69 results about "Digit recognition" patented technology

The invention relates to a method for testing a participant's ability to accurately detect speech under background noise, comprising: (a) audibly presenting a series of 2-bit numbers, 3-bit numbers, 4-bit numbers and / or 5-bit numbers in a random or fixed order to a participant's first ear at a fixed or varying signal-to-noise ratio (SNR) in a quiet or noisy environment, (b) audibly presenting a series of 2-bit numbers, 3-bit numbers, 4-bit numbers and / or 5-bit numbers in a random or fixed order to the second ear of the participant at a fixed or random signal-to-noise ratio (SNR) in a quiet or noisy environment, where the numbers are presented in the native language of the participant or the fluent language of the participant, (c) recording the numbers or sequence of numbers correctly recognized by the participant, and (c) storing the recorded numbers or sequence of numbers at the second ear of the participant. And (d) calculating a score as a function of the percentage of the number or sequence of numbers correctly replicated by the subject, or as a function of the sound intensity difference between the speech and noise required to achieve the correct recognition of 50% sequence of numbers. The invention also relates to a device and a method for measuring the digital recognition capability related to hearing loss, and to a computer-implemented method for evaluating the speech recognition capability of a participant.

The invention provides an intelligent submission method and device for manual measurement and reading data. Synchronously collecting data of dam monitoring points; performing target detection, number identification, pointer identification and scale identification on an instrument area in the image to generate structured measurement and reading data; intelligent matching and automatic filling of the structured measurement and reading data and report fields are realized through a natural language processing technology; performing anomaly detection and threshold judgment on the filled report data, identifying a potential risk level, and selecting a submission path through a preset grading submission mechanism according to the risk level; and synchronously uploading the hash value of the original image data and the structured data to a block chain system, executing double-chain storage, and automatically starting an intelligent contract of an emergency process when a preset triggering condition is met. According to the method, the dam monitoring data submission efficiency and accuracy can be effectively improved, intelligent identification and real-time hierarchical transmission of multi-source data under complex working conditions are realized, and the credibility and traceability of the data are guaranteed through a block chain technology.

The invention discloses a license plate recognition method and system based on deep learning, and the method comprises the following steps: collecting license plate image data, and generating an image data set; performing semantic decomposition operation, dividing into region code units, letter units and number units, and constructing a semantic structure chart; constructing a multi-path character recognition model, and taking an improved PCNN model as a trunk feature structure; respectively inputting the image data set into a multi-path character recognition model, outputting an area code recognition result, a letter recognition result and a number recognition result, and generating a candidate license plate recognition result; if illegal character combinations or structural unit missing information exists, path screening processing is executed, and a candidate path set is generated; reasoning and filling processing is executed, and a complemented path set is generated; and combining and outputting a license plate recognition result and a confidence alternative path set. According to the method, the character recognition accuracy is improved, meanwhile, the robustness to structure deficiency is enhanced, and the method has the advantages of being high in recognition precision and high in fault-tolerant capability.

The invention provides a general meter reading automatic identification method, and relates to the technical field of computer vision and deep learning, and the method comprises the steps: carrying out the image collection of a meter to obtain an original image containing an instrument panel region of the meter, and carrying out the image recognition of the original image, obtaining an integer area and a decimal area in the instrument panel area and corresponding coordinates thereof, and determining physical layout positions of the integer area and the decimal area in the instrument panel area according to the coordinates; segmenting a plurality of numeric character regions from the integer region; and performing number identification on each number character area and decimal area, and sequentially splicing a plurality of numbers obtained by identification according to corresponding physical layout positions to obtain the meter reading. The method has the beneficial effects that a multi-stage cascade detection method is adopted, interference is filtered layer by layer (positioning-segmentation-classification digital recognition) through cooperative work of multiple processes, and the problem that cross-specification universal recognition is difficult to realize by a traditional single detection model is solved.

