Abstract: A method and computer program product for recognizing handwriting. A handwritten character is captured as an image of black pixels and white pixels. The image is partitioned into segments, each of which having a pixel ratio of a total number of black pixels in the segment to a total number of black pixels in the image. A reference character has segments corresponding to the image segments. Each reference character segment has a value range of a pixel ratio of a total number of black pixels in the segment of the reference character to a total number of black pixels in the reference character. It is ascertained that the pixel ratio of more than a predetermined number of segments in the image are within the value range of the pixel ratio of the corresponding segments of the reference character, from which, the handwritten character is recognized as the reference character.

Abstract: An information recognition system includes: a display section displaying an image on a display surface at a predetermined display resolution; an image combining section combining a character entry guide with the image, the character entry guide assisting handwritten input to the display surface; an information detecting section detecting handwritten input information at a detection resolution which is higher than the display resolution, the handwritten input information input to the display surface according to the character entry guide; and a character recognizing section performing character recognition based on the information detected at the detection resolution.

Abstract: Described herein is an interactive digital software program and hardware that enables rapid acquisition of textual or audio subject matter, its conversion to editable text and immediate compression into a user understandable summary. The software program maximizes “time on task” while minimizing the time-consuming steps of “concept capture” and “compression”. The instant invention provides an accurate condensate of textual subject matter in a fraction of the time it would take to prepare such a document by manual note taking. In a single step, mobile devices such as cameras, camera phones, tablets, iPODs™, scanners and the like rapidly capture textual images convert them to OCR and to a user understandable summary in a fraction of the time it takes to process such a document by manual note taking. With more study time available for repetitious practice of the lesson, the user improves preparedness and performance on tests and presentations.

Abstract: Disclosed is a method of sequencing character information in order to increase precision of character recognition. The method includes: a pre-processing that extracts character information from an image to binarize the extracted character information through a predetermined threshold and extracts and thins a center line of the binarized character information; normalizing the pre-processed character information to character information according to a predetermined criteria; and sequencing the normalized character information using structural features including an end point or a divergence point of the character information. The present invention suggests an angle normalization method of input character information, a structural feature position determining method, and a structural feature numeral string generating method to strongly recognize characters configured by various fonts obtained from a natural scene regardless of an angle or a size of the characters.

Abstract: A printing apparatus includes a print drawing data storage storing first print drawing data from a print data generation apparatus, an administration information unit storing administration information of the first print drawing data, and an image processing unit. The print data generation apparatus includes a pattern data register registering pattern data corresponding to first image information, a pattern data converter, a first image converter converting the pattern data into the first print drawing data, a second image converter converting second image information into second print drawing data, and an image composition unit combining the first and second print drawing data. The image processing unit determines whether administration information of first print drawing data newly received and already stored in the administration information unit are the same. If so, the image processing unit combines the first print drawing data already stored and the second print drawing data.

Abstract: Printer systems and methods provide a plurality of unique identification codes to assignment devices in various geographical locations in order to assign a unique code to a single item of commerce through affixing tags or the like thereon or by direct printing. Information regarding which code is associated with which item of commerce may be captured and stored in database(s) along with other advertising, authenticity, distribution, manufacturing, note, quality control, and retail information. Inquires may be made regarding the codes by users with handheld devices including cellular phones, PDAs, notebook computers, barcode scanners, RFID readers, etc. through carrier networks, LANs, and WANs in order to obtain information about the item of commerce or related products. Stored information from the database may be provided to the users in response to their inquiries. Information may also be uploaded by the handheld devices for counterfeiting, diversion, and other tracking purposes.

Abstract: The present invention provides a method for an Optical Character Recognition (OCR) system providing recognition of characters that are partly hidden by crossing outs due to for example an imprint of a stamp, handwritten signatures, etc. The method establishes a set of template images of certainly recognized characters from the image of the text being processed by the OCR system, wherein the effect of the crossed out section is modelled into the template images before comparing these images with the image of a visually impaired crossed out character. The modelled template image having the highest similarity with the visually impaired crossed out character is the correct identification for the visually impaired character instance.

