Abstract: This posture state estimation device is capable of estimating with high accuracy the posture state of an object. The posture state estimation device (100) is a device for estimating the posture state of an object having a plurality of sections connected by joints on the basis of image data that images the object, and has a section candidate extraction unit (140) for extracting a section candidate for a section from the image data, a complementary section candidate extraction unit (160) which estimates that a portion of an unextracted section for which a section candidate has not been extracted is being shadowed by an already extracted section for which a section candidate has been extracted in order to extract a section candidate of the unextracted section, and a posture state estimation unit (170) for estimating the posture state of the object on the basis of the extracted section candidate.

Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: obtaining from a user one or more data queries; identifying a product of interest in response to the one or more data query; examining a plurality of product records to determine a set of related products that are related to the product of interest, wherein the examining includes performing image analysis to extract one or more product topic classifier from product image data representing one or more product; and providing one or more output in response to the examining.

Abstract: A query optimizer may receive a query block that includes a hint. The hint may include a unique object identifier to specify an object to which the hint applies. In some instances, the object may correspond to a nested query block. A query optimization plan may be determined based, at least in part, on the hint. The query execution plan may then be executed to query a data store.

Abstract: Interactive sequential pattern mining is disclosed. One example is a system including a sequence miner, and an interaction processor. A sequence database is received, the sequence database including a plurality of input sequences, where each sequence of the plurality of input sequences is an ordered list of events, and each event in the list of events includes at least one item. The sequence miner mines the sequence database for a plurality of candidate sequence patterns, the mining based on an interaction with a user. The interaction processor processes the interaction with the user, the interaction based on domain relevance of the plurality of candidate sequence patterns to the user.

Abstract: Methods of interpreting user actions for controlling electronic devices, as well as apparatuses and systems implementing the methods. User actions can involve eyes, head, face, fingers, hands, arms, other body parts, as well as facial, verbal and/or mental actions. Hand and/or voice free control of devices. Methods for large as well as fine motion and placement of objects. Use of actions before and during other actions to confirm the intent of the other actions. Objects can be moved or warped based on combinations of actions. Measurement of eye gaze, and iterations and helper signals for improved accuracy of control. Triggers to start and end recognition of user actions and generation of device commands.

Abstract: Various embodiments of a framework which allow, as an alternative to resource-taxing decompression, efficient computation of feature maps using a compressed content data subset, such as video, by exploiting the motion information, such as a motion vector, present in the compressed video. This framework allows frame-specific object recognition and action detection algorithms to be applied to compressed video and other media files by executing only on I-frames in a Group of Pictures and linearly interpolating the results. Training and machine learning increases recognition accuracy. Yielding significant computational gains, this approach accelerates frame-wise feature extraction I-frame/P-frame/P-frame videos as well as I-frame/P-frame/B-frame videos. The present techniques may also be used for segmentation to identify and label respective regions for objects in a video.

Abstract: A method includes identifying one or more objects in one or more images of real-world scenes associated with a user, adding the identified one or more objects to a list of real-world objects associated with the user, assigning each object in the list of real-world objects to an object class based on object recognition, and providing a notification to the user that a content item has been associated with an object class assigned to one of the objects on the list of real-world objects associated with the user. A computer readable storage medium stores one or more computer programs, and an apparatus includes a processor-based device.

Abstract: A method and an apparatus for recognizing characters using an image are provided. A camera is activated according to a character recognition request and a preview mode is set for displaying an image photographed through the camera in real time. An auto focus of the camera is controlled and an image having a predetermined level of clarity is obtained for character recognition from the images obtained in the preview mode. The image for character recognition is character-recognition-processed so as to extract recognition result data. A final recognition character row is drawn that excludes non-character data from the recognition result data. A first word is combined including at least one character of the final recognition character row and a predetermined maximum number of characters. A dictionary database that stores dictionary information on various languages using the first word is searched, so as to provide the user with the corresponding word.

