Patent application number | Description | Published |
20080304748 | METHOD AND SYSTEM FOR LINE EXTRACTION IN DIGITAL INK - A method and system of line extraction in a digital ink sequence of handwritten text data points is provided in which a stroke sequence comprised of a sequence of strokes is obtained, the strokes are segmented into a sequence of substrokes by applying a stroke segmentation algorithm, angular differences between neighbouring groups of substrokes, in the sequence of substrokes, are calculated, and the positions of the extrema of the angular differences are determined, thereby identifying the substrokes at line breaks and enabling line extraction. | 12-11-2008 |
20090022399 | PROCESSING SYSTEM FOR IDENTIFYING A STRING FORMED FROM A NUMBER OF HAND-WRITTEN CHARACTERS - The present invention is a processing system for identifying a string formed from a number of hand-written characters. The system includes a processor and memory, an input device and an output device, a bus connecting the processor, memory, input and output devices, as well as an external interface for connecting the bus to an external database. The processor is configured to perform the steps of determining character probabilities for each character in the string, each character probability representing the likelihood of the respective character being a respective one of a number of predetermined characters; and determining template probabilities for the string, each template probability representing the likelihood of the string corresponding to a respective one of a number of templates, each template representing a respective combination of character types. | 01-22-2009 |
20090046936 | METHOD OF COMPRESSING DIGITAL INK - A method of compressing a digital ink input including a sequence of strokes is provided in which each stroke is represented as a series of digital words representing x and y co-ordinates, at least one reference co-ordinate of each stroke is expressed in absolute terms, and a co-ordinate other than the at least one reference co-ordinate is expressed as an offset from a preceding co-ordinate. The co-ordinate other than the at least one reference co-ordinate is represented as a combination of an estimate determined from the previous m co-ordinates and a residual error value. | 02-19-2009 |
20090074295 | METHOD OF MODIFYING CLASSIFICATION SCHEME STORED IN PROCESSING SYSTEM - The present invention provides a method of modifying a classification scheme for classifying hand-written characters to thereby make the classification scheme user dependent. The classification scheme includes a number of allographs, each allograph representing a respective style of a respective letter. The method includes obtaining at least one hand-written character, and then selecting an allograph representing the character. One or more of the allographs are then modified in accordance with the selection, to thereby reflect the fact that the allograph corresponds to a style of letter used by the user. | 03-19-2009 |
20090238461 | System For Line Extraction In Digital Ink - A system is provided having a database storing annotation digital ink representing handwritten annotations on a printed document and a processor configured to segment the annotation digital ink into lines by obtaining a stroke sequence comprised of a sequence of strokes, removing small strokes less than a threshold length, segmenting the strokes into a sequence of substrokes by computing a relative angle for each line segment connecting successive stroke data points and segmenting the stroke into substrokes if the difference between successive relative angles is greater than a preset threshold, and identifying the substrokes at line breaks, thereby facilitating line extraction, by computing N-neighbourhood centroids, computing angular differences between N-neighbouring substrokes, or groups of substrokes and computing local maxima of the angular differences in the sequence of substrokes. | 09-24-2009 |
20100063980 | SEARCHING AN ELECTRONIC FILING SYSTEM USING A HANDWRITTEN SEARCH QUERY AND A TEXT SEARCH QUERY - A method of providing an electronic filing system which is searchable using a handwritten search query, the method including the steps of: obtaining the handwritten search query using an input device; performing a search of at least one database based on a comparison between the handwritten search query and handwritten annotations made on interactive pages stored in the at least one database; and, providing the results of the search to a user and facilitating access to at least one interactive page identified in the results of the search. An apparatus is also disclosed. Preferably, the interactive page is provided to the user in the form of printed paper, and the handwritten annotations are user handwriting, symbols, drawings, indicia or the like. | 03-11-2010 |
20100067796 | SYSTEM FOR ESTIMATING DIGITAL INK ORIENTATION - A system for estimating the orientation of digital ink is provided which has an optically imaging pen and a processor. The processor measures the azimuth of the pen at a sampling rate during writing by the pen on a surface printed with tags and estimates the orientation of the digital ink using the measured azimuth of the pen at the sampled points. Each tag encodes data on an identity of the surface associated with a digital description of the surface and on the respective location of that tag on the surface. The digital ink is generated by associating the digital description with the data encoded by the tags optically imaged by the pen during the writing. | 03-18-2010 |
