CN113536282A - Safety protection system based on otoacoustic sensing - Google Patents
Safety protection system based on otoacoustic sensing Download PDFInfo
- Publication number
- CN113536282A CN113536282A CN202110672881.1A CN202110672881A CN113536282A CN 113536282 A CN113536282 A CN 113536282A CN 202110672881 A CN202110672881 A CN 202110672881A CN 113536282 A CN113536282 A CN 113536282A
- Authority
- CN
- China
- Prior art keywords
- user
- signals
- safety
- module
- analysis 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
- 238000012706 support-vector machine Methods 0.000 claims abstract description 15
- 239000000284 extract Substances 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 3
- 230000007123 defense Effects 0.000 abstract description 2
- 210000000613 ear canal Anatomy 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G06F21/44—Program or device authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/30—Security of mobile devices; Security of mobile applications
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Telephone Function (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a safety protection system based on otoacoustic sensing, which comprises an acquisition module, an analysis module and an authentication module, wherein the acquisition module acquires echo signals returned by the signals of a user auditory canal by playing specific signals, the analysis module extracts the constructed characteristics by processing data, and the authentication module identifies the identity of the user by SVM support vector machine algorithm modeling. The invention can ensure the safety and normal operation of the mobile terminal, reduces the safety cost, reduces the keeping cost of the user for the secret key and the risk of losing the secret key, and operates simultaneously with the original protection system as a safety protection measure, and enhances the safety because the biological characteristics are difficult to attack; the user does not need to memorize any secret key, and the effect of invisible protection can be achieved, so that the mobile terminal becomes a safe second defense line of the user mobile terminal and has wide applicability.
Description
Technical Field
The invention relates to the field of equipment safety, in particular to a safety protection system based on otoacoustic sensing.
Background
The mobile terminal is a computer device for portable use, including a mobile phone and other portable devices. With the technical development, the mobile terminal is changed from a simple conversation tool to a comprehensive information processing platform. The security guarantee of the mobile terminal is increasingly important, and the basic authentication modes generally adopted at present, such as passwords, screen locking patterns and the like, cannot effectively prevent intruders and are easily attacked. Face recognition is easily deceived by pictures/videos, and special hardware and equipment space are needed for iris recognition, fingerprint recognition and the like. Ear acoustic sensing refers to the characteristic of an echo signal passing through the ear canal of a user that is not the same as others due to biological differences.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a high-safety and high-applicability otoacoustic sensing-based safety protection system.
The technical scheme is as follows: the system comprises an acquisition module, an analysis module and an authentication module, wherein the acquisition module acquires echo signals returned by the signals of the auditory canals of the users by playing specific signals, the analysis module extracts the constructed characteristics by processing data, and the authentication module identifies the identities of the users by SVM support vector machine algorithm modeling.
The specific signal is a chirp signal, and is a signal with continuous linear variation of frequency in a duration period.
The analysis module comprises a denoising unit for filtering noise signals and a feature calculation unit for extracting feature vectors.
The denoising unit filters noise signals through a high-pass filter, and only retains high-frequency band signal data where a specific signal segment is located.
The feature calculation unit extracts feature vectors through a triangular filter bank, and the triangular filter is widely applied to processing of acoustic signals.
And the authentication module classifies the extracted characteristic value vectors by using SVM support vector machine algorithm modeling, and judges whether the user identity is an authenticated user.
Has the advantages that: compared with the prior art, the invention has the following advantages:
1. the invention can ensure the safety and normal operation of the mobile terminal, reduces the safety cost, reduces the keeping cost of the user for the secret key and the risk of losing the secret key, and operates simultaneously with the original protection system as a safety protection measure, and enhances the safety because the biological characteristics are difficult to attack;
2. the user does not need to memorize any secret key, and the effect of invisible protection can be achieved, so that the mobile terminal security protection method becomes a second defense line of the user mobile terminal and has wide applicability.
