Abstract: A system and method for creating a personalized font allow a user to write characters as they should appear when used within a word processing document. A sheet having a grid is printed. The grid includes a blank space and an indication of the character that should be written in the blank space. The user writes in the characters on the sheet and then scans the sheet to digitize the characters. A computer system then analyzes the scan to extract each character as written and associate the extracted character with the appropriate character of a character set. The digitized and associated character data is then saved as a font that may be used by word processing programs.

Abstract: A system and method for editing and transcribing using a structured freeform editor is provided. The method implemented in the system includes interpreting structure of freeform graphic elements and selectively editing the structure and/or selectively transcribing scribble elements to an editable format.

Abstract: The present invention provides a character recognition method and recording medium for recognizing characters entered in a document or the like including preprint information. An object of the invention is to recognize characters in contact with or superposed on the preprint information without using any knowledge of the preprint information or a difference in gray level. An image in an area where the characters to be recognized are present is divided into line segments individually, wherein the image is obtained by reading the preprint information and the entry characters. A recognition image is created by changing a combination of the plurality of line segments divided. A recognition result with the reliability is memorized by making the character recognition for the created recognition image. And the recognition result having a greatest reliability is output by executing the character recognition for all the combinations while changing the combination of line segments successively.

Abstract: A system and method for identifying and separating handwritten text from machine printed text in a document having a combination of handwritten text and machine printed text. In one embodiment, the present invention is installed as an intelligent printing control interface in a conventional computer and allows any document generated by any application to be selectively processed to remove any handwritten text prior to printing of the document, under the control of the user. In an alternative embodiment, the present invention is installed as an intelligent printing control interface in a conventional digital copy machine, which allows any document being copied to be selectively processed to remove any handwritten text prior to printing of the document, under the control of the user. The present invention employs a handwriting separation method which uses Hidden Markov Models to identify regions as either handwritten text or machine printed text.

Abstract: A method of automatically recognizing text. The text is divided into whole words which are each recognize. Each whole word is characterized according to its silhouette. The silhouette is characterized by features in the silhouette such as upwardly extending “polls” and downwardly extending “holes”. The silhouette may also be characterized by its first syllable blends. Numbers are assigned to each of the different characteristics, and numbers may also be assigned based on analysis of a database of different kinds of cursive words. Recognition may be automatically carry out prior recognizing system which recognizes in this way.

Abstract: Images of handwritten cursive records are extracted, and an automated search on the images of the cursive records is performed based on an ASCII query for a record. A cursive equivalent of the ASCII query is matched to the images of the cursive records, and a similarity value is generated to indicate the extent of match between features of the cursive equivalent of the ASCII query and features of each cursive record. The records are sorted based upon their similarity value determined in the matching process. This provides a candidate list of cursive record images to be manually examined by a user for the purpose of making a final determination as to whether any of the cursive records on the candidate list satisfy the query.

Abstract: A scanned document image, including add-on information such as handwritten annotations in addition to printed text lines, is processed by a handwriting detection method. First, at least one projection histogram is generated from the scanned document image. A regular pattern that correlates to the printed text lines is determined from the projection histogram. Second, connected component analysis is applied to the scanned document image to generate at least one merged text line. Each merged text line relates to at least one of the handwritten annotation and the printed text line. By comparing the merged text lines to the regular pattern of the projection histograms, the printed text lines are discriminated from the handwritten annotations.

Abstract: In a document in which a plurality of data items of different kinds are mixed, when one data item is edited, the relative positional relation to other data items is prevented from being destroyed, whereby information is prevented from becoming meaningless or from being changed. For example, when an edit is carried out on one data item, a deviation amount of that data item is derived and a shift process by the same amount is effected on the other data items, whereby the relative positional relation can be maintained among the data items.

Abstract: A recognition process for handwritten characters, including generating sub-segments representing at least one character stroke, the sub-segments each having a boundary enclosing the at least one stroke of the sub-segment, merging the sub-segments when the distance between centroids of the sub-segments are less than a predetermined threshold, and generating segments representing possible characters from the sub-segments.

