Abstract: An image processing apparatus performs character recognition processing on a character image in a character area to obtain character code data, and performs vectorization processing on the character image in the character area to obtain vector data. Based on the rule set for each of a plurality of color information definitions and the character color of the character image, the image processing apparatus generates a plurality of color information definitions that define colors to be used in rendering the character code data and the vector data, so that an electronic document is generated that contains the character code data, the vector data, and the plurality of color information definitions.

Abstract: An image processing apparatus which is capable of managing a large number of transfer jobs without using a large-capacity storage device. A transfer job for transferring image information input to the image processing apparatus to at least one destination is performed, and character information is extracted from the input image information. History information indicative of the execution result of the transfer job is generated, and recorded in association with the extracted character information in a storage device. At least one of at least one piece of history information and at least one piece of character information recorded in association with the history information are perused.

Abstract: A method is provided that includes capturing an input handwritten character with parameter representation for each stroke and applying a polygonal approximation thereto; assuming each polygonal line segment approximated to be vector that reaches an end point from a start point, and obtaining an angle between an axis that becomes a reference and each line segment as a polygonal line segment angle sequence; obtaining an exterior angle sequence of vertices of the line segments; making a sum of exterior angles of the same sign, where the same sign of plus or minus in the exterior angle sequence continues, to be a winding angle sequence; extracting a global feature according to each obtained sequence and a localized or quasi-localized feature in each curved portion divided corresponding to the winding angle sequence, hierarchically and divisionally; and performing character recognition by comparing the extracted result with a template of an object character.

Abstract: 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.

Abstract: In an aspect, a method includes the actions of displaying, at a touch-sensitive display, a plurality of characters that each represent a distinct consonant included in a language script; receiving, at the touch-sensitive display, a touch selection of a first character from the plurality of characters, the touch selection being received at a location on the touch-sensitive display at which the first character is displayed; and in response to receiving the touch selection: detecting a gesture input, selecting a vowel marker based at least in part on an association of the gesture input with one or more vowel markers; and displaying, at the touch-sensitive display, an updated representation of the first character based at least in part on the selected vowel marker. Other embodiments of this aspect include corresponding systems, apparatus, and computer programs, configured to perform the actions of the methods, encoded on computer storage devices.

Abstract: A processing device may recognize a number of input handwritten strokes, which may represent a mathematical expression, a chemical formula, or other two-dimensional structure. Rewriting rules of a grammar may be applied to the strokes to produce a number of possible recognition results. Each of the possible recognition results has a respective score based on a sum of rewriting rules applied to the strokes to produce respective ones of the possible recognition results. Input may be provided to identify misrecognized strokes and a correct terminal production, or symbol corresponding to the misrecognized strokes. Strokes may be misrecognized for many reasons, including parsing errors, over-grouping or under-grouping of matrices, and improper placement of a recognized terminal production, or symbol, with respect to a root structure. Correction hints may be leveraged for correcting types of errors mentioned above.

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, there is provided a character string input device. The device includes an input processing unit, a character string storage unit, an input prediction control unit, and an input prediction unit. The input processing unit inputs a character string with a character or a special code. The character string storage unit receives the character string with the character or the special code, adds the character to a stored character string, or updates the stored character string by the special code. The input prediction control unit controls a timing of extracting and sending at least part of the stored character string from the character string storage unit. The input prediction unit performs input prediction for the at least part of the stored character string output from the input prediction control unit and outputs a predicted character string.

Abstract: 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.

Abstract: A document processing apparatus includes: a character segmentation unit that segment a plurality of character images from a document image; a character image classifying unit that classifies the character images to categories corresponding to each of the character images; an average character image obtaining unit that obtains average character images for each of the categories of the character images classified by the character image classifying unit; a character recognizing unit that performs a character recognition to a character contained in each of the average character images; and an output unit that outputs character discriminating information as a character recognition result obtained by the character recognizing unit.

Abstract: Handwriting activity is recorded by use of electromyography (EMG) signals detected from muscles at several locations on the hand. The EMG signals are sensed and registered. The sensed signals are processed and stored, after which the signals are analyzed to reconstruct handwriting activity into a digital format. Machine edible text is generated and displayed along with a graphical depiction of the handwriting.

