19results about How to "Extract complete" patented technology

The invention discloses a bolt looseness detection method, system and device based on YOLOv8, a medium and a program, and belongs to the technical field of mechanical engineering. The method comprises the following steps: acquiring bolt image data of a to-be-detected area to obtain bolt image data; and inputting the bolt image data into a pre-trained YOLOv8 model for identification to obtain an identification result. According to the invention, the speed and accuracy of bolt looseness detection are improved, and high-precision identification of bolt state monitoring in a complex environment is ensured.

The present invention discloses a method for detecting three-dimensional changes in ground objects, an electronic device and a storage medium, wherein the detection method comprises accurately registering two time-phase point clouds, and setting a reference time-phase point cloud and a time-phase point cloud to be detected; calculating the normal vectors of the time-phase point cloud to be detected and the reference time-phase point cloud; calculating the local Euclidean distance and the local density; improving the local Euclidean distance according to the local density to obtain the density-adaptive local Euclidean distance; extracting the points to be detected whose density-adaptive local Euclidean distance in the time-phase point cloud to be detected is greater than the distance threshold to the candidate change area; eliminating the misdetected points in the candidate change area caused by modeling deformation; clustering the points in the candidate change area, calculating the area corresponding to the clustering cluster, and further eliminating the misdetected points according to the area and the area threshold. The present invention has better noise resistance and better detection accuracy.

The invention discloses a judgment document element extraction method based on a large model, a storage medium and equipment, and the method comprises the steps: collecting a large number of judgment documents, carrying out the cleaning and word segmentation of each judgment document, and marking key element information; taking the judgment document as the input of the large language model, outputting a key element extraction result of the judgment document, setting a reward function based on the marked key element information, and performing feedback optimization on the large language model in combination with a dominant actor-commentator algorithm; and inputting a newly obtained judgment document into the optimized large language model, and extracting key element information. The judgment document element information can be accurately extracted, the analysis efficiency and accuracy of the judgment document are effectively improved, and manual intervention is reduced.

The present invention provides a tailwater treatment and recycling system for aquaculture, which identifies the global water body inside the culture pond, determines the tailwater distribution state information inside the culture pond, and adjusts the operation state of tailwater extraction from the culture pond; also performs non-contact scanning detection on the water body inside the sedimentation tank, analyzes the sedimentation action data of the sedimentation water body inside the sedimentation tank, and analyzes the sedimentation action data to ensure that the sediment is precipitated as completely as possible; then determines the reaction progress information inside the decomposition tank, and then adjusts the decomposition reaction environmental conditions inside the decomposition tank to effectively reduce the nutrient concentration of the tailwater; also adjusts the transportation state of the tailwater that has completed the decomposition reaction and is circulated and injected into the culture pond according to the real-time culture state information of the culture pond, and adjusts the oxygenation operation of the tailwater that has completed the decomposition reaction according to the oxygen content of the water body in the culture pond, to ensure that the culture pond can continuously and stably obtain a clean and high-oxygen content circulating water supply.

The present invention provides a method for establishing a clothing image segmentation model and a clothing image segmentation method, which solves the problem of low segmentation accuracy in the clothing image segmentation algorithm in the prior art. The method for establishing a clothing image segmentation model includes making a clothing image data set; annotating the image at the pixel level, annotating different categories of clothing into different colors; using a data enhancement module to enhance the original image; building a deep neural network segmentation model: training the deep neural network segmentation model; using a post-processing module to post-process the output of the deep neural network segmentation model; the post-processing module includes a fully connected conditional random field. Using the encoding and decoding method, the extraction of edge and spatial information is relatively complete, and the segmentation result has smoother edges and obvious background distinction; adding a post-processing module improves the classification confusion of the segmentation result, reducing a large number of misclassified chaotic points.