Abstract: In computerized recognition having multiple experts, a method and system is described that obtains an optimum value for an expert tuning parameter in a single pass over sample tuning data. Each tuning sample is applied to two experts, resulting in scores from which ranges of parameters that correct incorrect recognition errors without changing correct results for that sample are determined. To determine the range data for a given sample, the experts return scores for each prototype in a database, the scores separated into matching and non-matching scores. The matching and non-matching scores from each expert are compared, providing upper and lower bounds defining ranges. Maxima and minima histograms track upper and lower bound range data, respectively. An analysis of the histograms based on the full set of tuning samples provides the optimum value. For tuning multiple parameters, each parameter may be optimized by this method in isolation, and then iterated.

Abstract: A user interface for an electronic device has a pen based input device (256) that captures a collection of coordinates that correspond to handwritten information. According to certain embodiments, a processor (260) carries out a command recognition process in which a command gesture (124, 130, 134, 138, 142, 144, 148) is recognized (210) in the collection of coordinates. The command gesture identifies a set of coordinates form at least a portion of the collection of coordinates that represent a command (120). The identified coordinates are then extracted (220) and translated to a command (230) for execution (244).

Abstract: Character recognition includes detecting a union of characters, preprocessing the union of characters, comparing the preprocessed union of characters with one or more template symbols, and applying a decision rule to either reject a template symbol or decide that the template symbol is included in the union of characters. Such preprocessing involves representing the union of characters as one or more curves, and parameterizing the curve(s); and, regarding various classes of transformation, forming one or more shapes for the curve(s). The comparing operation involves forming one or more geometric proximity measures, and determining for every shape the values of those measures between the shape and correspondingly determined shapes for the template symbols. Applying a decision rule involves selecting one or more template symbols in consideration of the values.

Abstract: The present invention utilizes generic and user-specific features of handwriting samples to provide adaptive handwriting recognition with a minimum level of user-specific enrollment data. By allowing generic and user-specific classifiers to facilitate in a recognition process, the features of a specific user's handwriting can be exploited to quickly ascertain characteristics of handwriting characters not yet entered by the user. Thus, new characters can be recognized without requiring a user to first enter that character as enrollment or “training” data. In one instance of the present invention, processing of generic features is accomplished by a generic classifier trained on multiple users. In another instance of the present invention, a user-specific classifier is employed to modify a generic classifier's classification as required to provide user-specific handwriting recognition.

Abstract: Methods and systems are provided for analyzing and assessing documents using a writing profile for documents, such as a payment instrument. A method may include providing a document to a computer system. In an embodiment, the method may further include assessing whether writing in an information field approximately matches a writing profile representation from at least one information field from at least one other document. In certain embodiments, the matching writing profile representation may be associated with a corresponding text representation in a computer processable format in memory on the computer system. In some embodiments, the information field may be associated with the text representation corresponding to the matching writing profile representation.

Abstract: A method of generating a document using a processing apparatus (112) such that the text thereof is intended to look like hand writing, wherein the method comprises providing characters (600), having one or more parameters associated therewith, such that at least one occurrence of any one character (600) has at least one parameter (which may be the shape of the character) varied between at least some occurrences of that character (600) by the processing apparatus (112) such that the appearance of any one character (600) is different from at least some other occurrences of that character. In other embodiments the characters need not look like hand writing and variations between characters may be recorded in order to increase the security of a document.

Abstract: Methods and systems are provided for analyzing and assessing documents using a writing profile for documents, such as a payment instrument. A method may include providing a document to a computer system. In some embodiments, the method may further include obtaining information on writing in an information field of the document. In certain embodiments, the obtained written information in the information field and written information in at least one other information field may be compared to at least one writing profile representation. The writing profile representation may be obtained from at least one other document. In one embodiment, at least one of the writing profile representations may include written information from the information field and written information from at least one of the other information fields obtained from at least one of the other documents. In some embodiments, the comparisons may be used to verify the obtained written information.

Abstract: Methods and systems are provided for analyzing and assessing documents using a handwriting profile for documents, such as a payment instrument. A method may include providing one or more documents to a computer system. In one embodiment, handwriting profile representations may be determined for information fields of the document. The determination may use handwriting from at least one of the information fields of the documents. In some embodiments, handwriting profile representations may be updated from one or more additional documents. In certain embodiments, a document may be provided to a computer system for assessment. Assessment may include comparing handwriting in the information fields of the document to handwriting profile representations from information fields of at least one other document. In an embodiment, the method may include assessing fraud in the document using at least one of the comparisons.