Abstract: An image processing method and apparatus to reduce storage resource consumption includes determining, by a server, a first geometric shape according to a first image unit in a first image from an encoding-side device, where a similarity between the first image unit and the first geometric shape falls within a preset range; and sending encoding information of the first image to a decoding-side device, where the encoding information of the first image includes indication information of the first geometric shape and indication information of a location of the first image unit in the first image.

Abstract: Based on a user's current action in an application, a set of the most likely actions to be taken next by a user is determined, such as based on a historical sequence of actions that the user, or a number of other users, have taken in the past. Based on historical sequence of events, a predictive GUI may be generated that can be dynamically updated automatically based on actions that are determined to be undertaken next by the user.

Abstract: The present disclosure relates to an apparatus for appraising an article. The apparatus for appraising an article includes: a communication unit receiving a photographed image including a partial image an entire image of the article; and a processing unit analyzing the photographed image, extracting characteristic point information of the photographed image based on a result of the analyzing of the photographed image, comparing the characteristic point information with reference information for the article to determine authenticity and an appearance grade of the article, and calculating an evaluation amount of the article based on the authenticity and the appearance grade of the article.

Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. In particular, a multi-view interactive digital media representation (MVIDMR) of a person can be generated from live images of a person captured from a hand-held camera. Using the image data from the live images, a skeleton of the person and a boundary between the person and a background can be determined from different viewing angles and across multiple images. Using the skeleton and the boundary data, effects can be added to the person, such as wings. The effects can change from image to image to account for the different viewing angles of the person captured in each image.

Abstract: Systems and method are provided for controlling a vehicle. In one embodiment, an object classification method includes receiving sensor data associated with an object observed by a sensor system of an autonomous vehicle and determining, with a processor, a bounding curve associated with the sensor data. A plurality of bounding curve features are determined based on a set of convexities and concavities associated with the bounding curve. The object is classified by applying the plurality of bounding curve features to a machine learning model and receiving a classification output.

Abstract: An image quality assessment and restoration system may include a processor and a memory storing instructions to receive an input image, receive a predetermined number of parameter candidates, generate a reconstructed image from the input image for each parameter candidate, sort the reconstructed images by the overall comparative quality between them and determine the best reconstructed image, calculate the overall comparative qualities between the remaining reconstructed images and the best reconstructed image, eliminate any parameter candidates that are suboptimal based on the calculated overall comparative quality, iteratively generate and sort additional reconstructed images and eliminate suboptimal parameter candidates until each of the remaining parameter candidates is converged, and output the converged parameters for use in image restoration. The overall comparative quality may depend upon the local gradient-based structure information and/or the global texture quality information.

Abstract: A computing device can determine visual words for images in a first set of images associated with a description that includes a term. Each visual word can describe pixels in an image. The device can determine visual words for images in a second set of images that are associated with a description that does not include the term. The device can determine a set of visual words that are associated with the term. The device can determine regions in images corresponding to visual words in the set of visual words. The device can associate the respective determined regions for the images with the term in a database. When a search query is received that includes an image that is determined to be associated with the term, the database can be utilized to determine images responsive to the query by identifying images that are also associated with the term.

Abstract: An information processing system according to one embodiment includes an extraction unit and a generation unit. The extraction unit extracts a word specified by a user and contained in a request transmitted from a user terminal and an image displayed as a choice on the user terminal in response to the request. The generation unit generates combination data by associating image data corresponding to the image and obtained from an image storage unit with a name based on the word.

Abstract: Systems and methods for responding to an image query from a computer user are provided. According to the disclosed subject matter, in response to receiving an image query, a search engine identifies the subject matter of the query image according to similar images. An entity name is determined from the similar images and is mapped to a known entity of the search engine. Based on the known entity, related information regarding the known entity is obtained and one or more search results pages directed to the known entity are generated. At least one of the generated search results pages is returned to the computer user as a response to the image query.

Abstract: A method includes determining a plurality of harvest content items. The harvest content items are ranked based on a performance metric. Matching criterion aspects of the harvest content items are determined. Aspects of a candidate content item are compared with the plurality of harvest content items according to the matching criterion aspects. A subset of the harvest content items that are similar to the candidate content item is determined. A transformation for the candidate content item is selected and applied to the candidate content item to generate a transformed content item.

