238 results about "Palm print" patented technology

Embodiments of this application disclose a palm print recognition method, a method for training a feature extraction model, a device, and a storage medium, and belong to the field of computer technologies. The method includes: obtaining sample hand images for each of a plurality of sample user identifiers, at least two of the sample hand images associated with the each of the plurality of sample user identifier being acquired from image acquisition devices having different image acquisition characteristics; calling a feature extraction model to extract sample palm print features of the plurality of sample user identifiers; and adjusting the feature extraction model according to the sample palm print features of the plurality of sample user identifiers.

Disclosed in the present invention are a palmprint recognition method and apparatus, which relate to the technical field of palmprint recognition authentication, and solve the problem of low palmprint recognition accuracy caused by incapability of correcting palm postures in the prior art. The palmprint recognition method comprises: acquiring a palm image to be recognized; performing key point detection on the palm image on the basis of a preset first key point detection method, so as to obtain a first palm key point set; constructing an affine transformation matrix on the basis of the first palm key point set; on the basis of the first palm key point set and the affine transformation matrix, performing alignment and extraction on the palm image by means of a preset alignment and extraction method, so as to obtain first palmprint information, the first palmprint information comprising a palmprint attention region and a palm key point set; and inputting the first palmprint information and pre-stored second palmprint information into a preset first recognition model, and outputting a recognition result. The present invention can align palm images and correct palm postures, and can refine the granularity of palmprint features, thus improving the precision and accuracy of palmprint recognition.

The invention discloses a palm image recognition method and system based on fusion of a convolutional neural network and an image neural network, and belongs to the technical field of crossing of biological feature recognition and artificial intelligence. The problems that in the prior art, local texture features and a global topological relation are separated, dynamic scene adaptability is poor, and multi-modal features are not fully fused are solved. The method comprises the following steps: 1) designing a dual-path hybrid network architecture (DPHGCN), extracting multi-scale local texture features through a lightweight CNN, constructing an adaptive graph structure by using a dynamic graph generator (DGG), and modeling a topological relation between key points in combination with a graph attention network; 2) developing a cross-modal feature alignment module (GIPL), and realizing dimension mapping and semantic alignment of CNN feature graph and graph node embedding; and 3) providing a layered attention fusion mechanism, and combining space attention, topological attention and cross-modal attention to dynamically weight and fuse heterogeneous features. According to the method, 98.7% of recognition accuracy is achieved on a public data set, the reasoning speed reaches 32 ms / frame, 76.2% of robustness is still kept in a 50% shielding scene, and the method can be widely applied to the fields of financial payment identity authentication, medical palmprint pathological analysis, real-time security verification and the like.

The invention relates to the technical field of palmprint recognition, and discloses a palmprint recognition method based on multi-feature fusion, and the method comprises the steps: collecting a palmprint image, carrying out the preprocessing of the palmprint image, and generating a palmprint ROI image; extracting a multi-scale feature vector of the palmprint ROI image and a histogram feature vector of the palmprint image; splicing the multi-scale feature vector and the histogram feature vector to generate a target feature vector; and calculating the similarity between the target feature vector and the feature vector of the palmprint in a preset database, and outputting a palmprint recognition result according to the similarity. A hierarchical multi-scale filtering mechanism is utilized to process features of different scales layer by layer, and rich texture features are effectively captured; the importance of different scale features is dynamically adjusted by using a multi-scale channel attention mechanism, so that the network pays more attention to feature information beneficial to a recognition task; the histogram features are extracted and fused with the multi-scale features, so that the recognition result is more effective, the accuracy of the recognition result is improved, and the robustness of the recognition result is enhanced.

The invention provides a low-carbon intelligent safety roof system based on multi-information interaction, and the system comprises a roof integrated control module which achieves the integrated control based on an automobile roof structure. The layered structure is adopted, structures with different functions are mounted and integrated in a layered mode, the multifunctionality of an automobile roof is improved, sunroof palm print / gesture unlocking is adopted, a sunroof can be rapidly opened for escape in an emergency, CO2 / smoke concentration, temperature and infrared thermal imaging recognition in an automobile and accumulated water liquid level height are monitored in real time, and the safety of the automobile is improved. Through opening and closing of a roof skylight, an in-vehicle air conditioner, in-vehicle spraying and air exhaust ventilation, various problems of harming life and property safety during running or stopping of various automobiles are effectively avoided, and roof integrated control independent of an automobile console and low-carbon and environment-friendly manufacturing materials are adopted. Intellectualization, safety and low carbon of the roof are achieved through multi-information interaction, the limitation of single function design of a traditional roof system is broken through, and multifunctionality of the automobile roof is achieved.