Abstract: A handwriting detection sheet includes a handwriting layer, a code layer and an optical layer. The handwriting layer can display handwriting. The code layer is placed on a rear-face side of the handwriting layer. The code layer includes plural code images arranged in a matrix manner. In the code images, position codes are encoded with a light absorption material that absorbs infrared light. The optical layer is placed on a rear-face side of the code layer. The optical layer reflects infrared light and allows visible light to pass through.

Abstract: 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.

Abstract: The present invention provides for the recovery of characters entered into at least one data entry zone of a data entry window. A method in accordance with an embodiment includes: storing a first image of the data entry window during data entry; subtracting a reference image from the first image to obtain a delta image, wherein the reference image is an image of the data entry window without data entered; identifying at least one non empty zone of the delta image and the location of the at least one data entry zone on the data entry window from the location of the at least one non empty zone on the delta image; extracting at least one character by applying optical character recognition to the least one non empty zone; and inputting the at least one character into the location of the at least one data entry zone.

Abstract: Various technologies and techniques are disclosed that improve cursive handwriting recognition. Cursive handwriting input is received from a user. The system performs a hierarchical prototype search as part of a recognition operation. A same space search is performed against a mixed database that has both print and cursive samples. A same space search is also performed against a cursive database that has only cursive samples. The results of these two same space searches are merged into a combined alternate list. The combined alternate list is then used as a constraint for the dynamic time warp searches that are performed against the mixed and cursive databases, respectively. The results of the dynamic time warp searches are also merged into a final combined alternate list, and the combined alternate list is used to make a recognition decision regarding the user's handwritten input.

Abstract: A method for matching an image-form textual string in an image to a regular expression is disclosed. The method includes constructing a representation of the regular expression and generating a candidate string of characters from the image-form textual string. The method further includes ascertaining whether there exists a match between the image-form textual string and the regular expression, the match is deemed achieved if a probability value associated with the match is above a predetermined matching threshold.

Abstract: The present invention discloses an on-line identifying method of hand-written Arabic letter. The advantage of the present invention is that the multilayer coarse classification algorithm based on the local characteristic of Arabic letter fully utilize the various local characteristics of Arabic letter, obtain the first candidate letter aggregation matching with the inputted hand-written Arabic letter according to the first level coarse classification formed by the stroke number of letter, and then obtain the second candidate letter aggregation matching with inputted hand-written Arabic letter according to the other local characteristics and the first candidate letter aggregation. The application of the algorithm enables that the inputted hand-written Arabic letter only need to match with the standard letter stored in the predetermined letter library and the corresponding standard letters of the second candidate letter aggregation.

Abstract: This method includes: extracting a feature vector for an input character from a reading result of the input character; calculating distances between the feature vector for the input character and vectors including average vectors stored in a system dictionary storing, for each character, the average vector and distribution information, and feature vectors stored in a user dictionary; extracting the top N character codes in an ascending order of the calculated distances; obtaining second distribution information for the character codes, which are included the user dictionary and in the top N character codes; calculating, for each of the top N character codes, a second distance with the feature vector for the input character, by using, for the character codes, which are included in the user dictionary and in the top N character codes, the second distribution information; and identifying a character code whose second distance is shortest.

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: Disclosed herein is a method, computer system and computer program product for identifying a writing system associated with a document image containing one or more words written in the writing system. Initially, a document image fragment is identified based on the document image, wherein the document image fragment contains one or more pixels from one or more of the words in the document image. A set of sequential features associated with the document image fragment is generated, wherein each sequential feature describes one dimensional graphic information derived from the one or more pixels in the document image fragment. A classification score for the document image fragment is generated responsive at least in part to the set of sequential features, the classification score indicating a likelihood that the document image fragment is written in the writing system.

Abstract: Laser display systems using at least one scanning laser beam to excite one or more fluorescent materials on a screen which emit light to form images. The fluorescent materials may include phosphor materials.

