Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

310 results about "Fingerprint detection" patented technology

A dynamic low-overhead traffic obfuscation method based on packet length distribution

The present invention discloses a dynamic low-overhead traffic obfuscation method based on data packet length distribution, and belongs to the technical field of defense against encrypted traffic fingerprint detection. The problem of insufficient dynamics and high resource overhead of the traditional traffic obfuscation method in the prior art is solved; the present invention combines the distribution-based data packet length mapping method and the segmentation and stacking-based data packet modification method, and finally proposes a dynamic low-overhead traffic obfuscation method based on data packet length distribution. For each data packet in a data packet sequence, the target data packet length is first obtained by the distribution-based data packet length mapping method, and then the data packet is modified to the target length by the segmentation and stacking-based data packet modification method, and finally the obfuscated data packet sequence is obtained. The present invention effectively avoids the operation of introducing padding data in the data packet modification process, reduces the additional bandwidth overhead, and can be applied to obfuscate traffic in an actual network environment.
Owner:HARBIN INST OF TECH

Industrial Internet of Things data acquisition and elastic transmission method

The invention relates to the field of industrial Internet of Things data processing, in particular to an industrial Internet of Things data acquisition and elastic transmission method. The method comprises the following steps: acquiring a process unit topology and monitoring target configuration, performing process unit code registration, probe layout scheme generation and acquisition session configuration structure registration processing, and generating an acquisition session configuration structure; time anchor point unified processing, change node alignment sequence generation and contact value grading threshold registration processing are executed, and a data importance grading table structure is generated; executing fingerprint detection session list generation, network state fingerprint matrix construction and network state category judgment processing, and generating a network state category structure; and carrying out elastic transmission strategy graph construction and strategy version record registration processing to generate an elastic transmission execution configuration structure. According to the invention, through multi-level data processing and intelligent state perception, accurate alignment of data acquisition and elastic self-adaption of transmission are realized, and the reliability and efficiency of an industrial Internet of Things system are effectively improved.
Owner:SHENZHEN CHILINK IOT TECH CO LTD

Fingerprint detection method and device, program product and storage medium

The embodiment of the invention provides a fingerprint detection method and device, a program product and a storage medium, and the method comprises the steps: obtaining the native domain information of a to-be-detected fingerprint, the native domain information being original data collected when the to-be-detected fingerprint is subjected to fingerprint verification; performing fingerprint feature extraction on the native domain information to obtain a fingerprint feature matrix of the to-be-detected fingerprint; performing classification operation on the fingerprint feature matrix through a trained medium classification network to obtain a fingerprint medium classification vector of the to-be-detected fingerprint, the fingerprint medium classification vector being used for representing the probability that the to-be-detected fingerprint belongs to a plurality of medium types in a vector form; and determining the medium type of the to-be-detected fingerprint based on the fingerprint medium classification vector. Through the method and the device, the problem that the type of the fingerprint medium cannot be effectively detected in related technologies is solved.
Owner:SHENZHEN GOODIX TECH CO LTD

Living fingerprint detection method based on multispectral and micro pulse feature fusion

The invention relates to the technical field of living body fingerprint detection, and particularly discloses a living body fingerprint detection method based on multispectral and micro pulse feature fusion, which comprises the steps of signal synchronous generation, time domain alignment processing, feature matrix generation, weight dynamic adjustment, cross validation analysis, abnormal region sampling, living body model verification and living body authentication output. According to the method, the verification result is generated by synchronously collecting the multi-spectral reflection intensity and the skin displacement fluctuation sequence of the fingerprint area, dynamically adjusting the spectral absorption and pulsation track feature weight, performing cross validation to output the local abnormal area and obtain the supplementary feature data, and performing physiological coupling rule matching by using the preset living body judgment model. When three consecutive results do not conform to a living body rule, activating an anti-counterfeiting attack alarm protocol; according to the method, multispectral and micro pulse features are fused, and an environment adaptive weight mechanism is combined, so that the accuracy of living body detection is effectively improved, and the environment adaptability of a detection algorithm is enhanced.
Owner:SHENZHEN NEWABEL ELECTRONICS

