CN114218543A - Encryption and unlocking system and method based on multi-scene expression recognition - Google Patents
Encryption and unlocking system and method based on multi-scene expression recognition Download PDFInfo
- Publication number
- CN114218543A CN114218543A CN202111435070.6A CN202111435070A CN114218543A CN 114218543 A CN114218543 A CN 114218543A CN 202111435070 A CN202111435070 A CN 202111435070A CN 114218543 A CN114218543 A CN 114218543A
- Authority
- CN
- China
- Prior art keywords
- face
- expression
- image
- user
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/45—Structures or tools for the administration of authentication
- G06F21/46—Structures or tools for the administration of authentication by designing passwords or checking the strength of passwords
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a multi-scene encryption and unlocking system based on expression recognition, which comprises a camera module, a data acquisition module, a data storage module, a data processing module and an unlocking application module, wherein the camera module is used for acquiring images of a plurality of scenes; the data acquisition module shoots a user through the camera module, acquires a face image, establishes identity information by using the face image of the user, and prompts the user to sequentially acquire an expression sequence of the user and set an expression password; the data storage module stores relevant information; the data processing module analyzes the expression sequence, performs living body detection, feature extraction and face recognition on the face image, compares identity information, performs expression recognition on the face image to obtain an instruction, and obtains a comparison result by comparing the instruction with an expression password of a user; unlocking is completed through the comparison result, and the system is applied under different scenes; the system has strong reusability, can effectively cope with attacks possibly existing in different scenes, and ensures the information security and experience of users.
Description
Technical Field
The invention relates to the research field of expression recognition, in particular to an encryption unlocking system and method based on multi-scene expression recognition.
Background
Existing face recognition system
The existing face recognition system is widely applied to access management, access control and attendance checking, monitoring management and photo search. The existing face recognition technology is mature, a camera instrument is used for collecting real-time images, face detection and interception are carried out in the images to obtain face images, then preprocessing is carried out, an artificial neural network is used for face detection, features are extracted, and classification results of certain expressions are finally output through feature matching and retrieval.
Existing password unlocking system
Due to the protection of computer, mobile phone and even software privacy, various password unlocking modes are developed and applied, and the unlocking becomes faster, more personalized and more humanized. The original digital password unlocking is only to set the permutation and combination of simple numbers and then to hand unlocking, and the essence is to record the buttons of connecting lines according to the drawn path. With the development of technology, unlocking programs are increasingly diversified, and various unlocking functions which are more interesting than numbers and graphic passwords, such as fingerprint unlocking, face unlocking, voice unlocking, iris unlocking and the like, are developed. However, the security of these identification methods is relative, and there is no absolutely secure identification method. The trade-off between safety and convenience is not only in view of the development level of the technology, but also in view of the acceptance of consumers.
Existing cloud server technology
The cloud server is a basic computing component consisting of a CPU, a memory, an operating system and a cloud hard disk, and provides services such as computing, storage and network for various requirements of users by deploying software consuming computing unit resources on corresponding cloud services. Nowadays, due to the safe, reliable and elastically-telescopic computing service of the cloud server, a user can rapidly create a component cloud server without purchasing hardware, the cloud server has the advantages of high efficiency, operation and maintenance, and simplicity and convenience in management and expansion compared with a physical server, can meet multiple requirements of different use scenes and users, and is widely applied to various small and medium-sized enterprises and personal users in the internet industry.
Existing facial expression recognition equipment and technology
Facial expression features are extracted through facial photography, and different facial expressions are identified by using a trained classifier. Facial expression refers to the expression of various emotional states through the transformation of facial muscles, eye muscles, and oral muscles. Seven main emotions of humans: anger, happiness, sadness, surprise, disgust, fear, nature are all represented in a formulaic way by the facial expressions corresponding thereto. The current mood of the image pivot is analyzed after the expression is recognized through four steps of face detection, face registration, feature extraction and expression classification.
Equipment and technology for detecting existing human face living body
In order to attack the face recognition system, lawless persons crack the system by collecting face images of legitimate users and making various false body faces such as photos, videos, masks and the like. The liveness detection technique improves the security of face recognition systems by distinguishing whether the acquired face image is from a live face or a prosthetic person. The current in vivo detection is mainly divided into two types: one is in vivo detection by means of a picture classification model; the other type is a cooperative living body detection, which requires the user to complete the actions of turning the head, blinking and the like.