Abstract: An exemplary method for online character recognition of characters includes acquiring time sequential, online ink data for a handwritten character, conditioning the ink data to produce conditioned ink data where the conditioned ink data includes information as to writing sequence of the handwritten character and extracting features from the conditioned ink data where the features include a tangent feature, a curvature feature, a local length feature, a connection point feature and an imaginary stroke feature. Such a method may determine neighborhoods for ink data and extract features for each neighborhood. An exemplary character recognition system may use various exemplary methods for training and character recognition.

Abstract: According to one embodiment, a pattern recognition method includes calculating similarities of the input pattern with respect to respective categories, converting the calculated similarities of the input pattern with respect to the respective categories into first evaluation values based on a first table which indicates a relationship between similarities for respective categories and first evaluation values, calculating second evaluation values based on the calculated first evaluation values for the respective categories and prior probabilities for the respective categories stored in a second table indicating prior probabilities of the respective categories, and selecting a category corresponding to a maximum value of the calculated second evaluation values.

Abstract: An image of a known text sample having a text type is generated. The image of the known text sample is input into each OCR engine of a number of OCR engines. Output text corresponding to the image of the known text sample is received from each OCR engine. For each OCR engine, the output text received from the OCR engine is compared with the known text sample, to determine a confidence value of the OCR engine for the text type of the known text sample.

Abstract: A method and computer program product for recognizing handwriting. A handwritten character is captured as an image of black pixels and white pixels. The image is partitioned into segments, each of which having a pixel ratio of a total number of black pixels in the segment to a total number of black pixels in the image. A reference character has segments corresponding to the image segments. Each reference character segment has a value range of a pixel ratio of a total number of black pixels in the segment of the reference character to a total number of black pixels in the reference character. It is ascertained that the pixel ratio of more than a predetermined number of segments in the image are within the value range of the pixel ratio of the corresponding segments of the reference character, from which, the handwritten character is recognized as the reference character.

Abstract: A system for recognizing handwriting. A handwritten character is captured as an image of black pixels and white pixels. The image is partitioned into segments, each of which having a pixel ratio of a total number of black pixels in the segment to a total number of black pixels in the image. A reference character has segments corresponding to the image segments. Each reference character segment has a value range of a pixel ratio of a total number of black pixels in the segment of the reference character to a total number of black pixels in the reference character. It is ascertained that the pixel ratio of more than a predetermined number of segments in the image are within the value range of the pixel ratio of the corresponding segments of the reference character, from which, the handwritten character is recognized as the reference character.

Abstract: A handwriting recognition device includes a main body having a side surface and an operation surface perpendicularly connecting to the side surface, and a first lens module and a second lens module arranged at opposite sides of the side surface. A first optical axis of the first lens module extends to perpendicularly cross a second optical axis of the second camera module outside the side surface. An overlapped area of a view angle of the first lens module and a view angle of the second lens module is defined as an input area. The first lens module is configured to capture a first picture of a handwriting tool in the input area. The second lens module is configured to capture a second picture of the handwriting tool in the input area. The handwriting recognition device calculates coordinates of the handwriting tool according to the first and the second pictures.

Abstract: One or more techniques and/or systems are disclosed for compensating for affine distortions in handwriting recognition. Orientation estimation is performed on a handwriting sample to generate a set of likely characters for the sample. An estimated affine transform is determined for the sample by applying hidden Markov model (HMM) based minimax testing to the sample using the set of likely characters. The estimated affine transform is applied to the sample to compensate for the affine distortions of the sample, yielding an affine distortion compensated sample.

Abstract: A method of inputting a series of characters into an electronic device comprising a display, the method comprising: detecting a first input associated with a first one of a plurality of discrete areas of the display for entering characters on the display; and recognizing the first input in the first one of the plurality of discrete areas as a first character input while a second one of the plurality of discrete areas is operable to detect a second input for recognition as a second character input, the recognition of the second character input occurring separately to the recognition of the first character input.

