Abstract: An exemplary method includes receiving stroke information for a partially written East Asian character, the East Asian character representable by one or more radicals; based on the stroke information, selecting a radical on a prefix tree wherein the prefix tree branches to East Asian characters as end states; identifying one or more East Asian characters as end states that correspond to the selected radical for the partially written East Asian character; and receiving user input to verify that one of the identified one or more East Asian characters is the end state for the partially written East Asian character. In such a method, the selection of a radical can occur using radical-based hidden Markov models. Various other exemplary methods, devices, systems, etc., are also disclosed.

Abstract: A pen-enabled computing arrangement includes a handwriting capture interface and at least one processing element, such as in the form of a computing system and a digital pen that embodies a writing stylus. The handwriting capture interface can capture an electronic handwriting input. The processing element can sense an identifier associated with an object, and associate electronic handwriting input with the object. The processing element can then process the electronic handwriting input based upon the associated object. Printed paper with which the arrangement can operate to effectuate capturing and processing data may also be provided. Further, triggered verification of the sensed identifier may be provided when the identifier is sensed based upon initial electronic handwriting input corresponding to the identifier and the sensed identifier is unknown and/or improper.

Abstract: A system is presented for scanning entire books or document all at once using an adaptive process where the book or document has known fonts and unknown fonts. The known fonts are processed through a verification system where sure words and error words are determined. Both the sure words and error words are sent to OCR training where they are re-OCR'ed and repeatedly verified until they meet a predetermined quality criteria. Characters or words not meeting the predetermined quality criteria receive additional OCR training until all the characters and words pass the predetermined quality criteria. Unknown fonts are scanned and clustered together by shape. Outliers in the shapes are manually keyed-in. Those symbols that are manually classified go to OCR training and then to the known type optimization process.

Abstract: A method, system, and computer-readable medium containing computer-executable instructions are provided, for randomly relocating text character images of a scanned-in Asian character document to produce a shuffled image, wherein the meaning of text in the shuffled image is not understandable although individual characters forming the text in the shuffled image are recognizable. In one embodiment, the method includes generally four steps: (1) dividing an Asian character document image into a text image portion and a non-text image portion; (2) structuring the text image portion into a multiple resolution-level pyramid; (3) extracting shuffleable character images by analyzing the multiple-resolution-level pyramid; and (4) shuffling some or all of the extracted shuffleable character images to create a shuffled image. The shuffled (e.g., encoded) image can be reshuffled (e.g.

Abstract: An information processor includes: a character recognizing unit; a recognized character feature obtaining unit; a translation deciding unit; a translating unit; a translated result feature obtaining unit; an output deciding unit; an image receiving unit; and an output unit that, wherein the character recognizing unit recognizes a character in character image of the image data received by the image receiving unit, and the recognized character feature obtaining unit, in a case where a picture image other than the character is recognized, obtains a third feature related to a character included in the picture image.

Abstract: A program causes a computer to function as a document recognition apparatus, having an extraction unit for extracting connected components of pixels from an input image, a generation unit for generating a reference element that is connected components of pixels extracted by the extraction unit and combined elements obtained by combining the reference element and connected components of pixels adjacent to the reference element as an element to be estimated, a calculation unit for calculating a degree of certainty that indicates how much the element to be estimated generated by the generation unit seems to be a character, and a determination unit for identifying elements that seem to be characters among the elements to be estimated based on the degree of certainty calculated by the calculation unit.

Abstract: A spatial motion recognition system capable of recognizing motions in three-dimensional space as handwritings on a two-dimensional plane is provided. The system recognizes motions of a system body occurring in space based on position change information of the system body that is detected in a motion detection unit, displays the recognized motion information on a screen, or transmits to an external device the recognized motion information through a transmission/reception unit or a control signal corresponding to the motion information. A control unit produces a virtual handwriting plane having the shortest distances with respect to respective positions in predetermined time intervals based on three-dimensional track information obtained through tracking, and projects the respective positions in the predetermined time intervals onto the virtual handwriting plane to recover the motions in space.

