CN108376434B - Intelligent home control system based on Internet of things - Google Patents
Intelligent home control system based on Internet of things Download PDFInfo
- Publication number
- CN108376434B CN108376434B CN201810154287.1A CN201810154287A CN108376434B CN 108376434 B CN108376434 B CN 108376434B CN 201810154287 A CN201810154287 A CN 201810154287A CN 108376434 B CN108376434 B CN 108376434B
- Authority
- CN
- China
- Prior art keywords
- face
- user
- image
- face image
- double
- 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
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00563—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Abstract
The invention provides an intelligent home control system and device based on the Internet of things, wherein the system is used for identifying identity information of different users in a single image by setting a double-face image identification mode, so that high identification rate under the condition of lower similarity is realized, the safety and efficiency of face identification are improved, the problem of low identification efficiency caused by single-face identification is avoided, and the influence on an identification environment is reduced; in addition, the invention is provided with a plurality of second users matched with personnel identification verification, thereby improving the flexibility in the identification process and further ensuring the entrance guard safety of the users.
Description
Technical Field
The invention relates to the technical field of Internet of things and smart home, in particular to an intelligent home control system based on the Internet of things.
Background
Face identification belongs to the biological identification field, is applied to the intelligence lock field with it, can change the tradition habit that people need carry the key and just can open the door, through opening of face identification control door, has avoided people to forget the inconvenience that the key can not open the door greatly. In addition, the mechanical key has the risk of losing and being stolen, and the human face recognition has higher safety as the authentication. Compared with fingerprint identification, the face identification has the advantages of non-contact and convenience, and is more easily accepted by users, but the face identification has some defects when being used on a door lock. For example, the door lock is generally installed on a door, the height of the door lock is fixed during installation, and for users with different heights, problems of difficulty in capturing face images, low recognition accuracy and insufficient recognition speed may be caused, and particularly, when a child goes home alone, the child needs to swipe the face conveniently and quickly to enter the home. In addition, at present, adjustment to the camera is mostly manual adjustment, and it is comparatively inconvenient to use, also difficult accurately with the camera adjust to required angle, user experience is relatively poor, and causes the influence to face identification's accuracy.
In order to solve the above problem, document CN107146305A uses a human body sensing module to determine whether a person enters a sensing area, and an image collecting module is used to collect a face image of the person entering the sensing area; the cooperation of the image acquisition module, the transmission mechanism and the main processor realizes that the main processor can automatically carry out self-adaptive adjustment on the angle position of the image acquisition module through the transmission mechanism when the acquired image information does not contain a complete face image, thereby enlarging the effective range of face identification, improving the accuracy of face identification and having the advantages of high intelligent degree, convenient operation and high identification speed. The remote control of lock and the long-range discernment function of visitor have been realized to the cooperation of removing end and wireless communication module. The light filling lamp is used for filling light for the image acquisition module, and ensures that the image acquisition module can acquire enough clear images.
Firstly, although the method can improve the image recognition efficiency by adjusting the image acquisition module, the single biological information recognition method inevitably requires higher requirements on the image acquisition efficiency, and the recognition of the biological information recognition method is greatly influenced by environmental factors, so that the single biological information recognition method has great limitations; secondly, the method is only an external adjusting method in the image recognition process, and the image recognition is not effectively improved, so that a method for improving the biological characteristic recognition efficiency of the intelligent door lock is needed to be provided, so that the biological information recognition efficiency, flexibility and accuracy are improved, and the diversified and personalized experience of a user is further met.
Disclosure of Invention
The invention provides an intelligent home control system based on the Internet of things, which comprises the following modules:
the intelligent door lock comprises a first similarity judging module, a second similarity judging module and an image acquisition module, wherein the first similarity judging module is used for unlocking the image acquisition module by the intelligent door lock to acquire a first face image when a human body induction module in the intelligent door lock of the intelligent home induces that a human body of a first user enters a preset induction area; performing feature comparison on the first face image and a first face image stored in a memory of the smart home, and executing a door lock unlocking module when a result of the feature comparison is greater than or equal to a preset first similarity threshold value; when the result of the feature comparison is smaller than a preset first similarity threshold value, executing a double-face recognition starting module;
the double-face recognition starting module is used for prompting the first user to enter a double-face image recognition mode, and sending a face recognition verification request to a mobile terminal client of a second user related to the first face image stored in the memory after the first user confirms that the first user enters the double-face image recognition mode; after the second user agrees to the face recognition verification request, restarting the image acquisition module to acquire a double-face image simultaneously containing a first face image of the first user and a second face image of the second user;
the human face number recognition module is used for recognizing the human face number in the double-human-face image, and if the human face number in the double-human-face image is 2, the comprehensive similarity judgment module is executed; if the number of the faces in the double-face images is not 2, prompting the first user and the second user to re-acquire the double-face images, and returning to re-execute the face number recognition module;
the comprehensive similarity judging module is used for acquiring the double face image by the processor of the intelligent door lock and identifying a first face and a second face in the double face image; respectively comparing the image of the first face and the image of the second face with the first face image and the second face image stored in the memory to obtain the comprehensive similarity of the double face images; when the comprehensive similarity is larger than or equal to a preset comprehensive similarity threshold value, executing a door lock unlocking module; when the comprehensive similarity is smaller than a preset comprehensive similarity threshold value, judging that face recognition matching fails, and prompting the first user to change the opening mode of the intelligent door lock;
and the door lock unlocking module is used for judging that the matching is successful and unlocking the intelligent door lock.