The existing face recognition unlocking and payment system has insufficient capability of resisting different types of attack technologies, the research on security vulnerabilities is incomplete, an intruder uses certain artifacts to imitate a real user, or an algorithm cannot recognize a correct user face and the like to attack the system; the existing digital password is too simple, and aiming at the problems that a single digital password has numerous existing cracking methods with low cost and easy implementation, the form is simple, the insecurity is high and the like, the requirements of users cannot be met more and more; the existing password system is rarely unlocked through the facial expression, although the technology of face recognition is rapidly developed in recent years, the technical development of further unlocking by utilizing the facial expression is not mature and is not widely applied; the existing facial expression password system only takes a single facial expression as decoding, so that the complexity is low, and the content form is not rich enough; (6) most of the existing living body detection technologies for face recognition require a user to complete actions such as raising the head, blinking, closing the eyes, even reading characters aloud, and the like in a matching way, so that the time is long, and the user experience is poor; or expensive instruments such as an infrared camera and a multispectral camera are needed for detection, although the accuracy is high, the cost is too high, and the method cannot be widely popularized.
Disclosure of Invention
The invention mainly aims to overcome the defects of the prior art and provide an encryption unlocking system and method based on multi-scene expression recognition.
The first purpose of the invention is to provide a multi-scene encryption and unlocking system based on expression recognition;
the second purpose of the invention is to provide a multi-scene encryption unlocking method based on expression recognition, and the first purpose of the invention is realized by the following technical scheme:
a multi-scene encryption and unlocking system based on expression recognition comprises a camera module, a data acquisition module, a data storage module, a data processing module and an unlocking application module;
the data acquisition module shoots a user through the camera module, acquires a face image, establishes identity information by using the face image of the user, and prompts the user to sequentially acquire an expression sequence of the user and set an expression password;
the data storage module stores the facial image, the identity information and the expression password of the corresponding user, which are acquired by the data acquisition module;
the data processing module analyzes the expression sequence, performs feature extraction and face recognition on a face image which is a living body face in the face image, compares the identity information in the data storage module, further performs expression recognition on the face image to obtain a number or letter instruction, and obtains a comparison result by comparing the instruction with an expression password of a user in the data storage module;
and the unlocking application module completes encryption and unlocking through the comparison result and performs system application in subsequent different scenes.
Furthermore, the camera module is a terminal camera module and can acquire the face image of the user in time.
Furthermore, the data acquisition module acquires a face image through the camera module, identity information is established and stored in the data storage module by using the face image of the user, the identity information is established, then expression pictures are acquired for the user according to the code sequence, and then expression codes are set.
Further, the data processing module comprises a living body detection module, a face recognition module and a facial expression recognition module;
the living body detection module is used for preprocessing an overall image, wherein the overall image comprises a background image and a face image, and the preprocessing comprises the following steps: cutting, aligning and dividing the whole image, transforming and overlapping the space of the whole image, and operating by changing the color space of the whole image from a time domain to a frequency domain or a space domain; after preprocessing, carrying out depth feature extraction on the whole image by using a neural network, judging whether the face in the whole image comes from a living body according to the features of the whole image, and detecting whether the whole image has light and shadow abnormity, a mobile phone frame, paper, a display, plastic material reflection and skin line abnormity;
the face recognition module preprocesses a static face image, wherein the preprocessing comprises the following steps: adopting an artificial neural network to carry out face detection, determining the position, size and pose of a face, accurately identifying the positions of different features of the face, aligning the face, and carrying out gray scale and geometric normalization on a face image after a series of data enhancement operations; extracting the depth characteristics of the human face in the human face image through a network model after preprocessing, namely performing modeling and analysis processes on human face image data, performing search matching and comparison on the extracted characteristic data of the human face image and a characteristic template stored in a data storage module, and judging whether a user corresponding to the human face image is input into a system according to the identity information of the human face according to the similarity degree;
the facial expression recognition module is used for preprocessing the facial expression image of the face image acquired by the data acquisition module, and the preprocessing comprises the following steps: adopting an artificial neural network to carry out face detection, determining the position, size and pose of a face, accurately identifying the positions of different features of the face, aligning the face, and carrying out gray scale and geometric normalization on a face image after a series of data enhancement operations; and after preprocessing, carrying out frame aggregation on the facial expression image, extracting facial expression depth features by using a deep learning algorithm, combining multiple frames, inputting the facial expression image into a CNN (compact neural network), outputting an expression classification result, and converting the expression classification result into a digital instruction.