The invention provides a meter reading detection method based on a cascaded detection model, and relates to the technical field of intelligent metering of the Internet of Things, and the method comprises the steps: constructing a cascaded detection model which comprises a dial detection network, a character segmentation network and a digital classifier which are cascaded in sequence; the method comprises the following steps: acquiring a front image of a meter, inputting the front image into a cascade detection model, dynamically adjusting a feature perception range by a dial detection network according to a dial diameter of the meter, generating a dial region-of-interest frame, inputting the dial region-of-interest frame into a character segmentation network, and obtaining a character segmentation image of each character contained in the dial region-of-interest frame; and inputting the character cut images into a number classifier to obtain numbers contained in the character cut images, and taking a number sequence formed by combining the numbers according to the positions of the numbers in the region-of-interest frame of the dial plate as a reading detection result. The method has the beneficial effects that the problems of large dial positioning error, inaccurate character cutting, unstable number recognition and the like are effectively solved, the model volume is reduced by about 95% compared with a traditional single-stage model, and the calculation power demand is reduced.

The invention provides an implementation method based on light-induced linear reconfigurable artificial synapses, and belongs to the technical field of neuromorphic electronic devices and intelligent sensing signal preprocessing. The method comprises the following steps: providing an artificial synapse transistor capable of regulating and controlling conductance through voltage pulses, irradiating visible light in a channel or a conductance modulation area of the artificial synapse transistor, applying continuous voltage pulses under an illumination condition, reading the conductance in a preset time window after the last pulse is ended, and taking the conductance as a weight value of a corresponding pulse sequence; by adjusting illumination parameters, conductance is converted from nonlinearity to linearity along with the pulse number relation, the nonlinear factor is reduced compared with the dark state, the linear interval is widened, and linearity reconstruction in the weight updating process is achieved. According to the method, reconfigurable linear weight modulation can be obtained only by means of a light field and simple pulse driving, the method is suitable for high-fidelity compression coding of 5-bit and above time sequence pulses, feature separability and recognition accuracy can be remarkably improved in handwritten number recognition, handwriting identification and other scenes, and training time and energy consumption are reduced.

The invention provides a multivariate data regulation and control processing method based on three-dimensional visualization, belongs to the technical field of image data processing, and aims at solving the problem that an existing AI intelligent inspection unit mainly depends on a two-dimensional image to carry out instrument detection and digital recognition. In order to overcome the defects of inaccurate state analysis, insufficient multi-view data fusion and the like caused by target occlusion misjudgment and spatial information loss in the prior art, a multivariate data system is constructed by fusing a three-dimensional point cloud, a depth map and a multi-view two-dimensional image, and three-dimensional reconstruction, spatial feature extraction and a multi-modal data fusion algorithm are combined, so that the multi-view data fusion is realized. Accurate detection of a power distribution station house equipment target, three-dimensional visual analysis of state parameters and dynamic regulation and control processing are realized. According to the method, the anti-shielding capability of target detection, the accuracy of state analysis and the real-time performance of data regulation and control are effectively improved, the intelligent level of operation and maintenance management of the power distribution station house is remarkably optimized, and the labor cost and the fault risk are reduced.

This invention discloses a license plate recognition method and system based on deep learning, comprising the following steps: acquiring license plate image data to generate an image dataset; performing semantic decomposition to divide the data into region code units, letter units, and number units, and constructing a semantic structure graph; constructing a multi-path character recognition model with an improved PCNN model as the backbone feature structure; inputting the image dataset into the multi-path character recognition model respectively, and outputting region code recognition results, letter recognition results, and number recognition results to generate candidate license plate recognition results; if there are illegal character combinations or missing structural unit information, performing path filtering processing to generate a candidate path set; performing inference imputation processing to generate a complete path set; and merging and outputting the license plate recognition results and the set of confident candidate paths. This invention improves the accuracy of character recognition while enhancing robustness to structural defects, possessing the advantages of high recognition accuracy and strong fault tolerance.

The present application relates to a kind of mixed STDP training method and system based on threshold increment cycle counting, construct including input layer, hidden layer and classification output layer STDP network architecture, and the threshold voltage increment of neuron is counted and controlled to the unsupervised learning process of STDP network architecture, the supervised learning process of combination classification output layer adjusts the weight value corresponding to neuron, by applying threshold increment cycle counting and neuron responsivity screening, effectively constrain weight update, reduce the weight update frequency, to greatly reduce the overall amount of computation of training, help to improve training learning efficiency.The present application method is applicable to handwritten numeral recognition, compared with traditional STDP training algorithm, can reduce 2.5 to 3.5 times amount of computation and improve about 3% classification accuracy.