Abstract: A method for recognizing shapes is disclosed. A computer, such as a handheld computer with pen input, is used to receive a drawing from a user. The user's drawing is then analyzed to identify the location of potential vertices of angles or knots of splines using a technique of hypothesizing lines between known important points and calculating the distance between other points and that Postulated line. This process is repeated until all important points are located. Also disclosed is a method for determining whether a set of points is straight or curved.

Abstract: A handwriting trajectory recognition system, having a motion detection unit adapted to output electric signals based on changes in acceleration of a body of the system in space. A control unit adapted to detect non-stroke regions intervals where the motions of the system body are temporarily stopped and recover handwritings based on the electric signals is provided.

Abstract: A method for recognizing handwritten Chinese characters based on stroke recognition comprises steps of: recognizing handwritten strokes, updating stroke code sequences; retrieving in dictionaries/lexicons at least one corresponding character/phrase entry so as to obtain at least one candidate Chinese character/phrase; dynamically displaying the at least one candidate Chinese character/phrase; jumping to the step of recognizing strokes if it is judged that a next stroke is being written; inputting a displayed Chinese character/phrase into computers as the result of recognition if this character/phase is selected by the user.

Abstract: A method or apparatus according to an embodiment of the invention allows for entry of multi-stroke characters via a natural drawing interface and without requiring an expensive stylus-drawing surface combination.

Abstract: In a computing device that receives handwritten data, a method and system for finding matches for recognized handwritten words, by comparing a given search word (and possibly its alternates) with the words in a document, including recognized ink words and any possible alternates for those recognized words as returned by a recognizer. One described test looks for an exact match between an entered search word (and possibly its alternates) and the recognized words and their alternates stored in a handwritten document. Other tests are possible because of the use of alternates, which also may be returned with a probability ranking. For example, one scheme looks for a percentage of matching characters, with a user-determined threshold percentage. Other variations include giving different weight to certain characters, and/or factoring in the relative number of syllables and/or the relative lengths of the words.

Abstract: An image identification apparatus for identifying an image from a hand drawn representation of at least part of the image, the image identification apparatus comprising an image processor arranged in operation to generate a reference identification in response to spatial samples produced from at least part of the hand drawn representation, the reference identification being indicative of a first estimate of which of a plurality of pre-stored images corresponds to the hand drawn representation. and a controller which is arranged in operation to cause the image processor to produce a refined reference identification from the spatial samples and further spatial samples produced from a further part of the hand drawn representation, the refined reference identification being indicative of a refined estimate of which of the plurality of the prestored images corresponds to the hand drawn representation.

Abstract: Electronic note taking is enhanced by automatically modifying an electronic document corresponding to a user's meeting notes to include at least some data from an electronic calendar or scheduling system in which the user's meeting is scheduled. For example, when an electronic note is created for a specific meeting, information about the meeting from the user's electronic calendar or scheduling system can automatically be included in the new electronic note. This information may be provided in the note in a form that allows it to be electronically searched and shared with others.

Abstract: A method and system for searching digitally annotated computer documents, including searching the annotations. An annotated document may be open for viewing by a user, or alternatively present among closed files that are searched to find files that match a query. In one implementation, the document data and the ink-annotation data exist on two separate layers, with each layer having associated text content, whether as original text or as annotations that are recognized as text. When a user issues a query to search the annotated document, the query is passed to a search engine that performs the pattern matching on the text in each layer, to produce search results. The search engine may produce a search result data structure for each match, which may be sorted with other data structures into a list, such as sorted by pages and coordinates, to present them to a user in a logical ordering.

Abstract: A digitized writing is recorded in a digitized writing record including at least the position of each point of a writing in coordinates relative to a coordinate of a previous point thereof and time. The digitized writing record may be converted to image format.

Abstract: In a computing device that receives handwritten data, a method and data structure that enables extended data to be added to an existing ink word data structure without compromising backwards-compatibility. A flag in the header data structure is indicates to new ink processing programs the presence or absence of the extended data, and the size information maintained in the header is adjusted ensure that earlier versions of ink programs do not lose the extended data. The extended data is then added by including it in a copy of the existing ink word data structure, along with a tail structure that includes information describing the extended data and the tail structure to the new ink code, e.g., version and offset information. The tail structure can be used to locate a list of alternate word choices for an ink word that are maintained within the extended data.

