589 results about "Accurate segmentation" patented technology

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a segmentation and matching method, device, equipment and medium for an image background region. Multi-scale features are obtained through cavity convolution branch, fusion features are generated through weighted fusion, the fusion features are input into a decoder network to obtain a background segmentation mask, a background area image is obtained by combining the preprocessed image, and a visual converter model is input to extract background feature vectors; and performing similarity matching with a target feature vector in a preset feature database to retrieve a target image. According to the method, the segmentation accuracy and robustness are improved through combination of multi-scale feature fusion and the visual converter, meanwhile, the retrieval discrimination and reliability are enhanced through feature matching, the problems that an existing method is insufficient in segmentation precision and limited in retrieval capacity are solved, and precise segmentation and efficient retrieval of the background in a complex scene are achieved.

The invention discloses an overlapped cervical cytoplasm region segmentation method based on deep learning and a conditional diffusion model, and relates to the technical field of artificial intelligence analysis of medical images. According to the method, accurate segmentation of the overlapped cytoplasm region in the cervical cell image is realized through a morphological prior guided conditional diffusion process. The method comprises the following steps: constructing a multi-scale cervical cytoplasm mask pair image; designing a cytoplasm specific data enhancement and preprocessing process; building a multi-branch cervical cell morphology perception condition diffusion network; using a self-adaptive multi-scale combination loss function to optimize training; and a hierarchical classifier is adopted to freely guide sampling for reasoning. According to the method, the frequency domain and space domain features are fused, a cellular morphology and statistics priori knowledge base is established, and a strategy of generating complete cytoplasm by adopting non-overlapped parts is adopted, so that the problem that the traditional method is difficult to segment in complex backgrounds and overlapped regions is successfully solved, and reliable technical support is provided for early screening of cervical cancer.

The invention relates to the field of medical image analysis, in particular to a deep learning prediction system and method based on multi-modal thyroid cancer lymph node metastasis, and the system comprises a data collection module, a preprocessing module, a nodule segmentation module, a feature extraction module, a feature fusion module, a metastasis prediction module, an interpretability analysis module and a result display module. An ultrasonic image, an elastic imaging image, an ultra-micro blood flow image and clinical index data of a patient are integrated, an improved U-Net algorithm is used for precise segmentation of a thyroid nodule region, a multi-branch deep network is used for extracting multi-modal features, a dynamic weight fusion algorithm is used for integrating the features, and the accuracy of the thyroid nodule region is improved. According to the method, the thyroid cancer lymph node metastasis state (non-metastasis, central region metastasis or lateral neck metastasis) is predicted, meanwhile, a two-dimensional interpretability framework of Grad-CAM activation diagram and SHAP value contribution degree analysis is introduced, an intuitive prediction basis is provided for doctors, and the thyroid cancer lymph node metastasis prediction accuracy is remarkably improved.

The invention discloses a remote sensing image semantic segmentation method and system based on a dynamic attention mechanism, and relates to the technical field of remote sensing image processing, and the method comprises the following steps: carrying out the labeling and enhancement processing of a multi-scene remote sensing image, and generating a standardized data set; processing the data set through an encoder, and extracting a multi-scale high-dimensional feature map; decoding the multi-scale high-dimensional feature map, and fusing a decoding result with scale features to generate an optimized feature map; based on the optimized feature map, adopting a joint loss function to synchronously optimize segmentation, detection and classification tasks; performing dynamic up-sampling and boundary refinement on the optimized feature map, and outputting a structured analysis result; according to the method, the boundary information of the ground objects in the remote sensing image is accurately extracted through a dynamic processing flow and introduction of a double-flow decoder network and a multi-task joint optimization strategy, accurate segmentation and classification of the ground objects in a complex scene are achieved, and the overall effect of analysis and processing of the remote sensing image is improved.

The invention relates to the field of image processing, and particularly discloses a man-machine collaborative remote sensing image labeling method based on an SAM model, which does not directly input sparse prompts of a user into the SAM, but firstly utilizes a pre-trained remote sensing semantic segmentation model to pre-compute an image to generate a semantic graph rich in surface feature category information. On the basis, single-point interaction of the user is combined with the semantic graph, dynamic semantic prompt enhancement is carried out, namely, a user intention area is automatically recognized, a dense enhancement prompt set with definite positive and negative attributes is generated, the enhancement prompt set can convert the fuzzy intention of the user into a guide signal capable of being accurately understood by a machine, and the user intention is automatically recognized. According to the method, the segmentation process of the SAM model is constrained, the segmentation result which is consistent in semantics and accurate in boundary is generated, and the optimal mask is further optimized through semantic consistency, so that the segmentation ambiguity is fundamentally solved, and the efficiency and accuracy of remote sensing image labeling are improved.