20100067797 | METHOD OF ESTIMATING DIGITAL INK ORIENTATION - A method of estimating the orientation of digital ink is provided. The includes measuring, at a sampling rate during writing by an optically imaging pen on a surface printed with tags, the azimuth of the pen, and estimating, at the computer system, the orientation of the segment of digital ink using the measured azimuth of the pen at the sampled points. Each tag encodes data on an identity of the surface associated with a digital description of the surface and on the respective location of that tag on the surface. The digital description is stored by a computer system networked with the pen and the digital ink is generated by associating the digital description with the data encoded by the tags optically imaged by the pen during the writing. | 03-18-2010 |
20100079602 | METHOD AND APPARATUS FOR ALIGNMENT OF AN OPTICAL ASSEMBLY WITH AN IMAGE SENSOR - A method is described for positioning an image sensor at a point of best focus for a lens. The lens has an optical axis and the image sensor is moved to a plurality of positions along the optical axis. The image sensor captures an image of a target image at each of the plurality of positions through the lens. A measure of blur in the image captured is derived at each of the plurality of positions from pixel data output from the image sensor. A relationship is derived between blur and position of the image sensor along the optical axis. The image sensor is then moved to a position on the optical axis that the relationship indicates as the point of best focus where the image sensor is fixedly secured relative to the lens. | 04-01-2010 |
20100125451 | Natural Language Recognition Using Context Information - A method of recognising digital ink input by a user into a computer-based digital ink recognition system is disclosed. The user interacts with a paper-based document. The paper-based document has disposed thereon coded data indicative of a particular field of the paper-based document and of at least one reference point of the paper-based document. An image sensor in a sensing device captures images of at least some of the coded data when the sensing device is placed in an operative position relative to the paper-based document. The sensing device then decodes at least some of the coded data to form indicating data indicative of the identity of the field of the paper-based document containing the coded data and at least one of a position and a movement of the sensing device relative to the paper-based document. A server receives the indicating data from the sensing device, and processes the indicating data using a recognizer residing on the server to produce intermediate format data. The intermediate format data is then transmitted to an application which decodes the intermediate format data into computer-readable format data using context information associated with the paper-based document. | 05-20-2010 |
20100189352 | Classifying an Input Character - 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. | 07-29-2010 |
20100232699 | System For Line Extraction In Digital Ink - A system for line extraction in digital ink. The digital ink represents handwritten input and is comprised of a stroke sequence. The system comprises a processor configured for: receiving the digital ink from a pen device; segmenting the strokes into a sequence of substrokes; grouping substrokes about a selected substroke into a temporally preceding group of substrokes and a temporally subsequent group of substrokes; calculating a centroid for each substroke or group of substrokes; calculating angular differences between the selected substroke and its temporally neighbouring groups of substrokes; and determining positions of extrema of the angular differences. The extrema correspond to substrokes at line breaks, thereby enabling line extraction in the stroke sequence. | 09-16-2010 |
20100278429 | SYSTEM FOR MODIFYING CLASSIFICATION SCHEME FOR HANDWRITTEN CHARACTERS - A system for modifying a classification scheme for classifying hand-written characters. A memory stores the classification scheme, which includes a number of allographs, each allograph representing a respective style of a respective letter. A processor received data representing a hand-written character, and then selects an allograph representing the character. One or more of the allographs are then modified in accordance with the selection, to thereby reflect the fact that the allograph corresponds to a style of letter used by a user. | 11-04-2010 |
20100278430 | IDENTIFYING A STRING FORMED FROM A NUMBER OF HAND-WRITTEN CHARACTERS - 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. | 11-04-2010 |
20110007978 | Method Of Compressing Input Stroke Sequence - A method of compressing a sequence of strokes input at an input device of a processing system is provided in which each stroke input at the input device is represented as a series of digital words representing x and y co-ordinates, a reference co-ordinate of each stroke is expressed in absolute terms, and a co-ordinate other than the reference co-ordinate is expressed as an offset from a preceding co-ordinate by combining a residual error value and an estimate calculated from the previous m co-ordinates using the formula: | 01-13-2011 |