Abstract: A method for recognition of a handwritten pattern comprises the steps of forming (4) a representation of the handwritten pattern, forming (6) at least two sub-configurations by dividing the representation of the handwritten pattern, and processing the subconfigurations. The step of processing comprises the steps of comparing (8) each subconfiguration with reference configurations, selecting (10) at least one subconfiguration candidate for each subconfiguration among the reference configurations based on said step of comparing, and determining (12) at least one candidate pattern consisting of one selected subconfiguration candidate for each subconfiguration. The method further comprises the steps of comparing (14) the representation of the handwritten pattern to the candidate pattern, and computing (16) a cost function in order to find a closest matching candidate pattern.

Abstract: This present invention discloses a system and a method for presenting a real handwriting trace. The design of this invention can keep the real handwriting traces of the users and transmit the real handwriting traces to application software. Moreover, the prior trace identifying process is not necessary in this invention. Thus, the design of this invention does not have to spend time on the trace identifying process, and the mistakes during the trace identifying process can be avoided. Hence, this present invention can provide a system and a method for directly inputting traces into a file of application software by handwriting or hand-drawing. Preferably, according to this invention, the real traces of the users can be presented on the file of application software.

Abstract: A system (10) for recognizing handwriting includes an input/output device (12) and a second computer (24 or 28). The system (10) converts handwritten symbols to text by using a grammar (50) that is comprised of the text (60) that is expected to be entered into a text display/text input area (17) of an input/output device (12). The grammar (50) and handwriting-to-text conversion can be performed in either the input/output device (12) or a remote computer (24, 28).

Abstract: A method for analysis of a two-dimensional image. The two-dimensional image is scanned to form a digital bit-map of X-Y axis locations in the image. Gray-scale densities are measured at each of the locations, and are used to calculate third, Z-axis values. The X-Y-Z axis coordinates are plotted so as to form a virtual three-dimensional image having a contour that corresponds to variations in the gray-scale density in the two-dimensional source image. The virtual three-dimensional image provides for enhanced visualization, measurement and analysis of features and characteristics contained within the source image. The gray-scale density may be black-and-white gray-density or RGB color-density or other digital color mapping protocols reduced or converted, for example, to 8-bit 256 gray or color scale. The two-dimensional source image may be a sample of handwriting. A method for enhanced two-dimensional analysis using the digitized bit-map of the source image is also provided.

Abstract: In a computing device that receives handwritten data, a method and system that corrects for parser segmentation errors by sending an entire line of ink to a recognizer, and then comparing, on a word-by-word basis, the initial segmentation guesses of the parser with the more-thoroughly recognized segmentation results of the handwriting recognition engine. In the correction process, the ink words are efficiently adjusted with relatively little data manipulation. As the recognizer is fed a series of strokes on a line, the recognizer returns segmentation information. For ink word breaks that are the same for any given set of data, the existing ink word is unchanged. For ink words that are recognized differently relative to their initial segmentation, one or more new ink words are created and the handwriting (including stroke) data of the parser's ink word is manipulated to create a new ink processor word (or words) to match the recognizer output.

Abstract: A method of stricken-out characters identification in a handwritten text recognition process, comprising parsing the scanned image into regions and objects, defining objects, containing handwritten characters, applying structural or feature classifiers for primary character recognition, applying one or more supplemental feature classifier, preliminarily trained by characters of strike-out, to identify a stricken-out character if any.

Abstract: A method is described of bit-mapped image analysis comprising division of all analysis means at one's disposal into several groups differing in accuracy and further processing multi-stage analysis.

Abstract: The invention provides a method/system for estimating the orientation of a segment of digital ink using pen orientation information. In one form, the invention is a method of estimating the orientation of a segment of digital ink, the method including the steps of: measuring the azimuth of the pen at a sampling rate during writer generation of the segment of digital ink; and estimating the orientation of the segment of digital ink using the measured azimuth of the pen at sampled points.