Abstract: A device and system can physically position a camera lens between the eyes of the image of the person onscreen in a video conference. To position the lens, a mechanical device may position or move the camera lens. The mechanical device can include a movable armature that can move a small camera head (i.e., a lens with or without supporting electronics) from a first position of the computer monitor (e.g., the frame of the monitor) to a second position onscreen. The second position can place the lens near or over the image of the other party, for example, between the eyes of the onscreen image of the other party.

Abstract: Methods, non-transitory computer-readable storage mediums and systems for classifying features including labels or fields in digital images of forms and identifying any unclassified features utilizing a bitmap approach are provided. Each spatial template includes a set of features and a set of bitmaps, each bitmap indicating a spatial relationship between each feature and respective remaining features in each spatial template. The operations include selecting a spatial template from the spatial templates, classifying each extracted feature as one of features in the spatial template. The operations include generating at least one bitmap representing a spatial relationship for each unclassified feature in relation to classified features, comparing the at least one bitmap with each of a set of bitmaps in the selected spatial template, and identifying the at least one unclassified feature as one of features in the spatial template based on a result of the comparison.

Abstract: A method in one example implementation includes extracting a plurality of data elements from a record of a data file, tokenizing the data elements into tokens, and storing the tokens in a first tuple of a registration list. The method further includes selecting one of the tokens as a token key for the first tuple, where the token is selected because it occurs less frequently in the registration list than each of the other tokens in the first tuple. In specific embodiments, at least one data element is an expression element having a character pattern matching a predefined expression pattern that represents at least two words and a separator between the words. In other embodiments, at least one data element is a word defined by a character pattern of one or more consecutive essential characters. Other specific embodiments include determining an end of the record by recognizing a predefined delimiter.

Abstract: A system and related operating methods that achieve shared screen verification are presented here. One operating method begins by establishing a desktop sharing session between a publisher device and a viewer device, during which the publisher device renders a publisher display and the viewer device renders a viewer display that corresponds to the publisher display. The method continues by capturing first framebuffer data for a frame of the publisher display, capturing second framebuffer data for the corresponding frame of the viewer display. The method processes the first framebuffer data and/or the second framebuffer data to obtain processed framebuffer data having a consistent display resolution. Thereafter, the method compares the processed second framebuffer data to the processed first framebuffer data to obtain a measure of quality.

Abstract: A method for controlling unlocking includes the following operations. A reference feature point of a finger of a user is acquired when a touch operation on a fingerprint recognition sensor of a terminal is detected. A matching process is executed between the reference feature point set and a first feature point set, the first feature point set includes at least one feature point subset of a second feature point set, the second feature point set includes feature points of the entire or a majority portion of the finger. The terminal is unlocked when the reference feature point set is matched with the first feature point set.

Abstract: In accordance with one embodiment, an intelligent video thumbnail selection and generation tool may select a relevant and visually stimulating image from a video file and generate a thumbnail including the image. The image may be selected by computing a relevancy metric for an image in the file based on one or more selected relevant features, and comparing that relevancy metric with the metric of at least one other image in the file. In another embodiment, a series of images in a video file may be divided into shots. One of the shots may be selected based on a shot relevancy metric and a key image from the shot may be selected as a thumbnail based on a key image relevancy metric, where the shot relevancy metric and the key image relevancy metrics may be computed based on one or more relevant content features.

Abstract: A curved line correction apparatus includes a correction target receiving unit that receives selection of a correction target point when an instruction mark is placed on an arbitrary point on a curved line composed of a plurality of arranged points, a correction target range setting unit that sets a certain range of the curved line, including the correction target point, as a correction target range, and a correction unit that corrects a portion of the curved line within the correction target range by moving the correction target point and a point within the correction target range when movement of the instruction mark is received, in which the correction target range setting unit changes the size of the correction target range when an instruction input to change the range is received with the instruction mark being placed on the correction target point.

