29 results about "Signature recognition" patented technology

The invention discloses a signature recognition method and device, a storage medium, electronic equipment and a product, and the method comprises the steps: carrying out the extraction of a signature region in a file through a detection sub-model, and obtaining a first image; performing enhancement processing on the first image by using the preprocessing sub-model to obtain a second image; and obtaining a target signature feature in the second image through the identification sub-model, and determining the similarity between the target signature feature and a preset signature feature in a database, so as to determine a target identification result of the signature region based on the similarity. By adopting the technical scheme, the problem that the signature detection and recognition precision cannot be effectively improved when a complex background and a low-quality image are processed is solved. And furthermore, through cooperative work of the detection sub-model, the enhancement sub-model and the identification sub-model, a signature region is accurately positioned from the document, the image quality is optimized, and signature features are compared and analyzed, so that the authenticity of the signature is efficiently judged.

Techniques for identifying vulnerabilities in binary files using a code signature are disclosed. In some embodiments, a system, a process, and / or a computer program product for identifying vulnerabilities in binary files using a code signature includes collecting a plurality of binary files associated with a vulnerability (e.g., a known vulnerability); determining a function in the plurality of binary files that includes the vulnerability; and automatically generating a code signature (e.g., including wildcarding one or more instructions of the function) for detecting the vulnerability in the plurality of binary files.

The invention belongs to the field of image recognition and processing, particularly relates to a handwritten signature set construction method and system based on a protocol and computer equipment, and aims to solve the problem of how to improve the construction efficiency of a handwritten signature data set. The method comprises the following steps: performing text content identification on a protocol image file to obtain a text region block, a position of the text region block, and characters and character positions in the text region block; extracting characters in the text region blocks and splicing the characters to obtain text content; identifying a printed name and a handwritten signature in the text content, and matching the printed name with the handwritten signature to obtain a name pair set; and traversing and verifying the name pair set to obtain a labeling result of the handwritten signature. According to the method, the whole process automation of handwritten signature recognition, verification and labeling is realized, and the efficiency and accuracy of handwritten signature set construction are improved.

A request of a VPN client to connect to a second set of one or more networks is received by a first VPN server associated with a first set of one or more networks. The request comprises an identifier of the VPN client, an attestation of an access control server that the VPN client complies with a compliance profile required to access the second set of one or more networks, and a digital signature of the access control server. The digital signature is validated using a public key of the access control server. One or more common networks each included in both the first and second sets of networks are identified. A firewall of the first VPN server is modified to permit the VPN client to connect to the one or more common networks.

A request of a VPN client to connect to a second set of one or more networks is received by a first VPN server associated with a first set of one or more networks. The request comprises an identifier of the VPN client, an attestation of an access control server that the VPN client complies with a compliance profile required to access the second set of one or more networks, and a digital signature of the access control server. The digital signature is validated using a public key of the access control server. One or more common networks each included in both the first and second sets of networks are identified. A firewall of the first VPN server is modified to permit the VPN client to connect to the one or more common networks.

The invention discloses a method for identifying a signature in an image, electronic equipment, a storage medium and a program product. The method comprises the following steps: carrying out feature extraction on a signature image to obtain signature features; obtaining a target signature feature successfully matched with the signature feature from a plurality of preset signature features in a preset signature database; a target signature rule corresponding to the target signature feature is determined from a preset rule base, and preset signature rules corresponding to a plurality of preset signature features are stored in the preset rule base; and identifying the signature feature based on the target signature rule to obtain an identification result of the signature image, the identification result being used for representing whether the signature image satisfies the target signature rule. According to the invention, the technical problem of low identification efficiency of the signature in the image in the prior art is solved.

The present disclosure provides systems and methods for authentication control of content delivery. The method includes receiving a request for a content item from a computing device, the request including a security token associated with the computing device and an identifier of a domain group, identifying the domain group from the identifier, and retrieving a security key associated with the domain group. The method also includes decrypting a signature of the security token, identifying an authentication string, determining that the authentication string matches a server authentication string, and identifying a characteristic of the security token. The characteristic of the security token includes a confidence score. The method further includes comparing the confidence score of the security token to a threshold, determining that the confidence score does not exceed the threshold, and preventing the content from being sent to the computing device.