As a preferred embodiment, the method further comprises:
the first similarity threshold is greater than the integrated similarity threshold.
As a preferred embodiment, the method further comprises:
an administrator user of the intelligent home sets the double-face image recognition mode of the intelligent door lock so as to set a second user related to the face recognition of the first user; the first user possesses the single face identification authority of intelligence lock, the second user possesses the single face identification authority of intelligence lock or do not possess the single face identification authority of intelligence lock.
As a preferred embodiment, the restarting the image capturing module to obtain the double-face image simultaneously including the first face image of the first user and the second face image of the second user specifically includes:
the image acquisition module is restarted, the image acquisition module acquires double-face images, the double-face images simultaneously comprise a first face image of a first user and a second face image of a second user, and the second face image part covers a non-first face part in the first face image or the first face image part covers a non-second face part in the second face image in the double-face images.
As a preferred embodiment, the recognizing the number of faces in the double-face image specifically includes:
acquiring the double face image, identifying the areas of the first face image and the second face image, and segmenting a first image area where the first face image is located and a second image area where the second face image is located, wherein the first image area and the second image area form the double face image; and respectively preprocessing the images of the first image area and the second image area, positioning the faces of the preprocessed images, and taking the number of the successfully positioned faces as the number of the recognized faces.
As a preferred embodiment, the comparing the features of the first face image and the second face image with the first face image and the second face image stored in the memory to obtain the comprehensive similarity of the double face images includes:
comparing the image of the first face with the first face image stored in the memory to obtain a first face image similarity a 1; comparing the image of the second face with the second face image stored in the memory to obtain a second face image similarity a 2;
the overall similarity of the double face images a12= a1 c1+ a2 c 2; wherein c1 is the weight coefficient of the first face image similarity a1, and c2 is the weight coefficient of the second face image similarity a 2.
As a preferred embodiment, the prompting the first user to change the unlocking mode of the intelligent door lock specifically includes:
closing an image acquisition module of the intelligent door lock, and forbidding the first user to adopt a face recognition unlocking mode;
prompting the first user to adopt any one of the following unlocking modes: key unblanking, card swiping unblanking, fingerprint unblanking, bluetooth unblanking, infrared ray unblanking.
As a preferred embodiment, the sending a face recognition verification request to a mobile terminal client of a second user associated with the first face image stored in the memory further includes:
the intelligent door lock comprises a plurality of second users, when the first user enters a double-face image recognition mode, a processor of the intelligent door lock acquires position information of mobile terminals of all the second users related to the first face image, judges the linear distance between the second users and the intelligent door lock based on the position information, and only sends the face recognition verification request of the first user to the second users with the linear distance smaller than a preset distance threshold value or a plurality of second users with the closest linear distance.
In addition, the invention provides an intelligent home control device based on the Internet of things, which comprises the following modules:
the intelligent door lock comprises a first similarity judging module, a second similarity judging module and an image acquisition module, wherein the first similarity judging module is used for unlocking the image acquisition module by the intelligent door lock to acquire a first face image when a human body induction module in the intelligent door lock of the intelligent home induces that a human body of a first user enters a preset induction area; performing feature comparison on the first face image and a first face image stored in a memory of the smart home, and executing a door lock unlocking module when a result of the feature comparison is greater than or equal to a preset first similarity threshold value; when the result of the feature comparison is smaller than a preset first similarity threshold value, executing a double-face recognition starting module;
the double-face recognition starting module is used for prompting the first user to enter a double-face image recognition mode, and sending a face recognition verification request to a mobile terminal client of a second user related to the first face image stored in the memory after the first user confirms that the first user enters the double-face image recognition mode; after the second user agrees to the face recognition verification request, restarting the image acquisition module to acquire a double-face image simultaneously containing a first face image of the first user and a second face image of the second user;
the human face number recognition module is used for recognizing the human face number in the double-human-face image, and if the human face number in the double-human-face image is 2, the comprehensive similarity judgment module is executed; if the number of the faces in the double-face images is not 2, prompting the first user and the second user to re-acquire the double-face images, and returning to re-execute the face number recognition module;
the comprehensive similarity judging module is used for acquiring the double face image by the processor of the intelligent door lock and identifying a first face and a second face in the double face image; respectively comparing the image of the first face and the image of the second face with the first face image and the second face image stored in the memory to obtain the comprehensive similarity of the double face images; when the comprehensive similarity is larger than or equal to a preset comprehensive similarity threshold value, executing a door lock unlocking module; when the comprehensive similarity is smaller than a preset comprehensive similarity threshold value, judging that face recognition matching fails, and prompting the first user to change the opening mode of the intelligent door lock;
and the door lock unlocking module is used for judging that the matching is successful and unlocking the intelligent door lock.
The invention provides an intelligent home control system and device based on the Internet of things, wherein a double-face image recognition mode is set in the system, so that identity information of different users in a single image is recognized, and high recognition rate under the condition of lower similarity is realized, so that the safety and efficiency of face recognition are improved, the problem of low recognition efficiency caused by single-face recognition is avoided, and the influence on a recognition environment is reduced; in addition, the invention is provided with a plurality of second users matched with personnel identification verification, thereby improving the flexibility in the identification process and further ensuring the entrance guard safety of the users.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the embodiments and the drawings used in the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic diagram of an embodiment of an intelligent home control system based on the internet of things.