Drawings
FIG. 1 is a functional block diagram of the present system.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
As shown in fig. 1, a safety protection system based on otoacoustic sensing includes an acquisition module, an analysis module, and an authentication module. The acquisition module acquires echo signals returned by the signals in the auditory canal of the user by playing specific signals, wherein the specific signals are chirp signals and signals with continuous and linear frequency changes in duration. The analysis module extracts features of the construct by processing the data; the analysis module comprises a denoising unit for filtering a noise signal and a feature calculation unit for extracting a feature vector. The denoising unit filters noise signals through a high-pass filter and only reserves high-frequency band signal data where a specific signal segment is located; the feature calculation unit extracts feature vectors through a triangular filter bank, and the triangular filter is widely applied to processing of acoustic signals. The authentication module classifies the extracted characteristic value vectors by modeling through an SVM (support vector machine) algorithm, and judges whether the user identity is an authenticated user.
The use of the otoacoustic sensing-based authentication system comprises the steps of:
(1) and opening the mobile phone authentication program, playing a preset specific signal at the ear canal by using a mobile phone loudspeaker through the acquisition module, and simultaneously collecting a returned sound signal by using a microphone on the same side. The preset specific signals are consistent, and the physiological characteristics of different users determine that echo signals returned by the auditory canals and nearby structures are different, which is reflected in different frequency responses to different frequencies of the signals. The specific signal is a chirp signal, and in the embodiment, a chirp signal of 1.8k-2.2kHz is adopted, so that the human ear is insensitive to the high-frequency signal, and a verification process can be performed relatively insensibly. The mobile phone is limited to the performance of playing high-frequency signals, the high frequency of the frequency band can be higher, the authentication performance can be better, and a low specific signal frequency band can be adopted when a user is not sensitive to sound.
(2) The analysis module performs high-pass filtering on the acquired data. Because the environmental noise is generally in a low frequency band, only signals in the high frequency band are reserved after high-pass filtering, and particularly, the lowest frequency of the signals is required to be lower than the lowest frequency of the specific signals set in the step (2), so that most of noise can be filtered. The high pass filter used in this embodiment is a butterworth filter.
(3) The characteristic calculation of the analysis module uses a filter bank to extract characteristics, uses a filter bank formed by triangular filters, performs FFT Fourier transform on collected signals to a frequency domain to obtain energy distribution on a frequency spectrum, and passes the energy spectrum through the triangular filter bank to obtain energy values of data in a frequency band corresponding to the filter, so that characteristic vectors are formed, and the length of the characteristic vectors is the same as the number of the filter banks. The triangular filter in this embodiment adopts a filter bank composed of 24 triangular filters, and the number and bandwidth of the filter bank can be adjusted according to the operation performance and the system effect. The central frequency of the filter group is equidistantly distributed at 1.6k-2.2kHz, the frequency bandwidths of the filters are evenly distributed and are equal in length, the response at the central frequency is 1, and the response linearly decreases towards 0 until the central frequency of two adjacent filters is reached. The frequency response of the triangular filter may be defined as:
wherein m is the number of the filter, k is the frequency, and f (m) is the center frequency of the m filters.
(4) And (3) establishing a database for storing user ear acoustic data, wherein the data is the characteristic vector obtained in the step (3), and modeling is performed by using an SVM (support vector machine) algorithm according to the data of a legal user as a positive sample and the data of an illegal user as a negative sample. The authentication module establishes a recognition model, uses SVM support vector machine algorithm training to obtain parameters of a kernel function, and obtains the recognition model.
(5) When the user carries out the current authentication, the identity recognition is carried out, and if the user is correct, the equipment can be unlocked and operated normally. The user's legal data can be continuously accumulated during multiple authentications of the user, and the model can be retrained when the authentication system performance becomes poor.
Claims (6)
1. The utility model provides a safety protection system based on otoacoustic sensing which characterized in that: the system comprises a collection module, an analysis module and an authentication module, wherein the collection module collects echo signals returned by the signals of the auditory canals of the users by playing specific signals, the analysis module extracts constructed features by processing data, and the authentication module identifies the identities of the users by modeling through an SVM (support vector machine) algorithm.
