30results about How to "Reduce false recognition rate" patented technology

The invention discloses a multi-mode defect automatic classification method, device and equipment and a storage medium. The method comprises the following steps: acquiring a microscope image, an X-ray image and defect feature information data of a to-be-detected product; first classification processing is preferentially carried out based on the microscope image, when the first classification processing result meets a first preset reliability condition, the first classification processing result is taken as a final classification result, and when the first classification processing result does not meet the first preset reliability condition, the final classification result is taken as a final classification result. Performing feature fusion based on the X-ray image and the defect feature information data, and executing second classification processing; when the second classification processing result meets a second preset reliability condition, the second classification processing result serves as a final classification result, and when the second classification processing result does not meet the second preset reliability condition, defect type judgment is conducted based on key parameters in the defect feature information data, and the final classification result is output; the classification accuracy and efficiency can be improved, and the error recognition rate is reduced.

The present application relates to the technical field of sample pretreatment automation, and discloses a system of a full-automatic sampling tube cap screwing and pipetting workstation and a running method thereof.The system comprises a motion point definition module, a cap screwing adaptation identification module, a label scanning module, a pipetting planning and execution module, a cap screwing torque calling module and a real-time torque acquisition module.The system realizes continuous scanning and reliable identification of the cap profile in the motion state through a dynamic coordinate system and key motion points, dynamically calls matched torque parameters to execute cap screwing according to the identification result, and simultaneously acquires real-time torque data.The system synchronously completes sample label information analysis, pipetting path planning and pressure monitoring.The scheme realizes adaptive perception and closed-loop cap screwing control of the cap state, and improves the robustness of cap identification, the consistency of cap screwing action and the reliability of the overall process.

The present application relates to the technical field of face recognition, and particularly relates to a recognition method and system based on a dynamic face database, a computing device and a storage medium, comprising a face tracking server configured to acquire face information obtained by a channel camera and a regional camera, and to merge the face information obtained by the channel camera and the regional camera; a central face server configured to store face information left by a user when registering remotely, and to respectively identify face information collected by the face tracking server from the channel camera and the regional camera, and to send the identification results to a channel face server and a regional face server; the present application reduces the number of face databases by using face tracking and face recognition technology, forms a face server with multiple face databases, improves the recognition efficiency by accurately simplifying the face databases, and reduces the false recognition rate of face recognition.

The application discloses a portrait inspection and identification method based on gait cycle decomposition and multi-phase force analysis, and comprises the following steps: extracting the skeleton key points of a target object in a target object image set in a comparison video and the confidence score of each skeleton key point; extracting the features of the target object in the target object image set according to the skeleton key points of the target object, and obtaining the target object features, wherein the target object features comprise basic features, gait cycle features, gait stage features and gait parameter features; integrating the basic features, the gait cycle features and the gait stage features to obtain comprehensive features; respectively calculating the similarity of the target object features and the comprehensive features in the comparison video to obtain similarity calculation results and overall similarity calculation results; and obtaining the identity identification result of the target object according to the similarity calculation results and the overall similarity calculation results.

The invention discloses an API path aggregation identification method and device and a storage medium, and relates to the technical field of electronic digital data processing, and the method comprises the steps: carrying out the preliminary aggregation identification of API path data based on the path structure features of the API path data; if the preliminary aggregation identification is not successful, performing deep aggregation identification on the API path data based on word segmentation features and / or statistical features of the API path data; and generating an aggregation identification result of the API path data. According to the method and the device, the API path aggregation identification accuracy is improved.

This application provides a training method for a fingerprint recognition network, a fingerprint recognition method, an apparatus, and a medium. The training method for the fingerprint recognition network includes: determining fingerprint feature matching maps based on a first initial fingerprint image and a second initial fingerprint image; forming a training sample set from multiple fingerprint feature matching maps; and training an original neural network based on the training sample set to obtain a fingerprint recognition network. The technical solution provided by this application solves the problem of difficulty in distinguishing whether two different fingerprint images belong to the same finger, thus reducing the false acceptance and false recognition rates of fingerprint recognition.