The invention relates to the technical field of deep learning and computer vision, and discloses a histogram interactive attention-based pavement crack segmentation network processing method and system, so as to enhance the edge detail fidelity and improve the crack segmentation precision. The method comprises the steps of image preprocessing, up-sampling, down-sampling, feature fusion and image reconstruction processing. Wherein global feature modeling in the intensity sub-boxes and among the sub-boxes is realized by constructing a histogram interactive attention module (HIA); a double-branch detail enhancement feedforward module (DDEF) is introduced to enhance spatial detail and high-frequency edge information expression; meanwhile, a Fourier jump enhancement module (FFSM) is adopted to jointly refine jump connection features in a spatial domain and a frequency domain. Through the synergistic effect of the modules, the network can realize continuous recovery and structural consistency modeling of a crack boundary in a complex pavement environment, so that the accuracy and the stability of a segmentation result are remarkably improved.

The invention discloses an object three-dimensional reconstruction method, device and system based on deep learning. The reconstruction method comprises the following steps: acquiring a multi-view color image of an object through a controllable image acquisition device; reconstructing a sparse three-dimensional point cloud by using a motion recovery structure method and obtaining a camera pose; initializing parameters of the three-dimensional Gaussian sputtering model based on the sparse point cloud and performing training optimization; a target object semantic segmentation data set is constructed, and a low-rank adaptive technology is adopted to finely segment all models; generating prompts through an open vocabulary detection model at each view angle, obtaining an accurate segmentation mask, and optimizing a three-dimensional segmentation weight by adopting a joint loss function fusing color consistency loss and edge perception loss; and finally outputting the color three-dimensional point cloud of the target object. According to the method, the original image is segmented, so that the influence of the quality of the rendered image is avoided; the segmentation precision of the model in a specific scene is improved through field adaptive fine tuning; and the accuracy of the segmentation boundary is ensured by adopting a double-loss joint optimization mechanism.

According to the movie and television play table book extraction method and device, the storage medium and the computer equipment provided by the invention, after an audio and video file of a movie and television play is split into a video file and an audio file, feature recognition is performed on the video file to obtain a subtitle text, speaker face information and a video understanding text; performing voice understanding on the audio file to obtain a voice transcription text and a voice understanding text; wherein the voice transcription text can be corrected into the standard transcription text with high accuracy through the subtitle text. Therefore, based on the face information of the speaker, the line segment of each speaker in the standard transcriptional text and the audio and video file is aligned, so that speaker information with accurate segmentation and semantic coherence can be obtained; and then, through combination with a character side-writing text generated by side-writing analysis on the speaker based on the video, the voice understanding text and the speaker information, table book information is constructed, and related feature description of the character can be covered on the basis of containing the line content, so that the content and depth of the table book are enriched.

The invention discloses a camouflage object detection refining method based on an uncertainty mask Bernoulli diffusion model. The camouflage object detection refining method comprises the following steps: firstly, generating an initial segmentation mask by using a pre-training model; analyzing the image and the initial mask through a hybrid uncertainty quantization network (HUQNet), and generating a spatial uncertainty mask for identifying a residual region; taking the initial mask as a Bernoulli distribution mean value, modulating noise injection in combination with an uncertain mask, iteratively denoising through a Bernoulli diffusion model, and correcting a residual region in a targeted manner; and finally, fusing the refining result and the initial mask to determine an area, and outputting a final segmentation mask. The problems of large-range fuzzy edge, detail loss and false positive / negative correction existing in camouflage object detection in the prior art are solved. The camouflage object detection refinement device provided by the invention has wide application potential in multiple fields by improving the capability of accurately segmenting an object highly fused with the environment.

The invention discloses a method for estimating plant biomass based on map multi-modal feature extraction and fusion. The method comprises the following steps: acquiring a plant RGB image and a multi-spectral image; inputting the preprocessed RGB image and NIR wave band image into a double-model cooperation segmentation framework to realize image segmentation; binary image features, color features, texture features, reflectivity and the like are calculated, feature splicing is carried out, and high-dimensional features are constructed; carrying out dimension reduction on the high-dimensional features; and training a deep neural network through the effective features and the biomass to realize biomass estimation. According to the method, a zero sample learning-based double-model cooperation segmentation framework is utilized to realize accurate segmentation of a single plant on the premise that a large number of training sets are not needed; multi-modal feature information is extracted based on the segmented single plant image, an improved SHAP model is introduced to reduce the feature space dimension, and the inversion precision and the operation efficiency are improved while the information effectiveness is ensured; through a high-precision deep neural network model, rapid, lossless and accurate biomass acquisition is realized.

