Abstract: A character recognition method for recognizing a character of a medium is provided. A character image of an individual character from a medium is acquired and the character image is read out step by step to determine the character according to a hierarchical structure in which a set of predetermined characters are hierarchically classified into a plurality of groups configured of main groups and sub groups.

Abstract: A terminal includes a display unit and a controller. The display unit includes a touch sensor. The touch sensor senses a touch input. The display unit displays text. The controller divides a first part of the text, enlarges the first part, and displays the enlarged first part on the display unit in response to a first touch input that occurs on the displayed text and that is sensed through the touch sensor. The first part of the text corresponds to the first touch input.

Abstract: As a user writes using a handheld writing device, such as an electronic pen or stylus, handwriting input is received and initially displayed as digital ink. The display of the digital ink is converted to recognized text inline with additional digital ink as the user continues to write. A user may edit a word of recognized text inline with other text by selecting the word. An enlarged version of the word is displayed in a character correction user interface that allows a user to make corrections on an individual character basis and also provides other correction options for the word.

Abstract: Approaches are described for ranking multiple products or other items, such as products obtained in response to a search request submitted to a server. The ranking system determines a ranking score for the products based on both data available online and item data that must be computed offline due to longer computation time or unavailability of data. The ranking score can be used to rank the products and determine which products are the most relevant to the user. A hybrid boosting method is used to first train an online ranking function to produce an online ranking score for the item. In the second phase, an offline ranking function is trained to produce a second ranking score for the item. The online rank score is combined with the offline rank score at query time to produce a combined rank for the items in the search results.

Abstract: Music recognition is carried out by accepting a musical score of musical elements in a digital format, transforming the digital format into a composite musical data object that models the musical score, defining the key signatures in the composite musical data object probabilistically, computing start times to play musical elements in respective measures of the composite musical data object without regard to rhythmic values of other musical elements in the respective measures, and generating an output including the defined key signatures and computed start times.

Abstract: An image processing apparatus determines an orientation of an image according to acquired image information. The image processing apparatus includes an image information acquiring unit, a character string extracting unit, and an image orientation determining unit. The image information acquiring unit acquires image information. The character string extracting unit extracts a character string existing in a rectangular region surrounded by ruled lines or ruled lines and a periphery of the image in a partial area that is a part of the image and that meets a predetermined condition. The image orientation determining unit determines an orientation of the image according to a direction of the character string extracted by the character string extracting unit.

Abstract: A gesture-based system may have default or pre-packaged gesture information, where a gesture is derived from a user's position or motion in a physical space. In other words, no controllers or devices are necessary. Depending on how a user uses his or her gesture to accomplish the task, the system may refine the properties and the gesture may become personalized. The personalized gesture information may be stored in a gesture profile and can be further updated with the latest data. The gesture-based system may use the gesture profile information for gesture recognition techniques. Further, the gesture profile may be roaming such that the gesture profile is available in a second location without requiring the system to relearn gestures that have already been personalized on behalf of the user.

Abstract: A reduced-latency ink rendering system and method that reduces latency in rendering ink on a display by bypassing at least some layers of the operating system. “Ink” is any input from a user through a touchscreen device using the user's finger or a pen. Moreover, some embodiments of the system and method avoid the operating system and each central-processing unit (CPU) on a computing device when initially rendering the ink by going directly from the digitizer to the display controller. Any correction or additional processing of the rendered ink is performed after the initial rendering of the ink. Embodiments of the system and method address ink-rendering latency in software embodiments, which include techniques to bypass the typical rendering pipeline and quickly render ink on the display, and hardware embodiments, which use hardware and techniques that locally change display pixels. These embodiments can be mixed and matched in any manner.