Detailed Description
The embodiments of the present invention are further described below with reference to the drawings.
The first embodiment is as follows:
as shown in fig. 1, the invention provides an intelligent home control system based on the internet of things, which comprises the following modules:
the intelligent door lock comprises a first similarity judging module, a second similarity judging module and an image acquisition module, wherein the first similarity judging module is used for unlocking the image acquisition module by the intelligent door lock to acquire a first face image when a human body induction module in the intelligent door lock of the intelligent home induces that a human body of a first user enters a preset induction area; performing feature comparison on the first face image and a first face image stored in a memory of the smart home, and executing a door lock unlocking module when a result of the feature comparison is greater than or equal to a preset first similarity threshold value; when the result of the feature comparison is smaller than a preset first similarity threshold value, executing a double-face recognition starting module; it should be noted that the face feature comparison in this embodiment is not different from the conventional face recognition method in the art, and therefore, the details are not described herein. Illustratively, the first similarity threshold is 0.9.
The double-face recognition starting module is used for prompting the first user to enter a double-face image recognition mode, and sending a face recognition verification request to a mobile terminal client of a second user related to the first face image stored in the memory after the first user confirms that the first user enters the double-face image recognition mode; after the second user agrees to the face recognition verification request, restarting the image acquisition module to acquire a double-face image simultaneously containing a first face image of the first user and a second face image of the second user; it should be noted that the double face recognition mode in this embodiment is different from the aforementioned face recognition mode, that is, the single face recognition mode, and the double face image recognition mode is automatically turned on only when the single face recognition mode does not successfully perform face recognition, that is, the priority of the double face image recognition mode is lower than that of the single face recognition mode in a default case, which is set to be aimed at that double face recognition is required in the double face recognition mode, and complexity and difficulty of recognition are higher, so that the single face recognition mode is preferentially adopted in a conventional case, for example, when light in a recognition environment is good or a position of a head portrait of a first user is ideal, thereby increasing a recognition speed. For example, the second user associated with the first facial image may be preset by the administrator user, for example, the second user may be a family member of the first user, a friend living near the family of the first user, or even a neighbor of the first user, and the like, which is not limited herein. The purpose of the arrangement is that the second user can not only collect images on the mobile terminal of the second user for the first user to use in the face image recognition process, but also help the first user to carry out image recognition to unlock at the position of the intelligent door lock of the first user; therefore, the security of the access control of the first user can be ensured, and the security management of the access control of people needing to be monitored, such as children, can be facilitated; thereby improving the safety of the access control system in the using process.
The human face number recognition module is used for recognizing the human face number in the double-human-face image, and if the human face number in the double-human-face image is 2, the comprehensive similarity judgment module is executed; if the number of the faces in the double-face images is not 2, prompting the first user and the second user to re-acquire the double-face images, and returning to re-execute the face number recognition module; it should be noted that the number of faces being 2 is only an example, and in addition, face recognition may be simultaneously started after a plurality of second users agree to the request, and multiple face images corresponding to the plurality of second users may be obtained, so as to improve accuracy and security of image recognition. In addition, the first user and the second user are prompted to acquire double face images again, only the first user or the second user who does not successfully acquire a complete face image may be prompted to acquire images again, and all users may also be prompted to acquire images again, which is not limited herein.
The comprehensive similarity judging module is used for acquiring the double face image by the processor of the intelligent door lock and identifying a first face and a second face in the double face image; respectively comparing the image of the first face and the image of the second face with the first face image and the second face image stored in the memory to obtain the comprehensive similarity of the double face images; when the comprehensive similarity is larger than or equal to a preset comprehensive similarity threshold value, executing a door lock unlocking module; when the comprehensive similarity is smaller than a preset comprehensive similarity threshold value, judging that face recognition matching fails, and prompting the first user to change the opening mode of the intelligent door lock; it should be noted that, for example, the comprehensive similarity threshold is 0.7.
And the door lock unlocking module is used for judging that the matching is successful and unlocking the intelligent door lock.
As a preferred embodiment, the method further comprises:
the first similarity threshold is greater than the integrated similarity threshold. It should be noted that the reason why the first similarity threshold is set to be greater than the comprehensive similarity threshold is that, because the feature comparison is related to various environmental factors, the matching degree of a plurality of images can be reduced if the images are combined together after the feature comparison is performed separately, and therefore, in order to avoid the influence of excessively high setting of the similarity threshold on the accuracy of the recognition result, the comprehensive similarity threshold is set to be smaller than the first similarity threshold; therefore, the accuracy of image recognition is ensured, and the problem of inaccurate recognition result caused by over-high threshold value is avoided.
As a preferred embodiment, the method further comprises:
an administrator user of the intelligent home sets the double-face image recognition mode of the intelligent door lock so as to set a second user related to the face recognition of the first user; the first user possesses the single face identification authority of intelligence lock, the second user possesses the single face identification authority of intelligence lock or do not possess the single face identification authority of intelligence lock. It should be noted that the reason why the user right of the second user is lower than that of the first user is that the first user has a higher operation level, and the second user is only used as an assistant for the first user to perform face recognition; of course, the second user may also have the same user rating as the first user.