20110052066 | Handwritten Character Recognition - A method for classifying a handwritten 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. | 03-03-2011 |
20110084141 | METHOD FOR READING BARCODES IN ABSENCE OF LOCATION-INDICATING TAGS - A method of recovering a waveform representing a linear bar code, the method including the steps of: moving a sensing device relative to the barcode, said sensing device having a two-dimensional image sensor; capturing, using the image sensor, a plurality of two-dimensional partial images of said bar code during said movement; determining, from at least one of the images, a direction substantially perpendicular to the bars of the bar code; determining, substantially along the direction, a waveform fragment corresponding to each captured image; determining an alignment between each pair of successive waveform fragments; and recovering, from the aligned waveform fragments, the waveform. The method is performed only in the absence of a location-indicating tag in a field of view of the image sensor. | 04-14-2011 |
20110091110 | CLASSIFYING A STRING FORMED FROM A KNOWN NUMBER OF HAND-WRITTEN CHARACTERS - A method of classifying a character string formed from a known number of hand-written characters is disclosed. The method starts by determining character probabilities for each hand-written character in the character string. Each character probability represents a likelihood of the respective hand-written character being a respective one of a plurality of predetermined characters. Each predetermined character has a respective character type. Character templates having the known number of characters are next identified. Each character template has a respective predetermined probability and represents a respective combination of character types. Character sequence probabilities corresponding to each of the character templates having the known number of characters are next determined. The character sequence probabilities are a function of the predetermined probability of the respective character template and the character probabilities of the hand-written character in the character string. The character string is classified as the sequence of characters having the highest character sequence probability. | 04-21-2011 |
20110103690 | SYSTEM FOR DETERMINING DIGITAL INK ORIENTATION - A system for determining the orientation of digital ink is provided having a sensing pen and a processor. The system measures the orientation of the pen during writing by the pen on a surface printed with tags. Each tag encodes data on an identity of the surface associated with a digital description of the surface and on the respective location of that tag on the surface. The digital ink is generated by associating the digital description with the data encoded by the tags sensed by the pen during said writing. The orientation of the digital ink is determined using the measured orientation of the pen. | 05-05-2011 |
20110110593 | METHOD OF MODIFYING CLASSIFICATION SCHEME FOR HAND-WRITTEN CHARACTERS - A method of modifying a classification scheme for classifying hand-written characters. The method includes the steps of: receiving digital ink representing a handwritten character from an optically imaging pen; determining a selection value based on the similarity of the received character and a respective prototype vector of the stored classification scheme; selecting a prototype vector of the stored classification scheme in accordance with the determined selection value; selecting a class of the stored classification scheme in accordance with a selected prototype representing the character; selecting a stored user dependent weighted allograph in accordance with the selected prototype vector representing the character; modifying an allograph in the respective class; and storing a modified classification scheme which includes the modified allograph. | 05-12-2011 |
20110153633 | SEARCHING FOR HANDWRITTEN ANNOTATIONS APPEARING A GIVEN DISTANCE FROM DOCUMENT CONTENT - A method of searching a database containing documents with handwritten annotations stored in association with document content is disclosed. The method receives as inputs a handwritten annotation as a handwritten search input and a content element as a content search input. A search is then performed of the database for handwritten annotations in a document matching the handwritten search input and less than a given physical distance from document content equal to the content search input in the document. | 06-23-2011 |
20110180602 | METHOD OF IMAGING CODING PATTERN USING VARIANT REGISTRATION CODEWORDS - A method of decoding a coding pattern disposed on or in a substrate. The method comprises the steps of: (a) operatively positioning an optical reader relative to a surface of the substrate; (b) capturing an image of a portion of the coding pattern; (c) sampling and decoding registration symbols contained in the imaged portion; (d) constructing an imaged registration codeword of length r using the decoded registration symbols ordered in a defined sequence, the defined sequence being determined by positions of registration symbols relative to target elements in the imaged portion; (e) identifying one of v distinct registration codewords corresponding to the imaged registration codeword; (f) determining a registration corresponding to the identified registration codeword; and (g) using the identified registration to decode data symbols sampled from the imaged portion. | 07-28-2011 |
