30 results about "Biometric fusion" patented technology

This invention relates to a sorter integration and mode identification field characterizing in obtaining characters of man-face, iris, on-line signature and off-line handwriting of a user by various collecting devices then sending them to corresponding certification sub-modules to pick up the characters and match with the molding boards and outputting the matched marks to be normalized and sent to an identification combined module to get the final identification result by confidence integration or sent to a certification module to be imaged to a multi-dimension space to be sorted by a sorter to get a final result or to be certified and combined to get the final identification result.

A Bayesian belief network-based architecture for multimodal biometric fusion is disclosed. Bayesian networks are a theoretically sound, probabilistic framework for information fusion. The architecture incorporates prior knowledge of each modality's capabilities, quality estimates for each sample, and relationships or dependencies between these variables. A global quality estimate is introduced to support decision making.

A Bayesian belief network-based architecture for multimodal biometric fusion is disclosed. Bayesian networks are a theoretically sound, probabilistic framework for information fusion. The architecture incorporates prior knowledge of each modality's capabilities, quality estimates for each sample, and relationships or dependencies between these variables. A global quality estimate is introduced to support decision making.

The embodiment of the invention discloses a multi-biological-characteristic fusion identity authentication method, which adopts more than two types of biological characteristic identity information to carry out identity authentication and attestation so as to bring higher identification accuracy. The method of the embodiment of the invention comprises the following steps: collecting at least two types of biological characteristic identity information of a user to be identified; carrying out characteristic extraction on the at least two types of collected biological characteristic identity information to obtain corresponding characteristic information; according to the characteristic information, establishing characteristic matrixes, wherein the biological characteristic identity information, the characteristic information and the characteristic matrixes have one-to-one correspondence relationships; carrying out normalization processing on all characteristic matrixes; carrying out dynamic weighting fusion on all normalized characteristic matrixes to obtain a fusion characteristic matrix; according to the fusion characteristic matrix and a preset corresponding standard matrix , carrying out matching to obtain a corresponding matching score; and according to a Bayesian decision model and the matching score, obtaining an identity identification result of the user to be identified. The embodiment of the invention also provides a multi-biological-characteristic fusion identity authentication device.

The invention discloses an intelligent access control system based on multi-biometric feature fusion. The intelligent access control system comprises an image sensing collector, a sound sensing collector, a data processor and access control equipment; the image sensing collector is used for sensing a target, collecting face image information and sending the face image information to the data processor through a wireless communication module; the sound sensing collector is used for collecting sound information and sending the sound information to the data processor through the wireless communication module; the data processor is used for processing the received face image and sound information, fusing the feature information of the face image and the sound information, identifying, storingand training the feature information by virtue of a deep learning algorithm, and outputting a judgment result to the access control equipment; and the access control equipment is used for receiving the judgment result sent by the data processor and judging whether the access control responds or not. According to the invention, the defect of biological characteristic recognition in a single mode can be effectively overcome, and the safety of the access control system is improved.

The invention provides a face and voice multi-biometric fusion authentication method based on an Android platform, comprising that a user's face image is collected firstly, the user's face image is preprocessed, and the Adaboost algorithm is used to detect the face in the user's face image, and the face LBP feature is extracted to obtain the user's face feature; the user's face feature model is generated according to the user's face feature, and the user's face feature model of all users constitutes the image sample library. The invention is used for mobile phone authentication, especially theterminal security authentication of mobile finance type privacy application, which makes up for the shortcoming of single mode authentication, has higher reliability and security, and further ensuresthe information security of mobile phone users.

A biometric fusion electronic lock system contains a central processing module including an image processing unit, a voice processing unit, a digital signal processing unit, a logic processing unit, and an interface control unit. An image capturing module is electrically connected with the central processing module. A voice capturing module is electrically connected with the central processing module. A locking / unlocking module is configured to drive a locking latchbolt to lock or unlock the electronic lock system, and the locking / unlocking module is electrically connected with the central processing module. A storage module is set in a storage media of the electronic lock system so as to store facial features and voiceprint data captured by the image capturing module and the voice capturing module respectively. A liquid-crystal display (LCD) module is electrically connected with an interface control unit of the central processing module.

The embodiment of the invention provides a user identity authentication method and device, a user terminal and a server. The method comprises the steps of obtaining signature sensor data collected bya sensor of a user terminal in the current user signature process and handwriting screenshot data formed by a user in the signature process; based on the signature sensor data and the handwriting screenshot data, respectively identifying user identities; and if the verification results based on the signature sensor data and the handwriting screenshot data are legal, passing the identity authentication. According to the invention, the behavior characteristics of the handwriting process and the biological characteristics of the handwriting are fused for use, so that the identity authentication of the handwritten signature is carried out more accurately, and the identity authentication speed can be improved.