As a preferred embodiment, the restarting the image capturing module to obtain the double-face image simultaneously including the first face image of the first user and the second face image of the second user specifically includes:
the image acquisition module is restarted, the image acquisition module acquires double-face images, the double-face images simultaneously comprise a first face image of a first user and a second face image of a second user, and the second face image part covers a non-first face part in the first face image or the first face image part covers a non-second face part in the second face image in the double-face images. It should be noted that when the second user is near the intelligent door lock, i.e., in the unlocking site, the positions of the first user and the second user are not clearly divided, and the positions of the first user and the second user are common left and right positions, the image acquisition module acquires the double face image on site; when the second user is not near the intelligent door lock, namely the unlocking site, an upper left image interface and a lower right image interface can be presented for the first user to refer to.
As a preferred embodiment, the recognizing the number of faces in the double-face image specifically includes:
acquiring the double face image, identifying the areas of the first face image and the second face image, and segmenting a first image area where the first face image is located and a second image area where the second face image is located, wherein the first image area and the second image area form the double face image; and respectively preprocessing the images of the first image area and the second image area, positioning the faces of the preprocessed images, and taking the number of the successfully positioned faces as the number of the recognized faces. The double-face image is divided into a first image area, namely a left area, where the first face image is located and a second image area, namely a right area, where the second face image is located by any one of two dotted lines; then, respectively preprocessing the images of the left area and the right area, and further carrying out face positioning on the preprocessed images, namely respectively positioning the number of faces and the positions of the faces in the left image and the right image; thereby realizing the identification of the number and the position of the human faces. When the double face images are the positioning of the face images in the upper left area and the lower right area and the identification of the number, the method similar to the above is adopted for identification and positioning, and the description is omitted here. For example, the division principle of the regions may be a placement rule of the image acquisition module for different acquired images, that is, the image acquisition module defaults to arrange the two images in a left-right manner, and then divides the acquired images into left and right regions based on a dotted line, and the division position of the dotted line may be identified based on an edge detection method of the images, which is not described herein again.
As a preferred embodiment, the comparing the features of the first face image and the second face image with the first face image and the second face image stored in the memory to obtain the comprehensive similarity of the double face images includes:
comparing the image of the first face with the first face image stored in the memory to obtain a first face image similarity a 1; comparing the image of the second face with the second face image stored in the memory to obtain a second face image similarity a 2;
the overall similarity of the double face images a12= a1 c1+ a2 c 2; wherein c1 is the weight coefficient of the first face image similarity a1, and c2 is the weight coefficient of the second face image similarity a 2.
It should be noted that the method for calculating the similarity a1 of the first face image and the similarity a2 of the second face image adopts a matching algorithm that is conventional in the art, and details are not described herein. For example, the above-mentioned weighting coefficients c1 and c2 may be assigned according to the roles of the first user and the second user in the family of the administrator user, for example, if the user is the owner, the weighting coefficient c1 is given a larger weighting value of 0.9; if the second user is a user needing to be monitored, such as an old person and a minor person, a smaller weight value of 0.7 is given to the weight coefficient c 1; if the user is a person other than the family member, such as a friend or a neighbor, the weight coefficient c1 is given with the minimum weight value of 0.5; the assumed user may be the first user or the second user, and is not limited herein. Through the calculation, due to the introduction of the weight coefficients c1 and c2, the obtained comprehensive similarity a12 is smaller than the similarity of a single face image; but its recognition efficiency is increased. Therefore, the comprehensive similarity is adopted to carry out double-face recognition, the dependency on single face recognition can be reduced, the problem of recognition error caused by system error in the single face recognition process is avoided, the accuracy and the stability of face recognition are further improved, the high recognition rate under the lower similarity condition is realized, the safety and the efficiency of face recognition are improved, the problem of low recognition efficiency caused by single face recognition is avoided, and the influence on recognition environment factors is reduced.
As a preferred embodiment, the prompting the first user to change the unlocking mode of the intelligent door lock specifically includes:
closing an image acquisition module of the intelligent door lock, and forbidding the first user to adopt a face recognition unlocking mode;
prompting the first user to adopt any one of the following unlocking modes: key unblanking, card swiping unblanking, fingerprint unblanking, bluetooth unblanking, infrared ray unblanking. It should be noted that the above-listed unlocking methods are only an example, and are not limited to the above unlocking methods.
As a preferred embodiment, the sending a face recognition verification request to a mobile terminal client of a second user associated with the first face image stored in the memory further includes:
the intelligent door lock comprises a plurality of second users, when the first user enters a double-face image recognition mode, a processor of the intelligent door lock acquires position information of mobile terminals of all the second users related to the first face image, judges the linear distance between the second users and the intelligent door lock based on the position information, and only sends the face recognition verification request of the first user to the second users with the linear distance smaller than a preset distance threshold value or a plurality of second users with the closest linear distance.
It should be noted that the image recognition of any one second user is performed to cooperate with the first user to perform face recognition, and the obtaining of the location information of the mobile terminal of the second user is also performed to facilitate the second user to respond to the recognition operation of the first user at the fastest speed so as to improve the recognition speed; for example, if the second user is a neighbor of the first user, the response speed is usually the fastest when the straight line distance between the second user and the first user is the closest, and the neighbor is also the most efficient to perform face recognition in cooperation with the first user to unlock the lock as soon as possible. The straight line distance instead of the plane distance also considers the influence of the upper and lower floors which are not on the same horizontal plane on the method. In addition, the setting of the distance threshold may be adjusted according to actual needs, so as to flexibly set the number of the second users obtaining the verification response, for example, the number may be 50 meters, or may also be 5 kilometers, or even is not set, and is infinite by default, so that the first user obtains the most verification support of the second users.