Further, the unlocking application module controls whether the terminal is unlocked or not according to the comparison result of the identity information and the expression password of the data processing module and the data storage module, and if the identity information is not matched, the terminal prompts a user that the identity information does not exist, and the user asks for setting the identity information first; if the expression password is incorrect, prompting the user to input again; and if the identity information and the expression password are both correct, the corresponding application is completed according to the scene.
The second purpose of the invention is realized by the following technical scheme:
a multi-scene encryption unlocking method based on expression recognition comprises the following steps:
shooting a user through a camera module, acquiring a face image, establishing identity information by using the face image of the user, and prompting the user to sequentially acquire an expression sequence of the user and set an expression password;
analyzing the expression sequence, extracting and identifying the characteristics of a face image which is a living body face in the face image, comparing the identity information in the data storage module, further identifying the face image to obtain a number or letter instruction, and comparing the instruction with an expression password of a user in the data storage module to obtain a comparison result;
and completing encryption and unlocking through the comparison result, and applying the system in subsequent different scenes.
Further, the expressions of the expression sequence include: anger, happiness, sadness, surprise, disgust, fear and nature, setting the corresponding identification of the password length and the expression, and setting the password through the corresponding identification.
Furthermore, the password is set through the corresponding identifier, specifically, a number or letter instruction is set for the expression, and the password length are set through the number or letter instruction.
Further, the feature extraction and identification are carried out on the face image part which is a living body in the whole image, and the feature extraction and identification comprise living body detection, face identification and facial expression identification;
the in vivo detection specifically comprises the following steps: the method comprises the following steps of preprocessing an overall image, wherein the overall image comprises a background image and a face image, and the preprocessing comprises the following steps: cutting, aligning and dividing the whole image, transforming and overlapping the space of the whole image, and operating by changing the color space of the whole image from a time domain to a frequency domain or a space domain; after preprocessing, carrying out depth feature extraction on the whole image by using a neural network, judging whether the face in the whole image comes from a living body according to the features of the whole image, and detecting whether the whole image has light and shadow abnormity, a mobile phone frame, paper, a display, plastic material reflection and skin line abnormity;
the face recognition specifically comprises the following steps: preprocessing a static face image, wherein the preprocessing comprises the following steps: adopting an artificial neural network to carry out face detection, determining the position, size and pose of a face, accurately identifying the positions of different features of the face, aligning the face, and carrying out gray scale and geometric normalization on a face image after a series of data enhancement operations; extracting the depth characteristics of the human face in the human face image through a network model after preprocessing, namely performing modeling and analysis processes on human face image data, performing search matching and comparison on the extracted characteristic data of the human face image and a characteristic template stored in a data storage module, and judging whether a user corresponding to the human face image is input into a system according to the identity information of the human face according to the similarity degree;
the facial expression recognition specifically comprises: the method comprises the following steps of preprocessing a facial expression image of a face image acquired by a data acquisition module, wherein the preprocessing comprises the following steps: adopting an artificial neural network to carry out face detection, determining the position, size and pose of a face, accurately identifying the positions of different features of the face, aligning the face, and carrying out gray scale and geometric normalization on a face image after a series of data enhancement operations; and after preprocessing, carrying out frame aggregation on the facial expression image, extracting facial expression depth features by using a deep learning algorithm, combining multiple frames, inputting the facial expression image into a CNN (compact neural network), outputting an expression classification result, and converting the expression classification result into a digital instruction.
Further, the encryption and the unlocking are completed through the comparison result, and the application of the system under the subsequent different scenes is specifically as follows: controlling whether the terminal is unlocked or not according to a comparison result of the identity information and the expression password of the data processing module and the data storage module, if the identity information is not matched, prompting a user through the terminal, if the identity information does not exist, and asking for setting the identity information first; if the expression password is incorrect, prompting the user to input again; and if the identity information and the expression password are both correct, the corresponding application is completed according to the scene.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. the invention is convenient and easy to implement, and can meet the requirements of various occasions. The invention can shoot the facial expression image of the user by identifying the cameras of the terminals such as a computer, a mobile phone, an entrance guard and the like and convert the facial expression image into the password, and has high reusability, simplicity and convenience.
