38 results about "Palmar vein" patented technology

The present invention belongs to the field of biometrics, and more particularly relates to a method and device for finger vein recognition and detection that integrates texture and liveness features. The method comprises first installing an imaging device, a plurality of beam splitters, a plurality of reflectors, a filter, a light source module, and a processor in a preset position; placing the finger to be detected in the predetermined position to obtain multiple near-infrared venography images; then performing pixel-level registration to crop images of regions of interest with varying light intensities, combining these images into a multi-channel image; utilizing the known light intensity ratios of the multi-channel vein images and the camera's light response function to establish a finger transmission model; performing quantitative calculation of the transmission light offset for each point on the finger image; and comparing the registered finger transmission light offset map with the transmission offset map of the finger to be detected to determine whether the finger is the same and whether it is live. The present invention can address the problem of weak resistance to finger vein prosthesis attacks and video replay attacks encountered in the prior art.

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.

The present invention relates to the technical field of biometric feature processing and identification methods, and discloses a lightweight finger vein image recognition method for identifying the characteristics of specific finger veins, comprising the following steps: S1, acquiring a user's finger vein image; S2, calculating the finger's offset angle relative to the horizontal midline using an edge detection method, fitting the image midline to the horizontal midline through image rotation, and obtaining the required horizontal finger vein grayscale image by region-of-interest (ROI); S3, performing image enhancement by dividing the grayscale image into a certain number of grayscale squares of equal size and calculating the grayscale value histogram within the squares for equalization; S4, performing bilinear interpolation on the enhanced grayscale image under lightweight optimization, and then performing adaptive local threshold binarization to obtain a filtered finger vein image in the grayscale image. The present invention improves the security and efficiency of identity authentication and reduces the memory required, processor performance requirements, and production costs of the program in actual use.

The present invention discloses a method and device for binocular finger vein identity recognition. The method includes: calibrating the parameters of the left and right cameras; calculating two-dimensional left and right finger vein texture images; performing stereo rectification on the left and right finger vein texture images; obtaining finger vein texture point cloud data with a three-dimensional spatial topological structure; performing noise reduction processing on the finger vein texture point cloud data; constructing a model for cross-modal finger vein identity information representation with the collaboration of two-dimensional images and three-dimensional point clouds; calculating a combined representation vector of the fusion feature corresponding to the maximum correlation and the binocular finger vein feature attributes; constructing a finger vein feature database with identity identification attributes. According to the matching relationship between binocular infrared finger vein texture images, the present invention establishes a convolutional neural network model, converts two-dimensional finger vein texture images and three-dimensional finger vein texture point clouds into corresponding feature vectors, and constructs a combined representation of cross-modal finger vein feature information, thereby improving the identification ability of identity recognition.

This invention discloses a finger vein recognition method based on a joint loss and convolutional neural network. The method includes the following steps: acquiring a finger vein image, preprocessing the image, extracting the region of interest (ROI) of the finger vein image, and normalizing the image size; constructing a deep convolutional neural network for finger vein recognition, using a feature extraction network based on the ResNet34 architecture; training the model by using a joint loss function in Euclidean and cosine metric spaces to train the deep convolutional neural network so that the network model learns effective feature representations of finger veins; and determining a recognition threshold, using the false acceptance rate and false recognition rate as metrics, and finding the optimal recognition threshold through enumeration to achieve finger vein image recognition. The method is used for finger vein image feature extraction and matching, effectively performing finger vein identity recognition.

This paper proposes a method for detecting finger vein spoofing attacks based on capsule networks. Capsule networks are not only suitable for small-sample finger vein datasets, but also, by replacing neurons with vector-represented capsules on top of CNNs, they can better handle spatial information such as relative position and angle, enhancing the network's adaptability to finger offset and rotation scenarios. A Bayesian routing algorithm is proposed, incorporating the differential entropy of the capsules as a consideration in calculating activation values. During final classification, feature capsules with high activation probabilities and high concentration are selected, which helps improve the accuracy of classifying genuine and fake veins. By simulating the uncertainty of capsule parameters, training errors can be reduced, improving recognition accuracy.

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.

Facial vein and palm vein integrated equipment relates to the technical field of vein recognition equipment, and comprises a frame body, a camera, a recognition module and a control module, the camera comprises a facial vein acquisition camera and a palm vein acquisition camera, the facial vein acquisition camera is fixed on the front surface of the frame body, and the palm vein acquisition camera is fixed on the side surface of the frame body; the recognition module is mounted in the frame body and is in communication connection with the facial vein acquisition camera and the palm vein acquisition camera; the control module is installed in the frame body and is in communication connection with the identification module. The equipment integrates facial vein identity recognition and palm vein identity recognition, and is higher in flexibility and wider in use scene.

