1349results about "Metadata still image retrieval" patented technology

The invention provides an intelligent retrieval matching method and system for multidimensional data of image-text features, and relates to the technical field of icon image retrieval. Comprising the following steps: extracting image features, text content and semantic features of an icon image by using a convolutional neural network, an image segmentation attention mechanism network, a converter optical character recognition model and a bidirectional semantic understanding model, constructing the extracted features into heterogeneous feature tensors, and performing singular value decomposition to obtain icon feature fingerprint vectors; and constructing a multi-level index based on locality sensitive hashing, realizing rapid retrieval, calculating visual, text and semantic similarities in combination with a deep metric learning model, weighting according to variances and discrimination coefficients of similarity features to obtain a comprehensive similarity score, and outputting a retrieval result with the highest similarity.

A method of automated generation of contextually-relevant images for a music segment includes receiving at least one of basic metadata information and lyric information for the music segment, generating a first prompt for a computer-implemented machine-learning language model based on the at least one of the basic metadata information and the lyric information, receiving context information from the computer-implemented machine-learning language model in response to the first prompt, generating a second prompt for the computer-implemented machine-learning language model based on the context information, generating a third prompt by providing the second prompt as an input to the computer-implemented machine-learning language model, and generating an image descriptive of the music segment by providing the third prompt as an input to a computer-implemented machine-learning image generation model.

The invention discloses a defect file and image number association method based on multi-format analysis, and relates to the technical field of semiconductor detection and data analysis, and the method comprises the following steps: constructing a multi-format rule base, receiving batch Klarf files and corresponding defect image folders, and extracting image numbers in defect image file names; reading field names of a preset number of Defect data of the Klarf file, matching the field names with the multi-format rule base, and selecting an analysis strategy according to a matching result by adopting a self-adaptive analysis algorithm; the analyzed Defect data are preprocessed, the association confidence coefficient is calculated through a three-layer verification algorithm, and an association result table is generated; according to the invention, automation, standardization and high reliability of semiconductor defect detection data processing are realized.

A method and apparatus for generating photorealistic synthetic images by receiving multiple forms and multiple instances of user input corresponding to a user's visual idea, executing an iterative image search to identify pre-existing images semantically aligned with the user's visual idea, and using an image synthesis deep learning model to generate at least one synthetic image based on the multiple forms and instances of user inputs.

The invention provides a multi-modal geographic positioning method based on a knowledge graph. The method comprises the following steps: graph construction: constructing a geographic knowledge graph; image positioning: calculating the entity similarity between the to-be-queried image and each sub-image so as to select an image positioning candidate sub-image, calculating the image matching similarity between the to-be-queried image and each image positioning candidate sub-image so as to determine an image positioning target sub-image, and taking the latitude and longitude coordinates of each image positioning target sub-image as a positioning result; text positioning: converting a to-be-queried text into map representation, calculating the map similarity between a text query sub-graph and each sub-graph to select a text positioning candidate sub-graph, and calculating the semantic similarity between the to-be-queried text and each text positioning candidate sub-graph, and calculating a text matching similarity corresponding to each text positioning candidate sub-graph based on the graph similarity and the semantic similarity corresponding to each text positioning candidate sub-graph so as to determine a text positioning target sub-graph, and taking latitude and longitude coordinates of each text positioning target sub-graph as a positioning result.

The invention provides a noise robust text-to-image pedestrian retrieval method and device based on a soft label. The method comprises the following steps: calculating cosine similarity based on image global features and text global features, and normalizing the cosine similarity to generate a soft label representing image-text pairing confidence; distributing a sample weight for each training sample according to the soft label, and obtaining a joint weight for current iteration in combination with a dynamic weight factor progressively increased along with the training process; respectively constructing cross-modal contrast learning loss and similarity distribution matching loss by using the joint weight, and carrying out weighted summation on the cross-modal contrast learning loss and the similarity distribution matching loss to obtain a total loss function; and updating parameters of the image encoder and the text encoder by using the total loss function until training convergence, and obtaining a cross-modal alignment model. According to the method, robust cross-modal alignment can be realized, and the pedestrian retrieval accuracy in a noise scene is improved.