Abstract: According to one embodiment, an electronic device includes processing circuitry. The processing circuitry displays one or more first strokes input by handwriting on a screen, and executes, in response to input of the one or more first strokes, processing for displaying a second stroke group selected from stroke groups which are input candidates searched by using the one or more first strokes on the screen, the stroke groups including the second stroke group and another stroke group, the second stroke group and the another stroke group corresponding to a first character string. A value in any one of a size, a number of coordinates for displaying, and a length of time for inputting, of to the second stroke group is bigger than that of the another stroke group.

Abstract: According to one embodiment, a document search apparatus includes an acquirer, determiner, searcher, and display. The acquirer acquires data on a handwriting including coordinate data. The determiner determines a shape of the handwriting based on the coordinate data to determine a type of a query. The searcher searches the document according to a search method corresponding to the type of the query. The display that displays the document by a display method corresponding to the type of the query.

Abstract: An information processing system includes an operating unit that receives an input in response to a user operation and that runs under a first operating system; and a main body that runs under a second operating system and operates in response to the input received by the operating unit. The main body includes a generation unit that generates a command to direct rendering of a screen corresponding to an application being executed, and a command transmission control unit that provides control to transmit the command to the operating unit. The operating unit includes a receiving unit that receives the command from the main body, a screen rendering unit that renders the screen in accordance with the command received by the receiving unit, a display unit that displays the screen rendered by the screen rendering unit, and a reboot unit that reboots the operating unit in asynchronization with the main body.

Abstract: Methods and apparatus are provided for generating an animated message. Input objects in an image of the animated message are recognized, and input information, including information about an input time and input coordinates for the input objects, is extracted. Playback information, including information about a playback order of the input objects, is set. The image is displayed in a predetermined handwriting region of the animated message. An encoding region, which is allocated in a predetermined portion of the animated message and in which the input information and the playback information are stored, is divided into blocks having a predetermined size. Display information of the encoding region is generated by mapping the input information and the playback information to the blocks in the encoding region. An animated message including the predetermined handwriting region and the encoding region is generated. The generated animated message is transmitted.

Abstract: An airborne mine countermeasure system includes a processor coupled to a memory having stored therein software instructions that, when executed by the processor, cause the processor to perform a series of image processing operations. The operations include obtaining input image data from an external image sensor, and extracting a sequence of 2-D slices from the input image data. The operations also include performing a 3-D connected region analysis on the sequence of 2-D slices, and extracting 3-D invariant features in the image data. The operations further include performing coarse filtering, performing fine recognition and outputting an image processing result having an indication of the presence of any mines within the input image data.

Abstract: A method for recognizing a primitive in an image includes recognizing at least one primitive in the image to obtain at least one candidate shape of the at least one primitive, which at least one candidate shape has a respective confidence; determining whether the recognizing of the at least one primitive has a potential error based on the confidence; obtaining auxiliary information about the at least one primitive from a user in response to determining that the recognizing has the potential error; and re-recognizing the at least one primitive at least in part based on the auxiliary information.

Abstract: Methods, systems, and apparatuses, including computer programs encoded on computer-readable media, for capturing, using a camera, an image of a general writing surface. The captured image is compared with one or more previously saved images. A related image is determined based upon syntax and semantics of handwriting recognized in the captured image and the one or more previously saved images. A previous document associated with the related image is retrieved and set as the active document. A position of a writing instrument is mapped to a position within the previous document.

Abstract: A method for recognizing a primitive in an image includes recognizing at least one primitive in the image to obtain at least one candidate shape of the at least one primitive, which at least one candidate shape has a respective confidence; determining whether the recognizing of the at least one primitive has a potential error based on the confidence; obtaining auxiliary information about the at least one primitive from a user in response to determining that the recognizing has the potential error; and re-recognizing the at least one primitive at least in part based on the auxiliary information.

