130 results about "Feature adaptation" patented technology

The invention relates to the technical field of image denoising, and particularly discloses a dual-domain heterogeneous image denoising method, which comprises the following steps: extracting a preliminary feature map based on depth separable convolution; an encoder of a double-domain heterogeneous cooperative architecture is adopted in a shallow layer of a hierarchical double-drive encoding and decoding architecture to perform double-domain heterogeneous cooperative processing, through hierarchical feature adaptation, the shallow layer gives consideration to details and local structures, a deep layer focuses on global semantics, and dynamic allocation of computing resources is performed, so that the redundant computing burden is remarkably reduced; and splicing the processed image frequency domain information and the image space domain information, fusing features of each layer after hierarchical processing based on a vertical stripe perception fusion attention mechanism module connected between an encoder and a decoder in a jumping manner, and outputting the fused features to the decoder to obtain the sensitivity of denoising image enhancement to vertical stripe noise. And a noise area is suppressed in a targeted manner.

The invention relates to the technical field of neural network model optimization, and discloses an edge vision AI neural network model optimization method and system, and the method comprises the steps: carrying out the visual feature layering adaptive analysis of an input image, and obtaining the importance distribution of visual features, constructing an initial neural network model adapted to the edge device according to the importance distribution of the visual features; performing energy consumption and precision balance parameter optimization on the initial neural network model to obtain edge device optimization parameters; training the initial neural network model to obtain a trained edge vision model; performing visual semantic perception model pruning on the trained edge visual model to obtain a target network structure; according to the method, deployment optimization adaptive to hardware characteristics is executed according to the target network structure to obtain a visual model for efficient operation of the edge device, so that the model can adapt to heterogeneous characteristics of different edge computing platforms, and the application feasibility of a visual AI technology on diversified edge devices is improved.

The invention discloses an industrial defect detection method based on self-supervised fine tuning, and solves the problems of scarcity of industrial scene defect samples and weak model generalization ability. The method comprises the steps that a data set is divided and preprocessed, and the data robustness is improved through size scaling, random luminosity transformation, geometric enhancement and the like; extracting a foreground mask by using a saliency model, synthesizing a Perlin Noise and DTD texture fused pseudo-abnormal image, carrying out self-supervised fine tuning on the ImageNet pre-trained WideResNet-50, and enhancing the industrial data feature extraction capability; a model containing a visual trunk, feature aggregation mapping, noise feature adaptation and a discriminator is established, local neighborhood features are fused through Unfold operation, Gaussian noise is superposed to generate pseudo-abnormal features, and an abnormal score is output by the discriminator after multi-scale fusion. And the training adopts binary cross entropy and focus loss optimization parameters. The innovation points of the method are that self-supervised fine tuning adapts to industrial data distribution, feature aggregation improves fine-grained detection, and multi-scale fusion considers different defects.

The invention provides a power violation operation identification method based on multi-modal fusion, and the method combines pixel-level fusion of deep learning and a multi-spectral imaging collection technology to construct multi-modal data. A feature adaptation module is used for calibrating multi-scale feature distribution, visual semantics such as objects, scenes and actions in an image are aligned with vocabulary and sentence semantics in a language, multi-level injection is carried out on all levels of calibrated features, key features are strengthened, and violation related visual elements are highlighted. And capturing an operation dynamic process by adopting a neural network with time sequence coding capability, judging through a full connection layer and a classifier, and outputting a violation result. According to the invention, a multi-modal fusion method is adopted, accurate feature processing is carried out under complex illumination and shielding conditions, the recognition accuracy is greatly improved, the misjudgment rate is reduced, and the operation safety is guaranteed.

The invention provides a road inspection method and device in severe weather, electronic equipment and a storage medium, and the method comprises the steps: carrying out the recognition processing of a scene image through a road inspection model, and obtaining a road inspection result of a target road; the training process of the road inspection model comprises the following steps: acquiring a data set, wherein the data set comprises a severe weather image; performing feature extraction on the data set by adopting a pyramid network to obtain a plurality of levels of first feature extraction results; when information fusion is carried out on the first feature extraction results of the multiple levels, feature adaptation processing is carried out according to the first feature extraction results, and a second feature extraction result is obtained; performing feature enhancement modulation on the second feature extraction result by adopting double branches, and merging feature enhancement modulation results to obtain a modulation feature map; and predicting the modulation feature map to obtain a prediction result. The method has the beneficial effect that the vehicle type identification accuracy during road inspection in severe weather is improved.