Example two:
the invention provides an intelligent home control device based on the Internet of things, which comprises the following modules:
the intelligent door lock comprises a first similarity judging module, a second similarity judging module and an image acquisition module, wherein the first similarity judging module is used for unlocking the image acquisition module by the intelligent door lock to acquire a first face image when a human body induction module in the intelligent door lock of the intelligent home induces that a human body of a first user enters a preset induction area; performing feature comparison on the first face image and a first face image stored in a memory of the smart home, and executing a door lock unlocking module when a result of the feature comparison is greater than or equal to a preset first similarity threshold value; when the result of the feature comparison is smaller than a preset first similarity threshold value, executing a double-face recognition starting module;
the double-face recognition starting module is used for prompting the first user to enter a double-face image recognition mode, and sending a face recognition verification request to a mobile terminal client of a second user related to the first face image stored in the memory after the first user confirms that the first user enters the double-face image recognition mode; after the second user agrees to the face recognition verification request, restarting the image acquisition module to acquire a double-face image simultaneously containing a first face image of the first user and a second face image of the second user;
the human face number recognition module is used for recognizing the human face number in the double-human-face image, and if the human face number in the double-human-face image is 2, the comprehensive similarity judgment module is executed; if the number of the faces in the double-face images is not 2, prompting the first user and the second user to re-acquire the double-face images, and returning to re-execute the face number recognition module;
the comprehensive similarity judging module is used for acquiring the double face image by the processor of the intelligent door lock and identifying a first face and a second face in the double face image; respectively comparing the image of the first face and the image of the second face with the first face image and the second face image stored in the memory to obtain the comprehensive similarity of the double face images; when the comprehensive similarity is larger than or equal to a preset comprehensive similarity threshold value, executing a door lock unlocking module; when the comprehensive similarity is smaller than a preset comprehensive similarity threshold value, judging that face recognition matching fails, and prompting the first user to change the opening mode of the intelligent door lock;
and the door lock unlocking module is used for judging that the matching is successful and unlocking the intelligent door lock.
As a preferred embodiment, the method further comprises:
the first similarity threshold is greater than the integrated similarity threshold. It should be noted that the reason why the first similarity threshold is set to be greater than the comprehensive similarity threshold is that, because the feature comparison is related to various environmental factors, the matching degree of a plurality of images can be reduced if the images are combined together after the feature comparison is performed separately, and therefore, in order to avoid the influence of excessively high setting of the similarity threshold on the accuracy of the recognition result, the comprehensive similarity threshold is set to be smaller than the first similarity threshold; therefore, the accuracy of image recognition is ensured, and the problem of inaccurate recognition result caused by over-high threshold value is avoided.
As a preferred embodiment, the method further comprises:
an administrator user of the intelligent home sets the double-face image recognition mode of the intelligent door lock so as to set a second user related to the face recognition of the first user; the first user possesses the single face identification authority of intelligence lock, the second user possesses the single face identification authority of intelligence lock or do not possess the single face identification authority of intelligence lock. It should be noted that the reason why the user right of the second user is lower than that of the first user is that the first user has a higher operation level, and the second user is only used as an assistant for the first user to perform face recognition; of course, the second user may also have the same user rating as the first user.
As a preferred embodiment, the restarting the image capturing module to obtain the double-face image simultaneously including the first face image of the first user and the second face image of the second user specifically includes:
the image acquisition module is restarted, the image acquisition module acquires double-face images, the double-face images simultaneously comprise a first face image of a first user and a second face image of a second user, and the second face image part covers a non-first face part in the first face image or the first face image part covers a non-second face part in the second face image in the double-face images. It should be noted that when the second user is near the intelligent door lock, i.e., in the unlocking site, the positions of the first user and the second user are not clearly divided, and the positions of the first user and the second user are common left and right positions, the image acquisition module acquires the double face image on site; when the second user is not near the intelligent door lock, namely the unlocking site, an upper left image interface and a lower right image interface can be presented for the first user to refer to.
As a preferred embodiment, the recognizing the number of faces in the double-face image specifically includes:
acquiring the double face image, identifying the areas of the first face image and the second face image, and segmenting a first image area where the first face image is located and a second image area where the second face image is located, wherein the first image area and the second image area form the double face image; and respectively preprocessing the images of the first image area and the second image area, positioning the faces of the preprocessed images, and taking the number of the successfully positioned faces as the number of the recognized faces. The double-face image is divided into a first image area, namely a left area, where the first face image is located and a second image area, namely a right area, where the second face image is located by any one of two dotted lines; then, respectively preprocessing the images of the left area and the right area, and further carrying out face positioning on the preprocessed images, namely respectively positioning the number of faces and the positions of the faces in the left image and the right image; thereby realizing the identification of the number and the position of the human faces. When the double face images are the positioning of the face images in the upper left area and the lower right area and the identification of the number, the method similar to the above is adopted for identification and positioning, and the description is omitted here. For example, the division principle of the regions may be a placement rule of the image acquisition module for different acquired images, that is, the image acquisition module defaults to arrange the two images in a left-right manner, and then divides the acquired images into left and right regions based on a dotted line, and the division position of the dotted line may be identified based on an edge detection method of the images, which is not described herein again.