Abstract: A method for recognition of a handwritten character comprises the steps of determining a plurality of position features defining the handwritten character, and comparing the handwritten character to reference characters stored in a database in order to find the closest matching reference character. The step of comparing comprises the steps of computing a difference between one of the plurality of position features of the handwritten character and a corresponding position feature of one of the reference characters, determining, by lookup in a predefined table, a distance measure based on the computed difference and determining a distance measure for each of the plurality of position features of the handwritten character, and computing a cost function based on the determined distance measures. A device and a computer program for implementing the method are also described.

Abstract: An apparatus includes: (a) a character image extraction extracting character image data of handwritten characters filled into character entry boxes from image data scanned from a character entry sheet in which the handwritten characters are filled into the character entry boxes corresponding to respective character codes; (b) a character positional information storage section storing character positional information of font character space defined for each of characters; (c) a character positional information calculation section calculating the amount of movement for moving the extracted character image data to a character position of the font character space defined in the character positional information; (d) a character position alignment section moving the character image data to the character position of the font character space defined in the character positional information, based on the calculated amount of movement; and (e) a character font generation section generating font characters of the handwri

Abstract: A points based handwriting recognition system is suitable for hand held processor implemented devices with small touch pad writing surfaces. The writing surface is divided into a grid by a number of spaced discrete points. The user is instructed to write, as by a stylus, characters such as letters, numbers or symbols with the writing path extending through a predetermined sequence of the points which define the grid. The stylus must pass sequentially within a specified distance of mandatory points for processor recognition of each written character and may additionally pass within a predetermined distance of optional points.

Abstract: A method for recognizing input characters handwritten onto an input area of an input device, each point of the input area being represented by coordinate values. The method includes the steps of receiving a signal representative of an input character, determining an input position representative of the input character using information about the coordinate values, and recognizing the input character as one of a plurality of reference characters in a reference library. The recognizing step at least uses recognition features and a weighting function of each of the plurality of reference characters in the reference library and the input position. The signal includes at least information about the coordinate values of the input character.

Abstract: A method of character recognition includes detecting a union of characters, preprocessing the union of characters, comparing the preprocessed union of characters with one or more template symbols, and applying a decision rule in order to either reject a template symbol or decide that the template symbol is included in the union of characters. Preprocessing the union of characters involves representing the union of characters as one or more curves, and parameterising said curve or curves, and regarding various classes of transformations forming one or more shapes for the curve or curves. The comparing operation involves forming one or more geometric proximity measures, and determining for every shape the values of said geometric proximity measures between said shape and correspondingly determined shapes for the template symbols. Finally, applying a decision rule involves selecting one or more template symbols in consideration of the values.

Abstract: A method and system utilizing both (x, y) coordinate (“spatial”) stroke data and associated pressure information for improved handwriting recognition. The method and system can also be applied to all types of handwriting-based data entry applications and also to user authentication. The digitizer pad used in the computer system gives both spatial information and associated pressure data when a stroke is being drawn thereon, e.g., by a stylus. Pressure information can be used to differentiate between different character sets, e.g., upper case and lower case characters for certain alphabetic characters. The spatial stroke data then identifies the particular character. The pressure information can also be used to adjust any display attribute, such as character font size, font selection, color, italic, bold, underline, shadow, language, etc. The associated pressure information can also be used for recognizing a signature. In this case, a user is allowed to sign a name on the digitizer pad.

Abstract: The present invention discloses an apparatus and method of decoding information received over a noisy communications channel to determine the intended transmitted information. The present invention uses a vector fixed-lag algorithm to determine the probabilities of the intended transmitted information. The algorithm is implemented by multiplying an initial state vector with a matrix containing information about the communications channel. The product is then recursively multiplied by the matrix &tgr; times, using the new product with each recursive multiplication and the forward information is stored for a fixed period of time, &tgr;. The final product is multiplied with a unity column vector yielding a probability of a possible input. The estimated input is the input having the largest probability.

Abstract: The present invention is directed to a pointing device writing tip comprised of a surface being structured in a manner that while writing with the writing tip on a writing surface, the contacts of the writing tip with the writing surface produce different sounds in different directions. A hand writing recognition system is provided based on at least the recognition of sounds produced by the writing tip having a surface being structured in a manner that while writing with the writing tip on the writing surface, the contacts of the writing tip with the writing surface produce different sounds in different directions for use by the recognition system.