The present application relates to the technical field of digital recognition, and particularly provides a nixie tube content recognition method and device, electronic equipment and storage medium, wherein the method comprises: acquiring a continuous video image sequence of a nixie tube, acquiring position information of a nixie tube character display segment according to a preset frame number by using a template matching algorithm; recognizing bright and dark states of the nixie tube character display segment by using a support vector machine (SVM); acquiring a brightness sequence unit of the nixie tube character display segment under the preset frame number according to a preset nixie tube arrangement mode; classifying the brightness sequence unit by using a deep learning method and outputting a recognition result; and the device comprises: a nixie tube and a PC terminal connected with the nixie tube, the nixie tube and the PC terminal are configured in an asynchronous state, and the PC terminal comprises: an acquisition module, a position recognition unit, a brightness recognition unit and a training module. The purpose is to solve the misrecognition problem caused by uneven brightness and defects in the nixie tube content recognition process.

The invention discloses a medical B-ultrasonic image automatic analysis system and method based on deep learning. The system comprises an image preprocessing module, a follicle detection module, a digital recognition module, an OCR text extraction module, an intelligent matching module and a report generation module. The method comprises the following steps: performing tilt correction, region extraction and perspective transformation on a B ultrasonic image, detecting follicle positions and morphological parameters by using a YOLO-11 model based on a rotating bounding box, and identifying digital labels; extracting an image bottom size text by adopting a CnOCR engine, and correcting to obtain structured data; intelligently matching follicles, numbers and sizes by calculating the Euclidean distance, and establishing triple association; and automatically generating a structured JSON report in combination with an anomaly detection mechanism. According to the method, full-process automation of follicle monitoring is achieved, the analysis efficiency, accuracy and consistency are remarkably improved, manual dependence is reduced, and reliable support is provided for clinical decision-making of assisted reproduction.

The invention discloses a new building electrical installation acceptance method and device, and relates to the technical field of electrical installation acceptance, the method comprises the following steps: obtaining house numbers of different rooms and code numbers and resistance values of resistor devices preset in different rooms to obtain a data file, the code numbers and resistance values of the resistor devices having uniqueness; measuring and recording actually measured current values shown by the corresponding electricity meters after the electric brake master control room opens the electric brake of each room; and extracting the code number of the resistor device in the data file and the house number of the room where the resistor device is located by using a digital identification model, calculating to obtain a theoretical current value, and comparing the theoretical current value with the actually measured current value to judge whether the ammeter is correctly installed. The method is low in cost and easy and convenient to operate, manual errors are reduced, and the efficiency and accuracy of electrical installation acceptance are improved.

The application provides an image recognition simulation model and system, the image recognition simulation model comprising: an optical diffraction neural network for a handwritten digit recognition task, the optical diffraction neural network comprising: an input layer, a diffraction layer and an output layer; the input layer modulates incident light into a wavefront array carrying image information; the diffraction layer performs multiple diffractions on the light output by the input layer to simulate a convolution weight matrix, and adjusts a phase distribution in a manner of error back propagation; and the output layer generates a focused light spot corresponding to the number of categories, the focused light spot focusing on a number corresponding to a plurality of detection points, and a detection surface light spot intensity distribution of the focused light spot is used to represent a classification probability. Through nano structure design, high degree of freedom regulation of light field amplitude, phase and polarization is realized in a two-dimensional plane; meanwhile, through multi-layer cascading extension network depth, feature abstraction capability is improved, nonlinear mapping is realized through multi-layer cascading diffraction, and a classification light intensity distribution is directly output, and the light intensity distribution represents a classification result.