The invention relates to a multi-biological-feature fusion algorithm based on a particle swarm algorithm and a typical association analysis method. The algorithm is characterized in that an original data set image is reconstructed to be a 32*32 image; two-times convolution, feature selection, and full connection are carried out to use 120-dimensional one-dimensional feature vectors for the 32*32 image after pretreatment; the one-dimensional feature vector is analyzed by using a typical association analysis method to obtain a feature vector with the highest association degree, wherein the feature vector is used as a multi-biological-feature fusion feature vector; and the fusion feature vector is sent into an ELM classifier for classification. According to the invention, on the basis of theconvolutional neural network structure, different biological-feature image features are fused by introducing the particle swarm optimization algorithm and the typical correlation analysis method to obtain a complete biological feature set, thereby carrying out effective authentication. The multi-biological-feature fusion algorithm having high accuracy and stability can be applied to fields of image recognition and security inspection and the like.

The present invention provides a multimodal biometric feature fusion social insurance identity authentication system and method. The system comprises a system body, an automatic focusing camera, a prism, a color selective mirror, an ultraviolet source, an infrared source, a common source, a player, a display screen, a wireless communication module, an identity card reader and a processor. The automatic focusing camera is employed to collect the iris, the face and the fingerprints in the human being biometric features to extract biological features, fuse the extracted biological features into fusion feature information through the processor and bind the fusion feature information with the identity number. The multimodal biometric feature fusion social insurance identity authentication system and method greatly improve the identity authentication safety, improve the efficiency of the database retrieval, and are simple in structure, low in cost, saved in space, low in system complexity and easy to realize.

The invention discloses an encryption and decryption method based on multi-biometric feature fusion. The encryption method comprises the following steps that various biometric feature data is combinedwith a password through a Hash hash function to generate an encryption key; the encryption key in combination with the private data may encrypt the private data. In the application of an encryption and decryption method based on multi-biometric feature fusion,the encryption and decryption method based on multi-biometric feature fusion is applied to network transmission of streaming media electronic files such as photos and videos. On the basis of original information encryption, a security authentication technology with biological characteristics such as irises, fingerprints and finger veinsfused with passwords is added; the technical difficulty of information encryption and decryption is greatly improved, the secret key is more unique, due to the uniqueness of iris, fingerprint and finger vein, the scanning and reading speed is high, and imitation and recognition are not easy, the safety and rapidity of information encryption and decryption are enhanced, and the data transmission encryption and decryption of the camera are safer and more reliable.

An identity recognition system includes a target region acquisition module, a photoplethysmography signal conversion module, a biometric characteristic conversion module, a face characteristic acquisition module, and a comparison module. The target region acquisition module is configured to acquire a plurality of target region images from a plurality of face images. The photoplethysmography signal conversion module is configured to generate a photoplethysmography signal according to the target region images. The biometric characteristic conversion module is configured to convert the photoplethysmography signal into a biometric characteristic. The face characteristic acquisition module is configured to acquire a face characteristic from the face images. The comparison module is configured to fuse the face characteristic and the biometric characteristic into a fused characteristic and perform similarity calculation on the fused characteristic and a plurality of fused characteristics stored in a database to determine identity of an identified person.

The invention relates to the technical field of identity recognition methods, and discloses a multi-modal biological feature fusion identity recognition method. The multi-modal biological feature fusion identity recognition method comprises the following steps: S1, recognizing a user; s2, user registration; s3, user verification; s4, carrying out secondary verification; s5, alarm feedback; according to the invention, a dual-biological feature verification mode is adopted, any two of iris verification, fingerprint verification and voiceprint verification are selected, after identity information is input, any two verification modes of iris verification, fingerprint verification and voiceprint verification are verified, so that the risk of being stolen by people can be reduced, and when verification fails, secondary verification can be carried out, and a third verification mode is used for verification, so that the verification efficiency is improved. A user and an administrator at the receiving end judge the identity information of a user recognized at the input end, if the user is an untrusted user, positioning is started remotely, the control right of the input end is captured remotely, then the identity information is sorted, and an alarm is given.