2. According to the invention, the camera can be used for shooting the facial image of the human body, the facial expression is recognized and converted into the digital instruction, the facial expression of the user is recognized on line in real time, the complexity of the password is increased, the risk of password cracking is reduced, and meanwhile, the interestingness is increased.
3. The method and the system detect the background and the face in the facial expression picture by using the living body detection, prevent the prosthesis attack in various 2D and 3D modes, ensure the safety of user information in various scenes and improve the overall safety of the system.
4. According to the invention, the data processing and corresponding algorithm modules are executable program codes and then read out and executed through the cloud server background, so that complex hardware equipment is not required to process data, the space occupied by a product is saved, the data processing is efficient, and the user experience is improved.
5. The whole system supports wireless communication, can transmit data to the storage module in a wireless manner, is convenient to realize data storage, processing and data analysis operation, has fast data storage, cannot be lost, and enhances the safety and reliability of data storage. The data can be subsequently modified, processed and the like.
6. The invention can be used in the scenes of door control, computer and mobile phone unlocking, employee daily attendance card punching, online payment and the like, has strong reusability, can effectively deal with attacks possibly existing in different scenes, and ensures the information safety and experience of users
Drawings
FIG. 1 is a system structure block diagram of an encryption unlocking system based on multi-scene expression recognition according to the present invention;
fig. 2 is a block diagram of a data processing module according to embodiment 1 of the present invention;
fig. 3 is a flowchart of an encryption unlocking method based on multi-scene expression recognition.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but the present invention is not limited thereto.
Example 1:
an encryption and unlocking system based on multi-scene expression recognition is shown in fig. 1 and comprises a camera module, a data acquisition module, a data storage module, a data processing module and an unlocking application module;
the data acquisition module shoots a user through the camera module, acquires a face image, establishes identity information by using the face image of the user, and prompts the user to sequentially acquire an expression sequence of the user and set an expression password;
the data storage module stores the facial image, the identity information and the expression password of the corresponding user, which are acquired by the data acquisition module;
the data processing module analyzes the expression sequence, performs feature extraction and face recognition on a face image which is a living body face in the face image, compares the identity information in the data storage module, further performs expression recognition on the face image to obtain a number or letter instruction, and obtains a comparison result by comparing the instruction with an expression password of a user in the data storage module;
and the unlocking application module completes encryption and unlocking through the comparison result and performs system application in subsequent different scenes.
The method comprises the following specific steps:
a data acquisition module:
the data acquisition module is used for acquiring the identity, the face image data and the facial expression password data information of a user and transmitting the data to the data storage module, so that the data can be analyzed and processed conveniently by the calculation module. A user shoots a face image by utilizing a camera of a terminal such as a computer, a mobile phone, software and an entrance guard, and a data acquisition module acquires a face picture of the user and transmits the face picture to a data storage module to establish an identity information file. After the file is established, the acquisition module acquires the expression pictures of the user according to the password sequence and transmits the expression picture data to the calculation module for identification.
A data storage module:
the data storage module receives the user identity information and the face image data which are collected by the data collection module, and a password instruction obtained by the calculation module through recognizing the expression password set by the user, and provides comparison data with the recognition result of the calculation module for subsequent user unlocking so as to judge whether the identity and the password are correct.
A data processing module:
the data processing module mainly comprises a face recognition module, a facial expression recognition module and a living body detection module, as shown in fig. 2, and is responsible for completing key functions of comparing and retrieving features of the acquired face image and the face image in the data storage module, judging whether the face and the expression are attacked by an illegal prosthesis or not, and judging whether the password is matched or not.
Face recognition module
The module is responsible for preprocessing a static image, adopting an artificial neural network to carry out face detection, carrying out face alignment according to a face positioning point (landmark) detected by the face, and carrying out gray scale and geometric normalization on the image after data enhancement. Extracting face features in the image after preprocessing, modeling and analyzing face data, extracting corresponding face features, further performing retrieval matching and comparison on the features, and judging whether a user on the image is input into a system or not; the method specifically comprises the following steps: the face recognition module preprocesses a static face image, wherein the preprocessing comprises the following steps: adopting an artificial neural network to carry out face detection, determining the position, size and pose of a face, accurately identifying the positions of different features of the face, including canthus, pupil, mouth and nose, carrying out face alignment, carrying out gray scale and geometric normalization on a face image after a series of data enhancement operations, wherein the series of data enhancement operations comprise filtering, translation, overturning and rotation; and after preprocessing, extracting the depth characteristics of the face in the face image through a network model, namely performing modeling and analysis processes on the face image data, performing search matching and comparison on the extracted characteristic data of the face image and a characteristic template stored in a data storage module, and judging whether a user corresponding to the face image is input into the system according to the identity information of the face according to the similarity degree.