Abstract: Disclosed herein are methods and systems for generating a fingerprint for verification of a reference object, such as a layer or ply during a composite laminate layup procedure. An exemplary method includes generating a plurality of images of the reference object from a plurality of angles, removing at least one lighting effect from at least one reference image to generate at least one processed image, generating a reference fingerprint for the reference object based on the at least one processed image, generating at least one candidate image of a candidate object, generating a candidate fingerprint for the candidate object based on the at least one candidate image, comparing the candidate fingerprint and the reference fingerprint to determine whether a correlation exists between the candidate fingerprint and the reference fingerprint, and generating an alert based on the comparison of the candidate fingerprint and the reference fingerprint.

Abstract: A method and apparatus for managing content, where content received or generated in a device is automatically grouped and managed in real-time, and a computer readable recording medium having recorded thereon a program for executing the method which includes detecting whether content is received or generated by a device, grouping the received or generated content with another received or generated content, and displaying the grouped content on the device, wherein the another content includes at least one content received or generated before the detected received or generated content.

Abstract: Methods and systems for Assurance-enabled Linde Buzo Gray (ALBG) data clustering is described herein. In an implementation, a user model data from a database available to the processor is obtained. The user model data comprises data elements or users, each of which corresponds to features and feature values associated with the users. These data elements of the user model data are segmented into clusters using our segmentation approach with an initial accuracy criterion parametric value and the output is captured as segment data. The segment data output is checked for initial pareto validity. If successful, iterative segmentation run with incremental accuracy criterion using parameterized value is performed till the segmented clusters are determined valid against pareto validity check. The last successful pareto valid segmented cluster data is considered as the finalized segment output data.

Abstract: The present disclosure extends to methods, systems, and computer program products for generating attribute tables for holding and calculating attributes related to location and distance while a corresponding business plan is in an approval process.

Abstract: A system for checking data for errors, the system comprising a checking module operable to check tuples of data stored in a target database for errors, the tuples in the target database originating from the output of at least one query transformation module which applies a query transformation to tuples of data from at least one data source an identification module operable to identify a problematic tuple from a data source that produces an error in the target database, the identification module being operable to quantify the contribution of the problematic tuple in producing the error in the target database, and a description generation module operable to generate a descriptive query which represents at least one of errors identified by the checking module in the target database which are produced by the at least one query transformation module, and problematic tuples identified in a data source by the identification module.

Abstract: A facial recognition authentication on a device having a camera may operate with multiple enrollment profiles on the device. Multiple enrollment profiles may include separate profiles for different appearances of a user and/or separate profiles for different users authorized to use the device. The enrollment profiles may be generated using an enrollment process where the enrollment process is operated separately to generate each of the different enrollment profiles. During the facial recognition authentication process, a user may unlock the device by having a matching score for image(s) captured of the user that that exceeds an unlock threshold for at least one of the enrollment profiles. The user may have a matching score that exceeds the unlock threshold for multiple enrollment profiles. Each enrollment profile unlocks the device for the user may be updated using a template update process that operates independently for each enrollment profile.

Abstract: Described is a technology by which a mobile device outputs an alert for a reminder based upon a current location of the mobile device with respect to an entity (person, place or thing) associated with the reminder. The reminders may be maintained and provided by a service. Each reminder includes a reference to target-related information. When the device moves to within a threshold proximity of the target, and other criteria (e.g., time of day) is satisfied, an alert is output by the device. A user may gesture with a device towards an entity to set a reminder associated with that entity, or to get any reminder associated with that entity. A device may also get reminders by scanning or image processing, e.g., by reading a barcode associated with a product to get any reminders associated with that product.

Abstract: The invention relates to a dentel device for the treatment of a dental restoration part, comprising at least one operating program, a storage of the dental device and at least one detection device for at least one object. The detection device can detect data of the object and this data, in particular together with an operating program associated with the object, can be stored in a storage of the dental device or can be compared to the data of objects which have been stored in advance in the storage of the dental device. The dental device, depending on the comparison result of the data of a detected object with the data of objects which have been stored in advance in the storage of the dental device, starts the associated operating program or shows it for selection.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for shape detection are disclosed. In one aspect, a method includes the actions of generating a shape model that includes a predetermined shape with a predetermined scale and predetermined orientation. The actions further include receiving an image. The actions further include identifying edges that are parallel to the side of the shape model and that are a predetermined distance from the side of the shape model. The actions further include selecting a plurality of edges that likely correspond to edges of a shape that is similar to the shape model. The actions further include determining a fit score between the plurality of edges and each shape of a plurality of shapes that are similar to the shape model. The actions further include identifying a particular shape in the image that most closely fits the shape model.