Abstract: A multi-character continuous handwriting input method where a character is written on a touch unit and after an ith character is written, an (i+1)th character is written in an overlapping manner on the ith character. When a user is writing, it is determined whether a current stroke belongs to the ith character or (i+1)th character; if it is the (i+1)th character, the display color of the ith character is dimmed automatically, so that the user clearly sees the newly written character on a display screen. Multiple characters can be written continuously without pauses and when an (i+2)th character is written, the ith character disappears automatically from the screen, and the color of the (i+1)th character is dimmed automatically. Thus, the ability to continuously write multiple handwritten characters on a screen and the corresponding recognition and display processing significantly improves the input efficiency of handwritten text.

Abstract: Methods and apparatus for determining whether a media presentation device is in an on state or an off state are disclosed. A disclosed example method comprises determining first and second characteristics of a signature associated with a signal representative of media content presented via a media presentation device, evaluating the first and second characteristics to determine first and second fuzzy contribution values representing, respectively, degrees with which the first and second characteristics correspond to the media presentation device being in at least one of an on state or an off state, determining a third fuzzy contribution value based on a number of the first and second contribution values indicating the media presentation device is in one of the on or off states, and combining the first, second and third fuzzy contribution values for use in determining whether the media presentation device is in the on state or the off state.

Abstract: A method, a system, and a computer program product for evaluating a handwritten document comprising one or more text fields are provided. The method includes identifying a character in each of the one or more text fields in a digital image by applying a character recognition technique. The character type of the identified character is then compared with a predefined character type corresponding to the associated text field of the one or more text fields. The character type in each of the one or more text fields is then validated based on the comparison. Thereafter the identified character for each of the one or more text fields is recommended while digitalization of the handwritten document.

Abstract: An information processing apparatus includes: an image pickup unit, a recognition unit and an execution unit. The image pickup unit photographs a recording medium to generate a picked-up image. The recognition unit recognizes a handwritten mark in the picked-up image generated by the image pickup unit. The execution unit performs a predetermined process according to the handwritten mark recognized by the recognized unit.

Abstract: The encoding of a line pattern representation. The line pattern representation has a changing value in a first dimension as a function of a value in a second dimension. The line pattern representation is segmented into multiple segments along the second dimension. The line pattern representation is then encoded by assigning a quantized value to each of the segments based on the changing value of the line pattern in the first dimension as present within the corresponding segment. If the line pattern generally falls within a given range within a segment, the segment will be assigned a quantized value corresponding to that range. The encoding may be used to assign the line pattern representation into a category.

Abstract: A method for entering keys in a small key pad is provided. The method comprising the steps of: providing at least a part of keyboard having a plurality of keys; and predetermining a first probability of a user striking a key among the plurality of keys. The method further uses a dictionary of selected words associated with the key pad and/or a user.

Abstract: A method and system for providing hand-written command processing includes a network-connected application server receiving from a user device data storing hand-written information. The hand-written information is processed to identify one or more hand-written characters included in the data. A determination is made as to whether the identified characters include a command for initiating an action across the communication network. Upon determining that the characters include a command, the application server automatically performs the action identified by the command across the communication network. The action can include generating and sending a messaging service message or an e-mail, creating a scheduled reminder, creating and storing a checklist or note, or retrieving a previously stored checklist or note, based on information included in the hand-written characters. The user device may be a tablet-type user device.

Abstract: According to an embodiment, a feature calculation device includes an obtaining unit, a first calculator, and a second calculator. The obtaining unit is configured to obtain a point sequence group comprising a set of point sequences in which a sequence of a plurality of points is fixed. The first calculator is configured to, for each of the point sequences in the point sequence group, calculate a plurality of values related to a curvature of a shape of the point sequence, with a reference point of the point sequence as a reference, and calculate feature quantities based on the plurality of calculated values. The second calculator is configured to calculate a histogram representing a distribution of the feature quantities of each of the point sequences.

Abstract: Method, computer program product and user device for searching implemented at the user device, wherein an input is received from a user via a touch screen of the user device. Without user initiation of a temporary character recognition mode specifically to receive the input, the input is analyzed using character recognition. Responsive to the character recognition recognizing at least one character in said received input, a search mode is invoked in which one or more search results which at least partially match the at least one recognized character are displayed. The user may select one of the displayed search results.