Abstract: We disclose a trainable recognizer for multi-stroke symbols. Pen speed and the curvature are examined to segment a stroke into the constituent primitives. The primitives are determined to be lines or arcs using, for example, a least squares best fit method. Symbol recognition (training) results in the construction of definitions consisting of the constituent geometric primitives (lines and arcs), the properties of individual primitives, and the geometric relationships between them. A definition is learned by examining a few examples of a symbol and identifying which properties and relationships occur frequently. Thereafter, during symbol recognition (matching), an unknown symbol is identified by determining which definition matches the unknown with the least error. We disclose two recognition methods. One assumes that the primitives of a symbol are always drawn in the same order. This method is fast, but requires some care from the drawer.

Abstract: A character input apparatus accurately recognizes handwritten characters drawn one after another in a single input frame. A stroke matching unit obtains stroke information for each stroke in the inputted handwritten characters from the start/end area of the stroke in the input frame and the direction of the stroke, and detects stroke candidates for the stroke by comparing the stroke information with each set of stroke information in the stroke dictionary. An interval-based character detecting unit detects character candidates from detected stroke candidates by referring to the character dictionary that stores an stroke order for each character. With this construction, the apparatus is capable of accurately recognizing a plurality of characters drawn one after another in a single input frame.

Abstract: Cursive Chinese characters are analyzed using a semantic matching process whereby radicals within the character are first extracted and used to reduce the search space of the full lexicon to only those characters containing the matching radical. In performing the radical extraction, the input character is normalized and segmented into strokes that are in turn organized based on stroke up/down information and local maxima and minima information. Obscure breakpoints and connecting strokes are removed in the process. Dynamic program matching is then performed on a stroke basis in which stroke substitution costs are assessed on a point-by-point basis through a variety of techniques, including tangent vector analysis, center relationship assessment and starting point/ending point assessment. Dynamic programming costs are normalized based on the length of the reference radical and location dissimilarities are removed.

Abstract: An information processing apparatus and method capable of making a desired document using a simple operation based on highly object oriented features. In an embodiment, all writings in a source document are entered by an image scanner and decomposed into individual characters (character strings), symbols and/or graphicals. From them a recognize characters and graphicals block makes document element records which are stored into a document element file storage. A create descriptor elements block makes descriptor element records of document-carried written signs for descriptors for specifying requirements of a desired document from the document element records while referencing descriptor group attributes and descriptor element specifiers. A create descriptors block makes descriptor records from the descriptor element records in a first storage and the document element records in a second storage while looking up the descriptor element specifiers.

Abstract: Displaying a writing guide for a free-form document editor by detecting electronic ink, classifying the detected ink as corresponding to handwriting or a drawing, and displaying a handwriting guide or a drawing guide in response to classifying the detected ink as handwriting or a drawing, respectively. The writing guides can provide feedback regarding the classification of the detected ink and can be resized as additional ink is detected. The handwriting guide can comprise a writing area, writing guide portion, bullet guide, indent marker, character notches, gesture guide, or sacrificial guide to create meaningful structure within an outline object of an electronic document.

Abstract: This invention discloses a method for automatically segmenting and recognizing Chinese character strings continuously written by a user in a handwritten Chinese character processing system, comprising the steps of: creating a geometry model and a language mode; finding out all of potential segmentation schemes in the Chinese character strings continuously written by a user based on the associated timing information and said geometry model; recognizing the groups of strokes as defined by each of potential segmentation schemes and computing the probability characterizing the exactness of recognition results; correcting the probability characterizing the exactness of recognition results by said language model; and, selecting the recognition result and the corresponding segmentation scheme having the maximum probability value.

Abstract: A computer system operable in two modes for creating and selectively reproducing an individual's handwriting allows a user to produce text such as by word processing and display that text in their own handwriting. In a Create mode, the user separately inputs the characters of a character set in their own handwriting into a computer system. The input characters are then stored in a memory of the computer system. Each store character is associated with a key stroke on a keyboard. In a Reproduce mode, a desired character of the character set can be reproduced in the individual's handwriting by actuating the key stroke on the keyboard associated with the desired character.