30 results about "Biometric fusion" patented technology

The invention discloses a multi-modal biological feature layer fusion recognition method based on label identification correlation analysis. First, the feature set is fused with the category label information, and a criterion function is established for it, and the optimal projection vector is obtained by using the Lagrangian function, and the feature set with category information is obtained; secondly, for the feature set with category information, While minimizing its intra-class scatter matrix, maximize the correlation of the covariance matrix between the two modal feature sets, and extract the feature vector with higher discriminative ability; finally, the proposed fusion method is applied to the multi-modal The experimental results verify the effectiveness of the method proposed in this application and the rationality of the combination of the two algorithms.

The invention discloses a multi-biological feature fusion identity identification device, the structure of which includes a base device and a detection device, the base device and the detection device are installed and connected, the base device is composed of a station plate, a track, a top disc, and a bottom disc. It is connected with the track track, the track is installed and connected with the top disc, the top disc is locked with the bottom disc, the detection device includes a detection room, a detection door, and a column base, the detection room is buckled with the detection door, and the detection room is locked with the column base. The invention recognizer stands in the detection room, the detection board recognizes the head, face and iris of the recognizer, holds the fingerprint handle on the fingerprint handle for fingerprint recognition, and the pad pattern cover for foot recognition. Multiple recognition meets the needs of some banks or countries. For identity verification in specific places, in some high-level confidential places, multi-person identification can be used for all-round and in-depth identification to achieve effective protection and high-quality, high-guarantee security identification requirements.

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 software system account key management application, and specifically discloses a method and system for online information trusteeship that integrates biometric encryption technology, including the following steps, confirming the availability of a user account through a mobile phone number or email account and a verification code; Collect user biometrics; use biometric fuzzy vault algorithm to encrypt escrow information; upload and store encrypted escrow information; download encrypted escrow information; collect combined timing actions to complete live detection; use biometric fuzzy vault algorithm to complete escrow information reverse decryption; Supports automatic destruction of download information. The beneficial effects of the online information trusteeship method and system of the fusion biometric feature encryption technology of the present invention are: 1. Increase the amount of data supported by the fuzzy vault algorithm through the fusion of multiple biometric features; 2. Effectively fight against hackers through the action sequence live detection Imitation of a living body; 3. To ensure information security without requiring the user to enter a password.

The present invention is a multi-biological feature fusion recognition method based on image quality assessment. Firstly, the user's face and iris images are collected through the image collection subsystem and correspondingly preprocessed, and secondly, the preprocessed images are respectively sent to corresponding The identification and authentication subsystem of the identification and authentication subsystem performs steps such as quality assessment, feature extraction, and template matching, and outputs respective matching scores and corresponding matching quality confidence scores. Finally, these scores are normalized and sent to the identification and fusion subsystem, and the dynamic weighted fusion algorithm is used to obtain Identify the authentication result. The beneficial effect of the present invention is that: the method has higher recognition accuracy than a single face or iris recognition algorithm, and can realize high-precision personal identification; at the same time, the method is based on the existing mainstream fusion recognition algorithm. On the other hand, the useful information of image quality is extracted and applied to the fusion identification and authentication process to further improve the system identification performance.

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.