The invention relates to an unmanned aerial vehicle image high consequence area building identification method, system and device based on priori knowledge and a medium, and the method is characterized in that the method comprises the steps: obtaining a to-be-identified remote sensing image collected by an unmanned aerial vehicle at a set height and route parameters; inputting the obtained to-be-recognized remote sensing image into a pre-trained multi-scale space attention aggregation model to obtain a building probability graph of a high-consequence area building recognition result; wherein the multi-scale space attention aggregation model is constructed based on a U-Net model and is provided with a multi-scale space attention aggregation module and a self-adaptive loss function, and the multi-scale space attention aggregation module is used for carrying out multi-scale space attention aggregation processing on an input feature map; according to the method, the building in the remote sensing image acquired by the unmanned aerial vehicle can be accurately identified, and the method can be widely applied to the technical field of computer vision and remote sensing image processing.

The application relates to a multi-protocol adaptive control method, system, device and medium of an LED dimming power supply, which comprises the following steps: receiving a dimming signal output by an external dimming device, and preprocessing the dimming signal to obtain a target input signal; extracting protocol identification features from the target input signal, and constructing a protocol feature vector; matching the protocol feature vector with a preset protocol template library to generate a candidate protocol set and corresponding initial confidence; dynamically correcting the initial confidence by combining historical recognition results, signal quality indexes and output response consistency to determine a target protocol type; calling corresponding protocol analysis rules and control parameter templates according to the target protocol type to generate target dimming control parameters; and adjusting LED drive output based on the target dimming control parameters. The application has the effect of improving the adaptive identification capability of the LED dimming power supply for various dimming protocols.

The present application belongs to the technical field of photon counting imaging, and particularly relates to a pulse recognition method based on three-channel cross verification. The method comprises the following steps: S1: obtaining time sequence synchronized signal sequences of three channels output by a charge sensitive amplifier, and pre-processing the signal sequences of the channels to obtain respective deconvolution signals of the three channels; S2: designing a threshold based on the respective deconvolution signals of the three channels, and performing three-channel cross recognition on each pulse event by using the threshold to obtain a pile-up discrimination group and an amplitude extraction group; and S3: recording a pulse event with an amplitude to be extracted into a non-pile-up amplitude extraction group by using the relationship among a time interval of each pulse event, a pulse shaping width and an amplitude extraction width, and obtaining three-channel pulse amplitudes of each pulse event contained in the non-pile-up amplitude extraction group. The present application saves the time cost of debugging, and reduces the instability of results caused by human factors.

The application discloses a carotid artery mis-segmentation processing method and device for robot autonomous scanning, and the method comprises the following steps: calculating an average height; controlling the ultrasonic probe to start moving from the starting point of longitudinal scanning, and acquiring a current ultrasonic image in real time; calculating the height mean value and the height standard deviation of the longitudinal profile of the blood vessel; judging whether the longitudinal profile of the blood vessel is a jugular vein; if yes, calculating the moving distance along the X-axis direction of the tool coordinate system at the next moment and the exertion strength at the next moment; otherwise, taking the preset step length and the preset strength as the moving distance and the exertion strength at the next moment respectively, determining the moving direction at the next moment based on the trend of the longitudinal profile of the blood vessel; controlling the ultrasonic probe to move to the position at the next moment, and re-executing the above process until the ultrasonic probe moves to the end point of the longitudinal scanning. The method effectively reduces the adverse effect of carotid artery mis-segmentation on scanning, and ensures that the carotid artery can be continuously and stably tracked.

This application relates to the field of image processing technology and provides a method and electronic device for air gesture recognition. The air gesture recognition method includes: acquiring information of a hand image captured by a front-facing camera at a first moment; acquiring the screen content display direction of the electronic device at the first moment; determining a target preprocessing operation corresponding to the screen content display direction; performing the target preprocessing operation on the hand in the hand image to obtain an image to be recognized; and recognizing air gestures based on multiple frames of images to be recognized. This enables the finger orientation recognized by the electronic device during air gesture recognition to be consistent with the finger orientation of the user in the actual physical space, thereby ensuring compatibility with air gesture recognition under various screen content display directions and reducing the probability of misrecognition of air gestures.