Facial expression recognition module
After the facial expression recognition module receives the facial expression picture of the acquisition module, the facial expression recognition module firstly preprocesses the expression image, and after the alignment of the face positioning points and data enhancement, the gray scale and geometric normalization of the image are carried out. And after the preprocessing, performing frame aggregation, extracting the depth characteristics of the facial expressions by using a deep learning algorithm, combining multiple frames, inputting the facial image into CNN, and outputting the classification result of a certain type of expressions. 7 different emotions: anger, happiness, sadness, surprise, disgust, fear and natural emotion respectively represent numbers 1-7, and other identifiers can be used for representing and converting the classification result into a digital instruction;
living body detection module
The living body detection module firstly preprocesses an image, wherein the whole image comprises a background image and a face image, and the preprocessing comprises the following steps: cutting, aligning and dividing the whole image, transforming and overlapping the space of the whole image, and operating by changing the color space of the whole image from a time domain to a frequency domain or a space domain; after preprocessing, extracting the features of the whole image by using a neural network, classifying according to the features of the whole image, and judging whether the face in the whole image comes from a living body, wherein the judgment is to detect whether the whole image has abnormal light and shadow, a mobile phone frame, paper, a display, plastic material reflection and skin texture.
Unlocking the application module:
the application module controls whether the terminal is unlocked or not according to the identity and password comparison result of the computing module and the storage module, and if the identity is incorrect, the terminal prompts a user that the identity information does not exist, and the user asks to set the identity information first; if the identity card confirms that the password is incorrect, prompting the user to input again; and if the identity and the password are both correct, the corresponding application is completed according to the scene. Whether the door control, the computer, the mobile phone, the software and the like can be opened or not; whether the online payment is successful; whether the attendance system records the card punching information or not.
Example 2
An encryption unlocking method based on multi-scene expression recognition is shown in fig. 3, and includes the following steps:
shooting a user through a camera module, acquiring a face image, establishing identity information by using the face image of the user, and prompting the user to sequentially acquire an expression sequence of the user and set an expression password;
analyzing the expression sequence, extracting and identifying the characteristics of a face image which is a living body face in the face image, comparing the identity information in the data storage module, further identifying the face image to obtain a digital instruction, and comparing the expression password of the user in the data storage module through the digital instruction to obtain a comparison result;
and completing encryption and unlocking through the comparison result, and applying the system in subsequent different scenes.
Further, the expressions of the expression sequence include: anger, happiness, sadness, surprise, disgust, fear and nature, setting the corresponding identification of the password length and the expression, and setting the password through the corresponding identification.
Further, the expression is set with a corresponding identifier, specifically, a number or letter instruction is set for the expression, and a password length are set through the number or letter instruction.
Further, the feature extraction and identification are carried out on the face image which is a living body face in the face image, and the feature extraction and identification comprise face identification, facial expression identification and living body detection;
the in vivo detection specifically comprises the following steps: the method comprises the following steps of preprocessing an overall image, wherein the overall image comprises a background image and a face image, and the preprocessing comprises the following steps: cutting, aligning and dividing the whole image, transforming and overlapping the space of the whole image, and operating by changing the color space of the whole image from a time domain to a frequency domain or a space domain; after preprocessing, carrying out depth feature extraction on the whole image by using a neural network, judging whether the face in the whole image comes from a living body according to the features of the whole image, and detecting whether the whole image has light and shadow abnormity, a mobile phone frame, paper, a display, plastic material reflection and skin line abnormity;
the face recognition specifically comprises the following steps: preprocessing a static face image, wherein the preprocessing comprises the following steps: adopting an artificial neural network to carry out face detection, determining the position, size and pose of a face, accurately identifying the positions of different features of the face, aligning the face, and carrying out gray scale and geometric normalization on a face image after a series of data enhancement operations; extracting the depth characteristics of the human face in the human face image through a network model after preprocessing, namely performing modeling and analysis processes on human face image data, performing search matching and comparison on the extracted characteristic data of the human face image and a characteristic template stored in a data storage module, and judging whether a user corresponding to the human face image is input into a system according to the identity information of the human face according to the similarity degree;
the facial expression recognition specifically comprises: the method comprises the following steps of preprocessing a facial expression image of a face image acquired by a data acquisition module, wherein the preprocessing comprises the following steps: adopting an artificial neural network to carry out face detection, determining the position, size and pose of a face, accurately identifying the positions of different features of the face, aligning the face, and carrying out gray scale and geometric normalization on a face image after a series of data enhancement operations; and after preprocessing, carrying out frame aggregation on the facial expression image, extracting facial expression depth features by using a deep learning algorithm, combining multiple frames, inputting the facial expression image into a CNN (compact neural network), outputting an expression classification result, and converting the expression classification result into a digital instruction.
