758results about "Vectoral format still image data" patented technology

A method and system for visually annotating an image. Annotations and notes to images, such as digital medical and healthcare images, may be stored in a structured vector representation alongside image information in a single, non-volatile and portable file or in a separate file from the image. The annotations may be composed of point, line and polygon drawings and text symbols, labels or definitions and captions or descriptions. The annotations may be structured in a manner that facilitates grouping and manipulation as user defined groups. The annotations may be related to an image but not inextricably bound such that the original image is completely preserved. Annotations may further be selectively displayed on the image for context appropriate viewing. The annotations may be retrieved for purposes such as editing, printing, display, indexing and reporting for example, and may be displayed on an image for interactive use with an embedded self-contained user interface.

In an image retrieving and delivering system and an image retrieving and delivering method, a feature descriptor is retrieved from a data base, in which each of a plurality of images including a moving picture and a static picture is registered with a feature descriptor describing the feature of the image, according to a retrieval condition input by a user, a retrieval result satisfying the retrieval condition is obtained, and the retrieval result is edited and processed according to a delivery condition obtained from a user terminal in which the retrieval result is to be received.

In one example, an apparatus and method are provided for rendering map images. In one example, an apparatus (e.g., a map server) includes logic for causing the transfer of tiled vector image data in response to a map request, wherein the vector data is associated with stored map data divided into a plurality of tiles. The tiled vector image data is transferred to a remote device (e.g., a client device) for rendering of the map image. Additionally, the vector image data may comprise one or more attributes associated therewith, the one or more attributes configurable by a receiving device. For example, the map image may be rendered (e.g., customized) based on one or more local attributes to vary the language used, colors, how items in the map are displayed, and other imaging characteristics of the map image.

For generating a pictorial reference database from a plurality of digital images, distributed geographical sub-areas are defined (S1). For the geographical sub-areas, selected (S2) from the plurality of digital images are images with a geo-tag located in the respective geographic sub-area. Feature vectors are generated (S31) for localized visual features of the selected images. Based on the feature vectors, matching features are determined (S32) for pairs of the selected images. For pairs with matching features, in each case, a measure of visual similarity is computed (S33) based on different geometric arrangements of the localized visual features. Based on the visual similarity, clusters of images with matching objects are determined (S5) and stored (S6) in the pictorial reference database. The pictorial reference database can be generated automatically from a huge collection of images by dividing the images into geographical subsets which can be processed individually and possibly in parallel.

The embodiment of the invention discloses a method and a device for establishing a picture search correlation prediction model, and a picture search method and device. The method for establishing the picture search correlation prediction model comprises the following steps: using a training sample to train a pre-constructed original deep neural network, wherein the training sample comprises a query and picture data, and the original deep neural network comprises a representation vector generation network and a relevant computational network; and taking the original deep neural network which finishes training as the picture search correlation prediction model. The technical scheme of the invention optimizes the traditional picture search technology, and is better than the traditional technology and various fusion and variation capabilities on multiple aspects including the semantic matching of the query and a picture text, the semantic matching of the query and picture contents, click generalization and the like, and relevancy between a picture search result and the query input by the user can be greatly improved.

In an exemplary embodiment, a method, conducted on a server, sends renderable graphics information to a client device, said graphics information including at least one set of graphics information visible from a second view region and not visible from a first view region. The method includes determining a likelihood that a viewpoint undergoes movement from said first view region to said second view region. The method further includes sending said at least one set of graphics information upon determination that the likelihood that the viewpoint undergoes movement from said first view region to said second view region is greater than a predetermined threshold, said movement determined according to a predetermined motion path.

In one example, an apparatus and method are provided for rendering map images. In one example, an apparatus (e.g., a map server) includes logic for causing the transfer of tiled vector image data in response to a map request, wherein the vector data is associated with stored map data divided into a plurality of tiles. The tiled vector image data is transferred to a remote device (e.g., a client device) for rendering of the map image. Additionally, the vector image data may comprise one or more attributes associated therewith, the one or more attributes configurable by a receiving device. For example, the map image may be rendered (e.g., customized) based on one or more local attributes to vary the language used, colors, how items in the map are displayed, and other imaging characteristics of the map image.