2. The safety shield system of claim 1, wherein: the specific signal is a chirp signal.
3. The safety shield system of claim 1, wherein: the analysis module comprises a denoising unit for filtering noise signals and a feature calculation unit for extracting feature vectors.
4. The safety shield system of claim 3, wherein: the denoising unit filters noise signals through a high-pass filter, and only retains high-frequency band signal data where a specific signal segment is located.
5. The safety shield system of claim 3, wherein: the feature calculation unit extracts feature vectors through a triangular filter bank.
6. The safety shield system of claim 1, wherein: and the authentication module classifies the extracted characteristic value vectors by using SVM support vector machine algorithm modeling, and judges whether the user identity is an authenticated user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110672881.1A CN113536282A (en) | 2021-06-17 | 2021-06-17 | Safety protection system based on otoacoustic sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110672881.1A CN113536282A (en) | 2021-06-17 | 2021-06-17 | Safety protection system based on otoacoustic sensing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113536282A true CN113536282A (en) | 2021-10-22 |
Family
ID=78125090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110672881.1A Pending CN113536282A (en) | 2021-06-17 | 2021-06-17 | Safety protection system based on otoacoustic sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113536282A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180307818A1 (en) * | 2015-10-21 | 2018-10-25 | Nec Corporation | Personal authentication device, personal authentication method, and personal authentication program |
| CN108959866A (en) * | 2018-04-24 | 2018-12-07 | 西北大学 | A kind of lasting identity identifying method based on high frequency sound wave frequency |
-
2021
- 2021-06-17 CN CN202110672881.1A patent/CN113536282A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180307818A1 (en) * | 2015-10-21 | 2018-10-25 | Nec Corporation | Personal authentication device, personal authentication method, and personal authentication program |
| CN108959866A (en) * | 2018-04-24 | 2018-12-07 | 西北大学 | A kind of lasting identity identifying method based on high frequency sound wave frequency |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2835460C (en) | System and method for enabling continuous or instantaneous identity recognition based on physiological biometric signals | |
| CN104573458A (en) | Identity recognition method, device and system based on electrocardiogram signals | |
| CN111666549A (en) | Intelligent earphone and user identification method thereof | |
| Hestbek et al. | Biometric gait recognition for mobile devices using wavelet transform and support vector machines | |
| CN108415564B (en) | Electronic device, equipment control method and related product | |
| Almehmadi et al. | The state of the art in electroencephalogram and access control | |
| CN111339511A (en) | Identity validity verification method and device and terminal equipment | |
| Liu et al. | Human acoustic fingerprints: A novel biometric modality for mobile security | |
| CN113536282A (en) | Safety protection system based on otoacoustic sensing | |
| CN112949403B (en) | Reliable user authentication method and system based on biological characteristics of mandible | |
| CN111325118A (en) | Method for identity authentication based on video and video equipment | |
| CN108304073B (en) | Electronic device, unlocking control method and related product | |
| Sadeghi et al. | A novel spoofing attack against electroencephalogram-based security systems | |
| Wahid et al. | A Gaussian mixture models approach to human heart signal verification using different feature extraction algorithms | |
| CN114727294A (en) | Identity recognition method and system for communication | |
| CN111444489B (en) | Double-factor authentication method based on photoplethysmography sensor | |
| CN114003885B (en) | Intelligent voice authentication method, system and storage medium | |
| Deng et al. | Transferability of Adversarial Attacks on Synthetic Speech Detection | |
| CN113627238B (en) | Biological identification method, device, equipment and medium based on vibration response characteristics of hand structure | |
| Wu et al. | EarAE: An Autoencoder based User Authentication using Earphones | |
| CN115481380A (en) | Continuous identity authentication method based on sliding vibration signal | |
| CN112836194B (en) | Identity authentication method and system based on internal biological characteristics of human hand | |
| CN117156439A (en) | Implicit answer authentication method and system based on external ear acoustic perception | |
| Elsayed et al. | Cancelable speaker identification based on inverse filter | |
| CN115767534A (en) | Secure gesture password authentication method, system and equipment based on friction sound |
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 |