The present application relates to the field of image processing and target image recognition technology of civil optical equipment such as intelligent traffic, city supervision and commercial monitoring, and particularly relates to a multi-target characteristic recognition method based on photoelectric image, which aims to improve the adaptability and accuracy of target recognition in target optical imaging, and the method obtains target motion image through photoelectric equipment, divides the target into relative static, straight line motion and turning state according to a preset threshold, extracts target motion trajectory, judges target state, respectively carries out straight line and arc line fitting on the target trajectory of straight line motion and turning state, analyzes the overall motion state of multiple targets in the imaging image based on the motion state trajectory, and adopts corresponding individual motion trajectory statistical analysis method for different states, the multi-state adaptive analysis capability of the method significantly improves the recognition accuracy, and the recognition accuracy of the target with frequently changing state in a complex scene is improved by more than 30%.

This invention discloses a signal recognition method, apparatus, computer device, and storage medium. The method includes: acquiring a signal indicating ventricular fibrillation in a human body; performing time-frequency analysis on the signal to obtain the frequency content of different frequency bands corresponding to the i-th time point within a preset Hertz range; where i ranges from 1 to N, and N is the total number of time points; and identifying the type of the signal based on the frequency content of different frequency bands corresponding to each time point, wherein the type includes non-shockable ventricular tachycardia signals and ventricular fibrillation signals. In this technical solution, by utilizing the different frequency content of non-shockable ventricular tachycardia signals and ventricular fibrillation signals, the two signals can be effectively distinguished, thereby reducing the probability of misidentification of non-shockable ventricular tachycardia signals.

The invention discloses an electric power Internet of Things terminal equipment identification method and system based on network traffic, and belongs to the technical field of electric power Internet of Things terminal equipment identification. Traffic data acquisition is carried out on accessed terminal equipment, feature extraction is carried out on the acquired traffic data, and model training is carried out according to known equipment types; according to the method, automatic identification of the newly accessed terminal equipment is realized without modifying the configuration of the field terminal equipment or installing an agent program, the field deployment difficulty is greatly reduced, the vector is constructed through the multi-dimensional flow characteristics, the terminal equipment is identified from a multi-dimensional angle, the probability of misidentification is reduced, the identification accuracy is ensured, and the whole-process automatic identification is realized, so that the efficiency is improved. Manual participation is not needed, and the recognition efficiency is remarkably improved.

The application discloses a wide-angle delivery multi-modal AI quantum dot outdoor digital display device. The device comprises a camera, a multi-array microphone, a processor and a UHD large screen. The processor comprises speech recognition on an audio signal to obtain an initial text and a speech confidence level; the speech confidence level is compared with a preset threshold interval, if the speech confidence level is higher than the threshold interval, the initial text is taken as a recognition result; if the speech confidence level is within the threshold interval, characters of the initial text lower than a first threshold are replaced with corresponding characters of a lip recognition text and taken as the recognition result; if the speech confidence level is lower than the threshold interval, the lip recognition text higher than a third threshold is taken as the recognition result, otherwise, a recognition failure is taken as the recognition result; and the recognition result generates a corresponding interaction strategy. The application introduces a multi-modal recognition mechanism, so that a user can still realize stable man-machine interaction function without wearing any device.

The embodiment of the application provides a one-dimensional code recognition method and device, relates to the technical field of image processing, and the method comprises the following steps: processing an original image containing a one-dimensional code based on an ROI detection algorithm to obtain a to-be-recognized image; inputting the to-be-recognized image into a pre-trained identification prediction network model to obtain the identification of each code element contained in the one-dimensional code in the to-be-recognized image as a predicted identification; obtaining a first recognition result of the to-be-recognized image based on the predicted identification and a preset corresponding relationship between the identification and a decoding result; if the predicted identification satisfies a first condition and does not satisfy a second condition, determining the width ratio of a bar unit and a space unit contained in the one-dimensional code in the to-be-recognized image based on a one-dimensional code bar space positioning algorithm; obtaining a second recognition result of the to-be-recognized image based on the width ratio; and obtaining a final recognition result of the to-be-recognized image based on the first recognition result and the second recognition result. In this way, the probability of one-dimensional code recognition error can be reduced.