The invention discloses a multi-modal agricultural question and answer method and system for generating RAG based on retrieval enhancement, and the method comprises the steps: collecting and constructing crop disease image data containing a farmland complex background and corresponding text description, and forming an agricultural image-text knowledge database; based on the agricultural image-text knowledge database, multi-modal features of an input image and a query text are extracted, image-text joint similarity retrieval is carried out, and knowledge image-text candidates are obtained; inputting the knowledge image-text candidates into an image-text rearrangement module for rearrangement; taking the reordered image-text knowledge as condition input, accessing a large language model, and generating diagnosis description and prevention and treatment suggestions for the current crop diseases; and outputting a multi-modal question and answer result according to the image and question input by the user. According to the method, the agricultural image-text database is constructed, and multi-modal retrieval, rearrangement and large language model generation technologies are combined, so that accurate and efficient crop disease multi-modal question answering is realized, and the reliability of diagnosis and prevention suggestions is improved.

A condition generator analyzes a set of utility asset images of a particular utility asset using the ML (machine learning) model identify a type and condition of the particular utility asset depicted in the set of utility asset images. The identified condition is assigned a confidence score, and the set of utility asset images includes at least two images of the particular utility asset captured at different angles. The condition generator generates a descriptive tag for the set of utility asset images based on the identified type and condition. The descriptive tag characterizes an operational status of the particular utility asset. The condition generator stores the set of utility asset images and the generated descriptive tag in a utility asset database. The utility asset database stores images of utility assets.

The invention discloses a remote sensing image searching and matching method and device based on feature fusion, and relates to the technical field of remote sensing, a test image of an unmanned aerial vehicle or a heterogenous satellite is acquired, a feature library is established after preprocessing, and feature extraction and index establishment are performed on each base map in the base map library. And selecting a retrieval strategy according to the size of the test image, retrieving the name of the base image and cutting a related grid image. The method comprises the following steps: converting a test and grid image into gray scale and zooming, extracting feature points to form a set, estimating an affine transformation matrix by using a random sampling consensus algorithm, and preliminarily evaluating the number of matched inner points; if the first preset threshold value is exceeded, executing a fine matching step; and if the number of points in the fine matching step exceeds a second preset threshold value, returning to match the name of the base map and the longitude and latitude of the angular points. And if not, iterating precise matching until an optimal matching result and the longitude and latitude of the angular point are returned. The problem of how to efficiently and accurately find an image of a specific area for massive and multi-source remote sensing image data is solved.

The invention discloses a cross-view image geographic positioning method based on dynamic threshold pseudo tag self-training learning, and the method specifically comprises the following steps: introducing a difficult sample feature mining method, dynamically adjusting the loss weight of a sample according to the change of similarity, and building a dynamic difficult sample triple loss model; the method comprises the following steps: dynamically adjusting a confidence threshold value of a sample by adopting an index moving average weighting method, iteratively training and screening an unlabeled sample, namely a pseudo label, establishing a pseudo label self-training mechanism of a dynamic threshold value, mining and utilizing non-paired data, and solving the problem of high manual labeling cost; a reference image most similar to a query image is found through image retrieval, and the offset of a query position is predicted. Experiments on CVUSA and CVACT data sets show that as the distance threshold increases, the accuracy of the cross-view image geographic positioning method based on dynamic threshold pseudo tag self-training learning presents a stable rising trend, and the cross-view image geographic positioning method based on dynamic threshold pseudo tag self-training learning is superior to other methods under the same threshold condition.

The invention discloses a CAD drawing instant positioning method and device based on spatial index analysis, and relates to the related technical field of CAD drawing positioning, and the method comprises the steps: carrying out the multi-stage splitting identification of a multi-version target CAD drawing; performing associated indexing on the drawing version information, the drawing layer information and the drawing component set; semantic analysis and spatial association are carried out on the drawing text annotations; embedding and associating the drawing component space semantic tag set into a component-layer-drawing three-level association graph; performing matching indexing on the drawing semantic query request based on the drawing spatial index mapping table; and inquiring a topology path based on the component to carry out instant positioning and visual feedback. The technical problems that in the prior art, complex spatial relations and semantic information in the drawings are difficult to effectively process, and multi-version CAD drawings are low in retrieval efficiency, insufficient in instantaneity and inaccurate in positioning are solved, and the technical effect of improving the retrieval efficiency, query instantaneity and positioning accuracy of the multi-version drawings is achieved.

Systems and methods for image search result filtering can include obtaining a search query, determining a plurality of candidate image search results, processing the search query with a generative model to determine a plurality of search result criteria, and refining the plurality of candidate image search results based on determining whether the candidate results satisfy the plurality of search results criteria. The systems and methods can perform a plurality of determinations based on the output of the generative model.

