104 results about "Palm vein" patented technology

The invention discloses a novel graph contrast learning framework with mutual information maximization, and relates to the technical field of graph contrast learning, multi-modal learning and mutual information maximization. The framework comprises the following steps: constructing a nearest neighbor graph, spreading similar samples to data of a missing mode, optimizing a loss function, and performing clustering optimization. The existing method has two main problems: (1) the existing method is mostly suitable for complete data and has a poor processing effect on data of a missing mode; and (2) the current palmprint and palm vein fusion recognition technology does not completely capture the complex relationship between the palmprint and palm vein features, resulting in inaccurate clustering result. According to the method, the modal loss in the incomplete palm print and palm vein fusion recognition task is effectively reduced, and the clustering performance is enhanced. According to the method, the mutual information maximization loss function is introduced, the adaptability and robustness of the model to incomplete data are effectively enhanced, and the method has high recognition precision and clustering performance when processing incomplete multi-modal data.

The invention discloses a non-contact palm vein multi-mode identification system based on deep learning. The system comprises a multi-mode image acquisition and processing terminal, a mode matching and identification decision terminal, a safety protection and anti-counterfeiting terminal and an iterative optimization terminal. The multi-modal image acquisition and processing terminal is used for acquiring palm print and palm vein images, performing dynamic calibration, image quality enhancement and preprocessing, and outputting multi-modal images; the mode matching and identification decision terminal is used for carrying out feature extraction, multi-modal feature fusion, mode matching and identification decision and outputting a final matching result; the safety protection and anti-counterfeiting terminal is used for carrying out living body detection, anti-counterfeiting monitoring and data encryption; and the iterative optimization terminal is used for realizing model lightweight, knowledge distillation, end-to-end optimization and continuous learning. According to the invention, through deformation invariant feature extraction and cross-modal attention fusion, the recognition accuracy and environmental adaptability in a complex state are improved.

The invention provides a palm vein high-security identity authentication system based on spectral analysis and deep learning, and relates to the technical field of biological recognition, the system comprises a hardware layer, a data processing layer, an algorithm layer and an application layer, through an antagonistic living body detection module in the algorithm layer, in combination with physical modeling and a GAN (Generative Adversarial Network), the high-security identity authentication of a complex imitation is realized. The method comprises the following steps: carrying out effective identification of a high-biomimetic material, carrying out physical modeling to analyze the absorption characteristics of palm veins in a hyperspectral range, such as the difference between oxyhemoglobin and oxyhemoglobin and periodic spectrum micro-interference caused by heart rate, and providing living body evidence based on physiological dynamics; meanwhile, a high-simulation template sample generated by the GAN is used for training a discriminator, the insight ability of the system to a template means is further enhanced, and compared with single traditional texture or static signal detection, the system combines physical characteristics with deep learning, and the confidence coefficient of in-vivo detection reaches up to 99.99%.

The present application belongs to the technical field of palm vein recognition, and particularly relates to a palm vein recognition data enhancement method and system based on adversarial learning, which utilizes a conditional deep convolutional generative adversarial network composed of a generator and a discriminator, and synchronously trains the generator and the discriminator; step 2 selects a palm vein classifier and the trained generator to form an adversarial network, step 3 performs multiple batches of adversarial training on the palm vein classifier based on the adversarial network, generates adversarial samples for increasing the loss of the classifier and training samples based on real palm vein recognition data to form an augmented data set in each batch of training, trains the classifier, and updates the parameters of the classifier; and updates the noise vector set required for the next batch of adversarial training. The present application reduces the requirements for computing and storage resources in data enhancement, and provides more high-quality training samples for palm vein recognition model training.

The utility model discloses a multi-mode palm vein recognition terminal machine which comprises a multi-mode palm vein recognition terminal machine body, the outer wall of the multi-mode palm vein recognition terminal machine body is fixedly connected with a shell, the top ends and the bottom ends of the two sides of the multi-mode palm vein recognition terminal machine body are respectively provided with a square plate, and the square plates are fixedly connected with the inner wall of the shell. The two sides of the multi-mode palm vein recognition terminal machine body are each provided with two guide rods, the guide rods are fixedly connected with a square plate, the two guide rods located on the same side are sleeved with the same sliding plate, the sliding plates are slidably connected with the guide rods, and one side of each sliding plate is fixedly connected with a fixing base. According to the utility model, the multi-mode palm vein recognition terminal machine body can be effectively protected, the multi-mode palm vein recognition terminal machine body can be conveniently cleaned, dust is prevented from blocking a sensor, the quality of captured images is ensured to be clear, a user can clearly see displayed content, and the use experience of the user is ensured.