The invention provides an urban landscape semantic segmentation system adopting an EGLiteSeg model, and belongs to the field of image processing. Comprising three main parts: an encoder; an polymerizer; and a decoder. The EGLiteSeg framework adopts a lightweight encoder-decoder pipeline to carry out image processing, and an encoder of the EGLiteSeg framework is provided with a five-level DeSTDCNet framework. In the first four stages, depth separable convolution with the stride being 2 is utilized, and the AECA module automatically adjusts the size of a kernel according to the number of input channels so as to enhance the multi-scale feature adaptability. For context aggregation, the framework uses GDSPPM. The module processes features through deep convolution to enhance distinguishability, and then performs multi-scale pyramid pooling to capture hierarchical contextual information. The multi-scale features are connected together and fed into a decoder. The decoder is composed of two key components: a universal attention fusion module (UAFM) and a partition head. The method not only has high semantic segmentation accuracy, but also has superiority in real-time performance, and meets actual requirements.

The invention discloses a flow characteristic adaptive QoS intelligent prediction adjustment method, and relates to the field of network flow management, and the method comprises the steps: 1, collecting flow data in real time, and constructing a multi-dimensional characteristic vector based on protocol types, port numbers and user behavior dynamic classification; 2, high-frequency / low-frequency components are separated, and QoS parameter prediction is output through fusion of an LSTM short-term prediction module and a periodic trend analysis module; 3, solving a resource pre-allocation scheme by adopting reinforcement learning by taking minimization of packet delay as a target; and 4, executing traffic identification, speed limiting and priority queue scheduling by using NPU hardware unloading. According to the method, the precision is improved through a high-frequency / low-frequency combined prediction architecture, decision delay is compressed to a large extent through reinforcement learning and NPU cooperation, and meanwhile online model iteration is achieved through a prediction error triggering mechanism.

Systems and techniques are described herein for adapting a pretrained machine learning model. For instance, a process can include encoding a training image into a first feature vector, the training image including a first object located at a first location; generating a second feature vector based on a set of sinusoidal functions using a set of weights; combining the first feature vector with a second feature vector to generate a combined feature vector; processing the combined feature vector using a visual language model to obtain a second location for the first object; and adjusting the set of weights based on a comparison between the first location and the second location.

The embodiment of the invention provides a content recommendation method and device and a double-tower content recommendation model training method and device, and the content recommendation method comprises the steps: obtaining the content information of to-be-recommended content and the user information of a target user in response to a content recommendation task; the user information and the content information are input into a double-tower content recommendation model, recommended content for the target user is obtained, the double-tower content recommendation model comprises a user tower and a content tower, the user tower is used for extracting user features based on the user information, and the content tower comprises a feature adaptation layer; the feature adaptation layer is used for obtaining target content features corresponding to a task target of the content recommendation task based on the content information, and the recommendation content is obtained by decoding based on the target content features and the user features. The content representation can be dynamically adjusted according to the task target through the feature adaptation layer, so that the same content presents differentiated feature expression under different tasks, and the adaptation precision of the recommendation result to the specific task target is improved on the premise of not changing the double-tower structure.

The invention discloses an ultra-high-definition video stream adaptive coding method based on deep learning visual saliency, and the method comprises the steps: carrying out the five-scale Gaussian filtering processing and image pyramid construction of a video frame, and combining Sobel gradient, Laplacian edge and local binary pattern feature extraction to generate a multi-scale feature map; a pre-training saliency detection network is adopted, and a smooth saliency thermodynamic diagram is generated through processing of a feature adaptation layer, a residual encoder, a self-attention mechanism and a transposed convolution decoder; dividing the video frame into a high region, a middle region and a low region according to the saliency thermodynamic diagram, and establishing a regionalization coding parameter table; performing differentiated prediction modes, motion estimation and quantization strategies on different salient regions; and organizing coded data according to an H.265 / HEVC standard, and embedding the saliency thermodynamic diagram into supplementary enhancement information for transmission. According to the method, the important region concerned by the user can be intelligently identified, a differentiated coding strategy based on content semantics is realized, and the coding efficiency is remarkably improved.