The invention discloses an information retrieval method, a related device, equipment and a storage medium, and is applied to the field of artificial intelligence. The method comprises the steps of obtaining to-be-queried information and target instruction information; based on the to-be-queried information and the target instruction information, obtaining a first token sequence through a feature extraction layer included in an information retrieval model; performing bidirectional attention coding on the first token sequence through a backbone network included in the information retrieval model to obtain a second token sequence; pooling the second token sequence to obtain a target embedded vector; and according to the target embedding vector, obtaining a preset number of candidate information with the highest similarity as a retrieval result. According to the method, the complexity and the calculation cost of model deployment are reduced, and the target embedding vector generated by the model is more discriminative, so that the accuracy of a retrieval result is improved.

The disclosed techniques provide improved methods of operating system (OS) search. Users are enabled to search for documents, emails, presentations, content they entered into a web form, meetings they participated in, and other interactions they had with their computing device. To accomplish this, screenshots are periodically captured and indexed. Machine learning models are used to infer embeddings for visual elements of the screenshots and / or text extracted from the screenshots. A full text index of a relational database may also be populated with text extracted from the screenshots. The embeddings and full text index may then be used to retrieve screenshots in response to a user history query. For example, screenshots of embeddings within a defined distance of an embedding of the user history query may be selected. Query results from different embedding indices and relational databases may be ordered by applying different weights to different kinds of search scores.

The invention relates to DICOM image processing, in particular to a DICOM image preprocessing and quality control system based on Spark, and the system comprises a data collection module which collects a DICOM medical image from a data source, and automatically recognizes and extracts a key metadata field in the DICOM medical image; the index construction module is used for constructing a comprehensive and accurate index system according to key metadata fields of the DICOM medical images; the data standardization module is used for carrying out standardization processing on key metadata fields of the DICOM medical images, supporting version control and audit tracking on the key metadata fields and carrying out optimization processing on the DICOM medical images; the scoring module is used for carrying out objective quality evaluation on the DICOM medical image based on a multi-dimensional image quality evaluation model and calculating a corresponding comprehensive quality score; according to the invention, the defect that the DICOM medical images from different equipment manufacturers are difficult to efficiently preprocess can be overcome.

The invention discloses an unsupervised image-text retrieval method for deep joint semantic alignment based on CLIP, and relates to the technical field of image-text retrieval methods, comprising the following steps: S1, CJSAH extracts features of images and texts from a pre-trained CLIP backbone network; s2, respectively calculating feature similarity matrixes in the image and text modals in batches; s3, the feature similarity matrix is enhanced and fused into a joint modal similarity matrix which is used for supervising learning of hash codes; s4, after the features are spliced, semantic interaction is carried out through a Transf ormer encoder, and then comparison loss is calculated by disassembling the features subjected to modal fusion; when the comparison loss is calculated in the step S4, the CJSAH further introduces a momentum comparison learning module which comprises a momentum encoder and a dynamic queue so as to mine negative sample information in a larger range; experiments carried out on three widely used data sets show that the CJSAH provided by the invention obtains a satisfactory result in the aspect of total retrieval accuracy.

The invention discloses a multi-modal image searching method, and solves the problems that in the prior art, effective utilization of document image text information is lacked, and the multi-modal retrieval requirement in a complex scene is difficult to meet. According to the invention, the input image is classified by using the deep learning model, and the image classification result is obtained; the image classification result is a text image or a non-text image; generating a multi-dimensional composite feature vector for the text image; for a non-text image, generating a visual feature vector; retrieving a text image based on the multi-dimensional composite feature vector, calculating a comprehensive score by fusing the text semantic similarity, the abstract semantic similarity and the format visual similarity, and returning a retrieval result according to the comprehensive score; and for a non-text image, performing retrieval based on the cosine similarity of the visual feature vector, and returning a retrieval result.

The invention relates to a portrait file gathering method and device, an electronic device and a storage medium, and the method comprises the steps: obtaining snapshot face data, and obtaining a preset portrait static library; a plurality of initial portrait base maps carrying file identifiers are stored in the portrait static library; performing retrieval processing from a portrait static library based on the snapshot face data, and determining a plurality of first target portrait base maps matched with the snapshot face data in the initial portrait base map according to a retrieval result; generating a sub-archive list based on the archive identifier carried by each first target portrait base map; and querying a historical merging record corresponding to the sub-file list, establishing a merging file according to a query result of the historical merging record, and generating a file gathering result of the snapshot face data. Through the method and the device, the problems of low portrait file gathering efficiency and high cost in a lightweight scene are solved.