The invention provides a wetland ecosystem health evaluation method based on multi-source remote sensing data, and belongs to the technical field of wetland ecosystems, and the method comprises the steps: carrying out the dense dark pixel and Kalman filtering cooperative atmospheric correction of a multi-spectral remote sensing image to obtain a surface reflectance image, and achieving the precise segmentation of a wetland landscape through a graph cut theory, a spectral unmixing model based on an improved Gaussian kernel is utilized to embed physical constraints to invert water quality parameters, a laser radar canopy height priori constraint three-dimensional radiation transmission model is combined to invert vegetation parameters, and a mixed pixel decomposition result is optimized through a Markov random field. A water quality, vegetation and landscape three-dimensional comprehensive health evaluation system is constructed, degradation dominant factors are identified, and the technical problem that it is difficult for multi-source remote sensing data to cooperatively invert wetland ecosystem multi-dimensional health state parameters is solved.

The invention relates to the field of new energy, and discloses a photovoltaic system efficiency evaluation method and system based on unmanned aerial vehicle multi-source image fusion, and the method comprises the steps: collecting a visible light orthoimage, thermal imaging data and environment parameters of a photovoltaic system, and obtaining a registration result through employing an improved feature point matching algorithm; based on a registration result, combining spatial features of a visible light image and temperature features of thermal imaging, realizing accurate segmentation of the photovoltaic panel through a deep learning model, and identifying the type, the arrangement mode and the installation angle of the photovoltaic panel at the same time; establishing a mathematical model of the relation between the photovoltaic panel temperature distribution and the power generation efficiency, distinguishing the normal working temperature difference and the fault hot spot, and analyzing and determining the efficiency attenuation degree and the fault type of the photovoltaic system through a heat distribution mode. The method is accurate in image registration, good in data fusion effect, accurate in temperature anomaly detection and comprehensive in efficiency evaluation, and provides more efficient and accurate technical support for management and maintenance of the distributed photovoltaic system.

The invention discloses an intelligent bone marrow megakaryocyte morphology detection method which comprises the following steps: S1, data preparation: collecting and preprocessing a digital large map of a bone marrow smear, labeling megakaryocytes, and establishing a labeled sample; s2, generating and sorting a sample: extracting a small graph sample by taking megakaryocyte as a center; s3, constructing a deep learning model: constructing and training a deep convolutional neural network, and performing model optimization and performance improvement by using the generated small image sample set; s4, large image detection and reasoning: calling the trained model for reasoning by adopting a sliding window mechanism, and fusing detection results of a plurality of small windows back to an original large image through confidence weighting and a non-maximum suppression strategy; and S5, target cell segmentation: carrying out target segmentation on the detected megakaryocyte, and introducing a pyramid structure for cells with different sizes to obtain an accurate segmentation mask of each target cell. According to the method, the megakaryocyte detection and segmentation precision is improved through large image labeling, small image training and a sliding window reasoning strategy.

The invention provides a polyp image segmentation method based on multi-branch fusion and cross attention collaboration, belongs to the technical field of medical image segmentation, solves the problem of high omission ratio of small polyps by introducing an encoder structure based on Pvt v2 and combining multi-module collaboration, meets the requirement for precise detection of the small polyps clinically, and improves the detection accuracy of the small polyps. The early screening effect of the colorectal cancer is improved; by designing a multi-branch fusion module, the problem of fuzzy polyp edge areas is solved, the accuracy of segmentation results is improved, and an accurate basis is provided for judging polyp boundaries; the balance between the calculation efficiency and the feature capture capability is realized by providing a double-channel cross attention module, and the efficient and accurate segmentation of the complex polyp is ensured.

The invention discloses a landslide segmentation model based on multi-loss function fusion, particularly relates to the field of landslide monitoring, is used for solving the problems of precise segmentation of a landslide area and insufficient identification precision in a complex scene, realizes precise segmentation of a landslide image through multi-level feature extraction and adaptive optimization, and has remarkable beneficial effects. The detail identification of the landslide area is enhanced by utilizing self-adaptive channel response and multi-scale feature fusion, so that features of different scales are fully expressed; weighted combination and residual connection of global and local features ensure continuous transmission and integration of high-level and low-level features, and detail and global information are completely reserved. The spatial resolution is recovered through up-sampling and channel splicing, and it is ensured that a segmentation result is consistent with an original image; the multi-level nonlinear loss function improves the robustness of the model under the condition that the samples are unbalanced, samples difficult to classify are effectively concerned, and the model shows a high-precision segmentation effect in a complex scene.