Abstract: A handwriting apparatus has unit for acquiring first-handwriting data, storage unit for storing one-stroke-handwriting data and a first command as an instruction. The instruction corresponds to the one-stroke-handwriting data. When the first-handwriting data corresponds to the one stroke, a unit executes the first command when the corresponding first command is searched from the storage unit, a unit stores one-stroke-handwriting data and a second command as an instruction that corresponds to the one-stroke-handwriting data. The second command is different from the first command, and searches the storage unit for the second command corresponding to the one-stroke-handwriting data. There is a unit, when the corresponding second command is searched out from the storage unit, to execute the corresponding second command.

Abstract: A method for handwriting input includes recognizing a first character inputted by handwriting; providing a plurality of recognition results each with a code based on the recognition of the first character; recognizing a second character inputted by handwriting; and determining the first character based on the recognition of the second character. A handwriting input system for carrying out the method is also provided.

Abstract: Embodiments include an apparatus, device, system, computer-program product, and method. In an embodiment, a method is provided. The method includes receiving an annotation environment signal that includes a context information indicative of a recognizable aspect of an item. The method also includes receiving an expression signal that includes an annotation information indicative of a user expression associated with the recognizable aspect of the item. The method further includes electronically associating the context information indicative of a recognizable aspect of an item and the annotation information indicative of a user expression associated with the recognizable aspect of the item.

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: Aspects of the present invention relate to systems and methods for refining text color in a digital image. A pixel of interest from a first plurality of pixels in a digital image may be selected, and the first plurality of pixels may be separated into a second plurality of pixels and a third plurality of pixels based on the color value of the pixel of interest. A refinement color value may be calculated based on the second plurality of pixels when the second plurality of pixels meets a quantity threshold. When the second plurality of pixels does not meet the quantity threshold, the refinement color value may be calculated based on the third plurality of pixels. The refinement color value may be assigned to the pixel of interest.

Abstract: A method and system for preprocessing an image for Optical Character Recognition (OCR), wherein the image includes a plurality of columns is disclosed. Each column includes one or more of Arabic text and non-text items. The method includes determining a plurality of components associated with one or more of the Arabic text and the non-text items, wherein a component includes a set of connected pixels. On determining the plurality of components, a line height and a column spacing is determined for the plurality of components. The plurality of components are then associated with a column of the plurality of columns based on the line height and the column spacing. Subsequently, a set of characteristic parameters are calculated for each column and the plurality of components of each column are merged based on the set of characteristic parameters to form sub-words and words.

Abstract: An information processing apparatus includes a storage unit configured to store dictionary data in which a locus and one or more pieces of content are registered in association with one another, an input unit configured to input a locus in association with content, a comparison unit configured to compare the locus input by the input unit and a locus registered in the dictionary data, and an addition unit configured to add data to the dictionary data stored in the storage unit based on a comparison result generated by the comparison unit.

Abstract: A natural input system is described for creating and editing complex structures in a typeset application. The natural input system receives a typeset representation of an object and converts the typeset format to generate a standard digital ink representation. The natural input system provides the generated ink representation to a natural input application where can be manipulated by the user with a rich set of correction and editing features provided by the natural input application. Once the end user is satisfied with the recognition result in the natural input application, the natural input system receives the recognition result based on the modified digital ink representation. The natural input system may convert the received recognition result to the typeset application format and provides the modified typeset representation to the typeset application for merging into the document the user is editing.

Abstract: There are provided a word search apparatus, a word search method, and a computer program product. A words dictionary, and a character recognition dictionary for storing coordinate data of a standard character pattern of a handwritten character and a character are used to thereby search for, from the words dictionary, a word including a character corresponding to one or a plurality of character patterns extracted by performing a pattern matching. Only a character string corresponding to one or a plurality of character patterns is extracted from a search result of the words dictionary to generate a part of character string. A selection of one part of character string among the generated parts of character strings is received, and only a word including the selected part of character string is extracted from the search result based on the words dictionary, so that the extracted word is displayed.

Abstract: A system is disclosed for generating text responsive to both voice and handwriting input, including a microphone, stylus, and a tablet having an flat-panel display integrated into its surface. The system performs speech and handwriting recognition using a shared language model, which in one embodiment is trainable responsive to user correction of errors in either speech or handwriting recognition. Various other systems and methods are also disclosed.