As a preferred embodiment, the comparing the features of the first face image and the second face image with the first face image and the second face image stored in the memory to obtain the comprehensive similarity of the double face images includes:
comparing the image of the first face with the first face image stored in the memory to obtain a first face image similarity a 1; comparing the image of the second face with the second face image stored in the memory to obtain a second face image similarity a 2;
the overall similarity of the double face images a12= a1 c1+ a2 c 2; wherein c1 is the weight coefficient of the first face image similarity a1, and c2 is the weight coefficient of the second face image similarity a 2.
It should be noted that the method for calculating the similarity a1 of the first face image and the similarity a2 of the second face image adopts a matching algorithm that is conventional in the art, and details are not described herein. For example, the above-mentioned weighting coefficients c1 and c2 may be assigned according to the roles of the first user and the second user in the family of the administrator user, for example, if the user is the owner, the weighting coefficient c1 is given a larger weighting value of 0.9; if the second user is a user needing to be monitored, such as an old person and a minor person, a smaller weight value of 0.7 is given to the weight coefficient c 1; if the user is a person other than the family member, such as a friend or a neighbor, the weight coefficient c1 is given with the minimum weight value of 0.5; the assumed user may be the first user or the second user, and is not limited herein. Through the calculation, due to the introduction of the weight coefficients c1 and c2, the obtained comprehensive similarity a12 is smaller than the similarity of a single face image; but its recognition efficiency is increased. Therefore, the comprehensive similarity is adopted to carry out double-face recognition, the dependency on single face recognition can be reduced, the problem of recognition error caused by system error in the single face recognition process is avoided, the accuracy and the stability of face recognition are further improved, the high recognition rate under the lower similarity condition is realized, the safety and the efficiency of face recognition are improved, the problem of low recognition efficiency caused by single face recognition is avoided, and the influence on recognition environment factors is reduced.
As a preferred embodiment, the prompting the first user to change the unlocking mode of the intelligent door lock specifically includes:
closing an image acquisition module of the intelligent door lock, and forbidding the first user to adopt a face recognition unlocking mode;
prompting the first user to adopt any one of the following unlocking modes: key unblanking, card swiping unblanking, fingerprint unblanking, bluetooth unblanking, infrared ray unblanking. It should be noted that the above-listed unlocking methods are only an example, and are not limited to the above unlocking methods.
As a preferred embodiment, the sending a face recognition verification request to a mobile terminal client of a second user associated with the first face image stored in the memory further includes:
the intelligent door lock comprises a plurality of second users, when the first user enters a double-face image recognition mode, a processor of the intelligent door lock acquires position information of mobile terminals of all the second users related to the first face image, judges the linear distance between the second users and the intelligent door lock based on the position information, and only sends the face recognition verification request of the first user to the second users with the linear distance smaller than a preset distance threshold value or a plurality of second users with the closest linear distance.
It should be noted that the image recognition of any one second user is performed to cooperate with the first user to perform face recognition, and the obtaining of the location information of the mobile terminal of the second user is also performed to facilitate the second user to respond to the recognition operation of the first user at the fastest speed so as to improve the recognition speed; for example, if the second user is a neighbor of the first user, the response speed is usually the fastest when the straight line distance between the second user and the first user is the closest, and the neighbor is also the most efficient to perform face recognition in cooperation with the first user to unlock the lock as soon as possible. The straight line distance instead of the plane distance also considers the influence of the upper and lower floors which are not on the same horizontal plane on the method. In addition, the setting of the distance threshold may be adjusted according to actual needs, so as to flexibly set the number of the second users obtaining the verification response, for example, the number may be 50 meters, or may also be 5 kilometers, or even is not set, and is infinite by default, so that the first user obtains the most verification support of the second users.
The invention provides an intelligent home control system and device based on the Internet of things, wherein the system is used for identifying identity information of different users in a single image by setting a double-face image identification mode, so that high identification rate under the condition of lower similarity is realized, the safety and efficiency of face identification are improved, the problem of low identification efficiency caused by single-face identification is avoided, and the influence on an identification environment is reduced; in addition, the invention is provided with a plurality of second users matched with personnel identification verification, thereby improving the flexibility in the identification process and further ensuring the entrance guard safety of the users.
It will be understood by those within the art that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the methods specified in the block or blocks of the block diagrams and/or flowchart block or blocks.