Abstract: Apparatus, a method and a computer program are provided.

Abstract: An optimal recognition for handwritten input based on receiving a touch input from a user may be selected by applying both a delayed stroke recognizer as well as an overlapping recognizer to the handwritten input. A score may be generated for both the delayed stroke recognition as well as the overlapping recognition and the recognition corresponding to the highest score may be presented as the overall recognition.

Abstract: Methods and apparatus for using are provided for using neural signals to drive touch screen devices. An electromyography (EMG) device can receive neural based on electrical activity of one or more voluntary muscles of a user of the EMG device. The EMG device can filter the neural signals to generate a plurality of channel signals. A touch event can be determined based on the plurality of channel signals. The touch event can relates to user input for a touch-based interface of a touch-enabled device. The touch-enabled device can receive an indication of the touch event. The touch-enabled device can determine a touch operation for the touch-enabled device based on the touch event and then perform the touch operation.

Abstract: System and method for determining a classifier to discriminate between two classes—object or non-object. The classifier may be used by an object detection program to detect presence of a 3D object in a 2D image. The overall classifier is constructed of a sequence of classifiers, where each such classifier is based on a ratio of two graphical probability models. A discreet-valued variable representation at each node in a Bayesian network by a two-stage process of tree-structured vector quantization is discussed. The overall classifier may be part of an object detector program that is trained to automatically detect different types of 3D objects. Computationally efficient statistical methods to evaluate overall classifiers are disclosed. The Bayesian network-based classifier may also be used to determine if two observations belong to the same category.

Abstract: When a user or the like blocks a portion of a projected image, acquisition of position information about a drawing-designated position, which is designated using a pointing device, is inhibited, and a missing drawn portion is produced. However, a projection apparatus generates image data that is interpolated using a pattern image, thereby making it possible to draw a graphic object as drawn.

Abstract: With some splines, such as cardinal splines, irregularly spaced data points may cause undesired bumps. Bump moderation makes a spline curve more visually appealing by reducing bumps, and by doing so even if the curve happens to be already smooth in a mathematical sense. Data points P1, P2, and P3 are not suitably spaced an outlier is present in a set of linear distances between the points. The bump is moderated by moving a point of the spline along a pathway to a position for which the data points P1, P2, and P3 are suitably spaced. The pathway may be a Bezier segment or a line segment. A point is moved on the pathway to its midpoint, or to a particular portion of the pathway such as its central third or central fifth.

Abstract: A vehicle input apparatus includes a display screen that displays a cursor that indicates an operation item with respect to a predetermined operation object, an input device that outputs signals according to a sliding operation using the fingers of an operator on an operation surface, and a display control portion that controls movement of the cursor on the display screen according to the signals that are output from the input device. The display screen includes a plurality of display areas that are divided according to the number of the plurality of operation surfaces, and each of the plurality of operation surfaces is associated with a separate display area, and an operation range is set on the display screen so that the cursor can only be moved within the range of the respective associated separate display area.

Abstract: A method, apparatus and computer program product for entering text on a touch-screen device is presented. Entry of at least one letter of a word on a virtual keypad of a touch-screen device is detected. In response to the detection of an entry of least one letter of a word on a virtual keypad of a touch-screen device a first row of keys is displayed on the virtual keypad, the first row of keys comprising a predictive character set of keys based on the entry of at least one letter of a word.

Abstract: A visual media de-identification system is described. The system includes an image merger and a de-identifying engine. The image merger is configured to merge a sequence of images from a set of visual media data into an averaged image. The de-identifying engine is configured to: bound portions of the averaged image that are determined to be relatively fixed, wherein each bounded portion is identified by a corresponding position in the averaged image; generate a template comprising the bounded portions and the corresponding position for each bounded portion in the averaged image; and de-identify the sequence of images by obfuscating content in the bounded portions.