The invention discloses an action error prevention method and system based on AI identification. The method comprises the following steps: acquiring a standard action video and a to-be-detected action video; inputting the standard action video into a dynamic serialization analysis model for training, and extracting movement track features of standard human skeleton points and standard key objects; inputting the to-be-detected action video into the trained dynamic serialization analysis model to extract motion track features of to-be-detected human skeleton points and to-be-detected key objects; and comparing the motion trail characteristics of the standard motion with the motion trail characteristics of the to-be-detected motion to obtain an error value, and comparing the error value with a preset threshold to judge whether the motion is wrong or not. The method can overcome the defects that a traditional detection method is low in efficiency, difficult to capture motion dynamic characteristics, poor in adaptability and the like, manual operation errors can be found in time, and the product quality and the production efficiency are effectively guaranteed.

The invention provides a weak password detection method based on multi-modal feature fusion and dynamic behavior analysis. According to the method, multi-dimensional feature extraction is innovatively introduced, including password entropy, semantic relevance, user historical behaviors, system login frequency and the like, so that user feature adaptation is improved, and dependency on a static dictionary is reduced; in addition, through real-time interactive feedback, instant pushing of password strength evaluation and safety suggestions can be realized. Therefore, by means of the method, the problems that in an existing weak password detection technology, the static dictionary dependency is high, the user feature adaptation is insufficient, and real-time feedback is lacked can be solved, the weak password detection precision and defense efficiency of colleges and universities are remarkably improved, and an efficient and easy-to-deploy password security solution is provided for the education industry.

The invention provides a hyperspectral image one-class classification method and system based on adjacent channel grouping, and the method comprises the steps: inputting a hyperspectral image, extracting preliminary feature maps through a feature extraction layer, carrying out the fusion of the preliminary feature maps through a multi-scale feature fusion layer, and obtaining a first fusion feature map; performing channel attention processing on the first fusion feature map to obtain a second fusion feature map, mapping the second fusion feature map to a category label, and establishing a learning model to perform multiple rounds of training by adopting a self-adaptive sample optimization mechanism based on heterogeneous representation fusion, and continuously optimizing model parameters by adjusting weights of positive and negative samples to obtain a trained learning model, and predicting a new hyperspectral image by using the trained learning model to obtain a category in the new hyperspectral image. According to the method, self-adaptive resource allocation and multi-scale feature adaptation and fusion can be realized only by inputting a single sample, the positive and negative sample proportion score is self-estimated, and the classification precision is high.

The invention discloses a few-sample industrial processing anomaly detection method based on a pre-training model CLIP, and aims to solve detection pain points of scarcity of abnormal samples, high labeling cost and insufficient generalization in an industrial scene. The method comprises the following steps: data preprocessing: collecting an industrial image, dividing the industrial image into a support set only containing normal samples and a query set containing normal and abnormal samples, and combining data enhancement and local module clustering decomposition; cross-modal feature adaptation is carried out, text semantic anchor points are constructed through combination prompt integration, a residual adapter is inserted to optimize vision-text feature alignment, and multi-scale features are aggregated by adopting a harmonic average method; few-sample reference learning is carried out, a normal mode reference memory bank is constructed based on a prototype network, and feature learning is reinforced in combination with feature registration and alternate learning; and abnormal judgment: realizing abnormal recognition through cosine similarity calculation and a dynamic threshold value, and outputting an image-level confidence coefficient and a pixel-level segmentation image.

The invention relates to the technical field of train fault diagnosis, in particular to a fault diagnosis method for a train transmission system, and overcomes the defects that weak features are difficult to extract and fault features are difficult to effectively distinguish in the prior art. In combination with the strong feature extraction capability of a deep network model constructed by an InceptionResNetV2 network, local and global features are captured by using a parallel multi-branch structure and a residual adaptive fusion mechanism, and through multi-scale perception and residual cross-layer connection, the capture capability of the super-huge bearing weak fault time sequence-frequency domain features can be significantly enhanced, and the fault detection accuracy is improved. And finally, pre-training a model by using source domain data, extracting parameterized knowledge of the model, and migrating to a target domain to realize parameter fine tuning and feature adaptation, so that the generalization performance and convergence speed of fault diagnosis can be improved, different fault categories can be effectively separated, and feature aggregation of the same category can be realized.