Traditional Chinese medicine fingerprint detection method for traditional Chinese medicine preparation

The invention relates to the technical field of chemical component analysis, in particular to a traditional Chinese medicine fingerprint spectrum detection method of a traditional Chinese medicine preparation. The method comprises the following steps: acquiring high-dimensional spectrogram data of the bovine musk deer resuscitation powder, and performing qualitative characteristic analysis on chemical components of the bovine musk desuscitation powder to obtain a chemical component characteristic matrix of the bovine musk desuscitation powder; acquiring multi-modal production data of the bovine musk deer resuscitation powder, and performing high-dimensional feature fusion on the chemical component feature matrix of the bovine musk desuscitation powder and the multi-modal production data of the bovine musk desuscitation powder to obtain a sample feature embedding vector; constructing a chemical component dynamic network according to the sample feature embedding vector, so as to obtain a cattle musk deer resuscitation powder component collaborative network; generating a global fingerprint spectrogram based on the cattle musk deer resuscitation-inducing powder component collaborative network, and performing potential abnormal point spectrum peak correction to obtain an optimized fingerprint spectrogram; and constructing a feature model according to the optimized fingerprint spectrogram to obtain a quality evaluation model of the bovine musk deer resuscitation powder. The accuracy of quality control of the traditional Chinese medicine preparation can be improved.
Owner:XIAN TRADITIONAL CHINESE MEDICINE ENCEPHALOPATHY HOSPITAL CO LTD

Ultrasonic fingerprint detection method, device, electronic device and storage medium

The embodiments of the present application provide an ultrasonic fingerprint detection method, device, electronic device and storage medium. The ultrasonic fingerprint detection method includes: obtaining the current temperature and / or the current film-sticking state of the conductive medium, wherein the first side of the conductive medium is in contact with the ultrasonic sensor, and the second side of the conductive medium provides a pressing surface; determining the number of ultrasonic transmissions n according to the current temperature and / or the current film-sticking state; wherein n is a positive integer; controlling the ultrasonic sensor to transmit n ultrasonic signals to the conductive medium, and receiving an echo signal formed after each ultrasonic signal is reflected; and performing fingerprint detection according to the echo signal. The embodiments of the present application can significantly reduce the impact of noise on fingerprint detection, and can ensure the stability of the accuracy of fingerprint detection, thereby improving the performance of fingerprint detection.
Owner:SHENZHEN GOODIX TECH CO LTD

Terahertz trace molecule fingerprint spectrum detection method

The invention relates to the technical field of trace molecule detection, and provides a terahertz trace molecule fingerprint spectrum detection method which comprises the following steps: collecting a time domain signal of a sample under the condition that the sample formed by compounding a sample layer and a substrate layer is placed in a terahertz wave radiation area for radiation; the sample layer is obtained by coating an analyte on a substrate layer formed on the basis of a selected substrate material; converting the time domain signal of the sample into a sample frequency domain signal based on fast Fourier transform; acquiring a transmission spectrum according to the sample frequency domain signal and a reference frequency domain signal acquired by the test air, and extracting an absorption fingerprint signal of the analyte from the transmission spectrum; and establishing a standard equation between the content of the analyte and the intensity of the fingerprint signal based on the absorption fingerprint signals of the analyte with different contents. The detection mode is low in required cost, short in detection time and simple to operate, can realize ultra-wide spectrum detection of analytes, and is beneficial to promotion of wide application and development of trace molecule fingerprint detection.
Owner:MINZU UNIVERSITY OF CHINA

Fingerprint detection method for analgesic cream for knocks and falls

PCT designated stageWO2026016634A1Component separationReference sampleSimulation
Provided in the present invention is a method for detecting the fingerprint of an analgesic cream for knocks and falls, relating to the technical field of drug detection. The detection method comprises the following steps: preparing a test sample solution; preparing a reference sample solution; and injecting the test sample solution and the reference sample solution into a high performance liquid chromatograph, and recording the chromatogram. The method has the advantages of simplicity, stability, high precision, and good reproducibility. The method can conduct multicomponent fingerprint research on the analgesic cream for knocks and falls, and perform attribute research and similarity evaluation on main chromatographic peaks. The method comprehensively reflects the uniformity and stability of the analgesic cream for knocks and falls, and can evaluate, more comprehensively and scientifically, the quality of the analgesic cream for knocks and falls, thereby ensuring the quality and efficacy of the product.
Owner:GUANGZHOU BAIYUNSHAN PHARM CO LTD