The embodiment of the invention provides a biological feature fusion recognition device and method with a living body verification function, and the device is characterized in that the device comprises a biological feature fusion recognition main board, an image collection unit, an information interaction electronic screen, and a cavity shell; and the biological feature fusion recognition main board is electrically connected with the image collection unit and the information interaction electronic screen, and the biological feature fusion recognition main board, the image collection unit and the information interaction electronic screen are fixed to the cavity shell. The method comprises the following steps: sending a focal length adjusting instruction to calibrate the human face and eye positions by measuring the human face distance; obtaining an iris face recognition result and face body temperature information, and completing face living body detection; sending a living body verification instruction to a tester, and obtaining a palm distance; obtaining a palm vein recognition result and palm body temperature information through re-focusing; and comparing the two biological feature recognition results with the body temperature information result, verifying a living body detection result, and outputting identity information and authenticity thereof.

This invention relates to a sorter integration and mode identification field characterizing in obtaining characters of man-face, iris, on-line signature and off-line handwriting of a user by various collecting devices then sending them to corresponding certification sub-modules to pick up the characters and match with the molding boards and outputting the matched marks to be normalized and sent to an identification combined module to get the final identification result by confidence integration or sent to a certification module to be imaged to a multi-dimension space to be sorted by a sorter to get a final result or to be certified and combined to get the final identification result.

The invention discloses a multi-modal biological feature fusion device, whose structure includes a biological feature acquisition unit, a feature parameter extraction unit, a parameter normalization processing unit, a feature parameter fusion unit, and a biological feature recognition unit, which is similar to the prior art In contrast, the beneficial effects of the present invention are: the acquisition of five biometric features can be combined into ten groups of combined biometric features, any set of identification can be performed, the verification of a single biometric feature can be avoided, the security and accuracy of identification can be improved, and it can prevent partial The biometric feature is damaged and cannot be recognized, which leads to the failure of identification, providing more choices for identification. After fingerprint collection, use the sticky surface of transparent tape to remove the fingerprint, so that there is no fingerprint on the surface of the fingerprint sensor to prevent dust. The indirect infection of nails can ensure the cleanliness of the surface of the fingerprint sensor, which is conducive to the next fingerprint collection and helps to improve the accuracy of fingerprint collection and identification.

The invention discloses an electric car payment information authentication and encryption system and method based on biological characteristic fusion. An iris characteristic template and mobile phone IMEI card information are bound and encrypted through utilization of a fuzzy password box; a fingerprint template is converted and a BioCode is extracted; a plurality of pieces of characteristic information is integrated through binary serial connection; a secure channel from a mobile phone to a background database is established through utilization of a public key signature authentication algorithm; and a signature result is verified through utilization of a hash function, thereby realizing a lightweight encryption system of a charging station. The system and the method are relatively good in encryption performance. According to an identification technology fused with a plurality of biological characteristics, the relatively high accuracy and security are achieved; through combination of various algorithms of RSA, the hash function and fuzzy commitment, the multi-biological characteristic mixed encryption is realized; the system security is improved; the attack resistance is improved; the security of user information is ensured; the irreversible conversion is carried out on the biological characteristic template in the encryption process; and even if an attacker intercept data, the biological characteristics of the user cannot be restored.

The invention belongs to the technical field of key management and identity authentication related application, and discloses an access authentication and key derivation method and system for biological recognition identity authentication, and the method comprises the steps: in a registration stage, a user registers at a credible authentication center, and uploads all information such as biological characteristics, soft biological characteristics and identity labels; the fog node performs access authentication at the unified authentication cloud to obtain an identity identifier issued by the unified authentication cloud and a shared root key obtained through key negotiation, and after registration is completed, the fog node accesses the cloud-fog hybrid network; in the authentication stage, the user uploads feature information, and identity recognition is conducted through biological features; and the fog node and the unified authentication cloud generate parameters required by a soft biological feature key by using soft biological feature fusion, and generate the soft biological feature key and a session key by using key derivation, which are respectively used for encrypting and decrypting biological features and session messages. According to the method, the risk that the secret key is decoded can be obviously reduced, and the confidentiality of the biological characteristic privacy information of the user is enhanced.

The embodiment of the invention provides a biological feature fusion method and device, electronic equipment and a storage medium. The biological feature fusion method comprises the following steps: acquiring first biological features of at least multiple sources of a target; wherein the first biological characteristic belongs to at least two different levels; and fusing the first biological characteristics to form a second biological characteristic.

The invention discloses a biometric feature recognition multi-modal fusion method and device, a computer readable storage medium and equipment, and belongs to the field of biometric recognition. In the process of registration and verification / recognition of biological characteristics, various biological characteristic samples are collected, the mass fraction of the biological characteristic samples are obtained through sample quality judgment, the mass fraction and preset fusion threshold control parameters are compared according to a fusion strategy, and if fusion conditions are met, fusion processing is carried out. The fusion comprises sample data fusion, feature data fusion, comparison score fusion and comparison result fusion. Whether the fusion condition is met or not is judged according to the mass fraction of the multiple biological characteristic samples, fusion of the multiple biological characteristics is achieved, the limitation existing when identity recognition authentication is carried out through a single biological characteristic in a traditional method can be overcome, biological characteristic fusion processing is more reasonable and more effective, and a more comprehensive and safer guarantee is provided for identity identification and authentication.