Further, the encryption and the unlocking are completed through the comparison result, and the application of the system under the subsequent different scenes is specifically as follows: controlling whether the terminal is unlocked or not according to a comparison result of the identity information and the expression password of the data processing module and the data storage module, if the identity information is not matched, prompting a user through the terminal, if the identity information does not exist, and asking for setting the identity information first; if the expression password is incorrect, prompting the user to input again; and if the identity information and the expression password are both correct, the corresponding application is completed according to the scene.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (10)
1. A multi-scene encryption and unlocking system based on expression recognition is characterized by comprising a camera module, a data acquisition module, a data storage module, a data processing module and an unlocking application module;
the data acquisition module shoots a user through the camera module, acquires a face image, establishes identity information by using the face image of the user, and prompts the user to sequentially acquire an expression sequence of the user and set an expression password;
the data storage module stores the facial image, the identity information and the expression password of the corresponding user, which are acquired by the data acquisition module;
the data processing module analyzes the expression sequence, performs feature extraction and face recognition on a face image which is a living body face in the face image, compares the identity information in the data storage module, further performs expression recognition on the face image to obtain a number or letter instruction, and obtains a comparison result by comparing the instruction with an expression password of a user in the data storage module;
and the unlocking application module completes encryption and unlocking through the comparison result and performs system application in subsequent different scenes.
2. The expression recognition-based multi-scene encryption and unlocking system as claimed in claim 1, wherein the camera module is a terminal camera module capable of collecting face images of the user in time.
3. The expression recognition-based multi-scene encryption and unlocking system as claimed in claim 1, wherein the data acquisition module acquires a face image through the camera module, establishes and stores identity information in the data storage module by using the face image of the user, acquires expression pictures of the user according to the password sequence after establishing the identity information, and further sets an expression password.
4. The expression recognition-based multi-scene encryption and unlocking system as claimed in claim 1, wherein the data processing module comprises a living body detection module, a face recognition module and a facial expression recognition module;
the living body detection module is used for preprocessing an overall image, wherein the overall image comprises a background image and a face image, and the preprocessing comprises the following steps: cutting, aligning and dividing the whole image, transforming and overlapping the space of the whole image, and operating by changing the color space of the whole image from a time domain to a frequency domain or a space domain; after preprocessing, carrying out depth feature extraction on the whole image by using a neural network, judging whether the face in the whole image comes from a living body according to the features of the whole image, and detecting whether the whole image has light and shadow abnormity, a mobile phone frame, paper, a display, plastic material reflection and skin line abnormity;
the face recognition module preprocesses a static face image, wherein the preprocessing comprises the following steps: adopting an artificial neural network to carry out face detection, determining the position, size and pose of a face, accurately identifying the positions of different features of the face, aligning the face, and carrying out gray scale and geometric normalization on a face image after a series of data enhancement operations; extracting the depth characteristics of the human face in the human face image through a network model after preprocessing, namely performing modeling and analysis processes on human face image data, performing search matching and comparison on the extracted characteristic data of the human face image and a characteristic template stored in a data storage module, and judging whether a user corresponding to the human face image is input into a system according to the identity information of the human face according to the similarity degree;
the facial expression recognition module is used for preprocessing the facial expression image of the face image acquired by the data acquisition module, and the preprocessing comprises the following steps: adopting an artificial neural network to carry out face detection, determining the position, size and pose of a face, accurately identifying the positions of different features of the face, aligning the face, and carrying out gray scale and geometric normalization on a face image after a series of data enhancement operations; and after preprocessing, carrying out frame aggregation on the facial expression image, extracting facial expression depth features by using a deep learning algorithm, combining multiple frames, inputting the facial expression image into a CNN (compact neural network), outputting an expression classification result, and converting the expression classification result into a digital instruction.