Abstract: An exemplary method for online character recognition of East Asian characters includes acquiring time sequential, online ink data for a handwritten East Asian character, conditioning the ink data to produce conditioned ink data where the conditioned ink data includes information as to writing sequence of the handwritten East Asian 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 Hidden Markov Model based character recognition system may use various exemplary methods for training and character recognition.

Abstract: An image processing apparatus includes: a region extracting unit extracts a character region on an image; a character recognizing unit that recognizes characters in the character region extracted by the region extracting unit; a translating unit that translates a recognition result obtained by the character recognizing unit; and a changing unit that changes a constitution of the image with respect to the character region extracted by the region extracting unit according to a direction of the characters in the character region extracted by the region extracting unit, and according to a direction of the characters of the language translated by the translating unit.

Abstract: Handwriting interpretation tools, such as optical character recognition (OCR), have improved over the years such that OCR is a common tool in business for interpreting typed text and sometimes handwritten text. OCR does not apply well to non-text-only diagrams, such as chemical structure diagrams. A method according to an embodiment of the present invention of interpreting a human-drawn sketch includes determining a local metric indicating whether a candidate symbol belongs to a certain classification based on a set of features. The set of features includes, as a feature, scores generated from feature images of the candidate symbol. Also included is determining a joint metric of multiple candidate symbols based on their respective classifications and interpreting the sketch as a function of the local and joint metrics.

Abstract: The present invention provides method and system for preprocessing an image including one or more of Arabic text and non-text items for Optical Character Recognition (OCR). The method includes determining a plurality of components associated with one or more of the Arabic text and the non-text items, wherein a component includes a set of connected pixels. A first set of characteristic parameters is then calculated for the plurality of components. The plurality of components are subsequently merged based on the first set of characteristic parameters to form one or more of one or more sub-words and one or more words.

Abstract: A method for translating stenographic strokes includes the steps of receiving a series of stenographic strokes, creating a table of translations of one or more strokes within the series of strokes, sequentially assigning a score to each of the one or more strokes, determining at least one alternate translation to at least one of the translations in the table of translations, ranking the translations and alternate translations based on an accumulation of the score of the strokes within, and selecting one of the ranked translations or one of the ranked alternate translations based on a best score.

Abstract: The present invention generally describes a method for classifying a line segment of a handwritten line into a reference feature set, wherein said handwritten line comprises one or several curves representing a plurality of symbols. First, sample data representing said handwritten line is received. Next, a sample line segment in said received sample data is identified by detecting a sample line segment start point (SLSSP) and a sample line segment end point (SLSEP). Then, a sample feature set of said identified sample line segment is determined. Finally, the determined sample feature set is matched to a reference feature set among a plurality of reference feature sets.

Abstract: A method for personality assessment through analysis of handwriting is disclosed that provides a way to take into account the relative influence of personality traits indicated by different handwriting features, depending upon the type of handwriting features, and how strongly those features are expressed. The method improves the assessment of personality through handwriting analysis, by separating handwriting features into categories that highlight which aspects of the subject's personality are inherent and deeply-rooted versus changeable and superficial; as well as which aspects of the subject's personality are habitually expressed, versus non-habitually expressed. Handwriting features are separated into primary variables that represent more inherent aspects of the subject's personality, and secondary variables that represent less inherent aspects of the subject's personality.

Abstract: A method for reinterpreting stenographic data includes receiving stenographic data into a memory and analyzing the stored stenographic data at least one of in real time and thereafter to determine if a user desires to adjust at least one of anti-stacking values and at least one registration point of a stenographic key by at least one of adjusting at least one registration point of the stenographic key and examining the change to the stored data in real time on a display, and utilizing the adjustment of the at least one registration point on the stenographic data and adjusting at least one anti-stacking value and examining the change to the stored data in real time on a display, and utilizing the adjustment of the at least one registration point on the stenographic data.

Abstract: A clustering unit calculates, for clusters in a descending order of the number of pixels belonging thereto, a distance from a feature vector of a processing object pixel and a representative feature vector of an object cluster, and compares the distance with a first threshold. The processing object pixel is stored in a memory or the like as a pixel belonging to an object cluster when the distance is determined to be less than or equal to the first threshold.