System and method for tracing cloud computing environment deployments to code objects utilizing unique fingerprints

A system and method for improving inspection of software containers is presented. The method includes detecting a plurality of configuration files, each corresponding to a software container image corresponding to a software container deployed in the cloud computing environment; parsing a first configuration file to detect a first plurality of commands; generating a first fingerprint based on the detected first plurality of commands; parsing a second configuration file to detect a second plurality of commands; generating a second fingerprint based on the detected second plurality of commands; determining that the first configuration file matches the second configuration file in response to detecting a match based on the fingerprints; determining that the first configuration file mismatches the second configuration file in response to detecting a mismatch; and inspecting the first configuration file for a cybersecurity object in response to determining that the first configuration file matches the second configuration file.
Owner:WIZ INC

Quantitative fingerprint spectrum detection method for free fatty acid in wool crude fat and application of quantitative fingerprint spectrum detection method

The invention discloses a quantitative fingerprint spectrum detection method for free fatty acid in wool crude fat and application thereof, and belongs to the technical field of analysis and detection.The quantitative fingerprint spectrum detection method comprises the following steps that 1, a wool crude fat test sample is taken, the wool crude fat test sample is melted and then dissolved with a solvent, and a test sample solution is prepared; preparing a reference substance solution by using a reference substance; (2) performing HPLC (High Performance Liquid Chromatography) detection on the test solution and the reference solution, and recording chromatograms; analyzing the chromatogram of the reference substance solution, and drawing to obtain a standard curve; and (3) determining a common peak by utilizing a plurality of chromatograms corresponding to different batches of wool crude fat obtained in the steps (1) and (2), and quantifying by utilizing a standard curve to realize quantitative fingerprint detection of the free fatty acid in the wool crude fat. According to the method, the pretreatment method is simple, operation such as derivatization is not needed, the detection time is short, and quality detection, control and evaluation can be more objectively carried out on the wool crude fat.
Owner:ZHEJIANG UNIV +1

Optical fingerprint identification module and device and electronic equipment

The embodiment of the utility model provides an optical fingerprint recognition module and device and electronic equipment, the optical fingerprint recognition module comprises a camera, a shading part is arranged around the camera, and the camera and the shading part are arranged between the lower surface of a cover plate and a printed circuit board. The shading piece is used for shading light emitted by a light source to the side wall or the top of the camera and enabling the light emitted by the light source to enter the interior of a human finger on the upper surface of the cover plate and enter a view field area of the camera in a diffusion and transmission mode so as to form a fingerprint detection signal; the camera is used for receiving the fingerprint detection signal and detecting fingerprint information of the human finger according to the received fingerprint detection signal. According to the embodiment of the invention, the size of the optical fingerprint identification module is reduced, the human finger identification rate is improved, and true and false fingers can be distinguished.
Owner:SHENZHEN GOODIX TECH CO LTD

Fingerprint detection method for Yankanning tablets

The invention is applicable to the technical field of detection of Yankingning tablets, and particularly relates to a fingerprint detection method for Yankingning tablets, which comprises the following steps: preparing a Yankingning tablet test solution; preparing a reference solution; after the chromatographic conditions are matched with the system applicability, respectively injecting 5 microliters of the test solution and 5 microliters of the reference solution into a liquid chromatograph for determination to obtain a fingerprint spectrum and a reference fingerprint spectrum of the Yankingning tablets; and analyzing according to the fingerprint spectrum of the Yankingning tablet and the control fingerprint spectrum to obtain similarity information. According to the method, through a standardized detection process, various components in the Yankingning tablet are detected at the same time, the basis of pharmacodynamic substances of the Yankingning tablet is comprehensively reflected, and the quality of the Yankingning tablet can be comprehensively evaluated; by comprehensively analyzing the similarity between the fingerprint spectrum of the Yankingning tablets and the control fingerprint spectrum, the quality and consistency of the Yankingning tablets can be comprehensively evaluated, and the stability and reliability of quality evaluation of the Yankingning tablets are improved.
Owner:SI CHUAN SHENG SAN XING DUI ZHI YAO YOU XIAN GONG SI

