Abstract: A method for text recognition includes generating a number of text hypotheses for an image, for example, using an HMM based approach using fixed-width analysis features. For each text hypothesis, one or more segmentations are generated and scored at the segmental level, for example, according to character or character group segments of the text hypothesis. In some embodiments, multiple alternative segmentations are considered for each text hypothesis. In some examples, scores determined in generating the text hypothesis and the segmental score are combined to select an overall text recognition of the image.

Abstract: A method for classifying an input character is disclosed. Character models are used. Each character model is associated with an output character and defines a model specific segmentation scheme for that output character and an associated segment model. The model specific segmentation scheme defines a minimum length corresponding to a number of points in a stroke of the output character and a minimum length threshold. Using each of the character models, the input character is decomposed into segments and the segments are evaluated against the segment model of the respective character model to produce a score indicative of the conformity of the segments with the segment model. The character model that produced the highest score is selected and the input character is classified as the output character associated with the character model that produces the highest score.

Abstract: Multiple input modalities are selectively used by a user or process to prune a word graph. Pruning initiates rescoring in order to generate a new word graph with a revised best path.

Abstract: A digital tracing method and device, comprising a flat acquisition element (3) for digitizing a document (7) and a flat display element (5) for displaying said digitized document mounted on said flat acquisition element (3).

Abstract: A method and system for implementing character recognition is described herein. An input character is received. The input character is composed of one or more logical structures in a particular layout. The layout of the one or more logical structures is identified. One or more of a plurality of classifiers are selected based on the layout of the one or more logical structures in the input character. The entire character is input into the selected classifiers. The selected classifiers classify the logical structures. The outputs from the selected classifiers are then combined to form an output character vector.

Abstract: This invention provides an image editing method having a selecting step of selecting an edit target area, a cancellation step of canceling a selection of the edit target area selected in the selecting step, and an area selecting step of selecting again the edit target area by indicating the inside of the edit target area.

Abstract: A method of identifying a string formed from a number of hand-written characters is disclosed. The method starts by determining character probabilities for each hand-written character in the string. Each character probability represents the likelihood of the respective hand-written character being a respective one of a number of predetermined characters. Next, template probabilities for the string are determined. Each template probability represents the likelihood of the string corresponding to a respective one of a number of templates. Each template represents a respective combination of character types. The step of determining the template probabilities for the string includes the sub-steps of determining the number of characters in the string, selecting templates having an identical number of characters, and obtaining a template probability for each selected template.

Abstract: Various methods for written mathematical expression analysis are provided. One method may include receiving written input where the written input is representative of a mathematical expression. The method may also include analyzing the written input to identify at least one operator and at least one operand and constructing an expression tree based at least in part on predefined symbol relationships, the at least one operator, and the at least one operand. Similar apparatuses and computer program products are also provided.

Abstract: In a system for updating a contacts database (42, 46), a portable imager (12) acquires a digital business card image (10). An image segmenter (16) extracts text image segments from the digital business card image. An optical character recognizer (OCR) (26) generates one or more textual content candidates for each text image segment. A scoring processor (36) scores each textual content candidate based on results of database queries respective to the textual content candidates. A content selector (38) selects a textual content candidate for each text image segment based at least on the assigned scores. An interface (50) is configured to update the contacts list based on the selected textual content candidates.

Abstract: An image forming apparatus that allows easy and reliable extraction of a hand-written image and allowing reliable execution of a desired process on image data based on the hand-written image is provided. For this purpose, during a mark adding process, a scanner unit and an image processing unit form YMCK data based on an original image; a specific area extracting unit extracts image data of a specific area from the YMCK data; a mark image adding unit combines image data of the specific area with the mark image data to form combined data; and a printer unit outputs a first image based on the combined data. During image processing of the specific area, the scanner unit forms RGB data based on the first image; the mark area extracting unit extracts image data of the mark area from the RGB data; the specific area image processing unit performs prescribed image processing on the image data of mark area; and the printer unit outputs a second image based on the YMCK data after the prescribed image processing.