1. The name of the design product: biometric identification device. 2. The use of the design product: can identify palm vein, palm print and other information, carry out identity recognition and information acquisition, and is used in the fields of payment and access control identity recognition. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.

The method comprises the steps that when it is detected that the palm of a user is placed on a door handle, a bottom palm vein recognition module is triggered to recognize palm center veins of the palm, and when the palm center veins pass verification, the bottom palm vein recognition module is triggered to recognize the palm center veins of the palm; a top palm vein recognition module is triggered to recognize hand back veins of a palm, and after verification of the hand back veins is passed, the intelligent door lock is controlled to be unlocked; or when it is detected that the palm of the user is placed on the door handle, the top palm vein recognition module is triggered to recognize the hand back vein of the palm, after the hand back vein verification is passed, the bottom palm vein recognition module is triggered to recognize the palm center vein of the palm, and after the palm center vein verification is passed, the intelligent door lock is controlled to be unlocked. According to the invention, through a palm double-sided vein recognition mechanism, unlocking is carried out only when the comparison of double characteristics is passed, so that the recognition safety of the intelligent door lock is improved.

A biometric recognition device for palm prints and palm veins includes: a light source being used to emit illuminating beams in a near-infrared band; a polarizing unit being used to convert the illuminating beams to polarized beams which are emitted to a palm; an imaging unit receiving retroreflected beams from a palm and being used to converge the retroreflected beams to a focal plane; a polarizing beam splitter forming transmitted beams and reflected beams based on different polarization directions of beams from the imaging unit, wherein the transmitted beams propagate after pass through the polarizing beam splitter, and the reflected beams propagate after reflected by the polarizing beam splitter. An identity authentication method is further provided. Based on the non-contact technical solution, only one light source is used to obtain the palm print images and palm vein images at the same time and in the same space.

The invention discloses a palm biological feature fusion recognition method and device, a storage medium and equipment, and belongs to the field of biological feature recognition. According to the method, the characteristic that the distribution positions of the palm print main line and the palm vein blood vessels are relatively fixed is utilized, the intersection points of the palm print main line and the palm vein blood vessels serve as the feature points, the feature point set used for registration and recognition is constructed, feature-level fusion of the palm prints and the palm veins is achieved, and comparison is conducted through the fused feature point set, so that the registration accuracy is improved. Therefore, palm biological feature fusion recognition is realized. According to the method, the advantages that the palmprint principal line for palmprint recognition is thicker, obvious and stable in feature and not prone to interference compared with other features, the blood vessel near-infrared imaging for palmprint vein recognition is hidden and not prone to interference, and the advantages of correlation and dependence of relative position distribution of palmprint and palmprint vein are combined, so that the accuracy of palmprint and palmprint vein recognition is improved, and the accuracy of palmprint and palmprint vein recognition is improved. The recognition precision and the recognition reliability of biological characteristics are greatly improved, and accurate recognition of palm prints and palm veins is achieved.

The invention discloses a palm vein recognition method and system based on multispectral imaging and deep learning and a storage medium, and relates to the field of biological feature recognition, and the method comprises the steps: obtaining the multi-dimensional information of a palm through the synchronous collection of near-infrared, short-wave infrared and visible light wave band images, and then carrying out the adaptive weighted fusion and enhancement processing of a multispectral image, thereby achieving the recognition of the palm vein. In the core recognition step, a double-branch deep learning model is adopted, one branch extracts static structure features from the vein feature map, the other branch analyzes blood flow dynamic features from a time sequence image, and finally the static structure features and the blood flow dynamic features are fused for integrated living body detection and identity recognition. Through three-dimensional vein texture modeling and a dynamic living body detection anti-counterfeiting mechanism, faking attacks of photos, silica gel molds and the like are completely eradicated, and the problems that in a complex environment, performance of a traditional method is reduced, faking attacks are likely to happen, and speed and precision are difficult to consider at the same time are effectively solved.

The utility model discloses a novel intelligent lock structure which comprises a lock body and a lock cylinder arranged in the lock body, a main control circuit board is arranged in the lock body, and an unlocking induction area is arranged on the lock body. The main control circuit board is provided with a processor, and a palm vein recognizer, a face recognizer, a fingerprint recognizer, a password input device, a magnetic card recognizer, a mobile phone APP remote unlocking networking module, a remote temporary password receiver, a mobile phone NFC unlocking communicator and a real-time monitor which are connected with the processor; the lock body is provided with a key unlocking channel connected with the lock cylinder and an alarm connected with the processor. The door lock is reasonable in structural arrangement, the functions of the door lock are diversified, one or more structures can be selected for unlocking operation according to needs, remote unlocking control can be achieved, unlocking convenience and effectiveness are improved, use safety of the door lock can be improved, use requirements of different conditions can be met, and the door lock is worthy of popularization and application. And the applicability and the practicability are high.