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 present invention discloses a finger vein recognition method based on feature fusion. First, the input finger vein image is successively subjected to finger edge extraction, finger region segmentation, finger rotation correction, and extraction of the region of interest of finger veins. Then, the histogram of oriented gradients features of the region of interest of finger veins is extracted, and the local phase quantization features of the region of interest of finger veins are extracted. Finally, on this basis, the principal component analysis algorithm is used to perform feature selection on the above two kinds of features respectively, and the joint sparse representation classification method is used to fuse and recognize the above histogram of oriented gradients features and local phase quantization features, so as to achieve the final identity recognition. This solution further improves the security and effectiveness of identity recognition, has the advantages of good reliability and high use value, and can be widely applied to fields such as access control systems and security.

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.

This application relates to the field of fingerprint recognition technology, and particularly to a fingerprint recognition method, device, electronic device, and storage medium. The method includes: responding to a user's pressing operation, obtaining a confidence level of the sweat pore detection result based on the sweat pore information of the original fingerprint image of the fingerprint to be identified, and obtaining a confidence level of the vein detection result based on the finger vein characteristics; generating a time-series detection result based on the first start time of the sweat pore detection and the second start time of the finger vein detection, and calculating a comprehensive confidence level by combining the confidence levels of the sweat pore detection result and the vein detection result, thereby determining whether the fingerprint to be identified is a live fingerprint. This solves the problems of related technologies relying on single physical features, difficulty in identifying highly realistic fake fingerprints, and lack of spatiotemporal consistency analysis methods. By integrating multimodal biometric signals such as sweat pore features, finger vein features, and time-series consistency verification for comprehensive discrimination, effective prevention of forged fingerprint attacks is achieved.

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.

The present invention belongs to the field of automatic control, and particularly relates to a finger vein recognition method based on variable curvature Gabor convolution and a multi-branch structure, and a corresponding finger vein recognition system and finger vein verification device. The solution of the present invention first improves the traditional Gabor filter by adding variable curvature so as to extract information on different bending degrees in the vein curve. Secondly, the variable curvature Gabor function is constructed into a learnable VC-Gabor convolution layer, and the parameters of the VC-Gabor convolution layer are updated by using the backpropagation of the neural network, so that the directions, scales and curvatures of the learned VC-Gabor filters are more abundant, and complex manual parameter adjustment is avoided. Finally, a network model including a VC-Gabor convolution layer and an adaptive multi-branch structure is designed in combination with the convolution layer in the classical CNN network, and then the network model is used for rapid recognition of finger vein images. The present invention solves the defects of insufficient accuracy and poor robustness of the existing finger vein recognition methods.

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.

To provide a USB security key with high security. [Solution] The USB security key 1 comprises a circuit board 11 fixed by structural members inside an outer case 10, an embedded MCU main control chip 12 mounted on the circuit board 11 and containing a secure element 21, a palmar vein authentication module 13 connected above the circuit board 11 and electrically connected to the embedded MCU main control chip 12, and a USB data interface 14 provided at the end of the circuit board 11 and electrically connected to the embedded MCU main control chip 12. The palmar vein authentication module 13 acquires a palmar vein image and generates an authentication result signal, the embedded MCU main control chip 12 receives the authentication result signal, generates authentication data based on the authentication result signal, packages the authentication data into authentication response data according to a predetermined protocol, and outputs it via the USB data interface 14.

The application discloses a self-adaptive dual-mode identity recognition method for finger vein and external finger joint vein, and belongs to the field of biometric recognition technology.The method comprises the following steps: S1, collecting finger vein and external finger joint vein images; S2, pre-processing the finger vein and external finger joint vein images; S3, quality evaluation of the finger vein and external finger joint vein images and giving corresponding scores, and determining whether the images meet the requirements according to the scores; if the images meet the requirements, the next step is performed, otherwise, re-collection is prompted; S4, advantage feature coefficient assignment according to the quality of the corresponding finger vein and external finger joint vein images; S5, using an improved SIFT algorithm for the finger vein image and using a PHASH algorithm for the finger joint vein image to perform similarity matching with features in a database to obtain corresponding similarity; S6, combining the corresponding weight and the similarity through a weighted similarity function to obtain a corresponding weighted matching degree; S7, fusing the finger vein and finger joint vein weighted matching degrees through a fusion function to obtain a final fusion matching degree; and S8, threshold value judgment.The application has high recognition accuracy and robustness.