The invention relates to the technical field of biological feature image recognition, and discloses an image fusion recognition method and device based on an ultra-light network, a medium and equipment, and the method comprises the steps: carrying out the feature extraction of an input multi-modal image through employing an improved Co3Net network module, and obtaining a multi-scale feature; carrying out feature extraction on the input multi-scale features by adopting an ultra-light network module to obtain global features; a self-attention mechanism module is adopted to obtain a self-attention map according to the input global features; performing forward propagation on the self-attention map by adopting a forward propagation unit 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. By applying the method, the calculation complexity and parameter quantity of the palm print and palm vein recognition method can be reduced, and the problem that the method is difficult to operate efficiently on embedded equipment and mobile terminals with limited resources is solved.

The utility model relates to the technical field of intelligent locks, and discloses an intelligent lock handle and an intelligent lock, the intelligent lock handle is suitable for driving the intelligent lock to open, and the intelligent lock handle comprises a holding rod for a user to hold a sliding door; the palmprint recognition sensor is embedded in the circumferential surface of the holding rod and is suitable for acquiring palmprint information of a user and generating control information according to a comparison result of the acquired palmprint information of the user and preset palmprint information; the controller is electrically connected with the palmprint recognition sensor and suitable for controlling the intelligent lock according to control information generated by the palmprint recognition sensor, a user can directly open a door after holding the holding rod with the hand to complete palmprint recognition, recognition action and door opening action are combined into a whole, and the whole door opening process is simplified.

The invention discloses a highly convenient and safe palm lock, which comprises a lock body, a palm print acquisition module, a palm vein acquisition module, an iris recognition module, a control unit and a mechanical execution unit, and is characterized in that the palm print acquisition module is used for acquiring palm surface texture features and comprises an optical imaging unit and an infrared light supplement lamp; the palm vein acquisition module is used for acquiring vein blood vessel distribution characteristics in a palm and comprises a near-infrared light source and an infrared sensor; the iris recognition module is used for obtaining human eye iris texture features. Therefore, single-feature quick unlocking (convenience) and multi-feature combined verification (high safety) are supported, a user can dynamically configure a verification mode through a mobile phone APP to adapt to different scene requirements (such as household daily palmprint and office palmprint + iris), the three biological features are independently collected, the forging difficulty is high, the combined verification safety is high, and the verification efficiency is high. The palm fitting area is designed to be arc-shaped and aligned with the camera, and the identification time is less than or equal to 2 seconds.

A sample palm print image generation method includes generating a major palm print line according to a preset major palm print line distribution pattern, determining a palm print distribution region in which the major palm print line is located, generating a minor palm print line in the palm print distribution region based on a preset minor palm print line distribution pattern, generating a candidate palm print image based at least on the major palm print line and the minor palm print line, labeling the candidate palm print image with a candidate image label that represents a palm print distribution of the candidate palm print image including at least one of a major palm print line distribution or a minor palm print line distribution, and inputting the candidate palm print image to a palm print generation model to obtain a sample palm print image.

1. Name of the Design Product: Dynamic Graphical User Interface for Identifying the Status of an Electronic Device. 2. Use of the Design Product: An electronic device. 3. Design Key Points of the Design Product: Lies in the graphical user interface. 4. Picture or Photograph that Best Illustrates the Design Key Points: The front view of Design 1. 5. For planar products, other views are omitted. 6. Use of the Graphical User Interface: Used to dynamically display the identification status of the device so that users can understand that the device is currently identifying the input biometric features (such as face, fingerprint or palmprint). 7. Human-Computer Interaction Method of the Graphical User Interface: Users can click on the controls in the interface or slide to perform operations. For example, click on the "Password Unlock" control or the "AI Recognition" control in the front view. 8. Design 1 is designated as the basic design.

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 relates to a palm image acquisition method, system and device. The method comprises the following steps: acquiring the distance between a palm and palm image acquisition equipment; under the condition that the distance is within a preset range, acquiring the light intensity of the environment where the palm image acquisition equipment is located; according to the distance and the light intensity, setting a brightness value of the light supplement lamp; indicating palm image acquisition equipment to acquire an image of the palm; calculating the image quality of the image; and outputting the image under the condition that the image quality meets a preset image quality standard value. According to the scheme, on one hand, the mode of adjusting the brightness of the light supplementing lamp is adopted, and compared with adjustment of an image sensor, the adjustment speed is high, control links are few, and logic is simple; and on the other hand, when the palm print image and / or the palm vein image of the palm are / is collected, environmental factors such as the palm distance, infrared light and visible light are considered, the problems of too dark or too bright images, noise and the like can be effectively avoided, and the image quality is improved.

