1034results about "Still image data retrieval" patented technology

A mobile inventory robot system generates an inventory map of a store and a product database when a mobile inventory robot is manually navigated through the store to identify items on shelves, a location for each of the items on the shelves, and a barcode for each of the items. The system performs inventory of the items by navigating through the store via the inventory map, capturing a shelf image, decoding a product barcode from the captured shelf image, retrieving a product image for the decoded product barcode from the product database, segmenting the captured shelf image to detect an image of an item on the shelves, determining whether the detected image matches the retrieved image and, if not, setting an out-of-stock flag for an the item.

A framework is provided for describing multimedia content and a system in which a plurality of multimedia storage devices employing the content description methods of the present invention can interoperate. In accordance with one form of the present invention, the content description framework is a description scheme (DS) for describing streams or aggregations of multimedia objects, which may comprise audio, images, video, text, time series, and various other modalities. This description scheme can accommodate an essentially limitless number of descriptors in terms of features, semantics or metadata, and facilitate content-based search, index, and retrieval, among other capabilities, for both streamed or aggregated multimedia objects.

The present invention provides a system and method for accessing electronic data through entry of images as queries in search engine. The system uses various image capturing devices and communication devices to capture images and enter them into image database. Image recognition techniques encode images in a computer readable format. The processed image is then entered for comparison into at least one database populated with images and associated information. Once the newly captured image is matched with an image in the database, the information linked with that image is returned to the user.

A method for determining if a set of images in a large collection of images are near duplicates is described. The method includes processing the set of images, generating an image signature for each image in the set of images, and comparing the generated image signatures. The method can be used in clustering and ranking of images.

A computer-implemented method for automatically sharing media between users is provided. Collections of images are received from different users, where each collection is associated with a particular user and the users may be associated with each other. The collections are grouped into one or more albums based on the content of the images in the collection, where each album is associated with a particular user. The albums from the different users are grouped into one or more event groups based on the content of the albums. The event groups are then shared automatically, without user intervention, between the different users based on their associations with each other and their individual sharing preferences.

A Building Databases Manipulator builds databases for a variety of physical environments including buildings, terrain, and other site parameters, by scanning in or rapidly tracing or editing data, and verifying that the data is formatted and sufficient for use in other engineering applications, and generating a set of formatted data which is transportable. Grouping objects in layers allows for simultaneous conversion of all objects in one layer to have certain predetermined attributes (e.g., converting objects to be made from glass versus cement; converting objects within a layer to have a uniform, smaller or larger, height or width dimension).

Methods of detecting an object in an image using a convolutional neural network based architecture that processes multiple feature maps of differing scales from differing convolution layers within a convolutional network to create a regional-proposal bounding box. The bounding box is projected back to the feature maps of the individual convolution layers to obtain a set of regions of interest. These regions of interest are then processed to ultimately create a confidence score representing the confidence that the object detected in the bounding box is the desired object. These processes allow the method to utilize deep features encoded in both the global and the local representation for object regions, allowing the method to robustly deal with challenges in the problem of robust object detection. Software for executing the disclosed methods within an object-detection system is also disclosed.

Automatically synchronizing any of a group of associated multimedia assets is described is described. A particular one of the set of distributed multimedia assets is modified and the others of the set of distributed multimedia assets are then synchronized based upon the modification. An update edit list corresponding to the modification is generated which is then automatically forwarded to the others of the set of distributed multimedia assets. The update edit list is then used to synchronize each of the distributed multimedia assets to the particular multimedia asset so modified.

A method of establishing a connection between two image collections, the method includes providing a first image collection from a first user; providing a second image collection from a different second user; analyzing the first and second image collections to produce a similarity score between the first and second image collections; and establishing a link for sharing images or collection data between the first and second users based on the similarity score.

A system and method, which may be an offline method, extracts relevant image features about listing items in a network-based publication system for enabling image similarity searching of such listing items. When a seller lists an item, an image of the item is uploaded and may be sent to a picture processing service, which generates several digests. The digests are compressed data structures each representing a particular image feature such as edge, color, texture, or words. These digests are then stored in a search database, where the digests can be used to retrieve listings by image similarity at scale. A similar process can be performed for a query listing for searching the search database for items similar to the query listing.

An image retrieval apparatus generates an image feature list having a high and/or a low discrimination capability against other images based on the number of stored image features. Based on the image feature list, the image retrieval apparatus selects feature points extracted from a query image.

To compute a signature for an object comprising or represented by a set of vectors in a vector space of dimensionality D, statistics are computed that are indicative of distribution of the vectors of the set of vectors amongst a set of regions R_i, i=1, . . . , N of the vector space, at least some statistics associated with each region are binarized to generate sets of binary values a_i, i=1, . . . , N indicative of statistics of the vectors of the set of vectors belonging to the respective regions R_i, i=1, . . . , N; and a vector set signature is defined for the set of vectors including the sets of binary values a_i, i=1, . . . , N. The computing, binarizing, and defining operations may be repeated for two sets of vectors, and a quantitative comparison of the two sets of vectors determined based on the corresponding vector set signatures.