Those of skill in the art will appreciate that various operations, methods, steps in the processes, acts, or solutions discussed in the present application may be alternated, modified, combined, or deleted. Further, various operations, methods, steps in the flows, which have been discussed in the present application, may be interchanged, modified, rearranged, decomposed, combined, or eliminated. Further, steps, measures, schemes in the various operations, methods, procedures disclosed in the prior art and the present invention can also be alternated, changed, rearranged, decomposed, combined, or deleted.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (7)
1. The utility model provides an intelligent house control system based on thing networking which characterized in that, the system includes following module:
the intelligent door lock comprises a first similarity judging module, a second similarity judging module and an image acquisition module, wherein the first similarity judging module is used for unlocking the image acquisition module by the intelligent door lock to acquire a first face image when a human body induction module in the intelligent door lock of the intelligent home induces that a human body of a first user enters a preset induction area; performing feature comparison on the first face image and a first face image stored in a memory of the smart home, and executing a door lock unlocking module when a result of the feature comparison is greater than or equal to a preset first similarity threshold value; when the result of the feature comparison is smaller than a preset first similarity threshold value, executing a double-face recognition starting module;
the double-face recognition starting module is used for prompting the first user to enter a double-face image recognition mode, and sending a face recognition verification request to a mobile terminal client of a second user related to the first face image stored in the memory after the first user confirms that the first user enters the double-face image recognition mode; after the second user agrees to the face recognition verification request, restarting the image acquisition module to acquire a double-face image simultaneously containing a first face image of the first user and a second face image of the second user;
the human face number recognition module is used for recognizing the human face number in the double-human-face image, and if the human face number in the double-human-face image is 2, the comprehensive similarity judgment module is executed; if the number of the faces in the double-face images is not 2, prompting a user who does not successfully acquire a complete face image in the first user and the second user to acquire the double-face images again, and returning to execute the face number recognition module again;
the comprehensive similarity judging module is used for acquiring the double face image by the processor of the intelligent door lock and identifying a first face and a second face in the double face image; respectively comparing the image of the first face and the image of the second face with the first face image and the second face image stored in the memory to obtain the comprehensive similarity of the double face images; when the comprehensive similarity is larger than or equal to a preset comprehensive similarity threshold value, executing a door lock unlocking module; when the comprehensive similarity is smaller than a preset comprehensive similarity threshold value, judging that face recognition matching fails, and prompting the first user to change the opening mode of the intelligent door lock;
the door lock unlocking module is used for judging that the matching is successful and unlocking the intelligent door lock;
the respectively comparing the image of the first face and the image of the second face with the first face image and the second face image stored in the memory to obtain the comprehensive similarity of the double face images specifically comprises:
comparing the image of the first face with the first face image stored in the memory to obtain a first face image similarity a 1; comparing the image of the second face with the second face image stored in the memory to obtain a second face image similarity a 2;
the overall similarity of the double face images a12= a1 c1+ a2 c 2; wherein c1 is the weight coefficient of the first face image similarity a1, and c2 is the weight coefficient of the second face image similarity a 2.
2. The smart home control system of claim 1, further comprising:
the first similarity threshold is greater than the integrated similarity threshold.
3. The smart home control system of claim 1, further comprising:
an administrator user of the intelligent home sets the double-face image recognition mode of the intelligent door lock so as to set a second user related to the face recognition of the first user; the first user possesses the single face identification authority of intelligence lock, the second user possesses the single face identification authority of intelligence lock or do not possess the single face identification authority of intelligence lock.
4. The smart home control system according to claim 1, wherein the re-starting the image acquisition module to obtain the double-face image including the first face image of the first user and the second face image of the second user at the same time specifically includes:
the image acquisition module is restarted, the image acquisition module acquires double-face images, the double-face images simultaneously comprise a first face image of a first user and a second face image of a second user, and the second face image part covers a non-first face part in the first face image or the first face image part covers a non-second face part in the second face image in the double-face images.
5. The smart home control system according to claim 4, wherein the recognizing the number of faces in the double-face images specifically includes:
acquiring the double face image, identifying the areas of the first face image and the second face image, and segmenting a first image area where the first face image is located and a second image area where the second face image is located, wherein the first image area and the second image area form the double face image; and respectively preprocessing the images of the first image area and the second image area, positioning the faces of the preprocessed images, and taking the number of the successfully positioned faces as the number of the recognized faces.
6. The smart home control system according to claim 1, wherein the prompting of the first user to change the opening mode of the smart door lock specifically includes:
closing an image acquisition module of the intelligent door lock, and forbidding the first user to adopt a face recognition unlocking mode;
prompting the first user to adopt any one of the following unlocking modes: key unblanking, card swiping unblanking, fingerprint unblanking, bluetooth unblanking, infrared ray unblanking.
7. The smart home control system according to any one of claims 1 to 5, wherein the sending a face recognition verification request to a mobile terminal client of a second user associated with the first face image stored in the memory further comprises:
