19 results about "Finger vein recognition" patented technology

This invention relates to a method for authenticating maintenance personnel in a power monitoring system based on finger vein recognition. The method includes: acquiring finger vein images of maintenance personnel for liveness detection; generating a baseline template if successful; encrypting the baseline template with the maintenance personnel's joint identifier to generate ciphertext, and splitting it into multiple ciphertext fragments for separate storage; responding to an operator's request to operate the system, acquiring the operator's finger vein images in real time for liveness detection; extracting real-time feature vectors based on the finger vein images if successful; obtaining ciphertext fragments of the corresponding operator's personnel identifier and operating account from multiple storage nodes, reassembling and decrypting them to obtain the corresponding baseline template; responding to a first matching degree between the real-time feature vector and the corresponding baseline template satisfying a preset condition, calculating a fused feature vector based on the baseline template and the real-time feature vector; and determining whether the operator is allowed to operate the power monitoring system based on a second matching degree between the fused feature vector and the baseline template.

This invention discloses a finger vein recognition method and system based on deep metric learning and quality enhancement. The method includes: acquiring finger vein images and extracting regions of interest; using a Siamese network to learn the quality ranking relationship of image pairs, automatically evaluating image quality and filtering low-quality images; constructing an FV-FE-Net feature extraction network, training it under dual constraints of Euclidean distance and cosine angle using a joint loss function (triple loss + ArcFace loss), and extracting highly discriminative feature vectors; finally, identity authentication is completed through feature similarity matching. This invention eliminates the need for manual image quality annotation, effectively filters low-quality images, improves generalization ability and recognition accuracy in open-set recognition scenarios, and exhibits strong robustness and scalability, making it suitable for high-security identity authentication scenarios.

The utility model discloses a finger vein recognition mechanism which is used for reducing the influence of dust in the environment on a finger vein recognition area and improving the recognition rate. The device comprises a finger vein assembly, a track box and a sliding track structure, a containing space is formed in the track box, the finger vein assembly partially penetrates through the track box and is located in the containing space, and the side wall of the finger vein assembly is movably connected with the inner wall of the containing space through the track sliding track structure; the finger vein assembly comprises a working position and a storage position, and at the storage position, a recognition module on the finger vein assembly is located in the containing area; and at the working position, the finger vein assembly is controlled to slide along the sliding track structure, so that the upper end of the finger vein assembly slides out of the accommodating area.

The invention discloses a finger vein recognition method and system based on an improved deep learning network, and aims to solve the problems of low segmentation precision, unstable classification and high retraining cost, proposes GAN + CLAHE preprocessing, and constructs an R-LAB segmentation network which takes Xception as an encoder and introduces space and channel attention; designing improved Xception feature extraction containing a global average pooling and residual error compensation structure; and a cascade KNN based on cosine similarity is adopted to complete personnel identification and support dynamic registration. The system comprises a data preprocessing module, a segmentation module, a feature module, a classification module and an integration module, and comprehensive improvement of precision, efficiency and flexibility is achieved.

A finger vein recognition method based on compact binary coding learning relates to the technical field of pattern recognition and image processing. The method comprises the following steps: extracting finger vein texture difference vector, learning mapping function, mapping and feature integration, calculating and splicing block histogram, feature matching, finger vein recognition. The existing algorithm has two main defects: (1) most current methods highly depend on rich prior knowledge base, such dependence not only increases the complexity of implementation, but also is easily affected by adverse factors; (2) the sample quantity of existing finger vein database is small, and the finger vein recognition method based on deep learning is limited in practical application. The present application can effectively improve the recognition accuracy of finger vein recognition under the condition of few samples, and has strong self-adaptability and generalization. Therefore, the present application has certain application value and significance.

The invention discloses a two-view finger vein recognition method and system based on multi-scale Mama, and relates to the technical field of biological feature recognition. The method comprises the steps that a multi-scale Mama feature extraction module is used for conducting feature extraction on a finger vein image of each view angle, and multi-scale features are obtained; enhancing the multi-scale features in each view angle to obtain enhanced features of the two view angles; performing feature interaction on the enhanced features of the two view angles by using a Mamba feature interaction model to obtain interaction features of the two view angles; and splicing the interaction features of the two visual angles, and predicting the finger vein image category. According to the method, the problems of information loss and attitude sensitivity existing in single-view-angle recognition are solved, and the recognition performance and robustness of a recognition system are further improved.