5. The multi-scene encryption and unlocking system based on expression recognition is characterized in that the unlocking application module controls whether the terminal is unlocked according to the comparison result of the identity information and the expression password of the data processing module and the data storage module, and if the identity information is not matched, the terminal prompts a user that the identity information does not exist, and the user asks to set the identity information first; if the expression password is incorrect, prompting the user to input again; and if the identity information and the expression password are both correct, the corresponding application is completed according to the scene.
6. A multi-scene encryption unlocking method based on expression recognition is characterized by comprising the following steps:
shooting a user through a camera module, acquiring a face image, establishing identity information by using the face image of the user, and prompting the user to sequentially acquire an expression sequence of the user and set an expression password;
analyzing the expression sequence, extracting and identifying the characteristics of a face image which is a living body face in the face image, comparing the identity information in the data storage module, further identifying the face image to obtain a number or letter instruction, and comparing the instruction with an expression password of a user in the data storage module to obtain a comparison result;
and completing encryption and unlocking through the comparison result, and applying the system in subsequent different scenes.
7. The multi-scene encryption unlocking method based on expression recognition is characterized in that the expressions of the expression sequence comprise: anger, happiness, sadness, surprise, disgust, fear and nature, setting the corresponding identification of the password length and the expression, and setting the password through the corresponding identification.
8. The multi-scene encryption and unlocking method based on expression recognition according to claim 7, wherein a password is set through the corresponding identifier, specifically, a number or letter instruction is set for the expression, and the password length are set through the number or letter instruction.
9. The expression recognition-based multi-scene encryption and unlocking method as claimed in claim 6, wherein the feature extraction and recognition including living body detection, face recognition and facial expression recognition are performed on the face image part which is a living body in the whole image;
the in vivo detection specifically comprises the following steps: the method comprises the following steps of preprocessing an overall image, wherein the overall image comprises a background image and a face image, and the preprocessing comprises the following steps: cutting, aligning and dividing the whole image, transforming and overlapping the space of the whole image, and operating by changing the color space of the whole image from a time domain to a frequency domain or a space domain; after preprocessing, carrying out depth feature extraction on the whole image by using a neural network, judging whether the face in the whole image comes from a living body according to the features of the whole image, and detecting whether the whole image has light and shadow abnormity, a mobile phone frame, paper, a display, plastic material reflection and skin line abnormity;
the face recognition specifically comprises the following steps: preprocessing a static face image, wherein the preprocessing comprises the following steps: adopting an artificial neural network to carry out face detection, determining the position, size and pose of a face, accurately identifying the positions of different features of the face, aligning the face, and carrying out gray scale and geometric normalization on a face image after a series of data enhancement operations; extracting the depth characteristics of the human face in the human face image through a network model after preprocessing, namely performing modeling and analysis processes on human face image data, performing search matching and comparison on the extracted characteristic data of the human face image and a characteristic template stored in a data storage module, and judging whether a user corresponding to the human face image is input into a system according to the identity information of the human face according to the similarity degree;
the facial expression recognition specifically comprises: the method comprises the following steps of preprocessing a facial expression image of a face image acquired by a data acquisition module, wherein the preprocessing comprises the following steps: adopting an artificial neural network to carry out face detection, determining the position, size and pose of a face, accurately identifying the positions of different features of the face, aligning the face, and carrying out gray scale and geometric normalization on a face image after a series of data enhancement operations; and after preprocessing, carrying out frame aggregation on the facial expression image, extracting facial expression depth features by using a deep learning algorithm, combining multiple frames, inputting the facial expression image into a CNN (compact neural network), outputting an expression classification result, and converting the expression classification result into a digital instruction.