The invention discloses an image auditing method and device, a storage medium and a program product, and relates to the technical field of computers. The method comprises the following steps: acquiring an input image, a historical image library and an auditing rule library; obtaining at least two target historical images in a historical image library according to the input image and the historical image library; obtaining at least one target auditing rule in an auditing rule base according to the input image and the auditing rule base; and through the multi-modal large model, according to the input image, the at least two target historical images and the at least one target auditing rule, generating an auditing result of the input image, the auditing result of the input image being used for indicating that the input image is one of a violation image, a compliance image and an uncertain image. According to the method, the learning value of few samples is fully utilized, the open-source multi-modal large model can directly perform a security auditing task without fine tuning, the applicability of the multi-modal large model in a content auditing scene is improved, and the training cost of image auditing is reduced.

The invention provides an image searching method, which comprises the following steps of: when a new label is added to an image in a first image database, acquiring a first semantic feature of the new label; based on the first semantic feature, performing image retrieval in a first image database to obtain a first retrieval result and a confidence coefficient of the first retrieval result; if the confidence coefficient is smaller than the preset confidence coefficient, performing secondary retrieval in the first retrieval result based on the existing tag in the first retrieval result to obtain a second retrieval result; based on the second retrieval result, adding the newly added tag into an image corresponding to the secondary retrieval result to obtain a second image database; and after an image search instruction of the user is obtained, performing image retrieval in the second image database based on the image search instruction. The problems that in the database maintenance process, a new label needs to be added, the workload of adding the label again to the data is increased while the new label is added, and the database is difficult to maintain in an existing method are solved.

The invention relates to the technical field of information retrieval, in particular to a part three-dimensional model retrieval method and system based on feature extraction. The part three-dimensional model retrieval method comprises the following steps that a manufacturing industry part design drawing is obtained; geometric structure feature extraction and material feature extraction are carried out according to a manufacturing industry part design drawing, and geometric structure data and material data are obtained; constructing a part three-dimensional model based on the geometric structure data and the material data; performing process processing feature extraction according to a manufacturing industry part design drawing to obtain part process processing data; and performing process treatment, including surface treatment, heat treatment and welding treatment, on the part three-dimensional model according to the part process treatment data to obtain surface treatment data, heat treatment data and welding treatment data. Based on the information retrieval technology, the part three-dimensional model retrieval precision and the assembly reliability are improved, and the part design optimization rate and the production quality control efficiency are remarkably improved.

The invention relates to the technical field of intelligent management, in particular to an intelligent management system based on land survey data, which collects and stores a sample image of the land survey data through a collection assembly, monitors the regional temperature of hardware storage equipment through a monitoring module, and obtains the data sample image resolution of the hardware storage equipment. And storing monitored historical data through a prior analysis module. Further, a control module determines a significant risk impact period and a weak risk impact period based on the device operation risk tendency characterization value, and monitors a hardware storage device to determine whether sample image characterization parameters predict whether the land survey data transmission efficiency meets a predetermined criterion, to determine whether to start the thermal compensation device. The influence of the temperature difference of hardware storage equipment on the land survey data sample image acquisition efficiency in the system operation process is considered, the thermal compensation device is adaptively intervened, and then the land survey data sample image acquisition efficiency of the intelligent system is guaranteed.

The invention discloses a rock core identification method and system based on regional geological data, and the method comprises the steps: S1, collecting a rock core sample image, and constructing a rock core image data set; s2, dividing the core image data set into a training set and a test set, and training and testing the constructed classification model based on artificial intelligence; and S3, extracting formation lithology information in the regional geological map, and adjusting and optimizing the trained classification model by using the extracted formation lithology information. When the rock core recognition model is constructed, the regional geological data is introduced to optimize the model, the initial weight assignment of the model is optimized by introducing the regional geological data, the training efficiency, the accuracy and the generalization ability of the model are improved, and the model can be applied to different geological conditions and different regions.

The invention discloses a method and device for automatically designing a gas path diagram. The method comprises the following steps: carrying out element identification on an input three-dimensional model to obtain the element type of each element in the three-dimensional model; based on the element type, selecting elements contained in an action group through interaction setting of a client, and configuring corresponding action instructions for the action group to obtain action group configuration data; performing legend matching on elements contained in the action group to obtain model element legend data; and carrying out legend feature recognition on the model element legend data, and carrying out legend connection and content labeling on the basis of a legend feature recognition result and the action group configuration data so as to generate a gas path diagram. The technical problems that an existing gas circuit diagram is low in design efficiency and prone to errors are solved.