The invention discloses a field wheat three-dimensional character analysis method based on unmanned aerial vehicle multi-view three-dimensional point cloud, and the method comprises the following steps: S1, shooting a multi-view image and carrying out the three-dimensional reconstruction, and obtaining an original point cloud; performing interpolation segmentation and secondary segmentation, and outputting a plurality of cell point clouds; s2, performing data enhancement, starting model training, and obtaining each 3D bounding box; s3, extracting point cloud data of each planting row from each 3D bounding box by using a row segmentation algorithm, and calculating each static phenotype parameter; and S4, calculating five dynamic phenotypic parameters of the field wheat. According to the invention, based on the 3D wheat plot detection network and the row segmentation algorithm, the point cloud data and the 3D bounding box of the wheat are rapidly extracted, and accurate monitoring and accurate segmentation of the wheat are realized; based on accurate analysis of static phenotypic parameters, a new system of dynamic phenotypic parameters is provided, and based on the dynamic phenotypic parameters, the growth vigor and yield of wheat can be effectively predicted.

The invention discloses a CT-based osteoporosis intelligent diagnosis method and system, and relates to the technical field of medical image diagnosis, and the method comprises the steps: carrying out the positioning of a lumbar region in an abdomen or thoracic and abdominal CT image through a deep learning model; digitally modeling the shape and the internal structure of the vertebral body; and automatic diagnosis of osteoporosis is completed. According to the method, full-automatic positioning, accurate segmentation and intelligent diagnosis of osteoporosis of the lumbar region in a conventional abdomen or thoracic and abdominal CT image are realized, the accuracy and efficiency of diagnosis are remarkably improved, and the problems of strong subjectivity and poor repeatability caused by dependence on manual sketching or simple threshold segmentation in a traditional method are solved; the method can be directly operated based on clinical conventional CT data, is beneficial to large-scale osteoporosis screening and early intervention, and has remarkable clinical popularization significance and technical progress value.

The invention discloses a road surface meteorological state image segmentation method based on a YOLOv8-BRFA model. The method comprises the following steps: acquiring a near-infrared road surface meteorological image data set; designing a dynamic sparse attention mechanism and a hardware perception neural network based on a YOLOv8 network architecture, and constructing a road surface meteorological state segmentation model in combination with an adaptive decoupling detection head; training the road surface meteorological state segmentation model by using a near-infrared road surface meteorological image data set to obtain a trained road surface meteorological state segmentation model; and obtaining a to-be-detected road surface meteorological image, inputting the to-be-detected road surface meteorological image into the trained road surface meteorological state segmentation model, and carrying out road surface meteorological state identification and segmentation to obtain a positioning and segmentation result of the to-be-detected road surface meteorological image. According to the invention, through structure improvement, the calculation complexity is reduced while the precision of the image segmentation model is improved, and real-time and accurate segmentation and detection of the road surface meteorological state under the complex illumination condition are realized.

The invention discloses a remote sensing image segmentation method and system fusing stage perception and a multi-dimensional orientation mechanism, and belongs to the technical field of remote sensing image processing, and the method comprises the following steps: S1, carrying out the preprocessing of a to-be-segmented remote sensing image; s2, inputting the preprocessed to-be-segmented remote sensing image into a segmentation model of a fusion stage perception and multi-dimensional orientation mechanism to obtain a segmentation result graph of the to-be-segmented remote sensing image; wherein the segmentation model fusing the stage perception and the multi-dimensional orientation mechanism comprises a plurality of stage perception intensifiers and a multi-dimensional orientation cyclic key value module. According to the method, accurate segmentation of multi-scale, multi-direction and multi-category targets of the remote sensing image is realized on the basis of keeping light weight of the model.