Abstract: An area extraction method including obtaining a character lattice showing a connection relation between unit areas, which are obtained by separating a character string pattern in an image into patterns each recognized as corresponding to a single character, judging whether or not all combinations of each of the unit areas in the obtained character lattice and each of the unit areas in a regular lattice defining a regular connection relation between the unit areas are likely to be established, generating a path coupling between nodes corresponding to the combination of the unit areas which is determined as likely to be established, determining an optimum path from the generated paths based on a degree of coincidence with the regular lattice or the character lattice, and extracting from an image the unit areas in the character lattice corresponding to the determined optimum path.

Abstract: A method and system for cleaning handwriting for redisplay of the handwriting or for improved recognition accuracy is provided. The cleanup system receives handwriting that has been digitized. The cleanup system then analyzes the handwriting to identify strokes that satisfy a cleanup criterion. When a stroke has been identified as satisfying some cleanup criteria, the cleanup system cleans up the handwriting based on the detected criteria. In this way, the cleanup system generates handwriting that may have a more visually pleasing appearance to the reader.

Abstract: A method and apparatus for determining an orientation of a document including Korean text are presented. A binarized pixel image is created from the document image. Contiguous pixels are grouped and labeled using a bounding box. A spanning stroke may be detected from a group of the contiguous pixels. The orientation of the document is determined by comparing counts associated with spanning strokes in the left, right, top, and bottom halves of the bounding boxes.

Abstract: A mail server extracts a character unregistered in a portable terminal from received mail data and affixes the font data of the character concerned to the mail data or inserts a reading tag indicating the reading (pronunciation) of the character concerned into the mail data. The portable terminal additionally registers the font data affixed to the mail data into a font database before the received mail data are displayed. Furthermore, in the display processing of the mail data, a character for which the corresponding font data is unregistered is replaced by a no-font symbol and then displayed. Furthermore, the font of each character constituting the reading tag is read out and this font is displayed subsequently to the no-font symbol.

Abstract: A method and device are provided for segmenting an image of pixels into a number of fields. First the method finds field separators using the background of the image, in particular white areas on a newspaper page. Based on the areas in the image, a graph is constructed that has edges corresponding to the white areas and vertices where vertical and horizontal white areas intersect. The segmenting starts with assigning weights to the edges, in particular a weight indicating the Euclidean distance between the vertices. Then a list of shortest cycles is constructed via the edges and vertices in the graph. The fields are defined by the vertices and edges of the shortest cycles of the list.

Abstract: Illustrative embodiments provide a computer implemented method, a data processing system and a computer program product for transforming character data input between a first writing system and a second writing system. The computer implemented method comprises receiving character data input of a first writing system and ensuring the character data input contains normalized characters. A predefined transform is selected based on the character data input of the first writing system and output to a second writing system to transform the normalized characters of the first writing system to character data output of the second writing system, and providing the character data output to a display process.

Abstract: An information embedding apparatus (100) which embeds information by changing the character spacing in a document image includes a discrimination unit (101) which discriminates a text area in the document image, a circumscribed rectangle extraction unit (102) which extracts the circumscribed rectangle of each character in the text area, a determination unit (103) which determines, based on the position and size of each extracted circumscribed rectangle, whether a portion having a character spacing smaller than a threshold exists, a reduction unit (104) which, for a character determined to have a character spacing smaller than the threshold, reduces the size of the character in at least the character arrangement direction, and a character position changing unit (105) which changes, in accordance with information to be embedded, the position of a character determined to have a character spacing equal to or larger than the threshold, and that of a character reduced.

Abstract: A method and system for recognizing alphabetic characters that contain diacritics is described. An image analysis separates the character into its constituent components. The one or more diacritic components are then distinguished and isolated from the base portion of the character. Optical recognition is performed separately on the base portion. The diacritic is recognized through a special image analysis and pattern recognition algorithms. The image analysis extracts geometric information from the one or more diacritic components. The extracted information is used as input for the pattern recognition algorithms. The output is a code that corresponds to a particular diacritic. The recognized base portion and diacritic are combined and a check is performed for acceptable combinations in a chosen language. By separately recognizing the base portion and diacritic, the character sets used by the recognizer can be narrowed, resulting in greater recognition.