The application provides a crack segmentation method and system based on strain prior constraint, comprising: collecting a CT image of a to-be-tested sample; labeling a crack in the CT image of the to-be-tested sample to generate a corresponding label image; calculating three-dimensional strain field information according to the CT image of the to-be-tested sample to obtain a strain atlas corresponding to each CT image of the to-be-tested sample; constructing a neural network model, taking the CT image and the label image of the to-be-tested sample as input, and taking the strain atlas as prior constraint knowledge to guide the training of the neural network model; and inputting a to-be-segmented CT image and a strain atlas of the to-be-segmented CT image into the trained neural network model to obtain a pixel-level segmentation result. By introducing strain as prior constraint information, a good crack segmentation result is obtained through a convolutional neural network, and the objectivity and accuracy of the segmentation result are improved.

The application provides an encrypted traffic identification method and device, equipment and a storage medium, wherein the method comprises: identifying traffic to determine encrypted traffic, and sending the encrypted traffic to a corresponding hierarchical identification model for feature extraction and traffic source prediction, which can more finely identify and predict different types of encrypted traffic, effectively improving the identification rate of encrypted traffic and reducing the misidentification rate. Moreover, in the application, a hierarchical identification model is used to extract features from encrypted traffic, and identification is performed according to the features, avoiding the problem that existing identification technologies cannot be applied to all encrypted traffic, and improving the universality of different types of encrypted traffic.

The embodiment of the invention discloses a radar radiation source individual identification method and device for airport low-altitude security and protection. A specific embodiment of the method comprises the following steps: generating a radar signal fragment group set; performing self-supervised pre-training on the radiation source feature extraction network to update model parameters; constructing a radar radiation source individual identification model; performing joint optimization on the radar radiation source individual identification model through the known radiation source signal group set to generate a known radiation source center feature set; generating a known radiation source boundary parameter set according to the radar radiation source individual identification model and the known radiation source center feature set; and according to the known radiation source boundary parameter set and the radar radiation source individual identification model, performing radiation source individual identification on the real-time radar signal to generate a radar radiation source identification result. According to the embodiment, the generalization ability of the recognition model can be improved under the small sample condition, so that the individual recognition accuracy of the radiation source is improved, and the low-altitude security and protection safety of an airport is improved.

The invention discloses a risk prevention and control method and device for a financial manual seat and electronic equipment, and relates to the field of financial science and technology or other related technical fields, and the method comprises the steps: collecting a real-time voice signal interacted between the financial manual seat and a customer, and extracting a multi-dimensional dynamic feature from the real-time voice signal, the multi-dimensional dynamic features comprise acoustic features, semantic features and behavior features; matching the multi-dimensional dynamic features with a pre-constructed customer voiceprint model; based on the matching result and the multi-dimensional dynamic characteristics, evaluating the risk level of the real-time voice signal by adopting a risk evaluation algorithm; and under the condition that the risk level is greater than a preset risk threshold value, sending a risk early warning signal to a financial manual seat, and providing prevention and control suggestions and measures. According to the invention, the technical problem of low accuracy of a voiceprint recognition strategy adopted when a financial institution carries out telephone banking service security verification in the prior art is solved.

The embodiment of the present specification provides a method for determining the office area to which a device belongs, an access control method, a system, an apparatus and a device. The correspondence relationship between the device identifier of the network device and the office area range can be preconfigured. In the process of network authentication of the user device, the device identifier of the network device is sent to the server through the network device, so that the server determines the office area range to which the user device belongs based on the preconfigured correspondence relationship and the device identifier of the network device. Since the device identifier of the network device does not need to be manually configured by the user and will not change, misidentification can be reduced. Moreover, by realizing the identification of the office area range in the network authentication process, the development process can be reduced and the processing efficiency can be improved.