Abstract: Paper-based playback of media can be performed by electronically recording handwritten notes including pen strokes using a digital pen on a position-coded paper. A plurality of bounding areas is identified, e.g. by generating bounding areas around the pen strokes as they are developed. Each bounding box is provided with a time stamp which indexes a media file, which was recorded simultaneously with the handwritten notes. By placing the digital pen close to a handwritten note on the paper, the part of the media that was recorded when the specific note was written can be recalled. More specifically, the bounding box corresponding to the position of the digital pen is identified and the associated time stamp is used to find the media to recall. This paper-based playback of media can be performed in e.g. a stand-alone device or by a combination of a digital pen and a mobile phone.

Abstract: An image reading apparatus includes an image reader, a storage unit, and a control unit, wherein the storage unit includes a command storage unit, and the control unit includes a mark detecting unit that detects at least one mark matching the characteristic information of the mark from the margin of the manuscript read by the image reader to acquire the characteristic information of the detected mark, a positional information determining unit that detects coordinates of the mark in the manuscript to determine the positional information corresponding to the detected coordinates, a command searching unit that searches the command storage unit for the command associated with the characteristic information and the positional information using the characteristic information and the positional information as search keys, and a command executing unit that executes the processing specified for the command searched for on the manuscript.

Abstract: Presented is a method for selecting a label from a multiplicity of labels stored in a memory element. The method includes inputting a handwritten character into a handwritten input apparatus, associating an alphanumeric character with the handwritten input character using a character recognition apparatus, adding the associated alphanumeric character to an already input character string to produce an extended character string, comparing the extended character string with the labels stored in the memory element, and selecting one or more of the stored labels using the comparison. The alphanumeric character is selected from a dynamically alterable character set which contains only characters which, in addition to the already input character string, produce an extended character string, which is an initial component of at least one of the stored labels. Also presented is a motor vehicle navigation system in which address database entries are selected by the above described method.

Abstract: A method and device is provided for recognizing characters in a handwritten input representing an input character string. A character sub-string preceding an unrecognized character in the input character string is determined. Handwriting recognition is used to provide one or more candidate characters for the unrecognized character. One of the one or more candidate characters is then selected. The candidate character selected, is the one which is most likely to be a correct recognition of the unrecognized character based on the determined character sub-string.

Abstract: An embodiment of the invention provides a method including receiving input from a user, which includes a handwritten symbol. The input is compared to prototype symbols to determine whether the input includes a threshold degree of similarity with a prototype symbol. If the input does not include a threshold degree of similarity with a prototype symbol, the input is stored as a prototype symbol. If the input includes a threshold degree of similarity with a prototype symbol, it is determined whether the input represents a text character. If the input represents a text character, the text character is identified and a prototype text character is identified. The input is mapped to the identified text character and the identified prototype text character. If the input does not represent a text character, the input is mapped to a prototype shape, and the input is mapped to the prototype shape.

Abstract: A character input method applicable to a handheld electronic device is provided. The character input method includes the following steps. Firstly, a motion path of the handheld electronic device is sensed. Next, the motion path is transformed into a stroke path. Afterward, an input character corresponding to the stroke path is recognized.

Abstract: A method for graphology-based assessment of a subject's personality traits is disclosed which involves graphological analysis of inferred handwriting features that are derived from the subject's presentation features. The method includes: obtaining presentation features of a subject; deriving inferred handwriting features of the subject from the presentation features according to pre-determined rules of correlation between the presentation features and the inferred handwriting features; and then performing graphological analysis on the inferred handwriting features so as to provide an assessment of the subject's personality traits. Presentation features can include a subject's general appearance, attire, body language, facial expression, and/or conversational style, for example. Handwriting features can include zonal sizes, connective forms, the handwriting's pressure, spacing, size, and slant, level of script, primary and secondary variables, and/or overall form level data.