The invention relates to the technical field of image fusion and classification, and discloses a multi-modal image fusion recognition method and device, a medium and equipment. The method comprises the following steps: acquiring different types of multi-modal images; performing shallow feature extraction on the multi-modal image by using a convolutional layer, and performing feature fusion to obtain shallow fusion features; performing global feature extraction on the shallow fusion features to obtain global features; performing feature fusion on the shallow fusion features and the global features to obtain deep fusion features; performing local feature extraction on the deep fusion features to obtain local features; and performing full connection processing on the local features, and identifying to obtain a category label of the multi-modal image. By applying the method, fusion identification of the palm print and palm vein multi-mode images can be realized, and the identification accuracy and the equal error rate on a public data set and an incomplete data set are improved.

The present invention relates to an artificial intelligence Four Pillars of Destiny (Bazi) fortune-telling apparatus and method, a recording medium containing a computer program capable of executing this method, an artificial intelligence Four Pillars of Destiny fortune-telling service system and method using the same, more specifically, to an apparatus and method that improves the accuracy of Four Pillars of Destiny fortune-telling by utilizing artificial intelligence (AI) machine learning, deep learning, and large language models (LLM) to analyze past Four Pillars of Destiny readings, thereby enabling users to improve their understanding of their own Four Pillars of Destiny fortune-telling, a recording medium containing a computer program, and a service system and method using the same. An artificial intelligence-based Four Pillars of Destiny (Bazi) analysis device according to an embodiment of the present invention is characterized in that, in response to input Four Pillars of Destiny information, a computing device including at least a processor outputs Four Pillars of Destiny analysis data through Four Pillars of Destiny analysis and analysis, and in order to improve the accuracy of Four Pillars of Destiny analysis, the data analyzed based on answers (question and answer) obtained through a multi-stage questioning process, is comprehensively analyzed (descriptive statistics and inference statistics) by combining physiognomy (image), palm lines - palmistry (image), voice / voice physiognomy (voice) data and the Four Pillars of Destiny of people with similar Four Pillars of Destiny, and then utilizes artificial intelligence (machine learning and deep learning, etc.).

Certain biometric authentication and verification methods use multiple biometric modalities of a given user in order to enhance their security. Circumvention of such methods sometimes involves presenting multiple biometrics as if they come from a single user when, in fact, they arise from more than one person. To thwart such attacks, it is necessary to bind multiple biometric modalities to each other. One binding method captures physiological signals of a user, such as pulse rate, in conjunction with the capture of each biometric. When the physiological signals associated with each of the biometric modalities match, the biometrics are bound. Another binding method captures an intermediate biometric when capturing each of the multiple biometric modalities. When the intermediate biometrics match, the multiple biometric modalities are bound. For example, for face and finger biometrics, a palm intermediate biometric may be used.

1. Name of the design product: Palmprint recognition device. 2. Use of the design product: It can identify human palm information, perform identity recognition and information acquisition, and is used in fields such as payment and access control identity recognition. 3. Design key points of the design product: lies in the shape. 4. Picture or photo that best shows the design key points: Stereogram 1.

1. The name of the design product: the terminal device of the ladder control. 2. The use of the design product: used in the elevator, identify face, palm print, two-dimensional code, IC card access permission and display relevant state information. 3. The design points of the design product: in shape. 4. The picture or photo that can best show the design points: front view.

The embodiment of the disclosure provides a controllable palmprint sample generation method based on a stochastic differential equation; it relates to the field of computer vision. The method comprises constructing an unconditional diffusion model network architecture and defining a forward process and a reverse process; training an unconditional diffusion model according to the forward process and a palmprint image to obtain a noise image; according to the reverse process, the trained unconditional diffusion model is used for sampling the noise image to generate an unconditional palmprint sample; a conditional encoder is introduced into the trained unconditional diffusion model; the weights of the unconditional diffusion model are frozen, and the conditional encoder is trained according to a conditional image; when the conditional encoder loss function converges, the frozen weights are unlocked, and the unconditional diffusion model introduced with the conditional encoder is trained according to the forward process, the palmprint image and the conditional image; according to the reverse process, the trained unconditional diffusion model with the conditional encoder is used for sampling to generate a conditional palmprint sample. Thus, the palmprint sample authenticity, diversity and controllability are improved.

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.

1. The name of this design product: Palmprint recognition device. 2. Application of this product design: It can recognize human palm information, perform identity recognition and information acquisition, and is used in payment, access control and identity recognition and other fields. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: Stereoscopic drawing 1.