The present application relates to the field of handle error correction, and more particularly to a dynamic correction method and device for gamepad joystick offset error. The method comprises the following steps: detecting the player's no-input operation state, continuously collecting the original coordinate input value of the gamepad, and performing no-operation drift analysis to construct a static joystick dead zone; detecting the real-time operation signal stream of the player's handle, predicting the output behavior of the character in the scene, and generating game operation behavior data; based on the game operation behavior data, performing dynamic response deviation calculation, and constructing a handle drift vector field according to the static joystick dead zone; performing player operation intention analysis and unintended signal elimination processing on the real-time operation signal stream to obtain effective operation signals; performing reverse offset compensation calculation on the effective operation signals according to the handle drift vector field, and performing real-time joystick error correction. The present application corrects the signal recognition error of the gamepad, improves the response efficiency and accuracy of the game operation.

The invention is suitable for the technical field of data recognition, and provides a fingerprint recognition method and device for an intelligent water cup, and the method comprises the steps: collecting a fingerprint gray image through a fingerprint unit, and recognizing a core feature point in the fingerprint gray image; performing alignment processing based on the core feature points to obtain a target grayscale image; and dividing the target grayscale image and the standard grayscale image into a plurality of grid regions, and matching whether a user to be identified of the target grayscale image is the fingerprint user according to the plurality of grid regions. The fingerprint unit is used for collecting the fingerprint grayscale image and identifying the core feature points, and the unique features of the fingerprint of the user can be accurately extracted. The process not only improves the accuracy of fingerprint identification, but also effectively reduces the probability of misidentification.

The application relates to the field of production safety technology, in particular to a safety production hidden danger auxiliary inspection method and system based on an AI model. The method comprises the following steps: constructing an intelligent agent and multiple monitoring points according to original parameters of a production area; obtaining initial monitoring data according to a first-level monitoring strategy set by the intelligent agent, and setting an auxiliary monitoring strategy according to the initial monitoring data; obtaining a feedback data packet according to the auxiliary monitoring strategy; and the intelligent agent generates a hidden danger diagnosis result according to the feedback data packet. Based on the equipment structure parameters of the multiple monitoring points of the production area, comprehensive monitoring of the production area is realized, a correlation diagnosis model is constructed according to historical hidden danger data analysis, a correlation relationship network of the monitoring points and single-type hidden dangers is generated, multiple verifications of single-type hidden dangers are realized, and the misidentification rate of production hidden dangers is reduced. Linkage monitoring of different types of hidden dangers is realized, the overall identification efficiency of production hidden dangers in the production area is improved, and the safe operation in the production area is ensured.

The application discloses an online conference translation method and system, and belongs to the technical field of speech recognition. The language space is constrained by the interactive side signal, and the recognition uncertainty is reduced. In the recording stage, a target language label generated by a sliding gesture is introduced. The label reflects the language of the speaker to whom the speech is directed. The language label of the speaker's mother tongue is combined, the candidate language set is optimally converged into a two-language set of "mother tongue + target language", and the search space of speech recognition in the language dimension is significantly reduced from the "complete language set of the conference" to the "two-language set". Based on this, the misrecognition probability caused by multi-language competition is reduced, especially the probability of misrecognizing foreign language terms as mother tongue homophonic words is reduced, and it can be quickly determined which languages are involved in each sentence of speech, so as to quickly determine which mixed language model is used for speech recognition, and the speech recognition efficiency of mixed language speech is improved.