the intelligent door lock comprises a plurality of second users, when the first user enters a double-face image recognition mode, a processor of the intelligent door lock acquires position information of mobile terminals of all the second users related to the first face image, judges the linear distance between the second users and the intelligent door lock based on the position information, and only sends the face recognition verification request of the first user to the second users with the linear distance smaller than a preset distance threshold value or a plurality of second users with the closest linear distance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810154287.1A CN108376434B (en) | 2018-02-22 | 2018-02-22 | Intelligent home control system based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810154287.1A CN108376434B (en) | 2018-02-22 | 2018-02-22 | Intelligent home control system based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108376434A CN108376434A (en) | 2018-08-07 |
| CN108376434B true CN108376434B (en) | 2020-12-25 |
Family
ID=63017824
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810154287.1A Active CN108376434B (en) | 2018-02-22 | 2018-02-22 | Intelligent home control system based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108376434B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109409249A (en) * | 2018-09-30 | 2019-03-01 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN109447597B (en) * | 2018-12-27 | 2022-04-12 | 深圳市沃特沃德信息有限公司 | Method and device for attendance checking by multiple persons and face recognition system |
| CN110021101A (en) * | 2019-03-29 | 2019-07-16 | 深圳市九洲电器有限公司 | A kind of intelligent entrance guard control method and intelligent access control system |
| CN112070954A (en) * | 2020-09-14 | 2020-12-11 | 上海商汤智能科技有限公司 | Living body identification method, living body identification device, living body identification equipment and storage medium |
| CN113516814B (en) * | 2021-04-19 | 2023-04-18 | 新疆爱华盈通信息技术有限公司 | Intelligent supply method and terminal based on face recognition |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101142586A (en) * | 2005-03-18 | 2008-03-12 | 皇家飞利浦电子股份有限公司 | Method of performing face recognition |
| WO2011039040A1 (en) * | 2009-10-02 | 2011-04-07 | Tessera Technologies Ireland Limited | Improving face recognition performance using additional image features |
| CN103236103A (en) * | 2013-05-14 | 2013-08-07 | 苏州福丰科技有限公司 | Anti-follow access control system based on face recognition |
| CN103440691A (en) * | 2013-08-14 | 2013-12-11 | 毛振刚 | Bank exchequer long-distance defense management system |
| CN104599367A (en) * | 2014-12-31 | 2015-05-06 | 苏州福丰科技有限公司 | Multi-user parallel access control recognition method based on three-dimensional face image recognition |
| CN107195045A (en) * | 2017-05-18 | 2017-09-22 | 盐城工学院 | Gate inhibition's door bell and button system and safety-protection system |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202662026U (en) * | 2012-06-05 | 2013-01-09 | 上海锦江电子技术工程有限公司 | Multi-face recognition system |
| CN102945366B (en) * | 2012-11-23 | 2016-12-21 | 海信集团有限公司 | A kind of method and device of recognition of face |
| CN103714347B (en) * | 2013-12-30 | 2017-08-25 | 汉王科技股份有限公司 | Face identification method and face identification device |
| US10235822B2 (en) * | 2014-04-25 | 2019-03-19 | Vivint, Inc. | Automatic system access using facial recognition |
| CN106250851B (en) * | 2016-08-01 | 2020-03-17 | 徐鹤菲 | Identity authentication method, identity authentication equipment and mobile terminal |
| CN107077615A (en) * | 2017-01-12 | 2017-08-18 | 厦门中控生物识别信息技术有限公司 | Fingerprint method for anti-counterfeit and equipment |
-
2018
- 2018-02-22 CN CN201810154287.1A patent/CN108376434B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101142586A (en) * | 2005-03-18 | 2008-03-12 | 皇家飞利浦电子股份有限公司 | Method of performing face recognition |
| WO2011039040A1 (en) * | 2009-10-02 | 2011-04-07 | Tessera Technologies Ireland Limited | Improving face recognition performance using additional image features |
| CN103236103A (en) * | 2013-05-14 | 2013-08-07 | 苏州福丰科技有限公司 | Anti-follow access control system based on face recognition |
| CN103440691A (en) * | 2013-08-14 | 2013-12-11 | 毛振刚 | Bank exchequer long-distance defense management system |
| CN104599367A (en) * | 2014-12-31 | 2015-05-06 | 苏州福丰科技有限公司 | Multi-user parallel access control recognition method based on three-dimensional face image recognition |
| CN107195045A (en) * | 2017-05-18 | 2017-09-22 | 盐城工学院 | Gate inhibition's door bell and button system and safety-protection system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108376434A (en) | 2018-08-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108376434B (en) | Intelligent home control system based on Internet of things | |
| US11383676B2 (en) | Vehicles, vehicle door unlocking control methods and apparatuses, and vehicle door unlocking systems | |
| EP3647129A1 (en) | Vehicle, vehicle door unlocking control method and apparatus, and vehicle door unlocking system | |
| CN107578519A (en) | A kind of intelligent access control system and intelligent entrance guard method for unlocking | |
| US7120278B2 (en) | Person recognition apparatus | |
| US7567689B2 (en) | Authentication apparatus and authentication method | |
| US20040042645A1 (en) | Fingerprint recognition method, and fingerprint control method and system | |
| CN105868613A (en) | Biometric feature recognition method, biometric feature recognition device and mobile terminal | |
| JP2009003659A (en) | Authentication device, entrance management device, access control device, entrance management system, access control system, processing method therefor and program | |
| CN108734838B (en) | Intelligent lock with video-based biological feature verification device | |
| CN102385766A (en) | Palmprint-based authentication unlocking method, terminal and system | |
| CN105006077A (en) | ATM safe operation method and system based on fingerprint identification, and ATM | |
| CN108389290B (en) | Intelligent home control method based on Internet of things | |
| JP2013069155A (en) | Face authentication database construction method, face authentication device, and face authentication program | |
| CN112991599A (en) | Passage control method of multifunctional access control machine | |
| KR20160040037A (en) | The object authentication method and apparatus by the short-range video detection of multiple structure | |
| CN113003330A (en) | Intelligent elevator control method and system based on face recognition | |
| CN110838196B (en) | Intelligent door lock control method, intelligent door lock control system and intelligent door lock | |
| CN108520582B (en) | Automatic induction system for opening and closing automobile door | |
| CN113724420A (en) | Bimodal biological recognition anti-theft door and recognition method thereof | |
| CN106155787A (en) | The management method of application program, the managing device of application program and terminal | |
| KR102093858B1 (en) | Biometrics-based vehicle control device and vehicle control method using same | |
| KR101926709B1 (en) | Control apparatus for biometric and method thereof | |
| CN105138890A (en) | Authentication method, authentication device and terminal | |
| CN212160789U (en) | Face recognition access control system based on raspberry group |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201209 Address after: 506, Zhongxin science and technology building, Bagualing Industrial Zone, No. 31, Bagua Road, Hualin community, Yuanling street, Futian District, Shenzhen City, Guangdong Province Applicant after: Shenzhen Huake Intelligent Information Co.,Ltd. Address before: East house, 11th floor, building 6, yujingwan community, beiyihuan, Biyang County, Zhumadian City, Henan Province 463700 Applicant before: Chen Chong |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |