51results about How to "Stable training" patented technology

The invention discloses a polarization degree and light intensity image fusion method based on bidirectional cross attention. The method belongs to the technical field of polarization imaging, computational imaging and image processing. The technical problems that in the prior art, dynamic balance between structural detail keeping and polarization saliency enhancing is generally difficult to achieve, and particularly under the condition of a complex background or a low signal-to-noise ratio, texture missing or noise artifacts are prone to occurring in a fusion result are solved. A fusion mechanism capable of establishing a two-way information interaction relationship between a light intensity image and a polarization degree image is provided, and further processing is carried out aiming at a noise problem, so that more stable and more reliable polarization fusion imaging is realized.

The invention discloses a hydroelectric generating set fault diagnosis data enhancement method based on a diffusion model and generative adversarial training, and belongs to the field of industrial equipment fault diagnosis. According to the method, the data enhancement model combining the diffusion model and the generative adversarial network is constructed, a multi-modal non-Gaussian distribution mechanism and a latent variable control generation process are introduced, the limitation of a single Gaussian hypothesis of a traditional diffusion model is broken through, and richer and more real sample generation is realized. And a condition discriminator and a time sequence modeling mechanism are introduced, so that the training of the model under different noise levels is more stable, and the authenticity judgment capability of the discriminator on the generated sample is enhanced. The problems that an existing hydroelectric generating set fault diagnosis system is insufficient in sample, low in generated sample quality and unreal in sample distribution are solved, and the diversity and quality of data are remarkably improved.

The local super-resolution reconstruction algorithm based on the transmission line insulator infrared image includes the following steps: Step 1, image recognition; Step 2, image segmentation; Step 3, super-resolution reconstruction; By using the improved adversarial network structure, unsupervised reconstruction is adopted, the RRDB network structure is adopted, when the network structure is deepened, the stability of training can be maintained, the calculation amount and the use of memory are reduced, and the reconstruction effect is improved, the SeNET attention mechanism is added, from the feature channel level, according to the importance, the useful features such as the outline and the details of the insulator are improved, and the features which are not useful for the program are suppressed. The resolution of the current transmission line insulator infrared image is low, and when the insulator detection is carried out, the workload is large and the problems such as false detection and missed detection occur.

The invention discloses a trajectory prediction system based on convolution and self-attention. The trajectory prediction system comprises an overall network architecture, a training method and a reasoning output algorithm. The whole network architecture takes a road grating map, a vehicle motion state and target information as inputs, the inputs are processed through a DenseNet layer, a self-attention coding layer, a full-connection coding layer and a decoding output layer in sequence, and a prediction track is output; according to the method, a road grating map containing information such as a collision box and a road marking and a vehicle motion state are used as input, road environment constraints are associated with a self-attention mechanism, a polar coordinate track description mode fitting vehicle kinematics characteristics is adopted, a track parameter value range is limited, common errors and abnormal tracks are effectively avoided, and the method is suitable for popularization and application. Traffic rules and driving safety requirements are met, and the reasonability and safety of formed track prediction are prominent; based on 16000-frame multi-dimensional training data collected by a Carla simulator, errors are reduced in a verification set after optimization training, and errors in a crossing turning scene are reduced.

The present application belongs to the technical field of computer vision three-dimensional reconstruction, and specifically relates to a semi-supervised single-view 3D object reconstruction method. A small amount of labeled samples are used to train a neural network, and then the trained neural network is used to generate pseudo labels for unlabeled samples and guide the training of the unlabeled samples. At the same time, the present application proposes that a discriminator scores the quality of the generated pseudo labels, and limits the bias of low-quality pseudo labels on model training. In addition, the present application proposes a prototype shape prior module based on an attention mechanism, which serves as a bridge between images and 3D shapes, reduces the difference between the two modalities, and provides shape prior for the neural network, ensuring that the reconstructed 3D shape is natural. Compared with the current mainstream method in the industry, the present application is more accurate in three-dimensional reconstruction of a single image under the condition that the amount of labeled data is very small, and the generated 3D shape is more realistic and natural.

The invention discloses a reinforcement learning intelligent traffic signal control method and system based on state-driven retrieval enhancement. The method comprises the steps of collecting real-time traffic flow state information of a traffic environment and constructing a global traffic state vector, retrieving a knowledge base to obtain related knowledge fragments and performing weighted aggregation to obtain a comprehensive knowledge representation vector, and constructing a fusion decision model fusing retrieval enhancement and a Markov decision mechanism, training convergence of the strategy network is completed after the enhanced state vector is generated, traffic signal control is achieved based on the converged strategy network, the generalization adaptation capacity, the anti-interference capacity and the operation stability of the signal control strategy to various traffic scenes are improved, random fluctuation of traffic flow and sudden traffic conditions can be effectively coped with, and the traffic signal control method is suitable for being popularized and applied. Through knowledge retrieval and prior knowledge fusion, traceability and interpretability of a control decision are realized, the efficiency of traffic signal control is effectively improved, the occurrence rate of intersection traffic delay and congestion is reduced, and reliable support is provided for intelligent collaborative management and control of a road network.

This invention discloses a rapid calculation method for the broadband electromagnetic performance of microstrip lines and microstrip-like two-port structures. It relates to the fields of electromagnetic calculation and electromagnetic compatibility-aided design technology, and includes: acquiring and preprocessing the layout data of the microstrip port conductor to be tested, generating a binary layout image; inputting the binary layout image into a pre-trained convolutional neural network, outputting a real-valued encoded prediction vector of the complex mode eigenvalues ​​of the dominant mode at a preset sampling frequency; denormalizing and decoding the prediction vector to obtain complex mode eigenvalue samples; identifying the complex mode eigenvalue samples based on a second-order analytical model and analytically extending them to obtain the broadband modal impedance of the target frequency band; obtaining the port impedance matrix according to the reconstruction relationship, and converting and outputting broadband scattering parameters and electromagnetic performance results. This invention can significantly reduce the computational overhead of full-wave frequency sweep and improve the simulation efficiency of microstrip lines and the iteration speed of EMC design.

The application discloses a traffic signal timing method, device and equipment based on deep reinforcement learning, relates to the field of traffic control technology, and effectively reduces the overall waiting time of vehicles at the intersection by pre-allocating the green light time of each phase according to the queue length of the current intersection lane. The application further adjusts the green light duration of the phase by the good or bad feedback result of the interaction with the traffic condition before the start of the green light time of each phase, so as to realize real-time prediction of the optimal green light time of the current phase. Further, in order to better adapt to the uncertainty and complexity of the traffic flow, the mechanism of the phase is added to the design of the state, so as to avoid the case that different intersections are in different phase green light time when the number of vehicles at different intersections is the same, thereby making the training more stable, and effectively adapting to the reasonable allocation of the green light duration of the traffic signal under the condition of the complex changing traffic flow, so as to reduce the waiting time of the vehicles at the intersection.

This invention discloses a method and system for fault diagnosis of industrial equipment under complementary label constraints, belonging to the field of industrial intelligent operation and maintenance and fault prediction health management technology. The method includes: collecting and preprocessing equipment vibration signals; constructing a dual-head deep network based on one-dimensional residuals as a complementary label learning model; generating a joint probabilistic loss function using complementary labels based on maximum likelihood estimation, enabling the model to learn fault features from "negative" labels; and achieving high-precision fault classification using the trained model. This invention applies the complementary label learning paradigm in weakly supervised learning to industrial equipment fault diagnosis, achieving a diagnostic accuracy of over 90% on multiple standard bearing datasets such as CWRU and MFPT. This method significantly reduces the data labeling threshold and effectively solves the pain points of scarce fault samples and difficult labeling in industrial scenarios, possessing significant practical application value.

The invention relates to a cross-color gamut phase-guided double-attention fusion HDR imaging method. The method comprises the following steps: step (1), carrying out data preprocessing of denoising and cleaning on an original multi-exposure image sequence; step (2), obtaining standardized image data; (3) mapping a nonlinear pixel value into a linear physical illumination value for the standardized image data through a reverse application camera response curve, and outputting a linearized multi-frame image; step (4), splicing the linearized multi-frame images on a channel dimension, and constructing a unified input tensor containing complete dynamic range information; (5) performing convolution operation on the input tensor, and extracting shallow feature representation of local textures and edges of the image; extracting shallow layer features; and step (6), introducing a double attention mechanism to perform interaction and aggregation of global features, and outputting a fused high dynamic range feature map. The method can stably work in a dynamic scene and under an extreme exposure condition, and promotes the practical application of an HDR imaging technology.

The application relates to a video instance segmentation method based on a dynamic convolution decomposition of a lightweight attention mechanism; the method first inputs a video frame, and a backbone network independently extracts a feature map of each frame in the video; then the feature map extracted by the backbone network enters an HQT encoding and decoding module, the position change of an instance in each frame is accurately positioned by combining an output head, and three prediction branches are used to supervise model training; in the application, a convolution layer of an encoding network adopts dynamic convolution decomposition, a more compact model is obtained, model training is easier, the required parameter quantity is greatly reduced, the training speed is improved, and the training time is shortened; a lightweight HQT encoding and decoding module is provided, which helps to reduce model parameters and improve efficiency; the loss function is improved, model training is more stable, the convergence speed and convergence precision are improved, and the problems of imbalance between foreground and background in samples and imbalance between foreground categories under a long tail condition are relieved.

The present application belongs to the technical field of rehabilitation medical apparatus and instruments, and particularly relates to a robot system for gait training, which comprises a chassis module, the front and rear ends of the chassis module are provided with steering wheels, the chassis module further comprises a directional wheel and a driving wheel, and the directional wheel is connected with a lifting assembly; a pair of lifting modules are arranged in the middle of the chassis module, each lifting module is connected with a body state control module, and each body state control module is driven to move up and down through the lifting module; the robot system for gait training provided by the present application enables the pelvis of a patient to move freely, so that the patient can perform balance training.

The invention discloses a circular hole detection and binocular matching method considering peripheral features. Comprising the following steps: constructing a three-dimensional part model according to structure parameters of a to-be-detected part, and constructing a data set through a rendering method by utilizing the three-dimensional part model; constructing a circular hole detection and binocular matching model, and training by using the data set to obtain a trained circular hole detection and binocular matching model; the circular hole detection and binocular matching model comprises a feature extraction backbone network, a feature encoder, two parallel feature decoders and a feature segmentation module, and the two feature decoders are respectively a detection decoder and a matching decoder; and acquiring an actual binocular image of a to-be-detected part, and inputting the actual binocular image into the trained round hole detection and binocular matching model to obtain a round hole detection result. According to the method, the position relation between the circular holes and peripheral features such as the environment can be effectively utilized, and the accuracy and robustness of binocular matching and segmentation in a complex scene are improved.

This invention discloses a method for generating extreme power load samples, belonging to the technical field of extreme power load sample generation. The method includes preprocessing the original load sequence; separating the base load sequence and industrial disturbance components using an industrial load disturbance identification model; slicing the base load daily to form a daily base load sequence set; decomposing the daily base load sequence set to obtain multi-scale detail sequences; constructing multi-scale time-frequency feature vectors; performing density peak clustering based on the multi-scale time-frequency feature vectors to obtain extreme load pattern samples; performing fine-grained clustering of the extreme load pattern samples using a dynamic density clustering algorithm, followed by Markov random field optimization to obtain a spatiotemporal template for extreme events; designing a diffusion generation model based on the spatiotemporal template; training the model with the extreme load pattern samples; generating load sequences and superimposing them with the industrial disturbance components to obtain extreme load samples. This invention solves the technical problem that existing technologies cannot generate a large number of reasonable extreme load samples.

This invention discloses a method for displacement field recognition of cement-based materials based on a one-dimensional convolutional model. The method includes: S1: extracting the displacement field from a speckle image; using speckle image pairs as feature data, and using the lateral displacement field, longitudinal displacement field, and combined displacement field as label data, and normalizing the label data to obtain a sample dataset; S2: constructing a displacement field recognition model for cement-based materials based on a one-dimensional convolutional model; S3: constructing a model loss function containing the design parameters to be optimized by introducing physical loss, and training the displacement field recognition model based on the one-dimensional convolutional model for cement-based materials based on the sample dataset to obtain the optimal displacement field recognition model; and realizing the displacement field recognition of cement-based materials based on the optimal displacement field recognition model. This invention solves the problem of insufficient accuracy and efficiency in the displacement field recognition of cement-based materials by existing methods.