The embodiment of the invention provides a finger vein recognition technology (FIVRT) based on deep learning, and relates to a finger vein recognition method based on deep learning. The finger vein recognition technology is one of biological feature recognition technologies, has the characteristics of living body recognition, non-replicable in-vivo features, uniqueness, stability, non-cracking and the like, and has a higher safety coefficient than fingerprint recognition and face recognition. According to the embodiment of the invention, the finger vein feature values are extracted by using the FingerCavaNet network model and mapped into the feature vectors in the Euclidean space, the similarity between the two pieces of finger vein data is measured through the Euclidean distance between the two feature vectors, and the smaller the Euclidean distance is, the higher the similarity is. Therefore, personal identity authentication and identity confirmation are realized. The shape of the finger vein has uniqueness and stability, that is, the finger vein images of each person are different, the vein images of different fingers of the same person are also different, and the vein shape of a healthy adult does not change any more, so that a basis is provided for the finger vein to be used for identity recognition.

The application discloses a kind of finger vein identification method, device, computer readable storage medium and equipment, belong to the field of biometric identification.It includes: obtaining finger vein image;Calculate the gradient information of finger vein image, according to gradient information, find the finger boundary using greedy strategy;Detect finger joint on finger vein image, and extract the effective area of finger vein according to the finger joint and finger boundary;Through Gabor filter, the effective area is extracted, and the finger vein feature is obtained;Set sliding window on the finger vein image, and the finger vein feature of the finger vein image in sliding window is compared with the corresponding position of the finger vein feature template Similarity, find the finger vein image in the highest similarity sliding window as the maximum matching area;The similarity of maximum matching area and the corresponding position of finger vein feature template is used as matching score.The application can realize stable and efficient finger vein identification for different devices and different collection environments.

This application provides an electric two-wheeled vehicle, relating to the field of electric two-wheeled vehicle technology. The electric two-wheeled vehicle includes: a steering system comprising two throttles and a dashboard; a front cover, at least partially located below the throttles; a finger vein recognition module disposed on the throttles, the front cover, or the dashboard, the finger vein recognition module for collecting finger vein image information of the user, the finger vein recognition module including a housing and a recognition surface disposed on the housing; and a control system connected to the finger vein recognition module, the control system for controlling vehicle unlocking based on the verification result of the finger vein recognition module; the spatial posture of the recognition surface is configured such that when the user prepares to operate the electric two-wheeled vehicle, the user's finger is adapted to move in a direction approximately perpendicular to the recognition surface to contact the recognition surface. This electric two-wheeled vehicle can achieve fast unlocking without relying on external devices such as keys, NFC cards, or electronic devices, making unlocking more convenient for users and improving the user experience.

This application relates to the field of biometric recognition and image processing technology, and discloses a method, model, device, and medium for finger vein recognition based on a lightweight attention model with few samples. The method includes: acquiring raw finger vein images and extracting regions of interest (ROIs); preprocessing the ROI images; performing data augmentation on the training set images; constructing an LA-VGG network based on a VGG-19 network, introducing CA attention, PReLU, and cross-layer fusion to enhance subtle textures; introducing a loss function with additive angular margins during the training phase; training the LA-VGG network to obtain a finger vein recognition model; inputting the image to be recognized into the model, and outputting the identity recognition result. This invention can effectively alleviate the overfitting problem under small sample conditions, reduce the number of model parameters and computational complexity, improve the extraction capability of key finger vein texture features, and is suitable for deployment and application in resource-constrained devices and complex environments.

The present disclosure relates to a finger vein recognition system. The finger vein recognition system includes an IR camera, a handle having a sensor and an array of IR LEDs, and a microprocessor for controlling the array of LEDs and processing image signals received from the camera. The emission of each LED in the array of LEDs can be varied based on the position of the user's finger and the environment, which improves the quality of the image captured by the IR camera. The sensor detects the proximity of the user and activates the system.

The invention provides a diffusion model-based finger vein image generation method and device, equipment and a medium, and effectively solves the problem that the accuracy of a finger vein recognition technology is reduced due to various defects of an existing finger vein image. According to the method, noise diffusion processing and finger vein texture simulation are carried out based on an acquired real finger vein image to generate a finger vein diffusion image and a finger vein template image, and features in the finger vein diffusion image are extracted in a multi-scale manner to obtain a multi-scale finger vein feature map; converting the multi-scale finger vein feature map to the mask image to obtain a synthetic finger vein image; constructing a three-dimensional finger model for synthesizing the finger vein image, performing multi-view spatial transformation on the three-dimensional finger model to obtain a multi-view finger vein texture image, and obtaining a plurality of finger vein images; and evaluating the plurality of finger vein images to obtain corresponding evaluation results so as to screen out a target finger vein image.

The present application relates to the technical field of integrated circuits, and further relates to a mouse and an interactive system. The mouse comprises: a finger vein recognition circuit or a fingerprint recognition circuit, which is configured to generate finger vein verification information or fingerprint verification information; a key circuit, which is connected to the finger vein recognition circuit or the fingerprint recognition circuit, and is configured to extract key information; a mouse module circuit, which is configured to implement button operations and navigation operations of the mouse; and a control circuit, which is separately connected to the mouse module circuit and the key circuit, and is used for enabling the mouse module circuit and the key circuit to be independently recognized. Integrating a key circuit and a mouse module circuit into a mouse enables simultaneous connection of the mouse and a USB key to a host computer when the host computer has only one interface available.