According to the hardware-network collaborative optimization FPGA digital recognition system and method, the LeNet-5 network architecture is improved, the number of channels is adjusted to be a multiple of 4 so as to be matched with an FPGA parallel computing array, a ReLU activation function is adopted to replace traditional Sigmoid / Tanh, and 8-bit integer quantization processing is implemented; a four-level assembly line architecture (convolution-quantization-pooling-activation) is adopted in the aspect of hardware, a snakelike movement strategy and a double-Block dynamic storage scheme are combined, the energy efficiency ratio and the reasoning speed are remarkably improved while high recognition precision is kept, an end-to-end real-time processing function chain from image collection, neural network reasoning to result display is achieved, and the method has the advantages of being high in recognition precision and high in practicability. The data reuse rate is obviously improved, the storage access bandwidth is reduced, a referenceable low-power-consumption and high-performance solution is provided for edge computing applications such as intelligent monitoring and industrial quality inspection, and high real-time performance and practicability are achieved.

The invention relates to the technical field of artificial synapses, in particular to a composite artificial synapse which comprises a core functional layer, the core functional layer is a composite material layer, and the composite material layer is formed by mixing a SrAl2O4-based long afterglow material and a NaYF4-based up-conversion material; eu < 2 + > and Dy < 3 + > are doped in the SrAl2O4-based long afterglow material; yb < 3 + > and Tm < 3 + > are doped in the NaYF4-based up-conversion material; under excitation of near-infrared light, the NaYF4-based up-conversion material transmits energy to the SrAl2O4-based long-afterglow material through up-conversion luminescence, so that the SrAl2O4-based long-afterglow material generates long-afterglow luminescence, and a synaptic function is realized; through thermal stimulation, the release process of defect trap electrons in the SrAl2O4-based long afterglow material is regulated and controlled, and thermally induced synaptic plasticity is realized. According to the invention, SrAl2O4: Eu < 2 + >, Dy < 3 + > and NaYF4: Yb < 3 + >, Tm < 3 + > are coupled, so that long afterglow luminescence (LPL) of near-infrared triggering and thermal regulation is realized, and information encryption, handwritten number recognition and mechanical arm gesture control are realized by artificial synapses based on photo-thermal synergistic stimulation.

Device for external control of speed and / or performance parameters, comprising a physical identification means (starter chip card) and / or a digital identification means (app), both of which can be used individually or in combination.

A roller cutter for a raise boring tool includes a journal and a cutter shell positioned radially around the journal. The journal includes an external surface from which a journal end protrudes from. A seal retainer is positioned between the journal and the roller cutter, and wherein at least one digital identification tag is located on the roller cutter.

The invention relates to the technical field of artificial intelligence, and provides a handwritten numeral recognition method and related equipment based on multi-modal large model guidance, and the method comprises the steps: constructing a meta-training data set; performing style analysis on the support set image based on a multi-modal large model, generating a style description text, and encoding the style description text into a first prompt vector; performing off-line training on the small model according to the support set image and the first prompt vector based on a meta-learning framework; in an online recognition stage, generating a personalized style description text according to an unlabeled handwritten digital image of a new user through a multi-modal large model, and encoding the personalized style description text into a second prompt vector; adopting a self-supervised learning mechanism to carry out personalized adaptation processing on the trained meta-learning small model based on a second prompt vector; and recognizing a subsequently input handwritten digital image through the adapted meta-learning small model to generate a recognition result. According to the method and the device, high-precision recognition of personalized handwritten numbers can be quickly realized under the condition of no labeled sample, and meanwhile, the consumption of computing resources is reduced.

The invention discloses a method and a related device for gradient detection and positioning of a contact network positioner, and relates to the technical field of rail transit detection equipment.The method comprises the steps that an obtained to-be-detected image data set is input into a contact network recognition model YOLOv5E-L, and a category label and a picture set of a position detection frame are obtained; cutting the picture set of the category label and the position detection frame to obtain an intercepted locator picture and an intercepted pillar number plate picture set; carrying out LSD-based linear detection on the intercepted locator picture to obtain a locator slope value; and inputting the intercepted pillar number plate picture set into a number plate number identification model YOLOv5E-d to obtain the number on the pillar number plate. According to the invention, the geographic position and the angle data value of the positioner can be automatically detected in a non-contact manner, and the state digitization and informatization of the catenary positioner are realized.