20110180611 | CODING PATTERN COMPRISING MULTI-PPM DATA SYMBOLS IN A FORMAT IDENTIFIED BY REGISTRATION SYMBOLS - A substrate having a coding pattern disposed thereon or therein. The coding pattern comprises a plurality of macrodots encoding data symbols and registration symbols. Each data symbol is represented by d macrodots, each of the d macrodots occupying a respective position from a plurality of predetermined possible positions p. The respective positions of the d macrodots represent one of a plurality of possible symbol values. Each registration symbol, or a set of the registration symbols, identifies an integer value of d, with the condition that p>d. | 07-28-2011 |
20110180612 | CODING PATTERN COMPRISING MULTI-PPM DATA SYMBOLS WITH MINIMAL CLUSTERING OF MACRODOTS - A substrate having a coding pattern disposed thereon or therein. The coding pattern comprises a plurality of macrodots encoding contiguous data symbols. Each data symbol is represented by d macrodots, each of the d macrodots occupying a respective position from a plurality of predetermined possible positions p. The respective positions of the d macrodots represent one of possible symbol values, and a predetermined number of unused symbol values are selected to minimize clustering of macrodots between adjacent data symbols. | 07-28-2011 |
20110180613 | CODING PATTERN COMPRISING REGISTRATION CODEWORD HAVING VARIANTS CORRESPONDING TO POSSIBLE REGISTRATIONS - A substrate having a coding pattern disposed thereon or therein. The coding pattern comprises a tiling of contiguous grid cells, each grid cell being demarcated by t target elements and having t-fold rotational symmetry, each grid cell containing nt registration symbols, each registration symbol being encoded by a set of macrodots; and a tiling of contiguous tags, each tag consisting of an array of c grid cells, each tag containing a plurality of data symbols. There are ct possible registrations between a physical layout of the coding pattern and a logical layout of the coding pattern and any contiguous tag-shaped array of c grid cells contains cnt registration symbols. The registration symbols, taken in a defined sequence relative to the physical layout of the tag-shaped array, form a registration codeword of length r. There are v distinct registration codewords, each corresponding to a distinct one of the ct possible registrations. | 07-28-2011 |
20110180614 | CODING PATTERN COMPRISING NON-REPLICATED COORDINATE DATA SYMBOLS - A substrate having a coding pattern disposed thereon or therein. The coding pattern comprises a plurality of square tags of length l identifying two-dimensional location coordinates. Each tag comprises: a plurality n | 07-28-2011 |
20110180615 | CODING PATTERN COMPRISING CONTROL SYMBOLS - A substrate having a coding pattern disposed therein or thereon. The coding pattern comprises: a tiling of contiguous grid cells, each grid cell being demarcated by t target elements and having t-fold rotational symmetry, each grid cell containing nt control symbols, each control symbol being encoded by a set of macrodots; and a tiling of contiguous tags, each tag consisting of an array of c grid cells, each tag containing a plurality of data symbols, each data symbol being encoded by a set of macrodots. Any contiguous tag-shaped array of c grid cells contains cnt control symbols, which encode r | 07-28-2011 |
20110181916 | METHOD OF ENCODING CODING PATTERN TO MINIMIZE CLUSTERING OF MACRODOTS - A method of encoding a coding pattern for disposition on or in a substrate. The method comprises the step of encoding contiguous data symbols for the coding pattern. Each data symbol is represented by d macrodots on the surface, each of the d macrodots occupying a respective position from a plurality of predetermined possible positions p, the respective positions of the d macrodots representing one of i possible data values. The encoding step selects a predetermined number of unused symbol values in each data symbol in order to minimize clustering of macrodots between adjacent data symbols. | 07-28-2011 |
20110182464 | METHOD OF DECODING CODING PATTERN COMPRISING CONTROL SYMBOLS - A method of decoding a coding pattern disposed on or in a substrate. The method comprises the steps of: (a) operatively positioning an optical reader relative to a surface of the substrate; (b) capturing an image of a portion of the coding pattern; (c) sampling and decoding control symbols contained in the imaged portion to provide r | 07-28-2011 |
20110182521 | METHOD OF DECODING CODING PATTERN WITH VARIABLE NUMBER OF MISSING DATA SYMBOLS POSITIONED OUTSIDE IMAGING FIELD-OF-VIEW - A method of decoding a coding pattern disposed on or in a substrate. The method comprises the steps of: (a) operatively positioning an optical reader relative to a surface of the substrate; (b) capturing an image of a portion of the coding pattern, the coding pattern comprising a plurality of tags, each tag comprising a plurality n | 07-28-2011 |