A method can include identifying handwritten elements from a document image. The method can include generating embeddings for the handwritten elements, and the embeddings may represent features extracted from the handwritten elements. The method can include clustering the embeddings into clusters. The method can include processing the document image to identify areas within the document image designated for placement of a signature. The method can include, based upon locations of the areas within the document image, tagging each cluster as a signature cluster or as a non-signature cluster. The method can include outputting indications that a handwritten element is a signature element or is a non-signature element.

Embodiments of the present application provide a handwritten signature recognition method and device, electronic equipment and storage medium. The handwritten signature recognition method comprises: obtaining a handwritten signature picture to be recognized; performing single character detection on the handwritten signature picture to obtain position information of a target character region; merging target character regions that need to be merged based on the position information to obtain a merged character region; recognizing characters corresponding to each character region, the character region including the target character region that has not been merged and the merged character region; comparing the characters with a user name in user information, and determining that a handwritten signature in the handwritten signature picture is valid when the comparison result is consistent. The handwritten signature recognition method can improve the accuracy of handwritten signature recognition.

The invention discloses a contract signature identification method based on large and small model collaboration. The method comprises the following specific operation steps: converting an input electronic document into a picture format through a Python code; a label Img tool is used for labeling a signature area in the converted picture format, a training data set is constructed, and a YOLO11 model is trained; inputting the converted picture into the trained YOLO11 model, and extracting a signature image in the picture; the extracted signature image is processed by adopting a Hough circle and polar coordinate transformation technology, the signature image is leveled, and a new corrected signature image is generated; and inputting the original signature image and the corrected signature image into a Qwen2.5-VL-Instruct large model subjected to LoRA fine tuning together, identifying signature unit information, and outputting standardized and formatted results. The method has the beneficial effects that automatic identification of the signature in the document is realized, and the accuracy of signature positioning is improved; the output is more standardized and formatted, and the efficiency and reliability of signature unit identification are improved.

The invention discloses a signature identification method and device, a nonvolatile storage medium and electronic equipment. The method comprises the following steps: acquiring a to-be-detected image; for each signature in the to-be-detected image, the signature is split into a plurality of stroke units, and the stroke units are minimum units forming the signature; extracting handwriting features of each stroke unit, the handwriting features including geometric features and contour features; a handwriting recognition model is adopted to process and analyze the handwriting features, a plurality of matching probabilities are output, each matching probability corresponds to one target object, and the matching probabilities are used for indicating the probability that the signatures belong to the target objects; and determining the target object corresponding to the maximum matching probability in the plurality of matching probabilities as the affiliation object of the signature in the to-be-detected image. The technical problem of low accuracy of an identification result caused by neglecting detail information of a signature in a handwriting identification method in related technologies is solved.

Apparatus, systems, articles of manufacture, and methods to identify media using watermarks and signatures are disclosed. An example apparatus includes at least one memory, instructions, and processor circuitry to execute the instructions to: determine a first time and a category indicated by a watermark detected in the media, determine a search window based on the first time indicated by the watermark, the search window to at least one of (i) extend a first duration of time before the first time indicated by the watermark or (ii) extend a second duration of time after the first time indicated by the watermark, and compare (i) a query signature associated with a second time within the search window with (ii) a subset of reference signatures associated with the category to identify the media, the query signature generated from the media, the subset of reference signatures generated from reference media associated with the category.

The application provides a training method, a data processing method, equipment, a storage medium and a computer program product, which are applied to various information verification scenes such as cloud technology, artificial intelligence, intelligent transportation and vehicle-mounted devices; the method comprises the following steps: obtaining a training sample, wherein the training sample comprises a label image, a sample image, a signature label of the sample image, and a similarity label between the label image and the sample image; based on a to-be-trained model, the following processing is performed: extracting a first sample feature of the sample image and a second sample feature of the label image, performing signature identification based on the first sample feature to obtain signature identification information, and determining similarity prediction information based on the first sample feature and the second sample feature; combining the difference between the signature identification information and the signature label and the difference between the similarity prediction information and the similarity label, training the to-be-trained model, and obtaining a signature verification model. Through the application, the model training efficiency can be improved.