The application relates to a clock-drawing test scoring method and device, computer equipment and a storage medium. The method comprises the following steps: inputting a clock-drawing image dataset into an FCOS network to identify handwritten numerals in the clock-drawing image dataset; performing circle detection on the clock-drawing image dataset by using a maximum connected domain algorithm to obtain a clock region; based on the identification result of the handwritten numerals and the detection result of the clock region, performing pointer detection on the clock-drawing image dataset by using an image processing algorithm to obtain a pointer image of the clock-drawing image dataset, and performing hour hand and minute hand classification on the pointer image by using a breadth-first algorithm; scoring the handwritten numeral identification result, the clock region detection result, the pointer image detection result and the hour hand and minute hand classification result according to a set scoring rule, and adding all the scoring results to generate a clock-drawing test scoring result. The application can avoid evaluation fluctuations and differences caused by subjectivity and bias of artificial evaluation.

The invention belongs to the technical field of digital identification, and relates to a digital instrument test data auxiliary system, which comprises a data capture module, a data processing module, a data storage and judgment module and a human-computer interaction interface, the data capturing module collects the real-time state of an instrument data area through a monitoring camera, converts collected videos into pictures and transmits the pictures to the data processing module. The data processing module is used for carrying out region selection and image processing on the transmitted picture through an image processing system in computer software, and identifying digits in the picture; the data storage judgment module is used for transmitting the digits converted by the image processing system to a general data storage format or a database and marking the recording time of the digits; a user operates the human-computer interaction interface to realize various video digital capture requirements. According to the system, collected character images can be converted into digits to be stored in a computer, and test monitoring visually perceived by testers on site is replaced.

The application relates to a digital instrument reading recognition method based on an improved threading method, and the method is characterized in that the method comprises the following steps: acquiring a digital instrument image; pre-processing the digital instrument image; image correction: based on contour and polygon fitting, and referring to a Ransac algorithm, effective samples of the pre-processed digital instrument image are extracted, and the upper and lower boundaries and the left and right boundaries of the digital region of the digital instrument are respectively located, and a perspective transformation is used to correct a quadrilateral region containing numbers, so that the strokes of the nixie tube are horizontal and vertical; digital recognition: the corrected image is segmented into single characters by using a vertical projection method, and the improved threading method is used to complete the recognition of each character, so that the reading value of the digital instrument is obtained. Compared with the prior art, the application has the advantages of accurate recognition and good stability.

This invention belongs to the field of speech recognition technology, and discloses a digital speech recognition method, device, and medium, applicable to offline speech recognition modules on the edge and home appliances and consumer electronic devices with voice interaction functions. The method includes: acquiring the speech to be recognized; decoding the speech to be recognized through a speech recognition model to obtain a preliminary recognition result; reviewing N frames (N is a positive integer greater than 1) of phoneme probability output data to determine whether a preset digital confusion type exists; if it exists, correcting the preliminary result based on the corresponding confusion type's error correction strategy to obtain the final result; if it does not exist, directly outputting the preliminary result. This invention, through a process of "model decoding + frame review + targeted error correction," accurately solves problems such as path inclusion confusion and homonymous competition confusion in digital speech recognition. While ensuring real-time recognition, it significantly improves the accuracy of digital recognition, achieving low cost, high flexibility, and adaptability to the scenario requirements of edge devices.

The invention belongs to the technical field of artificial intelligence, and discloses a high-dimensional data dimension reduction system and method for semi-supervised local adaptive discriminant analysis, and the method comprises the following specific steps: 1), learning two independent projection matrixes for labeled data and unlabeled data; 2) setting residual constraints through the two projections to approach each other, and jointly converging to a unified low-dimensional space capable of distinguishing categories and reflecting an internal structure of data; (3) the projection of the labeled data can keep category discrimination information to the greatest extent, and the projection of the non-labeled data can keep the global manifold structure of the data optimally; the method is realized through a unified and solvable optimization objective function, and the method simultaneously utilizes marked and unmarked data, adaptively captures a local structure, is high in anti-noise capability, is suitable for semi-supervised high-dimensional data processing scenes such as face / handwritten digital recognition and gene data analysis, and shows remarkable advantages in classification on a standard data set.