Provided is a video image data generation system including a database for storing a plurality of image data photographed in various directions in various locations, correlating the directions and the locations with the stored image data, and correlating and storing a photographed sub-region when the image data is acquired, a route view point specifying device which specifies various locations and eye level directions arranged on a view point route, an image search engine which searches an image of an eye level direction specified from a location of a view point route specified by the route view point specifying device and outputs video data, wherein the image search engine searches image data stored in a database and the image data including a sub-region located in an eye level direction in each of a plurality of locations on a view point route by referencing photography direction data correlated with the sub-region.

Various aspects of the subject technology relate to systems, methods, and machine-readable media for selected image subset based search. The subject technology includes an image retrieval system using a convolutional neural network that is trained to identify features from pixel data and using an image search engine to search features of a cropped raw image against images having similar content. The system identifies a subset image corresponding to a user selection of a portion of an image. The system provides the subset image to a storage service to obtain a raw image. The system maps pixel data of the raw image corresponding to the selected portion of the image to create the cropped raw image, and fed through a feature extractor to form a corresponding feature vector. The feature vector of the cropped raw image may be searched against images having similar content to determine a prioritized listing of images.

Along with digitization of information, it has become more easy to share and use information over a broad range. It is very important to manage digital documents and documents obtained by printing the digital documents. After completion of a conference, each participant makes an MFP read a document image of a distributed reference. The MFP searches for a data file which matches the read document image with reference to information in a storage unit, and deletes the detected data file. If the number of pages of the read image is short, the data file cannot be detected, or the read document image shows a partial loss, the MFP generates a warning. Upon reception of a collection completion message, the MFP checks with reference to information in the storage unit if all data files associated with the conference are deleted. If a data file to be deleted still remains and that data file is printed, the MFP generates a warning.

Stored digital data is searched for on the basis of an input image, difference information is extracted by comparing the retrieved digital data and the input image, and the difference information is composited to the digital data. Digital data generated by composition is stored. When no digital data is retrieved, the input image is converted into vector data, and the image that has been converted into the vector data is stored as digital data. Obtained region segmentation information and an input image are composited, the composite image is displayed on an operation screen of an MFP, and a rectangular block to be vectorized is designated as a specific region from the displayed region segmentation information. A user designates the specific region by designating rectangular blocks in an image using a pointing device.

System and method for performing Collaborative Filtering while preserving complete user anonymity are provided. Each of a group of client devices sends a rating vector anonymously to a server. The cells in each rating vector correspond to a set of items, and selected cells have ratings provided by the user associated with the corresponding client device for the corresponding items. The server aggregates all the rating vectors into a rating matrix, and factorizes the rating matrix into a user feature matrix and an item feature matrix through approximation, such that the rating matrix equals the product of the user feature matrix and the item feature matrix. The item feature matrix is sent to the client devices. Each of the client devices calculates its own user feature vector based on its rating vector and the item feature matrix, and provides personalized recommendations on selected items based on the client's user feature vector and the item feature matrix.

A physical object is scanned and a digital image of the object is generated from the scan. At least one subset of the image, known as an “authentication region” is selected. A plurality of feature vectors, arising from the physical structure of the object, are extracted from certain locations of interest within an authentication region and combined to generate a unique identifier or “digital fingerprint” for that object. Preferably, authentication regions for feature vector extraction are automatically selected by a software process. To identify or authenticate an object, a system may compare a digital fingerprint of an object to digital fingerprints previously stored in a database. Digital fingerprint data may specify a set of features (also termed “locations of interest”) which may be referenced in the creation of a “fingerprint template” which is a template of certain locations of interest and / or attributes selected for authenticating a particular class of objects.

An apparatus and method detecting an object pose are provided. Key joint data of an object may be extracted, a candidate pose may be generated based on the extracted key joint data, and a most likely pose may be retrieved using a database, based on the generated candidate pose.