This application proposes a method and system for detecting digital human rendered videos. The method includes: receiving a digital human rendered video to be detected and converting it into a frame format; asynchronously performing various types of anomaly detection on the converted digital human rendered video, including: anomaly detection based on deep learning and convolutional neural networks, boundary anomaly detection based on adjacent image comparison, image segmentation anomaly detection, and video stuttering anomaly detection; obtaining the detection result for each anomaly detection, multiplying the detection score in each detection result by the corresponding weight to obtain the final target score of the digital human rendered video; determining whether the target score is less than a preset score threshold, and re-rendering the digital human rendered video if the target score is less than the score threshold. This method performs multi-layer image quality detection on computer-rendered digital human videos, which can eliminate anomalies and ensure the quality of digital human rendered videos.

This invention provides a training method, a command word recognition method, and an apparatus for a command word recognition model. The training method includes: acquiring audio of a first speech command word; decoding the audio of the first speech command word to obtain a first optimal decoding path and at least one second optimal decoding path; based on whether the first optimal decoding path contains the first speech command word and whether the at least one second optimal decoding path contains a second speech command word, calling the corresponding objective function to update the parameters in the command word recognition model based on the objective function; wherein the second speech command word is different from the first speech command word. This invention employs the method of calling the corresponding objective function and training based on the speech command word results contained in the decoding path, achieving the technical effect that the trained command word recognition model can effectively recognize and distinguish different preset command words. Therefore, this invention can significantly reduce the command word misrecognition rate.

The utility model discloses a pear variety identification device, relates to the pear variety identification technical field, the pear variety identification device comprises a work bench, the upper surface of the work bench is provided with a mounting rack, the upper surface of the work bench close to the mounting rack is provided with a rotating disc, and the outer wall of the rotating disc is uniformly distributed with four contact switches. Through the cooperation of the ejection mechanism, the identification mechanism and the auxiliary mechanism, the effects of reducing manual operation steps and reducing working intensity are achieved, the identification mechanism is used for identifying the variety of pears, after the identification result is obtained, the auxiliary mechanism receives information feedback, then the stepping motor drives the rotating disc and the identified pears to rotate, and the pears are accurately identified. And when the pears rotate to the corresponding auxiliary mechanisms, the ejection mechanisms start to work to eject the pears out, so that the pears enter the corresponding collecting frames through the auxiliary mechanisms, and in the process, the pears only need to be manually placed in the placing grooves, so that the working intensity is greatly reduced.

The invention discloses a blind sidewalk remote sensing image intelligent identification method based on a multi-modal large model, and relates to the technical field of multi-modal identification, and the method comprises the steps: extracting forward blind sidewalk semantic features and alternative facility semantic features in a prompt input set; respectively calculating semantic matching scores of the blind sidewalk candidate segments and the forward blind sidewalk semantic features and alternative facility difference scores of the blind sidewalk candidate segments and the alternative facility semantic features, and generating a semantic confrontation verification set; and according to the semantic confrontation verification set, reasoning semantic consistency of the blind sidewalk candidate segments and carrying out credibility sorting, generating credible blind sidewalk segments, analyzing a semantic topological relation of the credible blind sidewalk segments and executing evidence fusion judgment, and generating a blind sidewalk identification map. According to the method, the multi-modal large model is constructed, and semantic topological relation analysis, path combination processing and path topological reasoning and semantic evidence fusion are performed on credible blind sidewalk segments, so that the blind sidewalk candidate region recognition accuracy and blind sidewalk path complete recognition capability are improved.

This invention discloses a real-time intraoperative surgical instrument recognition system and method based on AR devices, belonging to the field of medical device management technology. The system includes: an AR glasses terminal, an edge computing unit, a surgical instrument library, a text matching module, and a highlight rendering module. The AR glasses terminal includes a camera module, a built-in display, and a voice input module, for use by surgical nurses. The edge computing unit receives a video stream and performs frame-by-frame decomposition, identifying instruments in the image using a surgical instrument recognition algorithm. This invention employs a hierarchical recognition algorithm to segment instruments into multiple layers, accurately matching each independent part with the corresponding feature information in the surgical instrument library, and then combining the matching probabilities of each part to determine the final recognition result. This invention effectively solves the problem of distinguishing similar instruments, significantly reduces the recognition error rate, and provides a guarantee for the safe and smooth conduct of surgery.