Abstract: A method for de-identification of visual media data, including: merging a sequence of images from a set of visual media data into an averaged image; bounding portions of the averaged image that are determined to be relatively fixed, wherein each bounded portion is identified by a corresponding position in the averaged image; generating a template comprising the bounded portions and the corresponding position for each bounded portion in the averaged image; and de-identifying the sequence of images by obfuscating content in the bounded portions.

Abstract: An image of real world is processed to identify blocks as candidates to be recognized. Each block is subdivided into sub-blocks, and each sub-block is traversed to obtain counts, in a group for each sub-block. Each count in the group is either of presence of transitions between intensity values of pixels or of absence of transition between intensity values of pixels. Hence, each pixel in a sub-block contributes to at least one of the counts in each group. The counts in a group for a sub-block are normalized, based at least on a total number of pixels in the sub-block. Vector(s) for each sub-block including such normalized counts may be compared with multiple predetermined vectors of corresponding symbols in a set, using any metric of divergence between probability density functions (e.g. Jensen-Shannon divergence metric). Whichever symbol has a predetermined vector that most closely matches the vector(s) is identified and stored.

Abstract: According to one embodiment, an electronic device includes a display processor, a transmitter and a receiver. The display processor displays on a screen a handwritten document including a plurality of strokes described by handwriting. The transmitter transmits to a system a handwritten part designated by a select range on the screen. The receiver receives from the system a reshaping result corresponding to the handwritten part. The display processor displays the reshaping result on the screen, the reshaping result and the handwritten part associated with each other.

Abstract: Disclosed is a method of operating a secondary device in a manner associated with operation of a primary device including obtaining first information corresponding to a media asset being output by the primary device, processing the first information to determine local media-signature information, transmitting the first information for receipt by a server, receiving secondary information from the server, wherein the secondary information includes a plurality of asset-media signatures that respectively correspond to respective portions of the media asset, attempting to determine a time-based correlation between at least one portion of the local media-signature information and at least one of the asset-media signatures, and outputting one or more portions of time-relevant asset streams from the secondary device, the one or more portions being determined at least indirectly based upon the correlation.

Abstract: Disclosed are a method for providing a user interface by mapping various types of multimedia to patterns drawn on a display, and a mobile terminal thereof. A user may draw a pattern according to his or her preference, and a controller may generate an object by mapping one or more multimedia data to the pattern. The controller may play the mapped multimedia data by tracking the multimedia data-mapped pattern. The controller may store the multimedia data-mapped pattern (object) in a memory. And, the controller may transmit the object to a selected specific party to provide an enhanced user interface (UI).

Abstract: An electronic system having a multiple of input keyboards is provided. The electronic system comprises a touch display unit and a processing unit. The touch display unit displays a plurality of input fields. The processing unit links each of a plurality of virtual input keyboards correspondingly to one of the input fields to perform data processing on the input fields according to the operation input on each of the virtual input keyboards.

Abstract: A method and system for signature-based unsupervised clustering of data elements. The method comprises receiving a plurality of clusters; generating a triangular matrix respective of the clusters; generating a signature for each of the clusters; generating a match score between each of two different clusters; storing the match score in a cell of the triangular matrix corresponding to the two clusters; determining whether any of the match scores is above a predefined threshold value; clustering every two clusters that are determined to have a score above a predetermined threshold; and repeating the generation of a triangular matrix respective of the clusters until a single cluster is reached. The system comprises an interface; a processor; a memory for storing at least one cluster; and a memory coupled to the processor, the memory containing instructions that, when executed by the processor, configure the system to perform the steps of the method.

Abstract: An apparatus and method for inputting a character using a keyboard displayed on a touch screen in a portable terminal. The apparatus and method determines if a touch signal is generated, with the keyboard displayed. Upon generation of the touch signal, a touched character is recognized by analyzing the touch signal. The character is displayed enlarged in a predetermined screen area. It is then determined if the touch has been completed, while the character is displayed enlarged. Upon sensing the touch completion, the character is displayed in a main screen area.