This invention relates to a method, apparatus, and medium for rapid sorting of poultry meat percentage based on X-ray imaging. The method includes: Step S1: acquiring X-ray images of the poultry to be tested; Step S2: identifying the sternal region and skin boundary based on the X-ray image; Step S3: drawing a normal at the sternal apex, obtaining the intersection of the normal at the sternal apex and the skin boundary as the first surface point, and obtaining the initial bone-skin distance based on the distance from the sternal apex to the first surface point; Step S4: obtaining the angle between the X-ray machine's visual axis direction and the normal direction of the first surface point as the consistency difference angle, obtaining the sternal integrity ratio and sternal principal axis attitude angle based on the sternal region, and correcting the initial bone-skin distance based on the consistency difference angle, sternal integrity ratio, and sternal principal axis attitude angle to obtain the corrected bone-skin distance; Step S5: obtaining the meat percentage grading result based on the corrected bone-skin distance. Compared with the prior art, this invention can achieve poultry meat percentage sorting based on X-ray imaging.

The application discloses a heat exchange station control method based on reinforcement learning, and mainly comprises two parts, wherein the first part is a simulation environment model of the heat exchange station learned based on a generative adversarial method, and the second part is a control strategy training of the heat exchange station using a PPO reinforcement learning technology, so that a good heat exchange station control method is obtained. The simulation environment model of the heat exchange station is constructed based on historical data of the heat exchange station, and a generative adversarial method is adopted to learn the simulation environment model, so that the simulation environment can obtain a good simulation effect in a state that has not appeared in the historical data. Then, the simulation environment model learned by the generative adversarial structure is used to train the control strategy by using the PPO reinforcement learning technology. Since the training process of the PPO reinforcement learning technology is relatively stable and the training process variance is small, the obtained control strategy can well complete the control target given by the design reward function, and the temperature of the control result will not lag.

The application belongs to the technical field of artificial intelligence, and relates to a visual language model dynamic multi-teacher hierarchical distillation training method and system. The method comprises the following steps: S1: training sample construction and model initialization; S2: hidden state sequence and output distribution acquisition; S3: sample level dynamic distillation control coefficient construction; S4: token level dynamic distillation control coefficient construction; S5: language distillation signal generation; S6: visual distillation signal generation; S7: output layer multi-teacher distillation loss calculation; S8: intermediate representation distillation loss calculation; S9: total loss function construction; and S10: distillation training. The method can balance language ability recovery and visual positioning ability maintenance, thereby improving the comprehensive performance and training stability of the visual language model.

The application discloses a kind of variable working condition equipment key component fault diagnosis method of class disequilibrium data driving. For the key rotating component in electromechanical complex equipment, obtain the vibration signal and its fault type under the normal and fault state operation of component, construct diagnostic data set and train model, so as to obtain the diagnostic result of the sensor data to be predicted using the trained fault diagnosis model. The application considers the complex situation that the current industrial monitoring data is under variable working condition and class disequilibrium, firstly applies channel-by-channel convolution to generate local feature enhancement weight matrix, and realizes feature enhancement in local feature space using fewer training parameters;Design and introduce wide-range convolution kernel considering the inherent physical characteristics of rotating components, fully and stably capture effective feature information under variable working condition, realize end-to-end fault diagnosis of key rotating components of electromechanical equipment. The application is simple and efficient, not only has theoretical innovation, but also has high practicability.

The application provides a multi-person AR system data offloading and resource allocation method under a 6G network framework, relates to the technical field of 6G mobile communication, selects an AR user as a Host user in each time slot, and the rest are Resolver users; the interaction weight between the Host user and the Resolver user is calculated by using a graph attention network; a data offloading model based on Stackelberg game is established, a multi-party utility function is constructed, a double-layer optimization problem is converted into a single-layer optimization problem, and a sequential quadratic programming algorithm is adopted to solve, so that the optimal data offloading decision is obtained; the resource allocation process is constructed as a Markov decision process, a reward function containing average delay and delay variance is defined, a double-delay deep deterministic policy gradient algorithm is adopted to output a resource allocation strategy of a continuous action space; through the combination of game theory and reinforcement learning, the environmental data redundancy and server rendering load are effectively reduced, the interaction consistency among multi-users is optimized while ensuring low delay, and the collaborative experience of the multi-person AR system is improved.