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

Abstract: A device for identifying a traffic sign in an image includes a Hough transformer implemented to identify a plurality of line sections running in different directions through the image in the image or in an edge image derived from same. The device further includes a shape detector implemented to detect a predefined shape in the image or in the edge image derived from same based on the identified line sections. The device apart from that includes a pattern identifier implemented to select an image section corresponding to the detected predefined shape based on the detected predefined shape and to identify a traffic sign based on the selected image section.

Abstract: The invention relates to a method for handwriting detection using a handwriting tool (2) being arranged for communicating with a further device (2) and comprising the following steps: recognizing characters using detection of movements carried out by means of said handwriting tool (2); determining the probability factor of at least one input character corresponding to a given character; and using said probability factor in a step for correction, completion and prediction of words being formed by said characters. The invention also relates to a device for such handwriting detection.

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: Processing an image with embedded metadata by determining an integer value of a byte and separate the integer value into a plurality of digits, converting each of the digits into an encoding value using a predefined conversion function, selecting a pixel block in a metadata container, encoding into the selected pixel block each of the encoding values, and after the pixel block is encoded using a lossy compression scheme and subsequently decoded into raw pixel data, extracting the metadata from the raw pixel data, and performing at least one predefined action using the metadata.

Abstract: The present invention provides a 3D handwriting recognition system that allows users to freely write words or characters in a 3D space in a touchless manner, without requiring any physical medium such as a pad or a tablet. The users' handwriting input in a 3D space will be tracked by an input device of the system that generates corresponding 3D motion data and wirelessly transfers the 3D motion data to a recognition device of the system. The 3D motion data will be converted and then mapped onto a 2D plane to generate corresponding 2D images for handwriting recognition. In this way, the users' inputting will never be limited to any screen, pad or plane, and the users will have more flexibility and enjoyable writing experience.

Abstract: Embodiments of a computer system, a method, and a computer-program product (e.g., software) for use with the computer system are described. These embodiments may be used to identify and correct errors in financial information that was extracted using character-recognition software, such as optical character recognition software and/or intelligent character recognition software. In particular, potential errors may be identified by comparing the financial information for a current financial transaction of a user with expected financial information from one or more previous financial transactions of the user. Error metrics for these potential errors may be determined and used to correct at least some of the potential errors. For example, values of the Levenshtein edit distance may be determined based on the comparison, and one or more potential errors associated with one or more minimum values of the Levenshtein edit distance may be corrected.

Abstract: The enhanced detection of a circular engagement gesture, in which a shape is defined within motion data, and the motion data is sampled at points that are aligned with the defined shape. It is determined whether a moving object is performing a gesture correlating to the defined shape based on a pattern exhibited by the sampled motion data. An application is controlled if determining that the moving object is performing the gesture.

Abstract: A handwriting apparatus includes unit acquiring first-handwriting data, unit storing one-stroke-handwriting data and a first command as an instruction, the instruction corresponding to the one-stroke-handwriting data and being executed with a device, unit, when the first-handwriting data corresponds to one stroke, searching the storage unit for the first command corresponding to the one-stroke-handwriting data corresponding to the one stroke, unit planning to execute the first command when the corresponding first command is searched out from the storage unit, unit storing one-stroke-handwriting data and a second command as an instruction which corresponds to the one-stroke-handwriting data, the second command being different from the first command, unit regarding the first-handwriting data as one-stroke-handwriting data at time intervals and search the storage unit for the second command corresponding to the one-stroke-handwriting data, and unit, when the corresponding second command is searched out from the

Abstract: A form processing program which is capable of automatically extracting keywords. When the image of a scanned form is entered, a layout recognizer extracts a readout region of the form image, a character recognizer recognizes characters within the readout region. A form logical definition database stores form logical definitions defining strings as keywords according to logical structures which are common to forms of same type. A possible string extractor extracts as possible strings combinations of recognized characters each of which satisfies defined relationships of a string. A linking unit links the possible strings according to positional relationships, and determines a combination of possible strings as keywords.