Various aspects of the subject technology relate to systems, methods, and machine-readable media for user drawing based image search. These aspects include an image retrieval system using a convolutional neural network trained to identify how users draw semantic concepts and using an image search engine to search against images having a similar concept. The aspects include mapping between concepts of the user drawing space and concepts of the image space such that images associated with the same concept are identified. For each input user drawing, the drawing is first processed through a concept classifier to identify a corresponding concept, and then through a feature extractor to form a corresponding feature vector. The results from the concept classifier and the feature extractor may be combined to search against a collection of images having a similar concept to determine a listing of images ranked by visual and semantic similarity to the input.

In response to a query of discernible facial attributes, the locations of distinct and different facial regions are estimated from face image data, each relevant to different attributes. Different features are extracted from the estimated facial regions from database facial images, which are ranked in base layer rankings by matching feature vectors in a bipartite graph to a base layer ranking sequence as a function of edge weights parameterized by an associated base layer parameter vector. Second-layer rankings define second-layer attribute vectors as bilinear combinations of the base-layer feature vectors and associated base layer parameter vectors for common attributes, which are matched in a bipartite graph to a second-layer ranking sequence as a function of edge weights parameterized by associated second-layer parameter vectors. The images are thus ranked for relevance to the query as a function of fusing the second-layer rankings.

Various aspects of the subject technology relate to systems, methods, and machine-readable media for composition aware image querying. A system may receive user input identifying a search query for content from a client device, where the user input indicates one or more queries assigned to one or more regions of a search input page. The system may generate a query vector for each query using a computer-operated neural language model. The system may compare the query vector to an indexed vector for each region of an image. The system may determine a listing of composition-specific images from a collection of images based on the comparison. The system may determine a ranking for each image in the listing of composition-specific images, and provide search results responsive to the search query to the client device. The search results may include a prioritized listing of the composition-specific images based on the determined ranking.

A method for determining positional relationships among objects represented in a database. A plurality of tiles are defined. A distribution of objects with respect to the tiles is determined. The distribution of objects is compared with respect to the tiles to identify objects fulfilling a primary filter condition related to an interaction of the objects with respect to the tiles. Objects are identified that fulfill a secondary filter condition related to an interaction of the geometries of the objects by analyzing the distribution of objects that fulfill the primary filter condition with respect to the tiles. Objects are identified that fulfill the secondary filter condition by comparing geometries of objects that fulfill the primary filter condition that the analysis does not identify as fulfilling the secondary filter condition.

The invention is directed to a process, an apparatus and a program for selecting objects in a PLM database containing modeled objects. The invention allows a user to rapidly display a view of the set of objects while allowing for selecting objects in the view, without the need for loading the complete and exact representations of all the objects of the view when the user is looking for particular objects to work on.

This invention provides an image processing method which allows easy re-use of image information that is stored to minimize deterioration of image quality and the storage capacity. Storage means is searched for original digital data corresponding to each input image. If no original digital data is found, the input image is converted into vector data, and is stored as digital data in the storage means. A sheet including at least one of information associated with the found original digital data when the original digital data is found in the search step and information associated with digital data which is obtained by converting the image into the vector data in the vectorization step and is stored in the storage step when no original digital data is found in the search step is generated, thus providing a sheet that allows easy re-use.

An object of the present invention is to provide an image retrieval system for computing similarity in the case when components are different between an image feature vector of a query image and the image feature vectors of images to be retrieved when retrieval is carried out by using features of images. A first image feature vector conversion device converts a query image feature vector into a first image feature vector for use in a similarity computation according to similarity computation image feature vector configuration information describing a given configuration of an image feature vector for use in a similarity computation. A second image feature vector conversion device converts an images-to-be-retrieved feature vector into a second image feature vector for use in a similarity computation according to the similarity computation image feature vector configuration information. The image feature vector similarity computation devices compare the first image feature vector with the second image feature vector according to the similarity computation image feature vector configuration information, and compute the similarity.