The invention discloses a processing method and system for OFD document conversion, and the method comprises the steps: triggering an OFD conversion operation when a PDF document is exported, so as to extract document structure information and document resource data; performing format conversion on the document structure information and the document resource data, and then adding the document structure information and the document resource data to an OFD resource library; performing text recognition on the text resource data to obtain text segment content information; performing position identification on the text segment content information and storing the text segment content information in the OFD resource library; according to the OFD document conversion method, the image resource data are subjected to image recognition to obtain image feature information, so that the image resource data are identified in the OFD resource library, the problems of format and style loss, incomplete resource processing, low conversion efficiency, insufficient integration level, poor cross-platform compatibility and the like in the existing OFD document conversion technology are solved, and low-cost, high-safety and multifunctional OFD document conversion is realized.

The invention relates to a method for carrying out industrial internet time sequence anomaly detection based on multiple scales and multiple features, and belongs to the technical field of time sequence anomaly in the industrial internet field. The method comprises the following steps: establishing an industrial internet time sequence anomaly detection model based on a time sequence period conversion network, a multi-feature extraction network, a data feature aggregation network and a frequency feature aggregation network; the method comprises the following steps: firstly, capturing various kinds of periodic information in a time sequence through a periodic extraction module, secondly, respectively extracting features in a time sequence period, features between channels of different dimensions and features of a time sequence in a period through a multi-feature extraction network, thirdly, aggregating the various features based on a data feature aggregation network, and finally, extracting the time sequence from the aggregated features. And performing aggregation based on a frequency feature aggregation network, outputting frequency aggregation features of the time sequence data sequence in a time sequence period, and detecting abnormality of the time sequence data by using the frequency aggregation features.

The utility model discloses a combined plant oil countercurrent extraction device, including the pre -immersion dredging residue device of series connection in proper order, multistage scraper pre -immersion machine and sieve plate type extractor, each scraper pre -immersion machine is obliquely arranged, and the middle baffle is fixed below upper chain, and the downlink section and the uplink section form the countercurrent channel of material and solvent, the sieve plate type extractor has upper and lower sieve plate and multistage oil bucket, and each level forms the cycle of spraying - collection - re - spraying, and dry material slide pipe enters first - class scraper pre -immersion machine through feed temporary storage box, feed rotary valve, and fresh solvent enters the last stage spraying of sieve plate type extractor, and the last stage oil bucket outlet of extractor is connected with the solvent inlet of last - class scraper pre -immersion machine through mixed liquid extraction pump, and the solvent outlet of pre -immersion dredging residue device is connected with the inlet of mixed liquid temporary storage tank, and the bottom outlet of mixed liquid temporary storage tank is connected with evaporation unit through evaporation feed pump. The device can improve the penetration and diffusion condition, reduce residual oil and improve the extraction efficiency.

The embodiment of the application provides an IPSA-based ship target identification method and system for an airborne infrared image, wherein the method comprises the following steps: preprocessing an acquired original airborne image; performing global threshold segmentation on the preprocessed image based on an improved PID search algorithm to obtain a global water mask, and performing processing on the preprocessed image based on a local adaptive threshold segmentation method to obtain a local water mask; generating a final water mask according to the global water mask and the local water mask; constructing a candidate target region in a non-water region constrained by the final water mask; determining all connected regions in the candidate target region, calculating the geometric features and the gray features of each connected region, and screening the connected regions according to a preset feature threshold to determine the connected regions meeting the screening condition as ship targets. The technical scheme provided by the application can adapt to a complex marine environment and efficiently and accurately extract ship targets.

The invention belongs to the field of coal gangue grading recognition, and particularly discloses a coal gangue grading recognition system based on deep learning, which comprises a coal gangue image acquisition module, a coal gangue edge separation module and a coal gangue classification module. According to the scheme, gray level inversion is carried out on the initial image to improve the detail definition, a bounded sum operator is applied to realize migration of low-brightness area pixels to a high-brightness area, adaptive threshold processing is adopted to screen edge pixels, and complete and accurate extraction of coal gangue edges is realized; the method comprises the following steps: extracting texture features by adopting empirical wavelet transform, fusing mean value, contrast and homogeneity features calculated by a gray-level co-occurrence matrix, building a deep convolutional pulse neural network fused with a pulse coding technology, introducing an arithmetic optimization algorithm to optimize key parameters of a coal gangue classification model, capturing spatial features and time sequence pulse features of a coal gangue image, and constructing a deep convolutional pulse neural network fused with a pulse coding technology; and comprehensive mining and efficient fusion of the multidimensional key features of the coal gangue image are realized.