20110185252 | CODING PATTERN COMPRISING MULTI-PPM DATA SYMBOLS WITH DIFFERENT LAYOUTS - A substrate having a coding pattern disposed thereon or therein. The coding pattern comprises a plurality of macrodots encoding first and second Reed-Solomon data symbols. Each first Reed-Solomon data symbol is represented by d macrodots, each of the d macrodots occupying a respective position from a plurality of predetermined possible positions p within a first symbol layout, the respective positions of the d macrodots representing one of a plurality of possible data values. Each second Reed-Solomon data symbol is represented by d macrodots, each of the d macrodots occupying a respective position from a plurality of predetermined possible positions p within a second symbol layout which is different than the first symbol layout, the respective positions of the d macrodots representing one of a plurality of possible data values. | 07-28-2011 |
20110185266 | METHOD OF DECODING A PATTERN-ENCODED COORDINATE - A method of decoding a coding pattern disposed on or in a substrate. The method comprises the steps of: (a) operatively positioning an optical reader relative to a surface of the substrate; (b) capturing an image of a portion of the coding pattern, the coding pattern comprising a plurality of square tags of length/identifying two-dimensional location coordinates; and (c) sampling and decoding x-coordinate data symbols within the imaged portion and y-coordinate data symbols within the imaged portion. The imaged portion has a predetermined diameter and is guaranteed to contain sufficient data symbols from each of the Reed-Solomon codes so that symbol errors are correctable in each of the codes during the decoding. | 07-28-2011 |
20110276596 | SYSTEM FOR INTERPETING DIGITAL INK - A system for interpreting digital ink is provided having a pen for imaging tags printed on a page to produce one or more types digital ink, an input for input of the digital ink, memory storing a page description having an identifier, a database of digital ink types, and searching algorithms specialized for searching the database, and a processor for interpreting the input digital ink using the stored description and algorithms. Each tag encodes its location on the page and the page identifier. The digital ink includes data on the page identifier and the pen motion relative to the imaged tags. The processor determines the input digital ink types, selects the algorithms specialized to the determined types, processes the input digital ink with the selected algorithms, searches the database for matches to the processed digital ink using the selected algorithms, and interprets the matches relative to the stored description. | 11-10-2011 |
20110292463 | SYSTEM FOR IDENTIFYING PHYSICAL PAGE CONTAINING PRINTED TEXT - A system for identifying a physical page containing printed text from a plurality of page fragment images. The system includes: (A) a handheld electronic device having: a camera for capturing a plurality of page fragment images at a plurality of different capture points when the device is moved across the physical page; motion sensing circuitry for measuring a displacement or a direction of movement; and a transceiver; (B) a processing system configured for: performing OCR on each captured page fragment image to identify a plurality of glyphs in a two-dimensional array; and creating a glyph group key for each page fragment image; and (C) an inverted index of the glyph group keys. | 12-01-2011 |
20110293181 | Handwritten Character Recognition System - A character classification system is disclosed. The character classification system has an input device for receiving a handwritten input character, and a processor. The processor is configured to, for each character model, each character model being associated with an output character and defining a model specific segmentation scheme for that output character and an associated segment model, the model specific segmentation scheme defining a minimum length corresponding to a number of points in a stroke of the output character: (i) decompose the handwritten input character into one or more segments in accordance with the model specific segmentation scheme of the respective character model; and (ii) evaluate the one or more segments against the segment model of the respective character model to produce a score indicative of the conformity of the one or more segments with the segment model. The processor then selects the character model that produced the highest score, and classifies the handwritten input character as the output character associated with the character model that produces the highest score. | 12-01-2011 |
20110293184 | METHOD OF IDENTIFYING PAGE FROM PLURALITY OF PAGE FRAGMENT IMAGES - A method of identifying a physical page containing printed text from a plurality of page fragment images captured by a camera. The method includes the steps of: placing a handheld electronic device in contact with a surface of the physical page; moving the device across the physical page and capturing the plurality of page fragment images at a plurality of different capture points; measuring a displacement or direction of movement; performing OCR on each captured page fragment image; creating a glyph group key for each page fragment image; looking up each created glyph group key in an inverted index of glyph group keys; comparing a displacement or direction between glyph group keys in the inverted index with a measured displacement or direction between the capture points for corresponding glyph group keys created using OCR; and identifying a page identity corresponding to the physical page using the comparison. | 12-01-2011 |