Intelligent terminal multi-mode equipment fingerprint detection method and system

The invention relates to an intelligent terminal multi-mode equipment fingerprint detection method and system, and belongs to the technical field of digital information transmission, and the method comprises the steps: a multi-dimensional feature collection module is used for collecting hardware bottom-layer features, software configuration features, behavior dynamic features and environment and time features; the adaptive feature fusion module is connected with the multi-dimensional feature acquisition module and is used for performing preprocessing, dynamic weight distribution and Hash fusion on the multi-dimensional features to generate an equipment fingerprint Hash value; the dynamic anti-bypassing verification module is connected with the multi-dimensional feature acquisition module and the adaptive feature fusion module, and is used for feature verification, Hook behavior recognition, core feature encryption storage and strategy updating; the method has the beneficial effects that the extreme uniqueness of fingerprints is realized by fusing 12-dimensional features and combining adaptive weight allocation and SHA-256 Hash fusion, different terminals can be accurately distinguished, and identity confusion caused by fingerprint repetition is avoided.
Owner:四川易景智能终端有限公司

Broadband terahertz fingerprint detection sensor based on gradient metasurface

The invention provides a broadband terahertz fingerprint detection sensor based on a gradient metasurface, and relates to specific molecular recognition and detection. The gradient metasurface array is integrated on the upper surface of the substrate; the gradient metasurface array comprises a plurality of micro antenna unit structures, and each micro antenna unit structure specifically comprises an equal-length metal microrod array and a gradient metal microrod array; the isometric metal micro-rod array comprises a plurality of isometric metal micro-rods which are arranged in parallel; the gradient metal micro-rod array comprises a plurality of gold micro-rods which are arranged in parallel and are gradually changed in length; and the plurality of metal micro-rods with gradually reduced lengths are inserted into the gaps formed by the plurality of metal micro-rods with equal lengths. The gradient metasurface provided by the invention shows extraordinary resonance density in a limited and small printing area, the metasurface which is operated on a wide spectrum at the same time is realized along with the increase of the complexity of a sample, abundant spectrum information can be obtained on the wide spectrum, and tiny differences in fingerprints can be analyzed and absorbed through narrow-band resonance.
Owner:NAT INNOVATION INST OF DEFENSE TECH PLA ACAD OF MILITARY SCI

Display device, display method and display panel

The invention provides a display device, a display method and a display panel. The display device comprises the display panel and a processor. The display panel comprises a plurality of pixel units and a temperature sensor module; the temperature sensor module is arranged corresponding to a fingerprint detection area arranged on the display panel and is used for monitoring a first environment temperature of the fingerprint detection area; each pixel unit comprises a plurality of sub-pixels; and the processor is used for querying a preset brightness compensation table based on the first environment temperature to obtain a target brightness compensation coefficient corresponding to the sub-pixel in the compensation temperature interval corresponding to the first environment temperature so as to perform gamma compensation on each sub-pixel in the fingerprint detection area. The environment temperature of the fingerprint detection area is monitored in real time, and the brightness compensation coefficient is dynamically adjusted to perform gamma compensation on each sub-pixel in the fingerprint detection area, so that the problem of inconsistent brightness and chrominance of light spots caused by temperature change is solved, and the fingerprint identification accuracy and the user experience are improved.
Owner:WUHAN CHINA STAR OPTOELECTRONICS SEMICONDUCTOR DISPLAY TECHNOLOGY CO LTD