The invention discloses a finger vein recognition method and device based on multi-domain feature enhancement and fusion, and relates to the technical field of biological feature identity recognition. The method comprises the steps of obtaining a to-be-recognized finger vein image; performing spatial domain feature enhancement, gray domain feature enhancement and frequency domain feature enhancement on the image to obtain a processed image; extracting the LBP feature of the processed image in a blocking manner to obtain an LBP feature vector of each block image; generating a geometric feature vector of each feature point in the processed image based on a morphological processing method, a feature point extraction method and a histogram statistical method; fusing the geometric feature vector of each feature point with the LBP feature vector of the block image where the feature point is located to obtain a fused feature vector; and based on an improved circular neighborhood position distance matching method, determining the category of the image by using the fused feature vectors of the feature points, the category of the database image and the fused feature vectors of the feature points. The identification performance can be improved.

The application belongs to the technical field of biological feature recognition, and discloses a finger vein recognition method based on an improved automatic coding network. The method is based on the improved automatic coding network, can learn the structure and features from unmarked data in an unsupervised manner, and improves the recognition accuracy. An error correcting code (ECC) suitable for real value features is used to protect the template, so that the security can be improved, the loss of detail information can be avoided, and the sensitivity and accuracy of the recognition system are improved.

The application discloses a finger vein recognition method and system based on dynamic balance of false recognition rate and false rejection rate, and the method comprises the following steps: obtaining a to-be-recognized finger vein image, and performing image preprocessing and ROI extraction processing to obtain an ROI region of the finger vein image; a finger vein recognition model is constructed, three-stage hybrid training is performed in combination with the ROI region of the finger vein image, and a trained finger vein recognition model is obtained; a balanced error rate evaluation index is constructed to evaluate the trained finger vein recognition model, and an evaluated finger vein recognition model is obtained; and finger vein recognition is performed on the to-be-recognized finger vein image based on the evaluated finger vein recognition model, and a finger vein recognition result is obtained. The application can meet the finger vein recognition requirements in multiple scenes and improve the finger vein recognition accuracy. The application can be widely applied to the technical field of finger vein recognition as a finger vein recognition method and system based on dynamic balance of false recognition rate and false rejection rate.

The invention discloses a finger vein recognition method and device, a storage medium and equipment, and belongs to the field of biological feature recognition. The method comprises the following steps: firstly, carrying out rotation alignment on a finger vein image through a finger center line, obtaining a region of interest, then obtaining an optimal matching region through a sliding window mode based on Gabor binary coding, and finally, carrying out local feature descriptor extraction and matching on the optimal matching region. According to the invention, the finger vein recognition of the local feature point and feature descriptor method is carried out through the finger midline registration and sliding matching strategy, the invalid comparison is greatly reduced, the effective local descriptor is concerned, and the matching efficiency is greatly improved.

The application provides a finger vein recognition method and device, electronic equipment and storage medium. The method comprises the following steps: obtaining a to-be-recognized image; performing feature extraction on the to-be-recognized image through a preset finger vein feature extraction model to obtain a finger vein feature; wherein the finger vein feature extraction model comprises a nonlinear feature extraction network; the nonlinear feature extraction network is obtained based on a nonlinear convolution kernel; performing finger vein recognition according to the finger vein feature to obtain a recognition result. The nonlinear feature network with less to-be-optimized parameters is used to replace the conventional linear feature network, thereby reducing the calculation cost and training time and making the model easier to train. Moreover, the nonlinear convolution network is applied to the finger vein recognition, the nonlinear parameter dependent convolution kernel provides additional nonlinear features for the finger vein recognition, the feature extraction capability of the network is stronger, and the recognition accuracy is higher.

The application discloses an identity verification method and device, electronic equipment and storage medium, and belongs to the field of image processing. The identity verification method comprises the following steps: acquiring a first finger vein image of a first user; performing image cutting on the first finger vein image to obtain a plurality of first finger vein sub-images of different regions, and the image cutting strategy of the first finger vein image is determined based on the texture offset degree of the first finger vein image; acquiring a first global feature vector of the first finger vein image, and acquiring a plurality of first local feature vectors of the plurality of first finger vein sub-images, wherein the first local feature vectors correspond to the first finger vein sub-images one by one; comparing the first global feature vector and the plurality of first local feature vectors with identity verification information of a second user registered in an identity library to obtain an identity verification result of the first user, and the identity verification information of the second user comprises a second global feature vector and a plurality of second local feature vectors. The method improves the finger vein recognition accuracy and efficiency.