The application discloses a palm vein recognition method and device, equipment and storage medium, the method comprises: through the camera shoots palm image, and through the palm detection model of pre-training from palm image identifies first palm area;In the case where the target brightness value of the first palm area does not satisfy the preset brightness range, the exposure of the camera is adjusted according to the target brightness value, and the next palm image is shot by the camera;In the case where the target brightness value of the first palm area satisfies the preset brightness range, the second palm area is identified from the palm image;Palm vein features are extracted from the second palm area to determine the corresponding identity information according to the palm vein features. Through the above technical means, the palm area in the palm image is detected, the camera exposure is adjusted according to the brightness value of the palm area, so that the palm image with appropriate brightness is quickly collected for palm vein recognition, the recognition efficiency is improved, and the problem that the palm vein recognition in the prior art takes a long time is solved.

1. The name of the design product: palm vein identification terminal (HF-MP51). 2. The use of the design product: the design product is used for the identification of identity information. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: front view.

The invention discloses a periscopic palm vein recognition method and an intelligent door lock, and the method comprises the steps: when a palm is placed in an area of a glass panel, a near-infrared light source emits infrared rays to the palm of a user; the reflecting mirror intensively guides infrared rays reflected by the palm to the imaging lens group; the imaging lens group optimizes the infrared light signal to obtain an optimized infrared light signal, and focuses the optimized infrared light signal to the image sensor; the image sensor converts the optimized infrared light signal into a digital image signal and sends the digital image signal to the control processing unit; and the control processing unit converts the digital image signal into a palm vein dark fringe image, extracts a palm vein feature value from the palm vein dark fringe image, and controls unlocking if the palm vein feature value exists in the memory. Through the periscopic optical structure design, ultra-short-distance high-quality palm vein imaging is achieved, a user does not need to adjust the hand position and distance deliberately, identity recognition can be completed only by naturally holding the door handle, operation is convenient, and the recognition success rate is high.

This invention discloses a palm vein recognition method based on a domain adaptation strategy, relating to the fields of biometrics, identity authentication, and palm recognition. The method includes: Step 1: Constructing a dataset, including a source dataset and a target dataset. All data from the source dataset and a portion of the target dataset are used as the initial training set, and the remaining data from the target dataset are used as the initial test set. ROI extraction is then performed, and the initial training set is split into a formal training set, and the initial test set is split into a formal test set. Step 2: Designing an adversarial domain adaptation network. Step 3: Pre-training on the source dataset to enable the classification module to achieve a pre-defined classification performance on the source dataset. Step 4: Performing adversarial training on the formal training set to enable the palm feature extraction module to learn domain-invariant features. Training ends when the preset number of iterations or model threshold is reached. Step 5: Testing using the formal test set.

The present invention relates to a miniaturized vein recognition module and a B-pillar trim panel integrated with same. The miniaturized vein recognition module comprises a camera module, a controller module and a micro switch module. The controller module comprises a PCBA, an MCU component, an SOC component and an RGB lamp being integrated onto the PCBA. The micro switch module is pressed by a hand to wake up and power on the vein recognition module. The camera module recognizes and collects palm vein feature information and transmits same to the controller module. The SOC component inside the controller module executes vein extraction, enhancement and feature comparison and the MCU component transmits a vein recognition result to an in-vehicle infotainment system, so that an in-vehicle infotainment center console gives feedback to lock and unlock vehicle doors. The present invention eliminates an original module housing structure, so that a required trim panel interior space size is relatively small, thereby better satisfying requirements for miniaturized B-pillar trim panels of framed and frameless vehicle doors.

The invention provides a non-inductive unlocking device and method for a shared vehicle based on palm vein recognition. The non-inductive unlocking device comprises an induction detection module, an image acquisition module, an algorithm control module and a communication module, the induction detection module is used for outputting a wake-up signal to the algorithm control module when determining that the front object is a human body target and determining that the distance between the human body target and the vehicle is smaller than a preset distance threshold value; the algorithm control module controls the image acquisition module to acquire a palm vein image of a human body target, and performs feature extraction on the palm vein image to obtain palm vein feature data; and the communication module is used for transmitting the palm vein feature data to the central control equipment, so that the central control equipment transmits the palm vein feature data to a background server for verification and unlocking. A tedious multi-process unlocking operation is simplified into a vehicle approaching-hand stretching identification operation mode. The time consumed from the time when the user gets close to the vehicle to the time when the unlocking succeeds is shortened, non-inductive rapid unlocking is achieved, and the unlocking efficiency of the vehicle is improved.