Abstract: A method for automatically recognizing Arabic text includes digitizing a line of Arabic characters to form a two-dimensional array of pixels each associated with a pixel value, wherein the pixel value is expressed in a binary number, dividing the line of the Arabic characters into a plurality of line images, defining a plurality of cells in one of the plurality of line images, wherein each of the plurality of cells comprises a group of adjacent pixels, serializing pixel values of pixels in each of the plurality of cells in one of the plurality of line images to form a binary cell number, forming a text feature vector according to binary cell numbers obtained from the plurality of cells in one of the plurality of line images, and feeding the text feature vector into a Hidden Markov Model to recognize the line of Arabic characters.

Abstract: A method of enabling a user to initiate an action via a printed substrate, said substrate comprising user information and coded data, said coded data being indicative of a region identity associated with the substrate and of a plurality of locations on the substrate, said method comprising the steps of: receiving, in a computer system and from a sensing device, mode data and interaction data, the sensing device being operable in a plurality of modes and the mode data being indicative of one of said modes, the interaction data being indicative of the region identity and at least one position of the sensing device relative to the substrate, the sensing device generating the interaction data, when operatively positioned or moved relative to the substrate, by reading at least some of the coded data; identifying and retrieving at least part of a page description corresponding to the printed substrate using the region identity; determining a mode of the sensing device using the mode data; identifying an action usin

Abstract: Various technologies and techniques are disclosed that improve handwriting recognition operations. Handwritten input is received in training mode and run through several base recognizers to generate several alternate lists. The alternate lists are unioned together into a combined alternate list. If the correct result is in the combined list, each correct/incorrect alternate pair is used to generate training patterns. The weights associated with the alternate pairs are stored. At runtime, the combined alternate list is generated just as training time. The trained comparator-net can be used to compare any two alternates in the combined list. A template matching base recognizer is used with one or more neural network base recognizers to improve recognition operations. The system provides comparator-net and reorder-net processes trained on print and cursive data, and ones that have been trained on cursive-only data. The respective comparator-net and reorder-net processes are used accordingly.

Abstract: It is shown how to select and insert a non-textual, e.g. a smiley, into an application such as a chat application in a communication terminal. A smiley insertion area in the form of a hand writing input area is displayed under the control of a user interface application. After recording that a stylus, or similar device, has been used in drawing on the touch sensitive display, the drawing is matched in an interpretation process against a pattern library consisting of smileys and other non-textual symbols. After a successful match, the smiley symbol is appended to the text that is being input.

Abstract: Recognizing handwritten words at an electronic device. A plurality of strokes is received at a common input region of an electronic device. The plurality of strokes in combination defines a word comprising a plurality of symbols, a relative geometry of a first subset of the plurality of strokes defines a first symbol and a relative geometry of a second subset of the plurality of strokes defines a second symbol such that the relative geometry of the first subset of the plurality of strokes is not related to the relative geometry of the second subset of the plurality of strokes, and at least one stroke of the first subset of the plurality of strokes is spatially superimposed over at least one stroke of the second subset of the plurality of strokes.

Abstract: In one example, video may be analyzed and divided into segments. Character recognition may be performed on the segments to determine what text appears in the segments. The text may be used to assign tags to the video and/or to the segments. Segments that appear visually similar to each other (e.g., segments that appear to be different views of the same person) may be grouped together, and a tag that is assigned to one segment may be propagated to another segment. The tags may be used to perform various types of tasks with respect to the video. One example of such a task is to perform a search on the video.

Abstract: A handwriting processing apparatus includes an acquiring unit configured to acquire coordinate information of handwriting input by an input unit and attribute information, the attribute information indicating a type of input of the handwriting; a determining unit configured to determined a kind of the handwriting using the attribute information; a handwriting processing unit configured to perform handwriting processing corresponding to the kind of the handwriting using the coordinate information; and a display control unit configured to control a display unit to display a result of the handwriting processing.

Abstract: An apparatus includes a reading unit configured to read image data, a recognition unit configured to recognize a region designated by a handwritten portion and processing associated with a color of the handwritten portion in the image data, and a display unit configured to display a preview by superimposing a recognized result and the region to be processed in the image data and displaying a content of the recognized processing on the displayed preview.