Abstract: The present invention discloses a method for recognizing a handwritten character, which includes the following steps of: obtaining a coarse classification template and a fine classification template; receiving a handwritten character input signal from a user, gathering a discrete coordinate sequence of trajectory points of the inputted character, and pre-processing the discrete coordinate sequence; extracting eigenvalues and calculating a multi-dimensional eigenvector of the inputted character; matching the inputted character with the coarse classification template to select a plurality of the most similar candidate character classes; and matching the eigen-transformed inputted character with sample centers of the candidate character classes selected from the fine classification template, and determining the most similar character classes among the candidate character classes. The present invention further discloses a system for recognizing a handwritten character.

Abstract: A method, apparatus and computer program product are provided for permitting access to an electronic resource that is associated with a hand-drawn indicator. In the context of a method, a method is provided that includes receiving an image of a hand-drawn indicator, such as a free-form hand-drawn indicator or a grid having a plurality of selectively fillable grid elements. The method may also identify an electronic resource associated with the hand-drawn indicator and permit access to the electronic resource associated with the hand-drawn indicator.

Abstract: A dictionary creating apparatus registers probability distributions each including an average vector and a covariance matrix, in a dictionary. The dictionary creating apparatus organizes plural distribution profiles of character categories having similar feature vectors into one typical distribution profile, and registers the typical distribution profile and the character categories to be organized, associated with each other, in the dictionary, without registering eigenvalues and eigenvectors of all character categories, associated with each other, in the dictionary.

Abstract: A handwriting recognition apparatus facilitates user entry of strokes one on top of another. The apparatus, which includes a processor and a display integrated with a touch sensitive screen, receives a series of strokes via the screen. Each stroke is defined by contact, trace, and lift occurrences. Each stroke appears on the display until occurrence of a prescribed event, and then disappears. The apparatus accumulates strokes into a buffer and interprets all accumulated strokes collectively against a character database and optionally a linguistic database, to identify multiple candidate strings that could be represented by the accumulated strokes. The apparatus displays candidate strings for user selection after all strokes have faded, or after receiving a user submitted delimiter, or after a given delay has elapsed following user entry of the latest stroke. Alternatively, candidate strings are displayed after each stroke without waiting for timeout or explicit delimiter.

Abstract: One or more techniques and/or systems are disclosed for constructing a compact handwriting character classifier. A precision constrained Gaussian model (PCGM) based handwriting classifier is trained by estimating parameters for the PCGM under minimum classification error (MCE) criterion, such as by using a computer-based processor. The estimated parameters of the trained PCGM classifier are compressed using split vector quantization (VQ) (e.g., and in some embodiments, scalar quantization) to compact the handwriting recognizer in computer-based memory.

Abstract: A method, system and computer program product for recognizing cursive and non-cursive handwriting. The invention comprises capturing a handwritten character as an image of pixels, partition the image into a plurality of segments each having a pixel ratio of the number of pixels in the segment divided by the total number of pixels in the image, and compare the pixel ratio for each segment to a value range associated with a corresponding segment of a reference character. The handwritten character is recognized as the reference character if more than a predetermined number of the segments in the image have the pixel ratios within the respective value ranges of the reference character.

Abstract: Techniques described herein may recognize handwritten characters that are written at least partially over the top of one another that are input to a computing device. The handwritten characters may be formed of one or more strokes. A user may write characters or parts of words over approximately the same area of graphical user interface (i.e., on top of each other) without having to wait for a timeout between character input and without having to select a button or provide another input indicating the character is complete before entering input for another character. Once a character is at least partially recognized, a graphical indication corresponding to the user input displayed on a screen may be altered. Such alterations may include fading or changing size or location of the graphical indication.

Abstract: Described is a technology by which online recognition of handwritten input data is combined with offline recognition and processing to obtain a combined recognition result. In general, the combination improves overall recognition accuracy. In one aspect, online and offline recognition is separately performed to obtain online and offline character-level recognition scores for candidates (hypotheses). A statistical analysis-based combination algorithm, an AdaBoost algorithm, and/or a neural network-based combination may determine a combination function to combine the scores to produce a result set of one or more results. Online and offline radical-level recognition may be performed. For example, a HMM recognizer may generate online radical scores used to build a radical graph, which is then rescored using the offline radical recognition scores. Paths in the rescored graph are then searched to provide the combined recognition result, e.g., corresponding to the path with the highest score.