The invention discloses a palm vein feature fusion recognition method based on deep learning, and the method specifically comprises the steps: carrying out the preprocessing of a palm vein image, and forming a training set and a test set; a G-DenseNet deep learning network model is designed, a Softmax classification layer is removed, a G-deep feature extraction network model is formed, feature extraction is carried out on palm center and big thenar vein images in a training set, and feature vectors are connected in series and fused to form fused feature vectors of a sample library; performing feature extraction on the two types of images in the test set by adopting a G-depth feature extraction network model, and performing series fusion on feature vectors to form a feature fusion vector to be identified; and performing classification identification on the feature fusion vector to be identified and the fusion feature vector of the sample library through the SMV classifier, and outputting a matching result. The recognition method solves the problems that an existing method is limited in recognition rate and poor in robustness, and is suitable for palm vein recognition with high-precision and light-weight requirements.

The invention relates to a method for rapidly extracting palm vein information from a palm print image, and belongs to the technical field of vein recognition and information security, and the method comprises the following steps: collecting the palm print image through a mobile terminal, converting the palm print image into an RGB data format, and then carrying out adaptive adjustment; carrying out filtering processing on the RGB three-channel image of the palmprint image after adaptive adjustment; extracting palmprint features, and performing feature fusion by using the palmprint features of the palmprint image in the R, G and B channels to obtain palmprint fusion features in the palmprint image; the palm vein information is extracted based on the palm print fusion features in the palm print image, the palm vein technology can be directly applied to the mobile terminal equipment, the similarity between the palm vein image and the palm vein image collected by a professional palm vein image collector is larger than 99%, the palm vein information is quite accurate, the accuracy of identity recognition is improved, and the user experience is improved. And the false identification rate is reduced.

1. Name of the product in this design: Fingerprint Password Lock (with Face and Palm Vein). 2. Purpose of this design: This design is used for electronic locks installed on cabinet doors. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

The application relates to the technical field of biometric image recognition, and discloses an image fusion recognition method, device, medium and equipment based on an ultralight network, the method comprising the following steps: adopting an improved Co3Net network module to perform feature extraction on inputted multi-modal images to obtain multi-scale features; adopting an ultralight network module to perform feature extraction on the inputted multi-scale features to obtain global features; adopting a self-attention mechanism module to draw a self-attention graph according to the inputted global features; adopting a forward propagation unit to perform forward propagation on the self-attention graph to obtain final forward propagation output; and adopting a classifier to obtain a multi-modal image classification label according to the final forward propagation output. The application can reduce the calculation complexity and parameter quantity of a palm print and palm vein recognition method, and solves the problem that the method is difficult to efficiently run on resource-limited embedded devices and mobile terminals.

The invention discloses a palm plane image acquisition method and device, electronic equipment and a medium, and relates to the technical field of image acquisition, and the method comprises the steps: obtaining a plurality of distance parameters between a palm plane and a camera, and determining a comprehensive distance value of the palm plane relative to the camera according to the plurality of distance parameters; determining a light supplementing strategy of the palm plane according to the comprehensive distance value; acquiring a palm plane image shot by the camera under the light supplementing strategy and a quality parameter of the palm plane image; and when the quality parameter of the palm plane image is smaller than a preset quality parameter, adjusting a shutter parameter of the camera, so that the quality parameter of the palm plane image is greater than or equal to the preset quality parameter. By adopting the method, the light supplement strategy can be adaptively adjusted under different conditions to obtain a palm plane image with uniform brightness and clear details, so that the imaging quality and recognition accuracy of palm vein features and palm print features are improved.

The embodiment of the invention relates to the technical field of biological recognition, and discloses a palm print and palm vein bimodal recognition method and electronic equipment. According to the method, the quality weighted fusion is performed on the plurality of palm print images of the same palm, the fused palm print feature vector with higher robustness is generated, and the process can adaptively improve the contribution of the high-quality image and suppress the interference of the low-quality image; synchronously acquiring corresponding palm vein images and extracting feature vectors of the palm vein images; and a progressive identification strategy is adopted, rapid preliminary screening is performed by using the fused palmprint features so as to reduce the identification range, and then a preliminary screening result is accurately authenticated in combination with the palmprint vein features with higher anti-falsification. According to the method, the quality sensitivity defect of palmprint recognition is effectively overcome through a quality adaptive fusion mechanism, the complementary advantage of bimodal is fully played, and the accuracy, stability and safety of identity recognition in a complex actual scene are remarkably improved.