Abstract: The present invention is a method of database searching. First, a language is selected and elements received. The system is searched to identify a unit number associated with each element, which is linked to a data unit containing morphological variants of the element. If none are identified, the element is broken into sub-textual units that may contain a prefix, compound-prefix, and/or suffix along with a primary element. A unit number is then obtained for the primary element. If this does not result in a match, the elements may be saved in a database for further linguistic development. A unit number associated with each matched element is then chosen, and the elements contained in the data units linked to the unit numbers are compared to a database index. If an element is associated with multiple unit numbers, this process is repeated until all data units have been compared to the database.

Abstract: Execution commands corresponding to the type of gesture are stored and by acquiring coordinate values of accepted handwriting input including gesture on a display screen, handwriting is displayed. When handwriting input is accepted, display data of handwriting is updated. When handwriting input is not completed, it is decided whether or not handwriting input is gesture input. When it is decided that the handwriting input is gesture input, the type of gesture is decided on the basis of the coordinate values of gesture on the display screen, an execution command corresponding to the type of gesture is read and the fact that the handwriting input is gesture input is displayed. When gesture input is completed, the execution command corresponding to gesture input is executed. Therefore, the user can make handwriting input according to the user's intent without performing mode switching.

Abstract: The present invention discloses a multi-touch and handwriting-recognition resistive touchscreen, which comprises a touch layer, a spacer layer, a sensing layer and a controller. The touch layer and the sensing layer are separated by the spacer layer and respectively have a plurality of strip-like touch loops and a plurality of strip-like sensing loops. The touch layer is superimposed on the sensing layer with the touch loops oriented vertically to the sensing loops. The controller respectively connects to and supplies voltages to the two terminals of each touch loop and the two terminals of each sensing loop to enable a digital-mode driving and an analog-mode driving in different time intervals. The controller can integrate the multi-touch function and the handwriting-recognition function. Alternatively, a switch is used to switch the controller to operate in the digital mode enabling the multi-touch function or the analog mode enabling the handwriting-recognition function.

Abstract: A form processing apparatus extracts layout information and character information from a form document. A candidate extracting unit extracts word candidates from the character information. A frequency digitizing unit calculates emission probability of a word candidate from each element. A relation digitizing unit calculates transition probability that relationship between word candidates is established. An evaluating unit calculates an evaluation value indicative of a probability of appearance of word candidates in respective logical elements. A determining unit determines the element and a word candidate thereof as the element and a character string thereof in the form document, based on the evaluation value.

Abstract: A system for presenting text found on an object. The system comprises an object manipulation subsystem configured to position the substantially planar object for imaging; an imaging module configured to capture an image of the substantially planar object; a text capture module configured to capture text from the image of the substantially planar object; an Optical Character Recognition (“OCR”) component configured to convert the text to a digital text; a material context component configured to associate a media type with the text found on the substantially planar object; and an output module configured to convert the digital text to an output format, wherein the system is configured to organize the digital text according to the media type before converting the digital text to an output format.

Abstract: A system for interactive note-taking is provided having a receiver for receiving interaction data from a note-taking device used to interact with a note-taking form having note-taking information and a plurality of coded tags printed thereon, and a processor for recording or retrieving the note-taking by identifying, from the received interaction data, at least one parameter relating to the note-taking. Each tag encodes data on an identity of the form and a location of that tag on the form. The note-taking device senses the tags and generates the interaction data with data on the sensed form identity and a position of the note-taking device relative to the sensed tags.

Abstract: A method for fingerprint recognition comprises converting fingerprint specimens into electronic images; converting the electronic images into mathematical graphs that include a vertex and an edge; detecting similarities between a plurality of graphs; aligning vertices and edges of similar graphs; and comparing similar graphs.

Abstract: A technique for continuously recognizing a character entry into a computer. In one example embodiment, this is achieved by drawing a character in a continuous stroke order using a stylus [210] on touch screen [220]. As associated data of the drawn continuous stroke order is then inputted into a continuous character recognizer [930] via the touch screen [220]. One or more hypothesis candidate characters including the continuous stroke order are then produced by the continuous character recognizer [930] upon a partial recognition. The produced one or more hypothesis candidate characters are then displayed substantially over the drawn continuous stroke order on a display device [230].

Abstract: A handheld electronic device including a data input module, a database and a display unit is provided. The data input module includes an image fetching unit and a pattern recognition unit. The image fetching unit is for fetching a pattern of an external object to produce image data. The pattern recognition unit is for transferring the image data to input data. The database is for storing several storage data items. Each storage data item has subject information. When the input data is related to one of the storage data items, the display unit is for displaying navigation information generated according to the subject information of the related storage data item.

