Abstract: The subject matter described herein relates to methods, systems, and computer readable media for dynamic cluster-based search and retrieval. An example method for dynamic cluster-based search and retrieval occurs at a server.

Abstract: Re-usage of part of object or object is highly important in manufacturing industry as it can drastically reduce cost and time spent on manufacturing. However, lack of proper information about availability of similar parts leads to redesigning of similar part. Existing databases for engineering drawings do not store categorized information due to which performing feature-based search is not possible. Present application provides systems and methods for extracting, digitizing, and using engineering drawing data. The system receives engineering drawing document and extracts text data present in each cell of table provided in document. Once table data is extracted, isometric views and views other than isometric views that are present in document are identified by the system using pretrained machine learning based model. The system further extract view labels and coordinate information from identified views.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for generating tags for an object portrayed in a digital image based on predicted attributes of the object. For example, the disclosed systems can utilize interleaved neural network layers of alternating inception layers and dilated convolution layers to generate a localization feature vector. Based on the localization feature vector, the disclosed systems can generate attribute localization feature embeddings, for example, using some pooling layer such as a global average pooling layer. The disclosed systems can then apply the attribute localization feature embeddings to corresponding attribute group classifiers to generate tags based on predicted attributes. In particular, attribute group classifiers can predict attributes as associated with a query image (e.g., based on a scoring comparison with other potential attributes of an attribute group).

Abstract: Performing a user initiated search query is disclosed and comprises receiving user input comprising description details of at least one desired object, retrieving a plurality of objects from a database sharing one or more of the description details of the user input, constructing a tree data structure based on the description details of the plurality of objects, the tree data structure comprising one or more attributes related to each of the plurality of objects retrieved, displaying visual images associated with the retrieved plurality of objects, the visual images matching at least one of the attributes related to the plurality of objects, and receiving a user selection of one or more of the visual images.

Abstract: An approach is provided for directing input received at a touch-enabled device to an intended input layer. User inputs are received at a touch-screen of a device. Each user input includes a set of one or more input properties. The touch-screen includes different interaction layers that include a transparent layer and an application layer. The approach analyzes the input properties associated with the received user inputs. Based on the analysis, the approach identifies an intended interaction layer as being either the transparent layer or the application layer. The approach then directs the user inputs to the identified intended interaction layer.

Abstract: A computer implemented system and method that combines data from multiple sources to provide a unified view of data using multi-layered conceptual modeling framework. The invention provides means to model conceptual data models at multiple levels of abstraction and a means to map them with each other and with physical models. A query rewriting approach adopted in the present invention is capable of translating queries down multiple levels of conceptual models into physical models and Conceptual modeling framework provide a means to capture and process semantic intent of data more accurately thereby reducing data integration errors significantly.

Abstract: Object manager information is maintained for object managers in a network indicating a device type of devices in the network managed by the object managers and device information providing information on the devices in the network, wherein the object managers have access to the object manager information. A determination is made from the object manager information a second object manager comprising one of the object managers in the network managing a same device type as the devices managed by the first object manager. The first and second object managers communicate to establish a migration relationship between the first and the second object managers. In response to a migration event at the second object manager, the first object manager accesses the device information for the second object manager to manage the devices currently managed by the second object manager.

Abstract: What is disclosed is a system and method for searching a repository of documents containing images using an image as a query. The present method enables the adjustment of a threshold level through a no-reference quality assessment of the query image which produces an estimated measure of quality for the image. For each image in each document in the repository, a distance is computed between a hash value of each image extracted from the document and the hash value of the query image. Documents are flagged as possible matches if the computed distance is less than the adjusted threshold. Documents flagged as a result of the search are retrieved and provided to the user. The present method can be used along or as an adjunct to text-based search techniques. Other embodiments are provided.

Abstract: Video systems are widely used in the field of surveillance of buildings, traffic, private homes, supermarkets and the like. For some applications it is useful to save the video information for a later access or analysis. As the saved data volume increases with the number of video cameras of a video system and the recorded time there is a need for video databases, which allow a fast searching for relevant video information.

Abstract: A database management program, a database management apparatus and a database management method can determine the sameness of shape data at high speed.

Abstract: There is disclosed a method in a mobile communications device, wherein the method comprises displaying a main image, selecting an object in the main image, displaying a plurality of object images comprising the selected object, selecting a target object image from the plurality of object images, and displaying a target candidate image associated with the target object image.

Abstract: An image may be received, a portion of which corresponds to a surface of an object, such as a book, a CD, a DVD, a wine bottle, etc. The portion of the image that corresponds to the surface of the object is located. The portion of the image is compared with previously stored images of surfaces of objects to identify the object. A record of the object is created and added to a library. The record of the object may comprise the image of the object, the portion of the image which corresponds to the surface of the object, and/or the received image itself. The record may comprise an indicator of a location of the object.