The invention discloses an object recognition method and related equipment. The method comprises the following steps: acquiring a palm vein image and an image brightness perception model of a to-be-recognized object; performing feature extraction on the palm vein image to obtain vein feature information of the palm vein image; performing brightness sensing processing on the vein feature information through an image brightness sensing model to obtain vein brightness information; performing vein intensity detection on the palm vein image based on the vein brightness information; when it is detected that the vein intensity of the palm vein image does not meet a preset vein intensity condition, brightness adjustment processing is carried out on vein brightness information of the palm vein image, and target vein brightness information is obtained; adjusting the image brightness of the palm vein image according to the target vein brightness information to obtain a target palm vein image; and performing object recognition on the to-be-recognized object through the target palm vein image to obtain an object recognition result. According to the invention, the visibility of palm veins can be improved, so that the accuracy of object recognition is remarkably improved.

1. The name of the design product: palm vein identification module. 2. The use of the design product: biometric technology based on the distribution characteristics of human palm vein blood vessels for identity verification, efficient and safe identity verification and management of personnel. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: design 1 front view. 5. Design 1 is designated as the basic design.

The application provides a palm vein fold point detection method with adaptive noise suppression and coupled feature enhancement, acquires a palm vein image to be processed; inputs the palm vein image into a trained fold point detection network to obtain the number and position information of the palm vein fold points, and the fold point detection network comprises a cascaded shallow feature extraction module, an adaptive noise suppression module, a coupled feature enhancement module and a decoder. The method realizes the suppression of the background noise of the palm vein image through the adaptive noise suppression module, then enhances the spatial dependence relationship between channels through the coupled feature enhancement module to realize the strengthening of the position information, simultaneously increases the kernel size from bottom to top through the pyramid structure and reduces the kernel depth through grouped convolution, realizes the capture of multi-scale information, and thus realizes the effective and accurate detection of the number and position of the fold points in the palm vein image.

The invention provides a biological feature authentication method and system based on category awareness, the system comprises a server and a client, after the client receives an authentication request, the client synchronously collects a to-be-authenticated palm vein image and a to-be-authenticated heart rate signal of a user, generates a multi-modal fusion feature, and sends the multi-modal fusion feature to the server; in combination with a local category distribution compensation prompt vector and the optimized discriminative activity prompt vector, constructing a target sequence, and inputting the target sequence into a multi-modal biological feature authentication model to obtain an authentication result of the user; wherein the category distribution compensation prompt vector is obtained by training a global distribution reference and a local multi-modal fusion feature sample, and the global distribution reference is generated by aggregating a plurality of client sample statistics by a server; the discriminative activity prompt vector is obtained by updating a global enhancement prompt vector issued by the client based on the server, and the global enhancement prompt vector is obtained by optimizing trained discriminative activity prompt vectors of a plurality of clients by the server. Therefore, a privacy-friendly authentication scheme adaptive to multiple scenes and multiple devices is realized.

The present application belongs to palm vein image quality evaluation method, in order to solve the technical problems that the hardware and software of non-contact authentication system in the existing palm vein biometric authentication system are relatively complex, and the existing authentication method does not consider ROI quality evaluation, provide palm vein image quality evaluation method, biometric authentication method, program product, adopt non-contact hardware device to obtain palm vein image, respectively using palm posture judgment model and palm ROI region target detection model, judge whether the collected palm vein image meets the requirements, and obtain palm vein image, then through ROI image quality evaluation model, the quality of the obtained ROI region is evaluated, the quality of palm vein image can be quickly and conveniently judged, the quality of the intercepted ROI image is evaluated before authentication, thereby improving the reliability of authentication.

This application discloses an identity verification method and system, belonging to the field of identity verification technology. The method includes: if the palm to be identified is detected to be within a preset recognition range, sending a first supplementary light command to a first supplementary light component and a second supplementary light component; sending a first image acquisition command to a first image acquisition device and a second image acquisition device; receiving a palm shape image and a palm print image sent by the first image acquisition device, and a palm vein image sent by the second image acquisition device; acquiring palm shape features, palm print features, and palm vein features corresponding to the palm to be identified based on the palm shape image, palm print image, and palm vein image, respectively; acquiring fusion features corresponding to the palm to be identified based on the palm shape features, palm print features, and palm vein features, and acquiring the identity recognition result corresponding to the palm to be identified based on the fusion features.