | Method and Device for Recognizing a Face and Face Recognition Module |
| CN102201061A (en) * | 2011-06-24 | 2011-09-28 | 常州锐驰电子科技有限公司 | Intelligent safety monitoring system and method based on multilevel filtering face recognition |
| CN104063702A (en) * | 2014-07-16 | 2014-09-24 | 中南大学 | Three-dimensional gait recognition based on shielding recovery and partial similarity matching |
| CN106251395A (en) * | 2016-07-27 | 2016-12-21 | 中测高科（北京）测绘工程技术有限责任公司 | A kind of threedimensional model fast reconstructing method and system |
| CN107680152A (en) * | 2017-08-31 | 2018-02-09 | 太原理工大学 | Target surface topography measurement method and apparatus based on image procossing |
| CN112001360A (en) * | 2020-09-09 | 2020-11-27 | 深圳中神电子科技有限公司 | Face recognition monitoring system based on intelligent adjustment |
Non-Patent Citations (1)
| Title |
|---|
| MAMORU ISHIMOTO ET AL.: "Pose-Robust Face Recognition based on 3D Shape Reconstruction", 《2009 FIFTH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112580541B (en) | 2021-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP3218004B2 (en) | Test signature verification method | |
| CN109145745B (en) | Face recognition method under shielding condition | |
| Soliman et al. | Feature level fusion of palm veins and signature biometrics | |
| CN111428689B (en) | Face image feature extraction method based on multi-pool information fusion | |
| WO2015131468A1 (en) | Method and system for estimating fingerprint pose | |
| CN109344909A (en) | A kind of personal identification method based on multichannel convolutive neural network | |
| CN109583452A (en) | A kind of identification of individual method and system based on barefoot footprint | |
| CN112132117A (en) | Fusion identity authentication system assisting coercion detection | |
| CN112580541B (en) | Clustering face recognition method and system | |
| JP2013218605A (en) | Image recognition device, image recognition method, and program | |
| CN110222660B (en) | Signature authentication method and system based on dynamic and static feature fusion | |
| CN111753710A (en) | Subdivided neural network face recognition method applied to logistics distribution | |
| CN116342968B (en) | Dual-channel face recognition method and device | |
| CN116612538A (en) | Online confirmation method of electronic contract content | |
| CN112614160B (en) | Multi-object face tracking method and system | |
| Izadi et al. | Introduction of cylinder quality measure into minutia cylinder-code based fingerprint matching | |
| CN115497125A (en) | Fingerprint identification method, system, computer equipment and computer readable storage medium | |
| Alonso-Fernandez et al. | Fusion of static image and dynamic information for signature verification | |
| CN110390268B (en) | Three-dimensional palmprint recognition method based on geometric characteristics and direction characteristics | |
| CN112598576B (en) | Safety verification method and system based on face recognition | |
| Karanwal et al. | Fusion of fingerprint and face by using DWT and SIFT | |
| JP2013218604A (en) | Image recognition device, image recognition method, and program | |
| Avazpour et al. | Optimization of Human Recognition from the Iris Images using the Haar Wavelet. | |
| CN111160306B (en) | Three-dimensional palmprint recognition method integrating multi-feature and principal component analysis | |
| Maltoni et al. | Fingerprint Matching |
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 |