The invention discloses a house safety detection method, system, equipment and medium, and relates to the technical field of intelligent building safety monitoring, and the method comprises the steps: collecting the data of key parts of a house through a sensor, and carrying out the preprocessing; and uploading the preprocessed data to a cloud end, constructing a feature adaptation graph network and structure time sequence memory network fusion model, performing multi-dimensional feature extraction and house potential safety hazard risk modeling, analyzing the change trend of the house structure and environment data, and identifying the potential safety hazard of the house. And according to a risk trend vector output by the fusion model and a configured multi-dimensional threshold rule, carrying out house potential safety hazard identification, and carrying out graded response early warning. According to the method, the problems of weak space-time sequence modeling, rigid response control and the like in the existing house safety monitoring technology are solved. A complete intelligent risk identification and early warning intervention closed loop is formed, the accuracy and timeliness of hidden danger discovery are improved, and the adaptive capacity and the actual implementation of the system in a complex environment are enhanced.

The invention provides a mine post personnel behavior identification method and system based on artificial intelligence, and the method comprises the steps: constructing a mine post dynamic behavior logic reference model, combing post personnel standard operation behavior and process node association logic, and dynamically adjusting the weight. Acquiring personnel behavior acquisition data, and performing adaptive processing on the data and the model to obtain to-be-identified behavior data; and calling a pre-trained AI behavior difference adaptation model to carry out bidirectional feature adaptation, and generating dynamically optimized behavior feature adaptation parameters. And based on the parameters, performing enhancement processing on the to-be-identified behavior data, mining hidden logic association, and generating an enhanced behavior difference feature set. And performing compliance verification according to a preset rule base to obtain a compliance verification result. And finally, generating a post behavior control instruction according to the result and sending the post behavior control instruction to a mine operation control terminal. According to the invention, behaviors of mine post personnel can be accurately identified, and operation safety and high efficiency are guaranteed.

The invention discloses a hyperspectral image segmentation method and device based on fusion point prompt and Markov diffusion, and relates to the technical field of hyperspectral image processing. The method comprises the following steps: performing spectrum-space dimension reduction processing according to hyperspectral initial data; on the basis of preset uniform distribution points, according to the spatial partitioning features, a spectrum-spatial feature adaptation module is used to carry out point prompt guided coarse segmentation; based on a cross double-attention mechanism, using a multi-modal fusion module to perform text-image feature fusion; performing multi-scale feature extraction by using a U-net encoder according to the hyperspectral initial data; diffusion reconstruction is carried out based on a symmetric codec convolutional network of a Markov diffusion model, and de-noised hyperspectral features and high-order fusion masks are extracted; and based on a cross entropy loss function, performing model optimization according to the segmentation prediction data. The hyperspectral image segmentation method is based on the text semantic features, fully considers the characteristics of the hyperspectral image, and is high in efficiency and robustness.

The invention discloses an intelligent matching system based on big data resources, and the system comprises a data acquisition module which collects multi-source matching data, carries out the fusion processing, and obtains user behavior characteristics and resource behavior characteristics from the processed multi-source matching data; the feature adaptation module is used for acquiring a user behavior feature matrix and a resource behavior feature matrix, and inputting the user behavior feature matrix and the resource behavior feature matrix by constructing an improved space-time convolutional network model to obtain an optimal preliminary matching factor; and the intelligent matching module is used for labeling high-quality matching tags, taking the high-quality matching tags as a labeling data set of a parameter calculation model based on a neural network architecture, obtaining optimal adjustment parameters through the parameter calculation model, making an optimal decision according to the optimal adjustment parameters, and providing a fine decision basis for intelligent matching of big data.

The application discloses a kind of multi-text feature adapter enhanced professional accomplishment named entity recognition method.The application is according to the meaning of content to professional accomplishment named entity and is labeled, and based on "BIO" method, professional accomplishment named entity is labeled with character tag;And with the characteristics and advantages of BERT model in the field of natural language processing, multi-text feature adapter is integrated into BERT to fine-tune the model, and MFEBERT model is proposed;Professional accomplishment named entity recognition model of MFEBERT+BiLSTM+CRF is constructed, MFEBERT utilizes the multi-text feature adapter to fuse the character-level features, lexical-level and part-of-speech-level fusion features of professional accomplishment named entity, learns the constraint conditions of professional accomplishment named entity by BiLSTM+CRF, and finally realizes the intelligent identification of professional accomplishment named entity, provides important technical support for scientific, accurate and effective construction of professional accomplishment evaluation index system, and helps to promote the innovative construction and application of education evaluation system.