The application relates to the technical field of real-time target detection and discloses a weakly supervised RT-DETR target detection method based on improved pseudo labels. The method generates pseudo labels by weakly supervising label data sets and enhances the pseudo labels, and an improved model comprising a lightweight backbone network, a pseudo label guided cross-scale interaction module and a decoder with a pseudo label position constraint mechanism is constructed. The model is trained end to end by adopting an iterative pseudo label updating strategy. The pseudo label guided cross-scale interaction module dynamically modulates the feature fusion process by using pseudo label information, thereby enhancing the feature discrimination ability of the model for multi-scale targets. The decoder with the pseudo label position constraint mechanism introduces the geometric prior of the pseudo label as a soft constraint into query optimization, thereby improving the positioning accuracy and training stability of the model under weak supervision and reducing the dependence on accurate labeled data.

This application provides a training method, generation method, and device for a scalp-to-brain magnetic resonance imaging (MRI) generative model, relating to the field of image processing technology. The training method uses scalp and real brain MRI samples to train a Wasserstein generative adversarial network (GAN) with a frequency domain attention mechanism and gradient penalty. This network includes an encoder, a generator, a feature discriminator, and an image discriminator. The encoder and / or generator integrate a neural network model based on the frequency domain attention mechanism. After training, the encoder and generator together constitute the target generative model. The model parameters are jointly optimized using a composite loss function that includes a frequency domain loss term. This application solves the problems of existing brain image generation technologies ignoring scalp structural information and difficulty in modeling global dependencies and high-frequency details. It achieves high-quality generation of brain MRI data from scalp MRI data, improves the structural integrity and topological fidelity of the generated data, and enhances the reliability of assisted diagnostic applications.

The application relates to a speech translation model modeling method and device based on speech synthesis data, and belongs to the technical field of natural language processing; the method solves the problem that, in the prior art, a speech translation model is inaccurate in translation results due to insufficient training data and insufficient utilization; the modeling method comprises the following steps: acquiring a general speech synthesis data set, and training a general speech synthesis model; acquiring a speech translation data set of a target field; fine-tuning the general speech synthesis model in the speech translation data set to obtain a special speech synthesis model; inputting source language labeled text into the special speech synthesis model, generating a plurality of pieces of speech synthesis pseudo data according to a pre-set proportion, and obtaining a pseudo speech data set; constructing an initial speech translation model, training the initial speech translation model by using the speech translation data set of the target field and the pseudo speech data set, and obtaining a speech translation model through loss function iteration and updating.

The application provides an image classification method and device, equipment and a storage medium. The method comprises the following steps: obtaining a first training set, the first training set comprising a plurality of images, each image being labeled with a class label corresponding to each image category; constructing a structure of a first neural network model for multi-label classification; training the constructed first neural network model according to the first training set to obtain a multi-category classification model. The application realizes the simultaneous classification of multiple image categories through one model. The model learns the correlation between the features of different categories through a bidirectional long short-term memory network, and the learned features have better robustness. If the classification accuracy of a certain image category is relatively low, a branch model corresponding to the image category is also trained, the model is corrected by using the branch model, and the problem of low classification accuracy of individual image categories is solved. The model is trained by combining a cross-entropy loss function and a smoothing loss function, the training is more stable, and the effect is better.

The invention belongs to the technical field of data generation, particularly relates to an electroencephalogram modeling method based on a diffusion probability model, and aims to solve the problems that an existing electroencephalogram generation method is unstable in training, limited in generation quality and insufficient in spatial information modeling. According to the electroencephalogram modeling method based on the diffusion probability model, an original electroencephalogram data set is divided into training and testing data, and data fragments are split; calculating power spectral density characteristics of each frequency band according to brain wave frequency bands, and mapping the power spectral density characteristics into a characteristic matrix; in the forward diffusion process, Gaussian noise is gradually added into the data until the data is close to pure noise, and then the data containing the Gaussian noise are input into a noise estimation network to train the original noise prediction capability of the noise estimation network; and finally, generating electroencephalogram data from pure noise by using the trained noise estimation network.