Abstract: Manually changing properties of each diagram element placed in a drawing becomes tedious. A significant amount of time is spent manually customizing diagram elements creating or editing a drawing. Functionality can be implemented within a drawing application to allow automatic diagram element customization based on a set of diagram element policies. Diagram policies specify conditions for customizing properties of a diagram element. Automatic customization of diagram elements reduces time spent creating drawings because diagram elements will be placed in a drawing in their desired configurations.

Abstract: A method of representing an object appearing in a still or video image, by processing signals corresponding to the image, comprises deriving a curvature scale space (CSS) representation of the object outline by smoothing the object outline, deriving at least one additional parameter reflecting the shape or mass distribution of a smoothed version of the original curve, and associating the CSS representation and the additional parameter as a shape descriptor of the object.

Abstract: A method of representing an object appearing in a still or video image, by processing signals corresponding to the image, comprises deriving a curvature scale space (CSS) representation of the object outline by smoothing the object outline, deriving at least one additional parameter reflecting the shape or mass distribution of a smoothed version of the original curve, and associating the CSS representation and the additional parameter as a shape descriptor of the object.

Abstract: A method of representing an object appearing in a still or video image, by processing signals corresponding to the image, comprises deriving a curvature scale space (CSS) representation of the object outline by smoothing the object outline, deriving at least one additional parameter reflecting the shape or mass distribution of a smoothed version of the original curve, and associating the CSS representation and the additional parameter as a shape descriptor of the object.

Abstract: A CoMFA 3D QSAR shape analysis may be performed on molecules arising from the same activity series that may be decomposed/viewed as assemblies of discrete identifiable subunits. The disclosed method provides for identifying in databases of whole molecules those molecular subunits that possess the same shape or shape and feature characteristics as the subunits of molecules used to perform the CoMFA analysis. Additionally, the method provides for estimation of the likely biological activity of molecules assembled from the subunits identified in the molecular database.

Abstract: An image file sorting method is executed by an image file sorting device, including a storage unit, a control unit, and an image reading unit, wherein the storage unit includes a sorting condition storage unit that stores a sorting condition to specify a sorting destination of an image file. The method includes a sorting keyword extracting step of extracting a sorting keyword from a marker portion of the image file read by the image reading unit, a sorting destination deciding step of deciding the sorting destination of the image file by collating the sorting keyword extracted by the sorting keyword extracting step and the sorting condition stored in the storing condition storage unit, and an image file sorting step of sorting the image file into the sorting destination decided by the sorting destination deciding step.

Abstract: A method of representing an object appearing in a still or video image, by processing signals corresponding to the image, comprises deriving a curvature scale space (CSS) representation of the object outline by smoothing the object outline, deriving at least one additional parameter reflecting the shape or mass distribution of a smoothed version of the original curve, and associating the CSS representation and the additional parameter as a shape descriptor of the object.

Abstract: The subject matter described herein includes methods, systems, and computer readable media for controlling presentation and selection of objects that are digital images depicting subjects. According to one aspect, a plurality of objects arranged in a plurality of vectors is presented via a presentation device. Each object in a second vector is associated with an object in a first vector. Each of the objects is a digital image depicting a subject. A first object presented in a first vector is selected in response to a first selection event associated with the first object. A second object non-adjacent to the first object is determined based on a predefined relationship associating the first object with the second object. The second object in the second vector adjacent to the first object in the first vector is presented via the presentation device in response to the determination.

Abstract: A multi-dimensional database and indexes and operations on the multi-dimensional database are described which include video search applications or other similar sequence or structure searches. Traversal indexes utilize highly discriminative information about images and video sequences or about object shapes. Global and local signatures around keypoints are used for compact and robust retrieval and discriminative information content of images or video sequences of interest. For other objects or structures relevant signature of pattern or structure are used for traversal indexes. Traversal indexes are stored in leaf nodes along with distance measures and occurrence of similar images in the database. During a sequence query, correlation scores are calculated for single frame, for frame sequence, and video clips, or for other objects or structures.

Abstract: In an aspect, reconstructing an image object associated with an input data set, includes for each step, in a series of iteration steps, determining an updated object from an input object based on a data model of the input object, a weighting-factor data set, and a gradient object, wherein the weighting-factor data set includes modified entries of the input data set. Reconstructing the image object further includes following a last iteration, outputting one of the updated objects as the image object.

Abstract: The number of index entries in a grid index for indexing geometric shapes is reduced by establishing a pool storage area for geometric shapes, selecting a threshold number of grid cells which a geometric shape may overlap, storing the shape in the grid index if a geometric shape overlaps a number of grid cells not exceeding the threshold number, and storing the shape in the pool storage area if the geometric shape overlaps a number of grid cells which exceeds the threshold number.

Abstract: The number of index entries in a grid index for indexing geometric shapes is reduced by establishing a pool storage area for geometric shapes, selecting a threshold number of grid cells which a geometric shape may overlap, storing the shape in the grid index if a geometric shape overlaps a number of grid cells not exceeding the threshold number, and storing the shape in the pool storage area if the geometric shape overlaps a number of grid cells which exceeds the threshold number.