20110293185 | HYBRID SYSTEM FOR IDENTIFYING PRINTED PAGE - A hybrid system for identifying a printed page. The system includes: (i) the printed page having human-readable content and a coding pattern printed in every interstitial space between portions of human-readable content, the coding pattern being either absent from the human-readable content or unreadable when superimposed with the human-readable content; and (ii) a handheld device for overlaying and contacting the printed page. The handheld device includes: a camera for capturing page fragment images; and a processor configured for: decoding the coding pattern and determining the page identity in the event that the coding pattern is visible in and decodable from the captured page fragment image; and otherwise initiating OCR or SIFT techniques to identify the page. | 12-01-2011 |
20110293186 | CLASSIFYING A STRING FORMED FROM HAND-WRITTEN CHARACTERS - A method of classifying a character string formed from a known number of hand-written characters is disclosed. The method starts by determining character probabilities for each hand-written character in the character string. Each character probability represents a likelihood of the respective hand-written character being a respective one of a plurality of predetermined characters. Each predetermined character has a respective character type. Character templates having the known number of characters are next identified. Each character template has a respective predetermined probability and represents a respective combination of character types. Character sequence probabilities corresponding to each of the character templates having the known number of characters are next determined. The character sequence probabilities are a function of the predetermined probability of the respective character template and the character probabilities of the hand-written character in the character string. The character string is classified as the sequence of characters having the highest character sequence probability. | 12-01-2011 |
20110299780 | CLASSIFICATION SCHEME AND SYSTEM FOR MODIFYING CHARACTER ALLOGRAPHS CONTAINED THEREIN - A system for modifying a classification scheme for classifying hand-written characters. The system includes a memory storing the classification scheme containing a plurality of user dependent allographs, each allograph representing a respective style of a respective letter; and a processor configured for: receiving data representing a handwritten character; selecting an allograph representing the handwritten character; modifying the allograph in accordance with the selection; and storing a modified classification scheme which includes the modified allograph. | 12-08-2011 |
20120093416 | SYSTEM FOR DETERMINING ORIENTATION OF DIGITAL INK - A system for determining the orientation of digital ink is provided having a sensing pen and a processor. The system measures the orientation of the pen during writing by the pen on a surface printed with tags. Each tag encodes data on an identity of the surface associated with a digital description of the surface. The digital ink is generated by associating the digital description with the data encoded by the tags sensed by the pen during said writing. The orientation of the digital ink is determined using the measured orientation of the pen. | 04-19-2012 |
20120141040 | METHOD OF COMPRESSING SEQUENCE OF STROKES - A method of compressing a sequence of strokes input at an input device of a processing system is provided in which each stroke input at the input device is represented as a series of digital words representing x and y co-ordinates, and a co-ordinate is expressed as an offset from a preceding co-ordinate by combining a residual error value and an estimate calculated from the previous m co-ordinates using the formula: | 06-07-2012 |
20120239397 | Digital Ink Database Searching Using Handwriting Feature Synthesis - A method of searching a digital ink database is disclosed. The digital ink database is associated with a specific author. The method starts by receiving a computer text query from an input device. The computer text query is then mapped to a set of feature vectors using a handwriting model of that specific author. As a result, the set of feature vectors approximates features that would have been extracted had that specific author written the computer query text by hand. Finally, the set of feature vectors is used to search the digital ink database. | 09-20-2012 |
20120328195 | Handwritten Character Recognition System - A handwritten character recognition system is disclosed. The system has an input device for receiving handwritten strokes, and a processor for classifying the handwritten strokes as an output character. The processor does so by calculating a degree of membership of the handwritten strokes to each of a plurality of character models. The character model that produces the highest degree of membership is selected and the handwritten strokes ate classified as the output character associated with the character model that produces the highest degree of membership. | 12-27-2012 |