The application discloses a self-adaptive wordpiece table level distillation method for a large language model, comprising the following steps: obtaining wordpiece probability distribution of teacher-student models at each generation step; extracting the union of the first K wordpiece indexes with the highest probability of each step respectively, and constructing an aligned candidate wordpiece set; calculating the absolute value of the teacher-student probability difference as the learning difficulty score of each candidate wordpiece, and collecting and constructing a global difficulty matrix; selecting high difficulty wordpieces from the difficulty matrix according to the current focus ratio to form a target distillation wordpiece set, and re-normalizing the student model probability; only calculating the divergence loss of the target wordpiece set and updating the student model parameters; and dynamically adjusting the focus ratio according to the real-time loss of the student during the training process. The application concentrates computing resources on difficult and high information wordpieces through dynamic self-adaptive screening, reduces the computing power consumption, improves the knowledge transfer accuracy, and is compatible with various distillation targets, and is suitable for deployment of large language models on resource-limited devices.

The invention relates to the technical field of seismic engineering, in particular to a multi-condition seismic oscillation generation method based on a diffusion model, which comprises the following steps: firstly, extracting multi-dimensional condition parameters such as a response spectrum, a peak acceleration, Arias intensity, energy arrival time, significant duration and a Husid curve from a seismic oscillation acceleration time history, and carrying out normalization processing; the acceleration time history is converted into a normalized logarithmic magnitude spectrum through short-time Fourier transform to serve as a learning target; constructing a Transform condition encoder to capture a coupling relationship of multi-source conditions, designing a de-noising network based on U-Net, and integrating a cross attention mechanism to realize accurate condition injection; a denoising diffusion probability model training strategy is adopted to optimize the noise prediction network; during reasoning, a denoising diffusion implicit model sampling strategy is adopted, phase information is iteratively reconstructed from an amplitude spectrum through a Griffin-Lim algorithm, and a seismic oscillation acceleration time history is obtained through inverse transformation. According to the invention, cooperative accurate control of the response spectrum and the energy non-stationary characteristic is realized, training is stable, reasoning is efficient, and diversity generation is supported.

The invention provides a WOA-GRU-based hydrogen atomic clock fixed parameter control method and device. The method comprises the following steps: acquiring and preprocessing a historical operation parameter time sequence of a hydrogen atomic clock; constructing a parameter time sequence prediction model taking a gating circulation unit as a core; performing global automatic optimization on the hidden layer size, the discard rate and the learning rate of the GRU network by adopting a whale optimization algorithm; training a GRU model by using the optimized hyper-parameters; and finally, obtaining a group of collaborative optimal fixed parameter values capable of enabling the hydrogen atomic clock to stably operate for a long time by utilizing the trained model in a rolling prediction mode. The GRU network with a more concise structure is adopted to replace a traditional LSTM network, intelligent global search of WOA is combined, the training efficiency and the model stability are remarkably improved while the prediction precision is guaranteed, and the method is particularly suitable for a hydrogen atomic clock control scene with limited data volume and high parameter noise and has good application prospects. Accurate, stable and intelligent fixed control of internal parameters of the hydrogen atomic clock is realized.

The invention provides a risk-adaptive robot hierarchical social navigation method and system, and relates to the technical field of strategy optimization, and the method comprises the steps: determining a speed fluctuation index and an acceleration fluctuation index based on the speed vector data of a pedestrian sample; performing weighted fusion on the speed fluctuation index and the acceleration fluctuation index to obtain an original uncertainty score, performing normalization on the original uncertainty score, and performing linear mapping to a preset unpredictability interval to obtain an unpredictability score; taking the robot state data sample, the pedestrian state data sample and the unpredictability score as input, taking a preset navigation point of the robot, an expected cruising speed of the robot and a prudent coefficient as output, and performing iterative training and optimization on the initial prediction network model in combination with near-end strategy optimization to obtain a target prediction network model; and inputting the current robot state data, the pedestrian state data and the unpredictability score into the target prediction network model, and determining a current navigation strategy.

This invention discloses an underwater concrete defect image recognition method and system based on a multi-level neural network cascade, belonging to the fields of underwater structure inspection and computer vision technology. It addresses the problems of limited sample size and class imbalance in marine concrete defects, ultimately achieving efficient, accurate, and automated identification of concrete defects in complex marine environments, meeting the practical needs of underwater structure operation and maintenance in marine engineering. The method includes: Step 1, acquiring image data of the underwater concrete structure; Step 2, inputting the image data into a trained improved WaterNet model for image enhancement processing; Step 3, inputting the enhanced image into a trained improved U-Net model for pixel-level segmentation to obtain the concrete defect recognition result; Step 4, annotating the defect area according to the recognition result and outputting the annotated image.