Abstract: An image creation and editing tool can use the data produced from training a neural network to add stylized representations of an object to an image. An object classification will correspond to an object representation, and pixel values for the object representation can be added to, or blended with, the pixel values of an image in order to add a visualization of a type of object to the image. Such an approach can be used to add stylized representations of objects to existing images or create new images based on those representations. The visualizations can be used to create patterns and textures as well, as may be used to paint or fill various regions of an image. Such patterns can enable regions to be filled where image data has been deleted, such as to remove an undesired object, in a way that appears natural for the contents of the image.

Abstract: Systems and methods are disclosed herein for detecting duplicate copies of a media asset and deleting or offloading one of the duplicate copies to different user devices. Specifically, a media guidance application, implemented at user equipment, may be used to record or store media assets from different media sources. The media guidance application may detect a duplicate copy of a previously stored media asset by comparing various attributes of the media asset. After detecting a duplicate copy of a media asset, the media guidance application may determine which of the duplicate copies of the same media asset is to be deleted, or to be transmitted for storage at a different user device.

Abstract: A method of segmenting a video sequence. A segment score is determined for each of a plurality of fixed length segments of the video sequence. Each of the segment scores provide a score for a plurality of actions associated with a corresponding fixed length segment. A current segment is selected from the segments of the video sequence. The segment score is selected for a further one of the segments, the further segment being disjoint with the current segment and being used to provide information about actions that were classified outside the current segment. A further segment score is determined for the current segment according to the selected segment score. The video is segmented based on the determined further segment score.

Abstract: A method and system are proposed to obtain a reduced speckle noise image of a subject from optical coherence tomography (OCT) image data of the subject. The cross sectional images each comprise a plurality of scan lines obtained by measuring the time delay of light reflected, in a depth direction, from optical interfaces within the subject. The method comprises two aligning steps. First the cross sectional images are aligned, then image patches of the aligned cross sectional images are aligned to form a set of aligned patches. An image matrix is then formed from the aligned patches; and matrix completion is applied to the image matrix to obtain a reduced speckle noise image of the subject.

Abstract: Systems and methods are disclosed herein for detecting duplicate copies of a media asset and deleting or offloading one of the duplicate copies to different user devices. Specifically, a media guidance application, implemented at user equipment, may be used to record or store media assets from different media sources. The media guidance application may detect a duplicate copy of a previously stored media asset by comparing various attributes of the media asset. After detecting a duplicate copy of a media asset, the media guidance application may determine which of the duplicate copies of the same media asset is to be deleted, or to be transmitted for storage at a different user device.

Abstract: Disclosed are a quantum system-based image pattern recognition computation apparatus and method for machine vision and a quantum system-based machine vision apparatus. The computation apparatus recognizes patterns between images in machine vision by using a quantum system. The computation apparatus includes a modeling unit and an interpretation unit. The modeling unit sets up an objective function based on the similarity between a first pattern derived from the relationships between points of interests of a first image and a second pattern derived from the relationships between points of interests of a second image. The interpretation unit finds an optimum first pattern and an optimum second pattern, in which the similarity between the first pattern and the second pattern is optimized, by interpreting a final quantum state obtained through an adiabatic evolution process of the quantum system in which the objective function is optimized.

Abstract: A data arrangement apparatus executes a process request on data stored in a database, calculates similarity of a process in a combination of the process request and the data, divides the data in such a manner as to distribute the similarity and processes a process request accepted for the divided data.