The application relates to the technical field of automatic driving perception, in particular to a space prior calibration and feature adaptation method and system for a sparse perception architecture, which freezes the interpolated position embedding matrix into a non-trainable state, so that the space layout sensitive representation (such as object relative position and scale relationship) learned in the pre-training stage is completely preserved, the space prior destruction caused by the re-learning of a downstream task is avoided, and the overfitting risk is effectively reduced. A learnable 1x1 one-dimensional convolution is used for calibration along the channel dimension, so that the trainable parameter quantity and the input resolution are completely decoupled. The image features output after the space prior protection and the channel response calibration have accurate geometric structures, so that the Deformable Attention (deformable attention) mechanism in a sparse perception method such as Sparse4D is accurate in positioning and rich in feature semantics when four-dimensional key point sampling is performed, and the overall performance of three-dimensional target detection is improved.

The application provides a kind of operation and maintenance scene visualization report generation method and system based on natural language question and answer, belongs to intelligent operation and maintenance technical field, method includes: receiving the natural language query input by user;Through the pre-training of large language model and the preset operation and maintenance terminology dictionary, the natural language query is parsed and entity is extracted, and the entity-field association table containing demand type is generated;According to demand type and semantic feature, the query type is judged to be data query or visual query;Based on the judgment result, generate structured query language sentence or visual instruction;Query is executed to the interface business database to obtain raw data;Raw data is processed and analyzed to obtain analysis result data;Call data feature adaptation algorithm to match chart type, generate and output visual report.The application realizes the full-link automation from natural language input to visual report output, reduces the operation and maintenance data interaction threshold, improves the operation and maintenance data processing efficiency and accuracy.

The invention discloses a few-sample anomaly detection method based on two-stage training, relates to the technical field of few-sample anomaly detection, and comprises a two-stage training network (TSTNet) based on metric learning, and in a pre-training stage, geometric consistency loss is introduced to promote convergence of normal samples and geometric variants thereof in a feature space. In a metric learning stage, an edge feature adaptation network is designed, fuzzy normal features can be clustered adaptively, and abnormal features are effectively isolated. A large number of experiments on an MVTecAD data set and a VisA data set show that the scheme exceeds the existing level, and under the two-sample experiment setting, the performance of the method on image level AUROC is improved by 1.2% and 2.4% respectively compared with the MVTecAD data set and the VisA data set.

The application discloses a video target recognition method based on multi-model hot switching, and belongs to the technical field of computer vision and video processing. The method comprises an arbitration module, a switching control module and a feature adaptation and buffer module. The arbitration module generates a switching preparation signal by extracting multi-dimensional indexes such as optical flow mean, local variance, target density and scene confidence in real time through a lightweight channel independent of main reasoning. The switching control module performs atomic replacement of a computation graph pointer in a vertical blanking period, and realizes millisecond-level hot switching with zero frame loss by combining an asynchronous pre-copy and a chasing mechanism of a double buffer. The feature adaptation and buffer module solves tensor shape mismatch between heterogeneous models through a pre-compiled adaptation layer. The application also provides optimization schemes such as multi-index nonlinear fusion decision, zero-copy memory management, local slice focus reasoning and edge-cloud hierarchical unloading, significantly reduces switching delay, guarantees continuous recognition of a video stream, and is suitable for edge computing scenes with limited resources.

The present invention belongs to the field of data mining technology and relates to a method for discovering the influence of key elements based on native-derivative topic transfer learning, including obtaining information including native topics and derived topics and related user information from an API interface provided by a social platform; constructing the early propagation network topology and propagation timing of derived topics, including using a joint distribution adaptive method to perform cross-domain feature adaptation on the content space of native topics and derived topics, and considering the sparsity of early data of derived topics, using an adversarial transfer learning method to compensate for the network structure; constructing a message-path-user ternary association graph of derived topics and performing cyclic iterative scoring to rank the influence of key elements of derived topics; the present invention can timely and accurately mine key elements in the early stage of the outbreak of derived topics, and the present invention can also be widely used in the precise placement of product advertisements, the discovery of important pathogenic genes, the prediction of popular research results, and the prevention of computer virus propagation.