An identity recognition system includes a target region acquisition module, a photoplethysmography signal conversion module, a biometric characteristic conversion module, a face characteristic acquisition module, and a comparison module. The target region acquisition module is configured to acquire a plurality of target region images from a plurality of face images. The photoplethysmography signalconversion module is configured to generate a photoplethysmography signal according to the target region images. The biometric characteristic conversion module is configured to convert the photoplethysmography signal into a biometric characteristic. The face characteristic acquisition module is configured to acquire a face characteristic from the face images. The comparison module is configured to fuse the face characteristic and the biometric characteristic into a fused characteristic and perform similarity calculation on the fused characteristic and a plurality of fused characteristics stored in a database to determine identity of an identified person. The identity recognition system of the present disclosure has a high-accuracy body identification ability, and can also confirm that theidentified person is a living body instead of a photo.

The invention discloses a multi-biometric feature fusion identity authentication device. The device structurally comprises a base device and a detection device, the base device is connected with the detection device and is composed of a standing disc, a rail, a top disc and a bottom disc, and the standing disc is connected with the rail; the rail is connected with the top disc, the top disc and the bottom disc are locked, and the detection device comprises a detection chamber, a detection door and a column base. The detection chamber is buckled with the detection door, and the detection chamber is locked with the column base. According to the invention, an identified person stands on the detection chamber, a detection plate carries out head, face and iris identification on the identified person, the identified person holds a fingerprint handle to carry out the fingerprint identification, and a grain padding cover is used for carrying out the foot identification, so that the multiple identification meets the identity identification of the banks or the national specific places, at some advanced confidential places, the multi-person multi-identity identification can be carried out comprehensively and deeply, the effective protection is achieved, and the high-quality and high-guarantee safety identification requirements are met.

The invention relates to a device for preventing people from entering a transformer substation without wearing a safety helmet. The safety helmet comprises a safety helmet body, an electronic lock, ahigh-definition camera, a displayer, a loudspeaker box, a transmission opening device and a control unit. The control unit controls the transmission opening device by receiving dual signals of the electronic lock and a safety helmet recognition device, so that workers who incorrectly wear safety helmets can be effectively prevented from entering the substation, and the safety of the workers entering the workstation is improved. Through a face recognition algorithm of multi-biometric feature fusion, according to different biometric feature spaces of different biometric features, the effective information amount of the different biometric features during fusion is further improved, the authentication time of the multi-biometric features is shortened, and the safety is ensured. Moreover, theimage of the upper area of the face is much smaller than that of the whole image, the safety helmet recognition module only recognizes the upper area of the face, and the safety helmet is standard equipment, so that the processing speed is high, and the detection efficiency is high.

The embodiment of the invention discloses a multimode biological feature fusion method and system. The method comprises the following steps: performing feature comparison on the feature data corresponding to each piece of biological data in the multi-modal biological data to generate a fractional vector of the multi-modal biological data, performing piecewise linear classification processing on the fractional vector to generate a decision value corresponding to the fractional vector, and identifying identity information corresponding to the multi-modal biological data according to the decisionvalue. By adopting the method and the system, various biological characteristics are fused through the linear classifier, useful information of each biological characteristic can be reserved, identity information is extracted from a high-dimensional characteristic space, and the accuracy of identity recognition can be ensured.

The invention discloses an identity recognition method based on multi-modal biological feature fusion based on an evolutionary strategy. The specific steps of the method are as follows: firstly, image data of three biological features of human face, static hand shape and palmprint are collected, and the extracted Feature extraction for each biological feature and feature authentication using the nearest neighbor classifier; then use the evolutionary strategy to adaptively adjust the weights of each classifier; finally use the adaptively adjusted weights to classify the face and static hand shape The recognition results output by the three classifiers corresponding to the three biometric features of the palmprint are weighted and fused to obtain the final recognition result. The present invention uses the evolutionary strategy to self-adaptively adjust the weight, and fuses the classifier with multiple biological characteristics through the weighting method on the decision-making layer to reduce the influence of the surrounding environment on the recognition result, so that the safety and adaptability of the recognition method are improved. Compared with other fusion methods, it has been greatly improved, and the fault tolerance of the recognition method has also been improved.