Abstract: Methods of organizing documents by reclassification and clustering are disclosed. In one embodiment, a method of clustering electronic documents of a document corpus includes comparing, by a computer, each individual electronic document in the document corpus with each other electronic document in the document corpus, thereby forming document pairs. The electronic documents of the document pairs are compared by calculating a similarity value with respect to the electronic documents of a document pair, associating the similarity value with both electronic documents of the document pair, and applying a clustering algorithm to the document corpus using the similarity values to create a plurality of hierarchical clusters. The similarity value is based on a plurality of attributes of the electronic documents in the document corpus.

Abstract: The printing system includes a handwritten character data extraction unit, a sample character data retrieval unit, a determination unit, a character practice worksheet creating unit, and a print control unit. The determination unit determines whether the matching ratio between a handwritten character extracted by the handwritten character data extraction unit and a sample character retrieved by the sample character data retrieval unit is equal to a first ratio or lower. If the determination unit determines that the matching ratio is equal to the first ratio or lower, the character practice worksheet creating unit creates a character practice worksheet containing the sample character that matches the handwritten character and a blank cell for handwriting practice formed next to the sample character. The print control unit controls the printing unit to print the character practice worksheet created by the character practice worksheet creating unit on paper.

Abstract: In authentication based on an image region read from a surface of a target object, authentication based on a position corresponding to the image region is executed. An authenticating server 2 receives an image region as an authentication target read from a surface of a target object possessed by a user together with an authentication request from the user, identifies a position corresponding to the image region as the authentication target and one reference image region corresponding to the image region as the authentication target in a plurality of previously stored reference image regions read from respective surfaces of a plurality of target objects, and executes authentication in response to the authentication request based on the identified position.

Abstract: Disclosed are techniques and systems to detect a layout of a source document. A process may include receiving content from a first page and a second page of the source document, designating sections in each page along a first direction of the page, and assigning similar sections to a group. For the group, the process may proceed by dividing sections for each page into discrete portions associated with 2D coordinate areas, and identifying sets of 2D coordinate areas for the discrete portions that contain content. The number of times each portion contains some content may be compared to a threshold to determine a layout of the group of sections.

Abstract: Edge-based recognition systems and methods are presented. Edges of the object are identified from the image data based on co-circularity of edgels, and edge-based descriptors are constructed based on the identified edges. The edge-based descriptors along with additional perception metrics are used to obtain a list of candidate objects matched with the edge-based descriptors. Through various filtering processes and verification processes, false positive candidate objects are further removed from the list to determine the final candidate object.

Abstract: A method for providing messaging-related information to a mobile device is discussed. The method includes receiving from the mobile device a request for messaging-related information, using the request to identify a device-type indication for the mobile device, identifying one or more presentation parameters for presenting the messaging-related content properly on the mobile device, and transmitting the messaging-related content to the mobile device in a format corresponding to the one or more parameters.

Abstract: A system and method for transmitting compressed image data includes an encoder, responsive to received image data representing an image, for minimizing a space-spatial frequency of the image data by applying a predetermined orthogonal function thereto to generate a mathematical representation of the image data and extracting coefficients of the mathematical representation of the image data. A transmitter transmits the coefficients of the image data from a first location to a second location. A receiver receives the transmitted coefficients of the image data at the second location from the first location. A decoder recreates the mathematical representation of the image data at the second location responsive to the received coefficients and the predetermined orthogonal function and generates the image data from the recreated mathematical representation of the image data.

Abstract: The present invention provides a measurement apparatus for measuring a position of a mark formed on a substrate, the apparatus including a detector configured to detect the mark to generate a detection signal, and a processor configured to process the generated detection signal to obtain a position of the mark, wherein the processor is configured to limit a range of the detection signal to be processed to obtain the position of the mark based on a statistic representing dispersion of a plurality of the position obtained with respect to a plurality of the mark.

Abstract: A system for early warning of health status decline includes at least one energy emitter configured to emit energy onto a field-of-view that contains an individual, and at least one energy sensor configured to capture reflected energy from within the field-of-view. A spatial measurement module calculates spatial measurements of a surface portion of the body of the individual when the individual is either stationary or moving about in real-time, based on data from the energy sensor. A comparator module detects deviations in measurements from baseline values indicative of a deterioration in health status of the individual.