Fingerprint detection liquid and fingerprint detection method

To provide a fingerprint detection liquid that can be readily produced without using a large amount of solvents other than fluorinated ones, and that remains usable even after storage for a predetermined duration.SOLUTION: A fingerprint detection liquid comprises: at least one compound selected from the group consisting of ninhydrin, a ninhydrin derivative, 1,8-diazafluoren-9-one, 1,2-indanedione, and hydrindantin; and a solvent containing a hydrochlorofluoroolefin having a boiling point of 40 to 90°C.SELECTED DRAWING: None
Owner:AGC INC

Solution soaking type fingerprint detection method based on AIEgens

The invention discloses a solution immersion type fingerprint detection method based on AIEgens, which comprises the step of carrying out immersion type fluorescent fingerprint detection based on the aggregation-induced emission effect of an organic fluorescent compound TPP-APBP-P. TPP is used as a luminous substrate, a long chain is connected to the luminous substrate to improve the lipophilicity of the luminous substrate, TPP-APBP-P is obtained, meanwhile, the PH of a solution is adjusted to improve the hydrophilicity of the luminous substrate, and finally the detection effect of the luminous substrate on potential fingerprints is improved; the fingerprint detector has very excellent detection effects on fingerprints in a high-temperature environment and aged fingerprints, and has high contrast, high sensitivity and high precision on fingerprint development.
Owner:ANHUI UNIV OF SCI & TECH

Application of metavanadate

The invention discloses application of metavanadate, and belongs to the technical field of fingerprint detection. And the metavanadate is cesium metavanadate or rubidium metavanadate and is used for displaying fingerprints. The metavanadate is excited by near ultraviolet light. The invention relates to a fingerprint development method, which adopts cesium metavanadate or rubidium metavanadate, and realizes fingerprint development through a powder scattering and brushing method, a direct brushing method, a powder scattering and shaking method or a powder scattering and blowing method. The preparation method comprises the following steps: dispersing carbonate and vanadium pentoxide in methanol to obtain a suspension; grinding and drying the suspension to obtain a mixture; and calcining the mixture to obtain the metavanadate fluorescent material. The carbonate comprises at least one of cesium carbonate and rubidium carbonate, and the metavanadate comprises at least one of cesium metavanadate and rubidium metavanadate.
Owner:JIANGSU POLICE INST

A detection method for UPLC quantitative fingerprint of zhangtou red pericarpium citri reticulatae

The application provides a kind of zhangtou red pericarpium citri reticulatae UPLC quantitative fingerprint detection method, belongs to the quality detection technical field of traditional Chinese medicine.The detection method is prepared by reference solution, preparation of test solution, using ultra high performance liquid chromatography analysis, multiple batches of liquid chromatogram is introduced into "traditional Chinese medicine chromatographic fingerprint similarity evaluation system", 21 common peaks are identified, similarity matching is carried out with 21 common peaks, and the control spectrum of zhangtou red pericarpium citri reticulatae is generated.On this basis, combined with hesperidin, sweet orange flavone, chuan chenpisi, tangeretin, 5-dimethyl chuan chenpisi 5 flavonoid content determination, zhangtou red pericarpium citri reticulatae quantitative fingerprint is established.The application realizes that fingerprint detection and the content determination of 5 flavonoids of zhangtou red pericarpium citri reticulatae can be completed at the same time through one analysis, can quickly, comprehensively and accurately evaluate the quality of zhangtou red pericarpium citri reticulatae, has good reproducibility and stability, and can provide technical support for the uniformity and stability of zhangtou red pericarpium citri reticulatae quality.
Owner:赣江中药创新中心

Optical fingerprint identification chip and electronic device

The application discloses an optical fingerprint identification chip and an electronic device. The optical fingerprint identification chip comprises a light-transmitting cover plate, a substrate and encapsulating glue. The substrate is provided with a touch component, a light-emitting component and a fingerprint identification die close to the surface of the light-transmitting cover plate. The touch component is used for responding to the touch operation of a finger on the light-transmitting cover plate and generating a trigger signal. The light-emitting component is used for emitting light to the light-transmitting cover plate according to the trigger signal. The fingerprint identification die is used for receiving the light reflected by the finger on the light-transmitting cover plate according to the trigger signal to perform fingerprint detection. The encapsulating glue is arranged between the light-transmitting cover plate and the substrate and connects the light-transmitting cover plate and the substrate. The optical fingerprint identification chip provided by the application is integrally packaged, and when the electronic device is assembled or repaired, the damage of the fingerprint identification die caused by accidental collision can be avoided, and the assembly process difficulty of the electronic device is reduced.
Owner:BEIJING XIAOMI MOBILE SOFTWARE CO LTD