The invention provides an SAR image polar region sea ice detection method and system based on deep learning and a medium, the land and the water area are segmented by using a water area detection algorithm based on a DeeplabV3 network, the segmentation precision of the DeeplabV3 network is improved by means of cavity convolution, a spatial pyramid pooling module and a decoder, and the calculation and memory overhead is reduced by using a lightweight MobileNet; then, a sea ice detection algorithm based on a short-term dense cascading STDC network is used for precisely segmenting sea ice and water in a water area, the STDC network reduces the calculation complexity through specific module design and keeps multi-scale information, and meanwhile, multiple optimization means are adopted in decoder design to improve the detection performance; in addition, data is prepared and augmented, and the generalization ability of the model is enhanced. The sea ice detection precision and efficiency are improved, and the method is suitable for resource-limited environments such as on-satellite environments and the like.

The invention belongs to the field of medical image analysis and processing systems, and discloses a medical image segmentation system based on dual-scale consistency, and the specific system scheme is as follows: taking a breast ultrasound image as an example, adopting a semi-supervised learning mechanism, carrying out supervised training on a small amount of labeled data, and carrying out unsupervised training on a large amount of unlabeled data; the backbone network is a dual-scale consistent teacher-student network, and accurate segmentation of a medical target is realized through feature extraction and feature interaction of a dual-scale medical image; a common constraint network of supervision loss, scale consistency loss and reliable pseudo-label loss is adopted for training, the scale consistency loss is used for implementing constraint on images before and after disturbance, more reliable pseudo-labels are obtained from prediction probability distribution of two teacher networks, and the reliable pseudo-label loss can guarantee smooth implementation of unsupervised training. According to the method, the dependence of the model on the annotation data can be reduced on the premise of ensuring the model segmentation precision.

The application belongs to the technical field of deep learning, and discloses a road accessory defect detection method and system based on deep learning. Guardrail target detection and classification: a PointRend model of a deep convolution network is used to realize accurate detection classification and precise segmentation of guardrails and anti-glare plates; guardrail deformation and fracture detection: when image target detection is performed and it is inferred that there is a guardrail in the image, the damage state of the neat boundary of the guardrail is further judged, and the damage state of the guardrail includes bending deformation and gap fracture; anti-glare plate missing and deformation detection: after image target detection, it is inferred that there is an anti-glare plate in the image, and the damage state of the anti-glare plate is further judged. The application can more conveniently obtain the damage state of the road accessory along the way, and can greatly reduce the working strength and working efficiency of maintenance personnel in combination with the correlation of the detection vehicle related equipment and the road stake number.

The invention provides a camouflage object semantic segmentation method and device based on an adaptive candidate strategy, and a medium, and the technical scheme of the invention obtains the category code of a to-be-segmented image through a coarse feature extractor and a classifier, achieves the transmission of semantic category information, and enhances the semantic perception capability of a subsequent segmentation task. Initial prediction of a camouflage object is carried out through a target detector and an adaptive candidate strategy, an optimal target attention box is generated, and robust space guidance is provided for a core segmentation task; according to the method, category coding and a target attention box are combined, multi-source information is fused and reconstructed through a multi-guide feature fusion module and a multi-task perception decoder, and an accurate segmentation result is output.

The invention relates to a crop plot identification method and system based on time sequence vegetation characteristics, and the method comprises the steps: constructing a normalized difference vegetation index time sequence according to a multi-temporal satellite remote sensing image, and generating a crop probability distribution diagram through a crop classification model; performing connected domain analysis on the crop probability distribution map, extracting the center of gravity of an effective connected domain as a forward attention point, scanning the crop probability distribution map by using a sliding window, and generating a reverse attention point; based on the forward attention point and the reverse attention point, segmenting the high-resolution remote sensing base map through a visual segmentation model, generating a candidate mask set, and screening to reserve a mask with the maximum area as a land parcel segmentation mask of the forward attention point; and combining all the plot segmentation masks to generate a crop plot identification graph, and converting the boundary of each plot segmentation mask into a geodetic coordinate sequence to obtain plot vector boundary data. The method improves the recognition accuracy, and achieves the automatic and precise segmentation of the boundary of the land parcel.

The invention discloses an accurate segmentation method and system for an abdominal organ image contour, and relates to the field of medical image processing, and the method comprises the steps: obtaining a to-be-segmented abdominal medical image sequence, CT image data at least containing one phase, and a corresponding Hensi unit matrix; based on an abdominal organ positioning network, obtaining a region of interest containing a target small organ and a preliminary space prior probability graph; a local HU goodness of fit diagram is generated through the dissection focusing path, a boundary response intensity diagram is generated through the boundary enhancement path, and a refined feature diagram is output; inputting the refined feature map into a main body segmentation network; fusing with corresponding hierarchical features of the decoder network, performing up-sampling and reconstruction, and generating an initial segmentation probability graph of the target small organ; and generating a final segmentation result graph and a comprehensive confidence graph. According to the method, the technical problems that in the prior art, due to the fact that inherent physical attributes are not fully mined and utilized, boundary positioning is fuzzy, the image segmentation precision is insufficient, and the confidence coefficient is low are solved.