The invention discloses a garment tie-dyeing process based on natural plant dye, and relates to the technical field of garment tie-dyeing, the garment tie-dyeing process comprises dye collection and preparation and garment pretreatment, during dye collection and preparation, natural plants are selected according to dyeing requirements, and the selected natural plants are treated; the ready-to-wear garment pretreatment is used for pretreating ready-to-wear garments to be tie-dyed. According to the method, the natural plant dye is extracted through synergistic use of an enzymolysis method and ultrasonic-microwave, plant cell walls are destroyed from internal and external aspects, the extraction efficiency of the dye is greatly improved, pigment components in plants can be extracted more sufficiently, more completely and more uniformly through the synergistic extraction mode, and the extraction efficiency of the dye is improved. The problem of incomplete pigment extraction possibly caused by a single extraction method is avoided, so that the extracted dye is fuller and purer in color and more stable in hue, meanwhile, the binding force between the dye and fabric fibers is favorably improved, and the color fastness to rubbing and the color fastness to washing of the dyed fabric are further enhanced.

The present invention discloses a system for extracting and identifying online or system commodity feature information, wherein the commodity feature information identification is to extract the attribute field describing a specific commodity, and relates to the field of commodity information feature identification. The feature extraction module comprises: a title module 301, a text description module 302, a picture description module 303, and a symbol separation module 304. The title module 301 obtains the commodity title text, performs word segmentation on the title, calculates the weight of the phrase, and outputs the brand name and commodity feature attributes. The present invention can predict and describe commodity feature information according to the category by setting a deep neural network model, enhance the weight of the commodity feature information calculation, and improve the accuracy.

The invention relates to the field of image detection, in particular to an illite and pine needle oil load uniformity detection method based on image recognition, which comprises the following steps: acquiring a composite powder microscopic image under a lateral illumination condition to obtain an effective detection grayscale image and a seed point set; carrying out joint evaluation on local gradient and curvature response of the effective detection grayscale image to obtain an artifact suppression factor; performing joint evaluation on the consistency of the region growth direction and the local flux characteristic to obtain a flux compensation factor; carrying out fusion modulation on the gray difference judgment cost through an artifact inhibition factor and a flux compensation factor, obtaining a final growth judgment cost, and generating a load region binary mask; a load uniformity index is obtained by carrying out gridding load rate statistics and dispersion calculation on a binary mask of a load area, so that the problem of load uniformity quantization misalignment caused by shadow error growth leakage and coexistence of early stop and missing detection on an oil film weak edge is solved.

This invention belongs to the field of accounting voucher recognition technology, specifically a deep learning-based intelligent recognition and automatic classification system for accounting vouchers. It includes: a multimodal acquisition and preprocessing module, a deep learning feature extraction module, an accounting voucher recognition module, an intelligent classification module, an intelligent verification and risk warning module, a voucher structure generation module, a record learning module, a system update module, a distributed storage and retrieval module, and an interface interaction and control module. The beneficial effects of this invention are: it can stably handle complex vouchers such as those that are blurry, have overlapping seals, are handwritten, or are mixed with other documents; it has a high accuracy rate in extracting key information; it can guarantee the accuracy of recognizing blurry, tilted, wrinkled, stamped, handwritten, and mixed-document overlapping vouchers; and it extracts key information completely to meet the needs of actual business scenarios.