The application discloses a kind of based on deep learning's digital identification method and system, method includes image acquisition, image optimization model design, digital number dimension flexible unit design, digital bit field navigation unit design, digital image recognition model establishment and digital identification.The application belongs to the field of image processing, specifically refers to a kind of based on deep learning's digital identification method and system, the scheme is through digital number dimension flexible unit, according to the dynamic adjustment receptive field of digital real size, based on digital bit field navigation unit, through forward control and reverse refinement, improve the accuracy of digital positioning;Based on contour weighted loss and morphological perception loss, strengthen the segmentation integrity of digital contour fuzzy area;Through double-way synchronous optimization, balance key stroke detail preservation and anti-interference ability;Based on the weight generated by digital pixel peripheral zone dispersity, and introduce structure difference loss, significantly improve the feature learning of digital contour area;Further improve digital identification effect.

The application discloses a digital coding real-time recognition method and system based on improved YOLOv5, belongs to the technical field of big data processing, and aims to solve the technical problem of how to accurately and efficiently recognize digital coding in real time. The method comprises the following steps: collecting coding pictures and background pictures and marking them; taking the background pictures and the coding pictures with marked information as sample pictures and performing data enhancement processing; constructing a digital recognition model based on an improved YOLOv5 network model with GhostNet and RepGhost introduced; performing model training and model testing on the digital recognition model; for digital coding that needs to be recognized, collecting a video in real time, performing digital detection and recognition on each frame of picture in the video through the trained digital recognition model, outputting the total number of numbers in the current frame of picture and the category information and coordinate information of each number, and obtaining the coding sequence of the numbers based on the coordinate information.

The present invention discloses a digital recognition method, device, and medium based on a lightweight network, relating to the field of intelligent operation and maintenance technology for rail transit. The method comprises: constructing a lightweight network, training it based on a digital tube digital data set, and obtaining a digital recognition model; acquiring a real-time image, and inputting images of each region of interest in the real-time image into the digital recognition model based on a preset region of interest for digital recognition, to obtain a digital numerical result. The present invention uses a historical data set to train the constructed lightweight network to obtain a digital recognition model. Based on the digital recognition model, the display data of the digital tube in the real-time image captured by the camera can be quickly identified through the preset region of interest. Compared with the traditional manual reading method, the accuracy and efficiency of data reading can be effectively improved.

The utility model relates to the field of fixing structures, in particular to a fixing structure of an SVM (Support Vector Machine) digital recognition device. The technical problem that in the SVM fixing process, due to the fact that most of existing SVM digital recognition device fixing structures are fixed to used equipment, certain limitation exists on steering angle and orientation control of an SVM digital recognition device, and the use applicability of the SVM digital recognition device fixing structures is lowered is solved. According to the technical scheme, the SVM digital recognition device fixing structure comprises an installation assembly, a support assembly, a base assembly and an SVM digital recognition device body, the SVM digital recognition device body is clamped by arranging an installation plate and a first protection plate, and therefore the problem that in the SVM fixing process, the SVM digital recognition device body cannot be fixed easily is solved. Most of existing SVM digital recognition device fixing structures are fixed to used equipment, certain limitation exists on steering angle and orientation control of an SVM digital recognition device, and the use applicability of the SVM digital recognition device fixing structures is lowered.

This invention relates to a continuous learning method and apparatus for a handwritten digit recognition model. The method includes: training a master recognition model based on a labeled dataset, and selecting image samples that are misrecognized by the master recognition model from the labeled dataset; training an auxiliary recognition model based on a training set of misrecognized samples, and cascading the master recognition model and the auxiliary recognition model whose performance complements that of the master recognition model to obtain a teacher model; training a student model using the teacher model based on a pseudo-label set and a real label set to obtain a distilled student model; when the recognition performance of the distilled student model reaches the recognition performance of the teacher model, replacing the master recognition model with the distilled student model, returning to the model training cascade step, and waiting for a new round of unlabeled datasets for continuous learning, thereby not only endowing the intelligent model with continuous self-learning ability, but also achieving the goal of overcoming the "catastrophic forgetting" phenomenon.