The invention provides a tunnel back break intelligent rapid identification technology based on machine vision. According to the method, firstly, the actual space distance of a reference point on a tunnel face is obtained through a laser range finder, and the pixel and physical size conversion proportion is calculated in combination with a shot tunnel face image; and then, screening high-quality guide information by using a visual language model CLIP, and driving a segmentation model SAM for fine adjustment of a tunnel scene to realize accurate segmentation of the tunnel face contour. The contour pixel area obtained through segmentation is converted into the actual physical area in combination with the conversion proportion, the actual physical area is compared with the preset tunnel design contour area, and therefore the over-excavation or under-excavation state of the tunnel face is automatically judged, and the size of the over-excavation or under-excavation area is determined. According to the method, the automation degree, precision and real-time performance of back break detection in tunnel engineering are remarkably improved, the limitation of traditional manual measurement is overcome, and key technical support is provided for intelligent tunneling of a tunnel.

The invention relates to the technical field of computer vision, and discloses a zero-sample and few-sample defect segmentation method and system based on a large model, and the method comprises the following steps: S1, providing a to-be-detected image and prior prompt information; s2, processing the to-be-detected image and the prior prompt information through a semantic alignment module, and generating a semantic alignment prompt code; s3, inputting the prompt code into a large language model, and generating defect related information including description and characteristics of defects; and S4, processing the to-be-detected image according to the defect related information through a defect segmentation module, and generating a pixel-level defect segmentation result. According to the invention, pixel-level defect segmentation under zero-sample and few-sample scenes is realized, detection tasks of various industrial scenes are supported, the to-be-detected image and prior prompt information are processed through combination of the semantic alignment module, the large-scale language model module and the defect segmentation module, and an accurate segmentation result is generated.

The invention discloses an image processing system and method for distinguishing xerophthalmia types, and relates to the technical field of image processing, and the method comprises the steps: firstly carrying out the standardization preprocessing of an original infrared meibomian gland image, further introducing an artifact perception link, and actively recognizing and positioning the interference regions, such as eyelash shielding and uneven illumination, in the image; and guiding the subsequent meibomian gland segmentation process by using the sensed artifact information, thereby realizing the accurate extraction of the meibomian gland form under the complex background. On the basis, multi-dimensional quantification is carried out on the precisely segmented gland form, and image features are converted into objective numerical indexes. And finally, carrying out comprehensive judgment on the numerical indexes by utilizing a decision tree model, and outputting standardized MGD severity grade. In this way, interference information brought by image artifacts can be intelligently suppressed, and therefore more robust and accurate MGD severity grading is achieved in a clinical image with poor quality.

The invention relates to the technical field of focus labeling, in particular to a medical image focus labeling method and system based on deep learning, and the method comprises the steps: collecting a multi-modal medical image, and carrying out the noise reduction and contrast enhancement preprocessing to obtain a medical enhanced image; segmenting a focus area through a deep convolutional network and generating a focus labeling mask image; and performing post-processing optimization on the mask image, inputting an optimization result into the sub-pixel level annotation generation model, and outputting a high-precision focus annotation coordinate sequence. According to the method, image quality and focus visibility are improved through multi-modal preprocessing, accurate segmentation is realized by using a deep convolutional network, traditional pixel-level precision limitation is broken through in combination with post-processing and a sub-pixel-level model, the problems of noise interference, contrast difference and boundary blur are effectively solved, and focus labeling fineness and spatial positioning precision are remarkably improved.

The invention discloses a particle geometric reconstruction and morphological parameter automatic evaluation method based on a three-dimensional image, and the method comprises the steps: firstly obtaining a three-dimensional gray image of a particle sample, carrying out the Gaussian noise reduction, binaryzation and watershed segmentation preprocessing, and achieving the precise segmentation of independent particles based on an established particle segmentation defect repair algorithm; and then, according to the segmented and marked three-dimensional particle image, an initial contour surface is reconstructed by using a marching cube algorithm to generate a particle surface grid, noise is suppressed by using a Taubin smooth optimization algorithm, a topological structure is automatically calibrated, and a digital model conforming to real particle surface features is constructed. And finally, importing each particle model into the created particle morphological parameter automatic evaluation software to realize quantitative analysis of particle morphological characteristics.