To provide an apparatus and method for efficiently displaying image content, which is sent and received between a server and a client, in a correct direction. An image content providing server stores, as property information, original angle information indicating correct directions of image content as metadata of the image content. The server generates content information including the original angle information and sends the generated content information to a client. This allows the client to understand the correct direction of the image content received from the server, and to obtain and display image data in the correct direction by performing rotation processing in the client device based on the obtained information or to request the server to perform the rotation processing.

The system, method and program are adapted for collecting images of job-site conditions, and plans and specifications. The images are annotated with attributes that relate to the location, time and trades involved and other aspects of the images. Job site images are collected with a camera connected to a portable data collection device. The data collection device is programmed with image attributes for a particular project. Images are also annotated with attributes gathered by sensors, such as GPS position data, moisture sensor information, and direction information. Images with attached attributes are uploaded to a database server and indexed into a relational database. Images can be flagged and determined to be Images for Resolution which triggers automatic notification to the involved parties and follow up to confirm resolution. Authorized participants can access images in near real time, to make funding, insurance and other judgments about the project. Images are archived for safekeeping and long term storage.

Systems and methods for generating and distributing photo filters are described. A photo filter publication application receives filter data and object criteria and generates a photo filter based on the filter data. The photo filter is associated with satisfaction of the object criteria. A photo filter engine then identifies that a client device has taken a photograph. The photo filter engine then provides the photo filter to the client device based on the photograph including an object that satisfies the object criteria. The photo filter may then be displayed as an option on a user interface of the client device. The object criteria may include associations between an object and a source of image data, for example, a brand of a merchant in which case the associated photo filter may include images associated with the brand of the merchant.

A presentation content management and creation system (10) comprises a database (30) of sorted media components coupled to be in communication with a controller (50) for scheduling and rendering media components selected from the database into a real time media presentation. At least one output device (14) is coupled to be in communication with the controller for outputting the real time media presentation and the controller renders the selected media components as the real time presentation is being communicated to the at least one output device.

Group keys and image group names of image groups to which the owner of a digital camera belongs are transmitted from a server to the digital camera. The image group names are displayed in list form and an image group name is selected from the list. The group key of the selected image group is transmitted from the digital camera to the server. The server sends the digital camera access information for accessing the user computer of another user who belongs to the image group identified by the received group key. The digital camera accesses the user computer based upon the access information and receives the image file desired.

A graphical user interface and method are described for designing and managing photo stories. For example, a graphical user interface (“GUI”) for creating photo stories according to one embodiment of the invention comprises: a photo story creation region associated with a particular photo story and having a plurality of photos assigned thereto, the photos being responsively grouped into a the photo story based on an analysis of the photos and the metadata associated with the photos; a photo story design template displaying a preview image of a photo story design using the photos within the photo story creation region; wherein the photos within the photo story design template are arranged based on the order in which they are displayed within the photo story creation region and wherein the photos within the photo story design are rearranged in response to user modification of the photos within the photo story creation region.

For retrieving information based on images, a first image is taken (S1) using a digital camera associated with a communication terminal (1). Query data related to the first image is transmitted (S3) via a communication network (2) to a remote recognition server (3). In the remote recognition server (3) a reference image is identified (S4) based on the query data. Subsequently, in the remote recognition server (3), a Homography is computed (S5) based on the reference image and the query data, the Homography mapping the reference image to the first image. Moreover, in the remote recognition server (3), a second image is selected (S6) and a projection image is computed (S7) of the second image using the Homography. By replacing a part of the first image with at least a part of the projection image, an augmented image is generated (S8, S10) and displayed (S11) at the communication terminal (1). Efficient augmentation of the first image taken with the camera is made possible by remaining in the planar space and dealing with two-dimensional images and objects only.

An electronic data system comprises memory storage having stored data, file system software, and a transaction file. The transaction file is maintained by the file system software, and includes a plurality of transaction records corresponding to transactions that have been or are to be executed on one or more files and/or the or more directories of the file system. The file system software operates to organize and maintain the stored data in the files and directories and also to coalesce multiple transaction records meeting one or more criteria into fewer coalesced transaction records. The physical memory space required by the transaction file is reduced by the transaction record coalescing. The coalesced transaction records may be constructed so that they represent a logical result of applying each transaction record of a transaction record set in chronological order. Once the coalesced transaction records have been committed in the file system, the physical memory used by the original transaction records in the set may be reclaimed for further use (e.g., to store further transaction records) or may be otherwise removed from further use (e.g., when the physical memory is located in a block of memory in a flash-like memory device that has reached its maximum number of write and/or erase cycles).

A method includes acquiring imaging data of a scene using an imaging tool. The method also includes extracting radio frequency identification (RFID) data stored in an RFID tag associated with the scene. The method further includes associating the RFID data with the imaging data.

The present invention provides techniques for efficient searching of a multi-modal biometric database. Nested searching improves search efficiency by using the results of a previous biometric modality search to limit the search population for subsequent biometric searches. The method can also be used in combinations of non-biometric searches limiting subsequent biometric searches or vice versa.

A reference comparison image obtained from a printed material is input. The grayscale feature amount of the reference comparison image is extracted. Using the extracted grayscale feature amount, a target comparison image corresponding to the reference comparison image is retrieved from a plurality of electronic data stored as target comparison images in a storage medium. The retrieved image is extracted from the storage medium and processed.