The invention relates to an intelligent cabinet multi-identity recognition information fusion method and system based on information entropy, and the method comprises the steps: carrying out the photographing of a human face image and a finger vein image through terminal equipment on an intelligent cabinet, and obtaining the feature vectors of the human face and the finger vein through a feature extraction algorithm; an improved deformable convolution algorithm is used for eliminating the measurement inconsistency of face features and finger vein features, and after feature alignment, the face features and the finger vein features are mapped to the same vector space and are connected in series to form a group of multi-identity feature vectors. And finally, judging whether the multi-identity feature vector is valid or not by using the lowest valid feature dimension obtained by the information entropy, outputting the valid feature vector, comparing the valid feature vector with a feature database, and outputting a recognition result. The face information and the finger vein information are comprehensively utilized, and the recognition precision and accuracy of the intelligent cabinet recognition system in a complex environment are effectively improved.

Provided in the present application are a feature extraction method and apparatus. In the present application, a plurality of finger vein images of the same finger which are captured at different angles are acquired, and then by means of the processing method in the present application, deformation of veins in each finger vein image, which deformation is caused by slight shaking of the finger, can be corrected on the basis of the plurality of finger vein images captured at the different angles, and thus finger vein features having relatively high accuracy are obtained, thereby facilitating an improvement in the accuracy of identity authentication performed by means of finger vein recognition.

The invention discloses a multi-level feature-based finger vein recognition method, device and equipment and a medium, and the method comprises the steps: constructing a finger vein recognition model based on a graph convolution neural network, obtaining a finger vein image data set, inputting each finger vein image in the finger vein image data set into a graph convolution layer, and obtaining a finger vein recognition model; performing multi-layer convolution operation on the finger vein image by using an image convolution layer to obtain a node feature matrix, and inputting the node feature matrix into a vector feature comparison layer to obtain a finger vein recognition deviation value; performing iterative training on the finger vein recognition model according to the finger vein recognition deviation value until the finger vein recognition deviation value reaches a preset standard; and in the actual identification process, the finger vein is identified and processed by using the trained finger vein identification model. According to the method, the multi-level features of the finger vein image can be effectively extracted, and the subtle differences of the finger vein can be accurately captured, so that the recognition accuracy is remarkably improved.

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 embodiment of the invention discloses an intelligent door lock control method and device, an intelligent door lock and a computer readable medium. A specific implementation mode of the method comprises the following steps: acquiring a palm vein image; inputting the palm vein image into a compressed sampling layer to obtain a compressed sensing measurement vector; inputting the compressed sensing measurement vector into an initial reconstruction image layer to obtain an initial reconstruction image; inputting the initial reconstruction image into a depth reconstruction image layer to obtain a depth reconstruction image; inputting the depth reconstruction image into a global local feature reconstruction image layer to obtain a palm vein reconstruction image; performing region-of-interest extraction on the palm vein reconstruction image to obtain a region-of-interest image; performing feature extraction on the region-of-interest image to obtain a region-of-interest feature vector; generating a palm vein matching result; and in response to determining that the palm vein matching result represents successful matching, controlling the door lock assembly to execute unlocking operation. According to the embodiment, waste of collected image resources can be reduced.

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 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 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 present invention proposes a finger vein recognition method and system based on a convolutional neural network and the SIFT (Scale-invariant feature transform) algorithm. The implementation process is as follows: First, obtain the finger vein image of the user to be recognized through data acquisition; Second, preprocess the received original vein image information and extract the region of interest of the image; Finally, extract the vein image feature information of the finger of the user to be recognized through the neural network in combination with the SIFI algorithm, and further perform recognition processing on the obtained finger vein image feature information of the user to be recognized, so as to achieve the purpose of recognizing the identity information corresponding to the finger vein information. The present invention can effectively extract finger vein features, improve the redundancy of noise, and significantly improve the recognition accuracy of the finger vein recognition system.

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 invention discloses a user authentication method, computer equipment and system based on a finger vein image, and relates to the technical field of image processing, and the method comprises the steps: obtaining a finger vein image of a user; the finger vein image is preprocessed; inputting the preprocessed finger vein image into a pre-trained multi-noise identification model to identify an image noise type; performing noise reduction processing on the finger vein image according to the image noise type; performing feature extraction on the finger vein image subjected to noise reduction processing so as to generate an image embedding feature vector; comparing the image embedded feature vector with a preset feature vector template; if the similarity between the image embedded feature vector and a feature vector template is greater than a preset similarity reference, authorizing the user to access; and if the similarity between the image embedded feature vector and the feature vector template is smaller than or equal to the similar reference, refusing the user access. By adopting the method and the device, the noise type in the finger vein image can be effectively identified, and different targeted measures are adopted for performing accurate noise reduction aiming at different image noise types, so that the authentication accuracy is improved.