The invention belongs to the technical field of geographic information technology and remote sensing image processing and service, and discloses a slice-free image service system and method based on dynamic projection and real-time mosaic, which abandons the traditional pre-slicing mode, directly provides online service based on original image data, and improves the service efficiency. The problem of redundant storage caused by pre-generation and storage of massive tiles is fundamentally eliminated, and storage space is saved by up to 90%. Meanwhile, when the original data is updated, the system does not need to carry out a time-consuming re-slicing process, real-time updating and publishing of services can be realized, and the core pain points of long data updating period and high delay in the traditional technology are thoroughly solved. Through the integrated dynamic projection engine and the real-time mosaic module, the on-demand service request of the client for any coordinate system, any spatial range and any resolution can be responded.

The invention provides an automatic material identification and matching method and system for a three-dimensional model and a medium, and relates to the technical field of material management, and the method comprises the steps: constructing a standardized material database, and extracting and standardizing material attribute information; analyzing first material description information in the three-dimensional software model by utilizing an SQL (Structured Query Language), and matching the first material description information with the material attribute information to obtain a first material matching result; extracting second material description information in the project material document by using VBA programming, and matching the second material description information with the material attribute information to obtain a second material matching result; and data integration is carried out through PowerBI, and a project material state visual billboard is constructed. The technical problems that in the prior art, a unified standardized material database is lacked, material description formats in different sources are inconsistent, expression is not standard, a construction material list cannot be accurately generated, and informatization and intellectualization of project material management are limited are solved.

The invention relates to the technical field of power grid image retrieval, and discloses a power distribution network inspection image rapid retrieval matching method and system, and the method comprises the steps: obtaining a to-be-retrieved inspection image of power distribution network equipment, and extracting the equipment structure features of the inspection image through a hierarchical convolutional network; quantifying a surface texture attenuation index of the power distribution network equipment through fractal dimension based on the equipment structure characteristics; performing mapping relation coupling on the surface texture attenuation index and a space coordinate of an equipment connecting piece to generate a dynamic feature coding sequence containing an equipment structure topological relation; performing time sequence consistency matching on the dynamic feature coding sequence and a pre-constructed reference image library, and aligning an equipment aging track through a dynamic time warping algorithm to generate a similarity sorting result; according to the method, the problems that effective features cannot be extracted during retrieval matching and the retrieval precision is low are solved.

The invention discloses a cultural relic exhibition hall AI intelligent shooting system based on binocular vision, and relates to the technical field of cultural relic digitization and interaction, and the system comprises a binocular vision image collection module which is used for shooting and storing a multi-view high-definition image of a cultural relic; the AI image splicing fusion module preprocesses the image and generates a panorama; the cultural relic three-dimensional reconstruction module constructs a three-dimensional model with fine textures; real-time fusion of the intelligent shooting module fusion model and a visitor image is carried out to generate an interactive picture; the interactive output and management module provides related functions and manages data; by integrating binocular vision image acquisition, AI image splicing and fusion, cultural relic three-dimensional reconstruction and real-time fusion intelligent shooting technology modules, intelligent upgrading of cultural relic display and visitor interaction is achieved, the system adopts a binocular camera shooting mechanism triggered by multiple strategies, timing and induction triggering modes are combined, and the intelligent upgrading of cultural relic display and visitor interaction is achieved. The method can flexibly adapt to the demands of different exhibition scenes, guarantees the high efficiency of cultural relic image collection, and avoids the waste of resources.

A picture frame and methods of setup, gifting, and / or use. Network connection allows digital frames to be set up remotely by a first user for a second user. The first user can upload photos from electronic devices or from photo collections of community members before the second user receives the frame device. The frame is thus ready for display upon powering on by the second user. An integrated speaker is used to automatically deliver spoken messages at start-up. The displayed photos are automatically shown and / or changed according to the detected viewers. The photos can be filtered and cropped at the receiver side. Clustering photos by content is used to improve display and to respond to photo viewer desires.

The invention discloses an image secret type cloud storage method and device based on feature block encryption, and the method comprises the steps: a cloud server receives and stores an encrypted image, an encrypted image feature set and a feature inner product, and forms an image database; the cloud server receives a feature ciphertext query feature uploaded by the authorized user when the authorized user needs to query the image; the cloud server performs retrieval according to the received ciphertext query features, separately calculates the similarity between color and texture sub-features in the ciphertext query features and features in each encrypted image feature set in the image database by using a hierarchical earth moving distance algorithm, and calculates the comprehensive similarity corresponding to each encrypted image; and screening out a plurality of encrypted images according to the comprehensive similarity and returning the encrypted images to the authorized user. According to the method, safe and efficient search of the image can be realized, and the image retrieval performance is improved.