Abstract: The technical subject is realizing a highly useful input-output device which can be used alone to independently input and output information, and, when connected with an information processing device, can function as an input device that depends on the applications of the information processing device. The input-output device comprises: a function of recognizing whether a connection with the information processing device through a connection unit is present by the connection recognition unit and transmitting a code value and/or a coordinate value converted by a processing unit to the information processing device through the connection unit; and a function of outputting the content data from the output unit or controlling operation based on the operation instruction when the connection recognition unit does not recognise a connection between the connection unit and the information processing device. The provided functions make the disclosed input-output device highly useful.

Abstract: 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: a ~ n = ? i = 1 m ? c i ? ? n - i where ci are coefficients selected to model characteristics of the input strokes, and ? represents either an x or a y co-ordinate.

Abstract: A system for interactive paper is described. Data fragments are captured at locations in a rendered document. A digital version of the document is optionally located. Markup data applied to the capture creates a rich set of interactions for the user. New models for publishing documents and new document-related services are described.

Abstract: An apparatus, method, and system for processing character data is provided, which selects a format of the character data to be used for generating print data. When a user instruction for printing character data according to character command data specifying the output of the character data is received, the format of the character data is selected based on the character command data.

Abstract: A word spotting system includes a semi-continuous hidden Markov model configured to model a handwritten word of interest. A writing segments extractor is configured to extract writing segments generally comprising images of handwritten character strings from a received document image. A word model adaptation processor is configured to adjust a shared pool of Gaussians of the semi-continuous hidden Markov model respective to the extracted writing segments. A modeler is configured to model extracted writing segments using the semi-continuous hidden Markov model with the adjusted shared pool of Gaussians to identify whether each modeled writing segment matches the handwritten word of interest.

Abstract: Disclosed is a method of searching a digital image of a document for a predetermined keyword. The method identifies a word in the digital image, the word comprising one or more shapes. A test matrix comprising a difference vector for each character of the word is generated, and a template matrix comprising a difference vector for each shape of the keyword is also generated, wherein a difference vector represents the differences between the visual features of a respective shape and the visual features of a collection of reference shapes. A measure of similarity between the word and the keyword is generated by comparing the test matrix and the template matrix.

Abstract: Embodiments include an apparatus, device, method, and computer program product. In an embodiment, a device includes a handheld writing device that includes a writing element, and a writing detector module operable to generate information indicative of a handwriting movement of the writing element. The device also includes a context detector module operable to generate information indicative of a content portion of a document proximate to the handwriting movement of the writing element.

Abstract: Generating typefaces from various images is disclosed in which any image, whether from a still photograph or a video frame, is analyzed to find various patterns existing in the image. These patterns may be evident from the image itself or may be discovered by applying various transforms to the image. The patterns obtained from the image are then compared against existing characters in existing typefaces in trying to find correlations between individual patterns and individual characters of the existing typefaces. When correlations are found, the character image representing the pattern that resembles the existing typeface character is analyzed for various typeface properties, such as weight, width, angle, and the like. Using these determined typeface properties and the visual elements of the character image, an entire set of characters making up a new typeface is generated.

Abstract: A print data generation apparatus includes a pattern data registration unit, a pattern data conversion unit and an image conversion unit. The pattern data registration unit registers pattern data corresponding to a print image readable by an electronic pen printed on a recording medium. The pattern data conversion unit converts the print image into the pattern data registered in the pattern data registration unit. The image conversion unit converts the pattern data converted by the pattern data conversion unit into drawing data of the print image.

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: Data on a document is recognized using at least two machine recognition processes. Data from one machine recognition process is used as reference data; data formed using the other recognition process is used as verification data. If the verification data matches the reference data, machine recognition may be verified. If the verification data does not exactly match the reference data, an assessment is made of the likelihood that the verification data is sufficiently close to the reference data to suggest an error in the verification data. This may be done by applying a fitness function to the verification data, to assess the likelihood that the verification data represents a mis-recognized version of the reference data. In one embodiment, the verification data is OCR data, and the reference data is MICR data.