Abstract: The invention provides a method, system, and program product for encrypting information. In one embodiment, the invention includes prompting a user for a password associated with a digital signature certificate stored in a digital pen, capturing a handwritten password made using the digital pen, displaying to the user the captured password, and encrypting information entered using the digital pen using the captured password. In some embodiments, the password may be captured from a predefined field on a digital page.

Abstract: Various technologies and techniques are disclosed that generate a teaching data set for use by a handwriting recognizer. Ink input is received from various ink sources, such as implicit field data, scripted untruthed ink, scripted truth ink, and/or ink from at least one other language in the same script as the target language for the recognizer. The ink input is used with various machine learning methods and/or other algorithmic methods to generate a teaching ink data set. Examples of the various machine learning methods include a character and/or word n-gram distribution leveling method, an allograph method, a subject diversity method, and a print and cursive data selection method. The teaching ink data is used by a handwriting trainer to produce the handwriting recognizer for the target language.

Abstract: A method for determining at least one recognition candidate for a handwritten pattern comprises selecting possible segmentation points in the handwritten pattern for use in segmenting and recognizing the handwritten pattern. The method further may comprise comparing segments of the handwritten pattern to templates. The comparison may return segment candidates forming possible recognition results of the segments of the handwritten pattern. The method further comprises forming a representation of sequences of segment candidates, said representation comprising data blocks corresponding to segmentation points, wherein a data block comprises references to data blocks corresponding to subsequent segmentation points. The reference may comprise information of segment candidates.

Abstract: A method, computer program product, and a data processing system for performing handwriting recognition of a language having character stroke order rules. A stroke parameter set describing attributes of a handwritten stroke is calculated, and a user input indicates a stroke order knowledge. A reference character dictionary includes a record having a plurality of reference parameter sets each defining attributes of reference character strokes. A stroke sequence number of the stroke parameter set is identified and at least one of the reference parameter sets are excluded from a comparison with the stroke parameter set based on the stroke sequence number.

Abstract: Methods and apparatuses for generating, by a computing device configured to interpret a handwritten expression, a symbol graph to represent strokes associated with the handwritten expression, are described herein. The symbol graph may include nodes, each node corresponding to a combination of a stroke and a candidate symbol for that stroke. The computing device may also generate a segment graph based on the symbol graph by combining nodes associated with a same stroke if strokes of their preceding nodes are the same. Also the computing device may perform a structure analysis on at least a subset of segment sequences represented by the segment graph to determine hypotheses for the handwritten expression. In other embodiments, rather than generate a segment graph, the computing device may determine segment sequences by selecting a number of symbol sequences from the symbol graph and combining symbol sequences having the same segmentation.

Abstract: System for implementing user handwriting according to the present invention, comprising : a handwriting input module (120) for receiving user handwriting including at least 100 to 200 characters by a user with sample sentences; a feature determining module (150); a distance determining module (160) for determining a vertical distance between an uppermost point mark and a lowermost point mark between 2 characters and their segments and a horizontal distance between a leftmost point mark and a rightmost point mark between 2 characters and their segments; a position determining module (170) for determining positions of the uppermost and lowermost point marks and the leftmost and rightmost point marks between 2 characters and their segments handwriting combining module (180) for combining several handwriting base on data recognized by the feature determining module (150), the distance determining module (160) and the position determining module (170); and a handwriting output module (200) for outputting handwriti

Abstract: An information processing apparatus includes a gesture locus data recognition unit configured to execute processing for recognizing gesture locus data included in locus data according to characteristic data of the locus data and gesture characteristic shape data included in gesture dictionary data and output a result of the processing, a separation unit configured to separate gesture locus data and locus data other than the gesture locus data from the locus data according to the result of the recognition by the gesture locus data recognition unit, and a character locus data recognition unit configured to execute processing for recognizing locus data of a character included in the locus data other than the gesture locus data according to the characteristic data of the locus data other than the gesture locus data which is separated by the separation unit, and the locus characteristic data of a character included in a character dictionary data, and output a result of the processing.