This invention provides an image processing system and image processing method which can promote efficient use of a memory by vectorizing all data of a representative object and, for the same or similar object, referring to the vectorized representative object and using difference data and also convert the same or similar objects at once by editing only the representative object. Input image information is vectorized. The vector data of a representative object is stored. Identity between a target object and the representative object is determined. If the two objects are identical, property information containing information about the reference destination of the vector data of the representative object is stored in place of the vector data of the target object.

The invention relates to a method and a system for fast making a vector font library. The system comprises a computer, a printer and a scanner. The method includes the steps of firstly, appointing character contents of a to-be-built font library and writing the same in a standard form through a machine; secondly, writing characters according to writing standards in the printed standard form through handwriting, and using the standard form as unit to collect the handwriting characters to obtain a plurality of form images; thirdly, segmenting the form images to obtain character closed contours, selecting some points as key points according to the character closed contours, and screening the key points to obtain optimal key point; fourthly, obtaining character vector contours according to the optimal key point, and generating the standard TrueType font library according to the character vector contours. The vector font library made by the method is high in quality, writing style of an original writer can be kept completely, no manual intervention is needed during font library generating, the high-quality standard font library is generated at one step by the scanned images, and batch production of personalized font libraries is facilitated.

The invention discloses a processing method for multiple-source and multi-temporal satellite image tile data. According to the processing method, a mass tile data organization structure with the time-space characteristic and the multi-source heterogeneous characteristic can be constructed, and metadata of multi-source heterogeneous satellite data tiles can be processed. The processing method comprises the steps of: (1) inputting a plurality of pieces of satellite image data, wherein each satellite image data comprises pixel data and metadata; (2) receiving a data warehousing request; (3) storing each metadata based on an image metadata table of BeyonDB, wherein each row of record description of the image metadata table comes from the metadata of the tile data of the same satellite image, and a plurality of pieces of tile data correspond to the same satellite metadata record; and (4) processing the pixel data by adopting a transverse blocking and longitudinal layering tile structure, and storing the mass tile data after processing the mass tile data by adopting a multiple-source and multi-temporal pyramid tile data file tree structure. The invention also provides a processing system, as well as a search method and a search system based on the processing system.

The invention provides an information recommendation method. The method comprises the steps of obtaining image information, and according to the image information, generating a user tag set corresponding to user identifiers, wherein the image information has the corresponding user identifiers; according to user tags in the user tag set and the corresponding image information, forming eigenvectorscorresponding to the user identifiers; inputting the eigenvectors to a trained information recommendation model, and outputting recommendation parameters of users for to-be-recommended information; and according to the recommendation parameters, recommending the to-be-recommended information to terminals corresponding to the user identifiers. The user tag set capable of reflecting user features isestablished through the image information; the recommendation parameters of the users for the recommended information are predicted by adopting the trained information recommendation model accordingto the user tag set; and the recommendation is performed according to the recommendation parameters, so that the recommendation accuracy is improved and the users not interested in the information areprevented from being disturbed. In addition, the invention provides an information recommendation apparatus, a computer device and a storage medium.

A crowdsourced search and locate platform, comprising an application server and a client interface application. The application server: receives connections from crowdsourcing participants; navigates a first crowdsourcing participant to a specific geospatial location; sends an image corresponding to the geospatial location to the first crowdsourcing participant; receives tagging data from the first crowdsourcing participant, the tagging data corresponding to a plurality of objects and locations identified by the first crowdsourcing participant. The client interface application: displays elements enabling an administrative user to configure a crowdsourced search and locate campaign; displays other elements enabling an administrative user to configure and run a crowdrank algorithm; and upon the user's selecting a particular object type icon, displays tags of the type selected by placing visual indicators at each tagged location of objects of the selected type within the plurality of image strips.

A system for modular image mining and search, comprising a plurality of image capture devices, a search engine, an indexing engine, a database, and user interface software. A plurality of image capture devices capture images and store them to a database. The indexing engine indexes images to create image data for each image with associated metadata and stores the information to the database. The interface software is used to request search queries via a search engine. The search engine accesses the image data to find images or parts of images that satisfy the search query.