10. The expression recognition-based multi-scene encryption and unlocking method according to claim 6, wherein encryption and unlocking are completed through comparison results, and application of systems in subsequent different scenes is performed, specifically: controlling whether the terminal is unlocked or not according to a comparison result of the identity information and the expression password of the data processing module and the data storage module, if the identity information is not matched, prompting a user through the terminal, if the identity information does not exist, and asking for setting the identity information first; if the expression password is incorrect, prompting the user to input again; and if the identity information and the expression password are both correct, the corresponding application is completed according to the scene.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111435070.6A CN114218543A (en) | 2021-11-29 | 2021-11-29 | Encryption and unlocking system and method based on multi-scene expression recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111435070.6A CN114218543A (en) | 2021-11-29 | 2021-11-29 | Encryption and unlocking system and method based on multi-scene expression recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114218543A true CN114218543A (en) | 2022-03-22 |
Family
ID=80698899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111435070.6A Pending CN114218543A (en) | 2021-11-29 | 2021-11-29 | Encryption and unlocking system and method based on multi-scene expression recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114218543A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116453196A (en) * | 2023-04-22 | 2023-07-18 | 北京易知环宇文化传媒有限公司 | Face recognition method and system |
| CN116664140A (en) * | 2023-08-02 | 2023-08-29 | 华北电力大学 | Carbon emission right trading method based on blockchain |
| CN117495384A (en) * | 2023-11-07 | 2024-02-02 | 广州准捷电子科技有限公司 | KTV face brushing payment method based on AI face recognition technology |
-
2021
- 2021-11-29 CN CN202111435070.6A patent/CN114218543A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116453196A (en) * | 2023-04-22 | 2023-07-18 | 北京易知环宇文化传媒有限公司 | Face recognition method and system |
| CN116453196B (en) * | 2023-04-22 | 2023-11-17 | 深圳市中惠伟业科技有限公司 | Face recognition method and system |
| CN116664140A (en) * | 2023-08-02 | 2023-08-29 | 华北电力大学 | Carbon emission right trading method based on blockchain |
| CN116664140B (en) * | 2023-08-02 | 2023-09-29 | 华北电力大学 | Carbon emission right trading method based on blockchain |
| CN117495384A (en) * | 2023-11-07 | 2024-02-02 | 广州准捷电子科技有限公司 | KTV face brushing payment method based on AI face recognition technology |
| CN117495384B (en) * | 2023-11-07 | 2024-04-26 | 广州准捷电子科技有限公司 | KTV face brushing payment method based on AI face recognition technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yuan et al. | Fingerprint liveness detection using an improved CNN with image scale equalization | |
| CN108985134B (en) | Face living body detection and face brushing transaction method and system based on binocular camera | |
| CN104361276B (en) | A kind of multi-modal biological characteristic identity identifying method and system | |
| CN114218543A (en) | Encryption and unlocking system and method based on multi-scene expression recognition | |
| CN109359548A (en) | Plurality of human faces identifies monitoring method and device, electronic equipment and storage medium | |
| CN111462379A (en) | Access control management method, system and medium containing palm vein and face recognition | |
| CN113591747B (en) | Multi-scene iris recognition method based on deep learning | |
| CN110599187A (en) | Payment method and device based on face recognition, computer equipment and storage medium | |
| CN205644823U (en) | Social security self -service terminal device | |
| Yin et al. | Fusion of face recognition and facial expression detection for authentication: a proposed model | |
| Kadhim et al. | A multimodal biometric database and case study for face recognition based deep learning | |
| Chen et al. | An Identity Authentication Method Based on Multi-modal Feature Fusion | |
| CN111428670B (en) | Face detection method, face detection device, storage medium and equipment | |
| Heusch et al. | A comprehensive experimental and reproducible study on selfie biometrics in multistream and heterogeneous settings | |
| Zhou et al. | Finger-knuckle assisted slap fingerprint identification for higher security and convenience | |
| CN113190819A (en) | Authentication method and device based on living body fusion characteristics and computer equipment | |
| Nethravathi et al. | Advanced Face Recognition Based Door Unlock System Using Arduino & MATLAB | |
| Peña et al. | Processing of Images Based on Machine Learning to Avoid Unauthorized Entry | |
| CN109859409A (en) | A kind of biometric discrimination method in cash equipment | |
| Adebayo et al. | Combating Terrorism with Biometric Authentication Using Face Recognition | |
| Melin et al. | Human Recognition using Face, Fingerprint and Voice | |
| Koodalsamy et al. | Face Recognition using Deep Learning | |
| Zhang et al. | Single Biometric Recognition Research: A Summary | |
| Bakshe et al. | Hand geometry techniques: a review | |
| Rao et al. | Innovative Solutions: LBPH Technology Driving the Future of Intelligent Security Systems |
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 |