Abstract: In practicing the present invention, in analyzing a Chinese character, a 3×3 square grid of 9 boxes is superimposed over the character. The character is analyzed based upon the shape of the stroke that is at the lowest elevation within the lower right-hand corner. A Table is consulted consisting of a plurality of elements including horizontal strokes, and the element most closely resembling the corresponding portion of the character is chosen. The user then consults a Root Table where characters all having in common the same part of the character immediately on top are displayed. From examination of the Root Table, the user narrows down the identity of the character to a smaller group. The pages to which the user is directed are carefully reviewed and the entire character may be found in a Form Block including pertinent information concerning the character.

Abstract: A method of organizing Chinese characters includes the steps of: generating Stroke Set; generating Symbol Set; generating Stroke Code Set; generating a sequential code for each of the Chinese characters to be organized; generating a spatial code for each of the Chinese characters to be organized; generating a character code for each of the Chinese characters to be organized; and organizing said character codes together with related the Chinese characters to be organized such that a Chinese character is adapted to be located by first locating the related character code of the Chinese character, then locating the Chinese character in responsive to the related character code of the Chinese character.

Abstract: The present invention employs the notion of a Chinese writing brush in moving a geometric figure to produce a style of calligraphy, where the area of the geometric figure is large or small, then the strokes of a character are thick or thin. Hence the purpose is that the variance of the strokes of a character can be achieved using the present invention. The present invention only decides a moving path for the strokes of a character and the size of a geometric figure at starting points and end points, and then moves the geometric figure along the moving path, where the area the geometric figure passes is the style of calligraphy.

Abstract: A system/method is presented for scanning entire books or document all at once using an adaptive process where the book or document has known fonts and unknown fonts. The known fonts are processed through a verification system where sure words and error words are determined. Both the sure words and error words are sent to OCR training where they are re-OCR'ed and repeatedly verified until they meet a predetermined quality criteria. Characters or word not meeting the predetermined quality criteria receive additional OCR training until all the characters and words pass the predetermined quality criteria. Unknown fonts are scanned and clustered together by shape. Outliers in the shapes are manually key-in. Those symbols that are manually classified go to OCR training and then to the known type optimization process.

Abstract: A text input device receives, in its information input circuit, a letter indicating a destination of transmission as information on the destination of transmission. The text input device stores, in its word-finder with learning function, an input text and an output text in a state correlated with the information on the destination of transmission or its attribute. The text input device in its text learning circuit controls a change in storage caused by correlating an input text matched to a text entered with the information on the destination of transmission or its attribute stored and coincident with the information on the destination of transmission or its attribute entered. When a text matched to the text entered is output, the text input device in its text converter takes out and outputs at least one output text stored.

Abstract: The present invention is a method of optical character recognition. First, text is received. Next all words in the text are identified and associated with the appropriate line in the document. The directional derivative of the pixellation density function defining the text is then taken, and the highest value points for each word are identified from this equation. These highest value points are used to calculate a baseline for each word. A median anticipated baseline is also calculated and used to verify each baseline, which is corrected as necessary. Each word is then parsed into feature regions, and the features are identified through a series of complex analyses. After identifying the main features, outlying ornaments are identified and associated with appropriate features. The results are then compared to a database to identify the features and then displayed.

Abstract: User friendly coding systems are provided for Chinese characters, either complicated or simplified. Each Chinese character is assigned a code based on the shape of the character. In particular, the characters sharing the same beginning strokes are grouped together. The coding systems are useful for searching or sorting Chinese characters, as well as for typing Chinese characters on a computer or word processor.

Abstract: A method of creating font format data from source font data includes analyzing the source font data to obtain glyph data for a plurality of glyphs, dissecting the glyph data, extracting midline data from the dissected glyph data, classifying the midline data as unique element data and common element data, associating unique element data and common element data to each glyph of the plurality of glyphs.

Abstract: Exemplary methods, systems, and computer-readable media for developing, training and/or using models for online handwriting recognition of characters are described. An exemplary method for building a trainable radical-based HMM for use in character recognition includes defining radical nodes, where a radical node represents a structural element of an character, and defining connection nodes, where a connection node represents a spatial relationship between two or more radicals. Such a method may include determining a number of paths in the radical-based HMM using subsequence direction histogram vector (SDHV) clustering and determining a number of states in the radical-based HMM using curvature scale space-based (CSS) corner detection.