Ultrasonic image acquisition method, ultrasonic fingerprint chip, electronic device and ultrasonic fingerprint detection method

PendingCN122637449AMedicineAcoustics
Embodiments of the present application provide an ultrasonic image acquisition method, an ultrasonic fingerprint chip, an electronic device and an ultrasonic fingerprint detection method. The ultrasonic image acquisition method comprises: in response to meeting an automatic image acquisition condition, acquiring a current temperature of an environment in which the ultrasonic fingerprint chip is located; determining whether a preset image acquisition condition is met based on the current temperature, wherein the preset image acquisition condition is a condition for indicating that the number of background images obtained at the current temperature is not up to standard, and the background image is an ultrasonic image without fingerprints collected by the ultrasonic fingerprint chip; and if the preset image acquisition condition is met, causing the ultrasonic fingerprint chip to perform ultrasonic image acquisition to obtain at least one target background image at the current temperature.
Owner:SHENZHEN GOODIX TECH CO LTD

Ultrasonic fingerprint detection method and apparatus, and electronic device and storage medium

Provided in the embodiments of the present application are an ultrasonic fingerprint detection method and apparatus, and an electronic device and a storage medium. The ultrasonic fingerprint detection method comprises: acquiring the current temperature and / or the current film status of a conductive medium, wherein a first side surface of the conductive medium is attached to an ultrasonic sensor, and a second side surface of the conductive medium provides a pressing surface; on the basis of the current temperature and / or the current film status, determining the number n of transmissions of ultrasonic waves, wherein n is a positive integer; controlling the ultrasonic sensor to transmit ultrasonic signals to the conductive medium n times, and receiving an echo signal formed after each transmitted ultrasonic signal is reflected; and performing fingerprint detection on the basis of the echo signal. The embodiments of the present application can significantly reduce the impact of noise on fingerprint detection, and can ensure the stability of the accuracy of fingerprint detection, thereby improving the performance of fingerprint detection.
Owner:SHENZHEN GOODIX TECH CO LTD

A biometric detection structure and a manufacturing method thereof

The present application discloses a biometric detection structure and a manufacturing method thereof. The biometric detection structure includes a light-transmitting layer, a light source and a photosensitive element are arranged on one side of the light-transmitting layer, and a high-refractive-index layer is arranged on the other side of the light-transmitting layer. By utilizing the original light source of the display screen and the light-transmitting layer, the light source necessary for optical detection is combined with the light source of the display screen itself, and a high-refractive-index layer is arranged on the original glass layer. Under the premise of not affecting the screen display performance, fingerprint detection is innovatively realized, and the detection effect is enhanced by arranging a dielectric layer between the light-transmitting layer and the high-refractive-index layer, realizing the compatibility between the display screen of the electronic device and the fingerprint recognition detection system. The manufacturing method provided by the present application is simple and easy to implement, and can be realized by continuously coating on the basis of the original structure of the display screen of the electronic device.
Owner:BEIJING YONGCHANG HUANYU INVESTMENT CO LTD

Foldable display apparatus and calibration method for fingerprint detection of foldable display apparatus

A foldable display apparatus and a calibration method for fingerprint detection of the foldable display apparatus. The foldable display apparatus includes a display panel and a fingerprint identification sensor. The display panel includes imaging holes. The fingerprint identification sensor includes sensing elements. The method includes: after the foldable display apparatus is switched from an unfolded state to a folded state, determining a target sensing element group corresponding to an imaging hole when the foldable display apparatus is in the folded state, the target sensing element group includes a target number of sensing element in the sensing elements, a center of the target sensing element group is located at a target position, and the target number is an integer greater than or equal to 1; and in the folded state, imaging a fingerprint pattern based on a signal fed back by the target sensing element group corresponding to the imaging hole.
Owner:WUHAN TIANMA MICROELECTRONICS CO LTD SHANGHAI BRANCH +1