Abstract: It is intended to provide an image composition apparatus, a control method and program of an image processing apparatus which, when a user wants to combine a photo image and a handwritten image, even if the image processing apparatus is used for other purposes or even if the power of the image processing apparatus is turned off while the user is creating the handwritten image, enables the user to subsequently resume the image composition work.

Abstract: A new unistroke text entry method for handheld or wearable devices is designed to provide high accuracy and stability of motion. The user makes characters by traversing the edges and diagonals of a geometric pattern, e.g. a square, imposed over the usual text input area. Gesture recognition is accomplished not through pattern recognition but through the sequence of corners that are hit. This means that the full stroke path is unimportant and the recognition is highly deterministic, enabling better accuracy than other gestural alphabets. This input technique works well using a template with a square hole placed over a touch-sensitive surface, such as on a Personal Digital Assistant (PDA), and with a square boundary surrounding a joystick, which might be used on a cell-phone or game controller. Another feature of the input technique is that capital letters are made by ending the stroke in a particular corner, rather than through a mode change as in other gestural input techniques.

Abstract: A method is provided for converting a two-dimensional image or bitmap of a handwritten manuscript into three-dimensional data The three-dimensional data can be used to automatically recognize features of the manuscript, such as characters or words. The method includes the steps of: converting the two-dimensional image into three-dimensional volumetric data; filtering the three-dimensional volumetric data; and processing the filtered three-dimensional volumetric data to resolve features of the two-dimensional image. The method can be used, for example, to differentiate between ascenders, descenders, loops, curls, and endpoints that define the overall letter forms in handwritten text, manuscripts or signatures.

Abstract: The present invention leverages spatial relationships to provide a systematic means to recognize text and/or graphics. This allows augmentation of a sketched shape with its symbolic meaning, enabling numerous features including smart editing, beautification, and interactive simulation of visual languages. The spatial recognition method obtains a search-based optimization over a large space of possible groupings from simultaneously grouped and recognized sketched shapes. The optimization utilizes a classifier that assigns a class label to a collection of strokes. The overall grouping optimization assumes the properties of the classifier so that if the classifier is scale and rotation invariant the optimization will be as well. Instances of the present invention employ a variant of AdaBoost to facilitate in recognizing/classifying symbols. Instances of the present invention employ dynamic programming and/or A-star search to perform optimization.

Abstract: A system is provided that includes a pen-enabled computing arrangement having a capture interface and at least one processing element. The capture interface can capture an electronic input defining a stroke through a plurality of concatenated regions. In addition, the handwriting capture interface can also optionally capture an electronic handwriting input based upon a position of the writing stylus with reference to a position-determining pattern. Each of the concatenated regions corresponds to a region of an identification pattern including a plurality of regions that are each associated with a character of an identifier associated with an object. The stroke includes a plurality of portions referenced to respective regions of the identification pattern such that the processing element can determine the identifier based upon the respective regions of the identification pattern, and associate the electronic input with the object associated with the identifier.

Abstract: A computer-implemented method of font identification includes receiving a first document, the first document including the first text set in a proportional font. Test text, corresponding to the first text of the first document, is received. The test text is set in a test font. A first fingerprint is generated, based on relative line widths of the first text of the first document. A second fingerprint is generated based on relative line widths of the test text, as set in the test font. The test font is then accepted as being consistent with a font of the first text, based on a predetermined strength of relationship between the first and second fingerprints.

Abstract: The present invention relates to interfacing with electronic ink. Ink is stored in a data structure that permits later retrieval by applications. The ink includes stroke information and may include property information. Through various programming interfaces, one may interact with the ink through methods and setting or retrieving properties. Other objects and collections may be used as well in conjunction with the ink objects.

Abstract: A method, system and computer-readable media for supporting text entry on a personal computing device by activating automated searching to search for completion candidates which are based on a partial text entry received from a user. The completion candidates are displayed in a search list. The user may select a completion candidate from among the completion candidates in the search list to correspondingly modify the partial text entry, or the user may decline all of the completion candidates displayed in the search list and terminate the automated searching. The system may further provide a digital keyboard for use in entering text.