The present invention relates to a method for detecting industrial Internet time series anomaly based on multi-scale and multi-features, and belongs to the technical field of time series anomaly in the field of industrial Internet. The present invention establishes an industrial Internet time series anomaly detection model based on a time series period conversion network, a multi-feature extraction network, a data feature aggregation network and a frequency feature aggregation network; a variety of periodic information existing in a time series is captured through a periodic extraction module, and then the features between time series cycles, the features between channels of different dimensions and the features of time series within a cycle are extracted through a multi-feature extraction network respectively; then, a variety of features are aggregated based on a data feature aggregation network; finally, aggregation is performed based on a frequency feature aggregation network, and frequency aggregation features of a time series data sequence in a time series period are output, and the frequency aggregation features are used to detect anomalies of the time series data.

The invention relates to a friction vibration behavior time-frequency characterization method, in particular to a metal powder sintering composite layer hard alloy friction vibration behavior time-frequency characterization method. The invention aims to solve the problems that when an existing time-frequency method is used for analysis, the extraction of image feature textures is not deep enough, the extracted features are not wide enough and not highly persuasive, time-domain and frequency-domain analysis needs to be combined, and an improved time-frequency analysis method often needs data adaptation and lacks universality. The method comprises the following steps: preprocessing a collected friction vibration data file; carrying out noise reduction processing on the collected vibration signals; acquiring a vibration signal time-frequency analysis image; performing graying processing on the time-frequency image; performing feature extraction on the vibration signal time-frequency image; carrying out dimension reduction screening on the vibration behavior characteristics based on an MIC maximum mutual information coefficient-BP neural network method; and fitting a stability characterization curve of the test system based on the vibration behavior. The invention belongs to the technical field of friction vibration behavior characterization.

The application relates to the technical field of underwater acoustic positioning, in particular to a self-adaptive underwater acoustic positioning correction method and system based on swarm intelligence, which comprises the following steps: reconstructing original signals of mutual detection of underwater acoustic reference nodes in a high-dimensional phase space, and extracting an arrival time characteristic vector from a phase domain trajectory; based on multi-target particle swarm optimization, performing multi-target optimization on a local neighborhood geometric structure of the characteristic vector to obtain optimal local linear embedding parameters; according to the parameters, globally splicing the characteristic vector manifold to obtain a time delay space manifold; performing variational mode decomposition on the time delay space manifold to obtain a dynamic deviation residual; according to a projection position of a target emission signal on the manifold, fusing the dynamic deviation residual to correct time delay distortion, and obtaining a self-adaptive time delay correction amount; and analyzing the correction amount intersection positioning to obtain a space position of a target to be positioned; the application can improve the correction efficiency of self-adaptive underwater acoustic positioning.

This invention provides a polyp image segmentation method based on depth guidance and a triple decoder. Using RGB images as input, the method expands the channels of the depth image, extracts its multi-layer features, and performs layer-by-layer feature fusion. This effectively utilizes the spatial structural characteristics of polyps in the depth image, enhances multi-scale semantic and spatial location information, and helps the network extract the polyp region more completely. A triple decoder architecture is designed to extract fine-grained detail features and deep semantic features of the polyps. The combined decoder integrates the advantages of both types of features, improving multi-scale feature extraction and fusion capabilities. A high- and low-resolution dual-branch feature extraction strategy is adopted to adapt to high-resolution input. Combined with the advantages of a pre-trained backbone network, this method reduces model computational complexity while ensuring no loss of polyp detail information, thus balancing segmentation performance and operational efficiency.

This invention relates to the field of image data processing technology, and in particular to an image data edge preprocessing method and system adapted to a tongue image analyzer. This invention pre-identifies and enhances weak boundary candidate regions, constructs and adaptively fuses a dual-branch system of high-frequency edge preservation and low-frequency noise reduction, accurately preserving weak boundary details while suppressing noise. Through gradient-guided directional enhancement, it achieves targeted enhancement and protection of low-contrast weak boundaries in tongue images, while effectively suppressing background noise. Ultimately, it provides high-quality input images with significantly improved signal-to-noise ratio and enhanced weak boundary features for classic Canny edge detection, enabling the stable and complete extraction of key anatomical edges that cannot be identified in traditional processes.