The invention relates to a visual feature adaptation method based on flight scene category driving, and belongs to the technical field of image processing. The method comprises the following steps: establishing a scene classification data set with labels; constructing an image feature extraction algorithm set; performing feature extraction on the images of the various flight scenes in the scene classification data set by using algorithms in the algorithm set one by one, and performing feature merging and dimension reduction to obtain representative features corresponding to the various scene images; then image clustering is carried out, and representative features of all images under each algorithm are clustered into clusters with the same number of scene categories through clustering; and according to the clustering result and the actual scene classification label of the image, calculating the index of the feature adaptation degree, which is used for representing the adaptation degree of the image feature extraction algorithm for processing a certain scene image. According to the method, accurate comparison of feature adaptation degrees of different feature extraction algorithms under various flight scene categories is realized, and a scientific basis is provided for feature selection in an aircraft visual task.

The invention discloses a scene feature joint modeling method, system, equipment and medium, and relates to the technical field of power grid engineering, and the method comprises the steps of completing spatial-temporal scale calibration, extracting independent feature vectors, generating a fusion feature map, screening key influence factors, generating comprehensive feature representation, and measuring and calculating cost and engineering quantity. The system comprises an acquisition and alignment module, a feature extraction module, a feature fusion module, a correlation analysis module, a depth modeling module and a prediction module. By constructing a space-time unified reference framework, multivariate cross-modal data is mapped to a unified space-time scale, and the problem of data islands is solved; a multi-resolution feature adaptation strategy is utilized to extract fusion features considering shallow details and deep semantics, and feature extraction comprehensiveness is ensured; and the influence of the key factors is quantified by establishing a regression mapping model, so that the accuracy and reliability of power grid project cost measurement and calculation are greatly improved.

The present invention discloses a method for recognizing large-angle license plate images, comprising: obtaining a training data set and a test data set, wherein the training data set comprises a first number of simulated large-angle motion-blurred license plate images with license plate numbers annotated, and the test data set comprises a second number of real large-angle motion-blurred license plate images; inputting the training data set into a pre-built adaptive license plate recognition network for end-to-end training to obtain a trained adaptive license plate recognition network, and inputting the test data set into the trained adaptive license plate recognition network for model evaluation and optimization to obtain an optimized adaptive license plate recognition network, wherein the adaptive license plate recognition network comprises a feature extraction module, a spatial transformation parameter prediction module, a scale-aware feature adaptation module, a feature adaptive integration module, an upsampling module, and a character recognition module; and inputting a license plate image to be recognized into the optimized adaptive license plate recognition network for license plate recognition to obtain a license plate recognition result.

This application discloses a method and apparatus for scientific chart data reconstruction based on semantic understanding and feature adaptation, relating to the field of scientific chart data reconstruction technology. The method includes: acquiring an image of the scientific chart to be reconstructed and identifying the data representation area and coordinate frame area; performing semantic parsing on the scale numbers within the coordinate frame area and constructing a mapping relationship between image pixel coordinates and image scale coordinates; identifying data markers within the data representation area and obtaining data sequences with different marker styles through multimodal feature vector clustering; applying the mapping relationship based on the image pixel coordinates of the data markers in each data sequence to obtain the scale coordinates corresponding to each data marker, thereby performing scientific chart reconstruction to obtain a reconstructed scientific chart image. This application solves the fundamental problem that existing tools are limited in scope due to their reliance on predefined templates, enabling a single technique to cover the vast majority of chart types in scientific publications.

The invention discloses a necking detection method based on geometric feature self-adaption. The necking detection method comprises the following steps that S1, the longest main axis of a simulation graph is determined; s2, selecting N feature points on the longest main shaft; s3, obtaining the minimum key size of the simulation graph at each feature point; and S4, judging whether the simulation graph has a necking risk or not based on each minimum key size. By identifying the geometric centroid and the longest principal axis of a graph, adaptively selecting feature points and performing omnidirectional scanning, the measured minimum critical dimension is compared with a set safety threshold, and a risk point which is most likely to generate necking on the graph is accurately positioned, so that the automation and objectification of risk detection are realized, and the risk detection efficiency is improved. Subjectivity and experience dependence of manual marking are avoided, and consistency of detection results is guaranteed; meanwhile, the method has good adaptability to complex or deformed contours, missing detection and misjudgment are effectively avoided, and the yield and reliability of chip manufacturing are improved.