Abstract: The present disclosure relates to classification of a material type of an object. A first phase applies an object classifier and a material classifier to obtain first object and material probabilities of the object. A second phase applies an interdependent object/material classifier to the first object and material probabilities to obtain further object and material class probabilities. The interdependent object/material classifier performs multiple iterations of calculating the further object and material class probabilities, and utilizes feedback in which an immediately preceding calculated prior further object class probability is included in a next iteration of calculating a further material class probability, and an immediately preceding calculated prior further material class probability is included in a next iteration of calculating a further object class probability.

Abstract: During operation of an electronic device such as a cellular telephone with a touch screen display or other electronic equipment, a voice recognition engine may gather data on spoken words. Data on the spoken words that are recognized may be maintained in a spoken word database maintained by an input processor with an autocorrection engine. A user may supply text input that contains mistyped words to the electronic device using the touch screen or a keyboard. The input processor may use the autocorrection engine to automatically replace mistyped words with corrected versions of the mistyped words. The corrected words may be displayed in real time as the user supplies the text input. The autocorrection engine may make word correction decisions based at least partly on information in the spoken word database.

Abstract: A stylus is used to modify the appearance of objects rendered on a touch-sensitive display. One of a plurality of objects on the display is selected by making contacting the object with the stylus. The stylus tilt and stylus contact pressure are determined. The appearance of the selected object is modified in response to the stylus tilt of the stylus and the stylus contact pressure.

Abstract: A multifunctional neural network system for prediction which includes memory components to store previous values of data within a network. The memory components provide the system with the ability to learn relationships/patterns existent in the data over time.

Abstract: Software, firmware, and systems are described for identifying characters in a handwritten input received from a user on an input device, irrespective of an angle that the input is received at. In one implementation, the system establishes an anchor point and distances from the anchor point to reference support lines. A set of candidate characters is identified based on received handwritten input. The system estimates support lines for each of the candidate characters. The system ranks the candidate characters based on a total deviation measurement from the expectation for each candidate, where the expectation in part is based on the established distance from the established anchor point to reference support lines, and identifies a best-ranked candidate based at least in part on a smallest total deviation measurement.

Abstract: A system comprises a generation unit which generates a browsing image by performing image processing for image data acquired by scanning; a holding unit which holds, in a storage unit for each use when the image data was printed out, information which defines image processing for converting the browsing image into image data for printing; a specification unit which specifies a use of image data corresponding to the browsing image upon accepting an instruction to print the browsing image; a conversion unit which converts the browsing image into image data for printing by deciding, in accordance with the information in the storage unit, image processing corresponding to the use of the specified image data, and applying the decided image processing to the browsing image; and a control unit which controls a printing unit to output the image data for printing.

Abstract: An information management apparatus includes a processor and a memory. The memory is configured to store computer-readable instructions that, when executed, cause the processor to perform processes including acquiring stroke data, the stroke data being data representing a trajectory and being data that includes information indicating positions on the trajectory, identifying, based on first stroke data, a first character string that is a character string formed by a first trajectory, identifying, based on second stroke data, a second character string that is a character string formed by a second trajectory, generating an image file that is a data file representing a third trajectory based on third stroke data, storing the image file in storing portion as a file including at least the first character string in a file name, and storing the image file in the storing portion in association with data representing the second character string.

Abstract: Portable electronic communication equipment, e.g., a mobile phone, includes a projector that is integrated into the mobile phone to project images, a camera senses views, including a view of projected images and of changes made to the projected image, e.g., by inserting an object, such as a finger, stylus, etc., into the projected image. The character of the changes, e.g., where a change occurs in an image, can be used as an input to the mobile phone. A method of using a portable communication device includes transmitting and receiving communications via a radio, projecting an image onto a surface, using a camera of the portable communication device to sense views including a view of a projected image by the projector, and detecting a change in the sensed view of the projected image to provide an input to the portable communication device.