The embodiment of the invention provides a protocol feature code identification method and device for heterogeneous PLC (programmable logic controller) equipment, and the method comprises the steps: collecting response message samples of different programmable logic controller protocols, and constructing a feature rule library according to the response message samples, the feature rule library being used for storing structured protocol feature information; a detection strategy is intelligently selected according to a target port, customized detection messages are generated for different protocols based on the detection strategy, and the customized detection messages are sent to equipment through the target port; receiving a response message of equipment, and extracting a feature code fragment in the response message; and performing feature value matching according to the feature code fragment and the structured protocol feature information in the feature rule base, and outputting a corresponding programmable logic controller protocol when matching succeeds.

The application discloses an electronic signature verification method and device, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence. In the application, the identity of a person to be verified is identified in real-time video communication, and after the identity verification is passed, the identity document of the person to be verified is obtained from a document database, and the identity information on the identity document is obtained through OCR identification. In the process of real-time video communication, a handwritten signature image is identified through a handwritten signature recognition model to obtain the identity information on the handwritten signature image. Whether the electronic signature verification is passed is determined by comparing the identity information on the identity document with the identity information on the handwritten signature image. In addition, the application also relates to blockchain technology, and video image data can be stored in the blockchain. The application can ensure the continuity of video connection while completing handwritten signature verification, improve the processing timeliness, and avoid malicious impersonation and signature behavior.

Mechanisms are provided for executing a privacy preserving computing operation. Features are extracted from line(s) of an electronic communication. Trained machine learning (ML) computer model(s) process the extracted features and generate classification output(s) for the line(s). The ML computer models process the features and generate a classification output for each line which specifies, for corresponding lines, a corresponding classification of the corresponding line as to whether it is a signature line or non-signature line, based on patterns in the features. Each line is annotated with metadata specifying the corresponding classification of the line based on the classification output, to generate an annotated set of data. The privacy preserving computing operation is executed on the electronic communication based on the annotated set of data.

The application discloses a signature recognition technology based on rhythm characteristics, obtains sample signature discrete track points and verification signature discrete track points, adopts speed logarithmic segmentation to obtain sample signature strokes and corresponding verification signature strokes, calculates rhythm characteristics of the sample signature strokes and the corresponding verification signature strokes, carries out distance measurement according to the rhythm characteristics to obtain total rhythm characteristic distance, and thus determines whether the verification signature is a signature of the signer or a copied signature. The application proposes rhythm characteristics with strokes as basic granularity, does not depend on a large amount of training data, is not limited to any language, character or handwriting form, processes any type of signal wave, satisfies translation stretching, rotation and sampling mode invariance of signature track based on a more scientific and reasonable normalization mode and measurement mode, supports cross-device verification, and can efficiently and accurately distinguish between copying and imitation.

The invention provides a signature recognition method based on a CNN-GNN fusion model, which combines a convolutional neural network and a graph neural network, can efficiently extract low-level semantic information such as color, texture and edge of a signature by utilizing the local spatial features of the convolutional neural network which is good at capturing an image, and improves the recognition accuracy of the signature. And then message passing and aggregation are carried out on the graph structure by using the graph neural network, so that the signature identification accuracy can be effectively improved, the robustness is good, the defects existing in traditional manual processing are effectively avoided, and the adaptability is high.

Disclosed embodiments relate to systems and methods for securing kernel-level system functions and validating kernel-level verification of signed binaries. Techniques include identifying, by a system patched by a kernel module, a file signed by a user; receiving, by the kernel module, a second key from the user; and validating the signature embedded in the file, by identifying the file; determining whether the signature is embedded in the file; and validating that the signature corresponds to the second key.

This application discloses a writing pen, a signature recognition method, and a system thereof. The non-writing end of the writing pen is equipped with a motion sensing device. When the writing pen writes on a planar writing trajectory generating device, the motion trajectory of the non-writing end is recorded. By comparing the motion trajectory and / or the planar writing trajectory, it is determined that the signature comes from a specific person.