In-screen fingerprint detection device and electronic equipment

The invention discloses an in-screen fingerprint identification device, comprising: a display screen comprising an upper surface for touch, a plurality of display pixels and a plurality of fingerprint identification pixels, a detection area for fingerprint identification being formed on the upper surface, the plurality of display pixels and the plurality of fingerprint identification pixels being arranged in the display screen at intervals, the fingerprint identification pixels are used for sensing detection light returned from a detection area range to obtain fingerprint information; the controller is used for controlling the display pixels to emit display light when the display screen displays a picture, and emitting detection light to the detection area when fingerprint identification is carried out; the processor is used for carrying out fingerprint identification according to comparison between fingerprint information obtained by the fingerprint identification pixels and a fingerprint template; wherein the distance between the fingerprint identification pixel and the adjacent display pixel is set according to the thickness of the display screen and the effective refractive index of the display screen.
Owner:SHENZHEN FUSHI TECH CO LTD

Systems and methods for detecting call provenance from call audio

Various embodiments of the invention are detection systems and methods for detecting call provenance based on call audio. An exemplary embodiment of the detection system can comprise a characterization unit, a labeling unit, and an identification unit. The characterization unit can extract various characteristics of networks through which a call traversed, based on call audio. The labeling unit can be trained on prior call data and can identify one or more codecs used to encode the call, based on the call audio. The identification unit can utilize the characteristics of traversed networks and the identified codecs, and based on this information, the identification unit can provide a provenance fingerprint for the call. Based on the call provenance fingerprint, the detection system can identify, verify, or provide forensic information about a call audio source.
Owner:GEORGIA TECH RES CORP

Live fingerprint identification system and fingerprint detection module

This invention provides a live fingerprint recognition system and a fingerprint detection module. The fingerprint detection module includes a spectral chip, a circuit board, an optical component, and a bracket. The spectral chip is disposed on and electrically connected to the circuit board. The bracket is disposed on the circuit board, and the optical component is fixed by the bracket and supported by the bracket in the photosensitive path of the spectral chip. The reflected light from the fingerprint to be tested is received by the spectral chip through the optical component, and the spectral chip detects the fingerprint information based on the spectral information of the reflected light.
Owner:BEIJING SEETRUM TECH CO LTD +1

An adaptive fingerprint-based meta-learning neural network fingerprint detection method

The application belongs to the technical field of artificial intelligence, and particularly relates to a meta-learning neural network fingerprint detection method based on self-adaptive fingerprints; the method is suitable for intellectual property protection of a plurality of downstream task models; a plurality of self-adaptive fingerprint samples are constructed for a target model, and then it is detected whether the outputs of the self-adaptive fingerprint samples in a suspect model can pass the detection of a meta verification model; the fingerprint detection mechanism of the application is based on the confidence vector output of the suspect model on the self-adaptive fingerprint samples, rather than the output label of the adversarial sample, and thus is not related to a specific task type and does not depend on training data, and can be widely applied to neural network fingerprint detection of various task types, such as classification, regression, and generation model, to protect the intellectual property of the neural network, and has good robustness and uniqueness for various positive and negative example suspect models.
Owner:FUDAN UNIVERSITY

Fingerprint detection method and device

The invention provides a fingerprint detection method and device. The fingerprint detection method comprises the following steps: acquiring a fingerprint image through a fingerprint sensor; determining a first score of the fingerprint image based on a first fingerprint detection mode; determining a second score of the fingerprint image based on a second fingerprint detection mode and the first score in response to the first score exceeding a first threshold value; and determining a fingerprint detection result based on the first score and the second score, thereby improving generalization and accuracy of fingerprint detection without adding extra hardware.
Owner:SAMSUNG (CHINA) SEMICONDUCTOR CO LTD +1