Abstract: Techniques for processing handwriting input based upon a user's writing style. Some techniques employ the style in which the user writes a single character, while other techniques alternately or additionally employ a group of allographs that form a handwriting style. Some implementations of these techniques, such as those implemented in writing style analysis tool, analyze one or more characters written by a user to identify a community, such as a geographic region or cultural group, to which the user's handwriting style belongs. Other implementations analyze one or more characters of a user's handwriting in order to alternately or additionally categorize the user's handwriting into a particular handwriting style. The writing style analysis tool may then provide the user with a handwriting recognition application specifically configured for that user's personal handwriting style.

Abstract: The present invention discloses a method to automatically arrange word string in a display. The word string includes two words. The method includes the following steps. The first step is to define the positions of the start position and the stop position of strokes of the two words. The second step is to group the start position and the stop position based on a threshold value. The third step is to circle the words based on the grouping result. The final step is to rearrange the two words based on a datum point.

Abstract: A system, method and computer program product for identifying spam in an image using grey scale representation of an image, including identifying a plurality of contours in the image, the contours corresponding to probable symbols (letters, numbers, punctuation signs, etc.); ignoring contours that are too small or too large given the specified limits; identifying text lines in the image, based on the remaining contours; parsing the text lines into words; ignoring words that are too short or too long, from the identified text lines; ignoring text lines that are too short; verifying that the image contains text by comparing a number of pixels of a symbol color within remaining contours to a total number of pixels of the symbol color in the image; and if the image contains a text, rendering a spam/no spam verdict based on comparing a signature of the remaining text against a SPAM template.

Abstract: A method of identifying at least one handwritten character composed of at least one stroke is disclosed. The method comprises providing a database comprising a plurality of sequences of strokes, the strokes of each sequence defining at least one character, at least some of said sequences comprising a plurality of strokes; capturing a string of handwritten characters, said string comprising the at least one handwritten character; and matching at least a part of the string with a sequence from said plurality of sequences. This method enables the recognition of multi-stroke characters where the positions of the strokes relative to each other are unknown or at least unreliable. A computer program product implementing this method and an electronic device comprising this computer program product are also disclosed.

Abstract: In an information processing method for recognizing a handwritten figure or character, with use of a speech input in combination, in order to increase the recognition accuracy a given target is subjected to figure recognition and a first candidate figure list is obtained. Input speech information is phonetically recognized and a second candidate figure list is obtained. On the basis of the figure candidates obtained by the figure recognition and the figure candidates obtained by the speech recognition, a most likely figure is selected.

Abstract: A system, method and computer program product for identifying spam in an image, including (a) identifying a plurality of contours in the image, the contours corresponding to probable symbols; (b) ignoring contours that are too small or too large; (c) identifying text lines in the image, based on the remaining contours; (d) parsing the text lines into words; (e) ignoring words that are too short or too long from the identified text lines; (f) ignoring text lines that are too short; (g) verifying that the image contains text by comparing a number of pixels of a symbol color within remaining contours to a total number of pixels of the symbol color in the image, and that there is at least one text line after filtration; and (h) if the image contains text, rendering a spam/no spam verdict based on a contour representation of the text that which appears after step (f).

Abstract: A word pattern recognition system based on a virtual keyboard layout combines handwriting recognition with a virtual, graphical, or on-screen keyboard to provide a text input method with relative ease of use. The system allows the user to input text quickly with little or no visual attention from the user. The system supports a very large vocabulary of gesture templates in a lexicon, including practically all words needed for a particular user. In addition, the system utilizes various techniques and methods to achieve reliable recognition of a very large gesture vocabulary. Further, the system provides feedback and display methods to help the user effectively use and learn shorthand gestures for words. Word patterns are recognized independent of gesture scale and location. The present system uses language rules to recognize and connect suffixes with a preceding word, allowing users to break complex words into easily remembered segments.

Abstract: A system, method and computer program product for identifying spam in an image, including (a) identifying a plurality of contours in the image, the contours corresponding to probable symbols; (b) ignoring contours that are too small or too large; (c) identifying text lines in the image, based on the remaining contours; (d) parsing the text lines into words; (e) ignoring words that are too short or too long from the identified text lines; (f) ignoring text lines that are too short; (g) verifying that the image contains text by comparing a number of pixels of a symbol color within remaining contours to a total number of pixels of the symbol color in the image, and that there is at least one text line after filtration; and (h) if the image contains text, rendering a spam/no spam verdict based on a contour representation of the text that which appears after step (f).