Abstract: A speech synthesis system and method is described. A speech segment database references speech segments having various different speech representational structures. A speech segment selector selects from the speech segment database a sequence of speech segment candidates corresponding to a target text. A speech segment sequencer generates from the speech segment candidates sequenced speech segments corresponding to the target text. A speech segment synthesizer combines the selected sequenced speech segments to produce a synthesized speech signal output corresponding to the target text.

Abstract: A system and method, which enable precise and automatic identification of characters, perform and calibrate data verification to ensure data reliability. The system can process these identified characters, such as override adverse conditions, adjusting and correcting unclear characters and their images.

Abstract: Described is a technology that provides an integrated platform for users to use different kinds of digital ink (e.g., handwritten characters, sketched shapes, handwritten formulas) when interacting with computer programs. The platform interprets the user's digital ink input and outputs one or more associated items into an application program. The output items can be customized for different application programs. In one aspect, the platform includes an ink panel having different operating modes for receiving digital ink, and a recognition service that recognizes different types of digital ink. The recognition service may include a unified recognizer that recognizes different types of digital ink, e.g., characters and shapes. Another recognizer may be included such as an equation recognizer. If the recognition result is text while in a non-text mode, the text may be used in a keyword search to locate items; otherwise, the recognition result may be used without keyword searching.

Abstract: A method to detect answers and notes inputted a game apparatus including: receiving user input data and determining the received user input data to be an answer character based on a characteristic of the user input data; displaying on the display the answer character contemporaneously with the determination of the received user data is the answer character; making a game determination based on the answer character; displaying a result of the game determination; determining the received user input data to be a note character based on the characteristic of the user input data; displaying the note character contemporaneously with the determination that the user input data is the note character; settling the note character as an answer character based on a user input made after the note character is displayed, and displaying the answer character determined from settling the note character.

Abstract: A language-neutral method for searching online handwritten notes is provided. The different algorithms contained in this method enable querying online multilingual handwritten documents with substrings of words rather than just whole words. More particularly, two approaches are presented —one based on partial Fréchet distance calculations and the other based on a pair hidden Markov models. The partial Fréchet distance is adapted from the traditional Fréchet distance concept to match a subcurve or prefix of a query word. The pair hidden Markov model used in the present application is adapted from pair hidden Markov models used in bioinformatics as generative models of local and global alignment of biological sequences.

Abstract: A method and system for recognizing a character affected by a noise or an obstruction is disclosed. After receiving an image with characters, a character being affected by a noise or an obstruction is determined. Then, areas in the character where the noise or obstruction affected are precisely located. Templates representing every possible character in the image are updated by removing equivalent areas to the areas in the character being affected by the noise or obstruction. Then, the character is classified in a template among the updated templates by finding the template having the highest number of matching pixels with the character.

Abstract: A method converts an outline character to a stylized stroke character by first identifying regions of the outline character, wherein each region is closed and disjoint. For each region, candidate locations for stroke bodies and terminals of the stylized stroke character are determined. The stroke bodies are then initialized and organized into a hierarchical tree stricture, and modified in an order of the hierarchical tree structure. End positions of the modified stroke bodies are then adjusted to match the outline character, and lastly, the terminals are selected for the adjusted stroke bodies.

Abstract: Embodiments include an article of manufacture, apparatus, device, system, computer-program product, and method. In an embodiment, an article of manufacture includes a display surface that includes a machine-distinguishable form identifier keyed to an electronic version of the form and at least two fields. Each field of the at least two fields respectively includes a unique machine-distinguishable field identifier keyed to a field of the electronic version of a form, a content area that accepts a hand-formed entry, and a unique user-understandable field identifier.

Abstract: An image processing apparatus includes an image reader for reading an image. A display controller displays the read image on a display device. A determination unit receives an area specified by an operation performed on the image displayed on the display device so as to determine a processing area to be subjected to predetermined image processing. A setting unit sets an operation area for providing an instruction to execute the predetermined image processing on the processing area determined by the determination unit, the operation area being based on an end point of the area specified by the operation.