The invention relates to the technical field of electronic contract management, in particular to a contract automatic full-link management method and system. The method comprises the following steps: inputting a storage address rule, a storage path rule and a delay pull time rule of an electronic contract of a current loan institution, and constructing a pull rule base; the big data platform matches and counts the difference between the electronic contract information and the loan order information; performing compensation pulling on the missing electronic contract according to the missing electronic contract details and the pulling rule base; the electronic contract is retrieved according to the missing electronic contract details and the pulling rule base, electronic contract information is read through the AI technology, and whether the electronic contract is valid or not is verified through the signature recognition technology. The invention provides an automatic full-link contract management method based on rule configuration, big data statistics and artificial intelligence recognition. Closed-loop management of unified pulling, missing recognition, automatic compensation and compliance verification of multi-mechanism electronic contracts is realized.

Apparatus, systems, articles of manufacture, and methods to identify media using watermarks and signatures are disclosed. An example apparatus includes at least one memory, instructions, and processor circuitry to execute the instructions to: determine a first time and a category indicated by a watermark detected in the media, determine a search window based on the first time indicated by the watermark, the search window to at least one of (i) extend a first duration of time before the first time indicated by the watermark or (ii) extend a second duration of time after the first time indicated by the watermark, and compare (i) a query signature associated with a second time within the search window with (ii) a subset of reference signatures associated with the category to identify the media, the query signature generated from the media, the subset of reference signatures generated from reference media associated with the category.

A method can include identifying handwritten elements from a document image. The method can include generating embeddings for the handwritten elements, and the embeddings may represent features extracted from the handwritten elements. The method can include clustering the embeddings into clusters. The method can include processing the document image to identify areas within the document image designated for placement of a signature. The method can include, based upon locations of the areas within the document image, tagging each cluster as a signature cluster or as a non-signature cluster. The method can include outputting indications that a handwritten element is a signature element or is a non-signature element.

The application provides an Internet-based multi-party signature electronic payment method and system, comprising: obtaining historical signature data, analyzing signature behavior statistical characteristics by using a machine learning algorithm, obtaining signature anomaly judgment quantitative standards, determining abnormal threshold values of signature duration, stroke number, pressure change and timestamp characteristics; according to the signature anomaly judgment quantitative standards, obtaining signature trajectory, speed and timestamp multidimensional characteristics, comprehensively analyzing the multidimensional characteristics by using a deep learning technology, obtaining an abnormal signature recognition accuracy; according to the abnormal signature recognition accuracy, establishing a signature behavior risk assessment model, quantifying the risk degree of signature behavior, obtaining a signature intervention strategy decision basis; if the difference between the signature timestamps exceeds a preset threshold value, triggering a signature delay anomaly warning, and starting a signature intervention measure.

The invention relates to the technical field of industrial automatic detection, and discloses a three-dimensional volume laser scanning and cloud computing processing method for a special-shaped metal can, and the method comprises the steps: firstly, synchronously collecting multi-source data such as diffuse reflection and mirror reflection image sequences; then, constructing a basic point cloud by using diffuse reflection data, resolving a surface normal vector of a data cavity region by using mirror reflection information, and fusing the basic point cloud and the surface normal vector to reconstruct a complete external point cloud; thirdly, recognizing a surface material through a polarization response signature, matching the surface material with a wall thickness priori model, and then adaptively planning key points to carry out physical thickness measurement to obtain a sparse wall thickness data set; and finally, performing interpolation on sparse data in combination with a prior model, establishing a continuous wall thickness function, calculating an internal point cloud and finally obtaining an accurate internal volume. According to the method, the problem of high-reflection surface measurement is solved, efficient and accurate modeling of the non-uniform wall thickness is achieved, and the accuracy and reliability of volume calculation of the special-shaped metal tank are remarkably improved.

Obtaining data from a plurality of first network components in a network. The data includes at least one detectable signature characterizing presence of at least one second network component that is incompatible with a modification of the network. Classify the obtained data to identify the at least one detectable signature. Identify the at least one second network component implicated by the classification results. Facilitate mitigation of the at least one second network component.

Systems and methods are disclosed herein for identifying users based on voice data and media consumption data. A media guidance application may generate a voice signature from the user's input and based on that signature identify some demographic characteristics of the user (e.g., age, gender. and other suitable characteristics). The media guidance application may retrieve user data for users that are associated with a household of the user and attempt to identify which of the users spoke the command. If multiple users are identified, based on the demographic characteristics. the media guidance application may use the content of the voice command (e.g., a type of media requested) to identify the user.