The present invention improves and perfects a newborn's palm print collection device and a database construction method, adopts an improved palm print detection film to achieve contact-type palm print collection and archiving of physical materials; ensures the effectiveness of non-contact collection through multiple means such as three-dimensional ranging, visual guidance, and feature object matching; improves collection accuracy by directly comparing a palm print-transferred film obtained during the contact-type palm print collection process with an image obtained during the non-contact palm print collection process; improves efficiency and accuracy by optimizing image processing and feature vector extraction algorithms; contact-type palm print collection and foot 3D molding are used to assist in improving the reliability of palm print collection, and their by-products can be directly archived or kept as a souvenir.

The utility model discloses an access control all-in-one machine based on face and palmprint recognition, which relates to the technical field of face and palmprint recognition and comprises a shell, a lifting mechanism is arranged at the bottom of the shell and comprises a support, the support is fixedly connected to the bottom of the shell, a motor is fixedly connected to the inner side of the support, and the motor is fixedly connected to the bottom of the shell. An output shaft of the motor is fixedly connected with a rotating shaft through a coupler, the bottom end of the rotating shaft is fixedly connected with a ball screw, and the outer wall of the ball screw is movably connected with a ball nut. Through the arrangement of the lifting mechanism, the function of adjusting the height of the first display screen according to the height of a user can be achieved, in the using process, the motor is started to drive the first display screen to ascend and descend to the proper height, and the situation that the height cannot be adjusted according to the height of the user is avoided. And therefore, the application range and the flexibility of the access control all-in-one machine are ensured.

The invention relates to the technical field of data processing, in particular to an article deposit management system based on the Internet of Things, which comprises a data acquisition module, an authentication deposit module, a deposit space distribution module and a deposit environment sensing module. The system manages the locker subsequently, authenticates the identity of the user through the authentication and storage module, realizes high-precision identification according to double authentication of the iris and palmprint of the user, and adjusts the double authentication through environment information to realize high-precision identification. The storage space of the storage cabinet is intelligently distributed through the storage space distribution module, the distribution of the storage cabinet space is precisely corrected through the storage environment sensing module, the situation that the storage space is unreasonably utilized is avoided, it is guaranteed that a user obtains a proper storage environment for storing articles, and reasonable distribution of the storage space is achieved.

1. The name of the design product: palmprint identification device. 2. The use of the design product: can identify the palm information of human body, carry out identity recognition and information acquisition, and be used in the fields of payment, access control identity recognition, etc. 3. The design points of the design product: in shape. 4. The picture or photo best indicating the design points: perspective view 1.

1. The name of the design product: palmprint identification device. 2. The use of the design product: can identify the palm information of human body, carry out identity recognition and information acquisition, and be used in the fields of payment, access control identity recognition, etc. 3. The design points of the design product: in shape. 4. The picture or photo best indicating the design points: perspective view 1.

This application provides a method for determining an artificial palm print generation model performed by a computer device. The method includes: performing data augmentation on a first real palm print image of a first user to obtain a data-augmented first real palm print image; obtaining a first artificial palm print image corresponding to the first user using a deep learning model using the data-augmented first real palm print image and a first identity control curve of the first user; adjusting, when a degree of similarity between the data-augmented first artificial palm print image and the data-augmented first real palm print image is not less than a preset similarity threshold, parameters of the deep learning model; and determining, when the degree of similarity thereof is less than the similarity threshold, the deep learning model as the artificial palm print generation model.

1. The name of this design product: Palmprint recognition device. 2. Application of this product design: It can recognize human palm information, perform identity recognition and information acquisition, and is used in payment, access control and identity recognition and other fields. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: Stereoscopic drawing 1.

The application relates to a user identification method and device combining biological characteristics, and relates to the field of user identification data processing, which comprises the following steps: identifying a palmprint angle and an image angle, analyzing palmprint angle similarities of the palmprint angle and a plurality of historical palmprint angle sequences, and analyzing image angle similarities of the image angle and a plurality of historical image angle sequences; obtaining a plurality of amount fluctuation similarities, combining the plurality of palmprint angle similarities and the plurality of image angle similarities, compensating and adjusting a plurality of palmprint probabilities and a plurality of image probabilities, obtaining a plurality of user probabilities, and outputting a user with the maximum user probability as a user identification result. The application can solve the technical problems that the traditional user identification method has low adaptability in a complex environment, cannot effectively identify the identity of a user, and has insufficient identification accuracy and reliability; through multi-modal information fusion, the precision, accuracy and reliability of user identity identification in a complex environment can be significantly 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.