Abstract: Exemplary techniques are described for selecting radical sets for use in probabilistic East Asian character recognition algorithms. An exemplary technique includes applying a decomposition rule to each East Asian character of the set to generate a progressive splitting graph where the progressive splitting graph comprises radicals as nodes, formulating an optimization problem to find an optimal set of radicals to represent the set of East Asian characters using maximum likelihood and minimum description length and solving the optimization problem for the optimal set of radicals. Another exemplary technique includes selecting an optimal set of radicals by using a general function that characterizes a radical with respect to other East Asian characters and a complex function that characterizes complexity of a radical.

Abstract: A method and system for entering Chinese characters into a computer by entering the size and shape of their strokes via a matrix, such as the 3×3 arrangement of the numbers one through nine found on a cell phone.

Abstract: A method for encoding characters includes identifying one or more sequences of the character codes that are likely to be generated due a segmentation error in application of a pattern recognition process, and associating a respective extension character code with each of the sequences. The area of an image containing characters is divided into segments, such that each segment contains approximately one character. The pattern recognition process is applied to each of the segments in order to generate an input string of character codes. At least one of the identified sequences of the character codes in the input string is replaced with the respective extension character code so as to generate a modified string. The output string is determined by comparing the modified string to a directory of known strings.

Abstract: A system of materials facilitates teaching Chinese characters to a child in progressive stages, whether or not the teacher is fluent in Chinese. Each stage associates a multi-colored object with a correspondingly multi-colored Chinese character that represents the object. For a child from birth to two years, a first stage material animates the object and morphs the object into the corresponding Chinese character. For a child two to four years, a second stage material to be read to the child by the teacher displays the object adjacent to the character, and material provides interactive means for the child to associate the object with the character. For a child four to seven years, a third stage story book displays text containing a sentence made of multiple characters and a scene corresponding to the meaning of the sentence, and for a child seven to nine years, a fourth stage group book presents multiple Chinese characters that share a common group element, whether meaning or sound.

Abstract: A method of creating font format data from source font data includes analyzing the source font data to obtain glyph data for a plurality of glyphs, dissecting the glyph data, extracting midline data from the dissected glyph data, classifying the midline data as unique element data and common element data, associating unique element data and common element data to each glyph of the plurality of glyphs.

Abstract: Out of a lot of fonts, the desired font is quickly found. For this purpose, out of a plurality of portions constituting a character displayed in a partial image retrieval area, the desired portion is selected. A retrieval area is clicked by a user, to retrieve a font on the basis of the selected portion. A list of the results of retrieval is displayed in a retrieval result area. Even if a font name is not memorized, a desired font can be found.

Abstract: To make searching for pictographic characters, such as Chinese characters, easier for novice learners of languages using pictographic characters, a subset of pictographic character parts of the pictographic character is generated. Then, the subset of the pictographic character parts is used to generate the pictographic character based on the subset of the pictographic character parts.

Abstract: A labeling process unit groups a continuous black pixel area as one group in the binary image data read by an image input device, and extracts the group bounding rectangle information about the group. A row extracting process unit extracts row rectangle information from the position information about the extracted group bounding rectangle. An overlap integrating process unit determines the overlap between the group bounding rectangles contained in the extracted row rectangle, and performs an overlap integrating process of integrating overlapping groups into one group. The ratio of the number of group bounding rectangles contained in the row rectangle before performing the overlap integrating process to the number of the group bounding rectangles contained in the row rectangle after performing the overlap integrating process is obtained, and the language of the characters written in the original is determined based on the difference in ratio.

Abstract: A system and method for translating a written document into a computer readable document by recognizing the character written on the document aim at recognizing typed or printed, especially hand-printed or handwritten characters, in the various fields of a form. Providing a pixel representation of the written document, the method allows translating a written document into a computer readable document by i) identifying at least one field into the pixel representation of the document; ii) segmenting each field so as to yield at least one segmented symbol; iii) applying a character recognition method on each segmented symbol; and iii) assigning a computer-readable code to each recognized character resulting from the character recognition method. The character recognition method includes doing a vector quantization on each segmented symbol, and doing a vector classification using a vector base. A learning base is also created based on the optimal elliptic separation method.

Abstract: Systems and methods that exploit unique properties of a language script (e.g., condition joining rules for Arabic language) to enable a two tier text recognition. In such two tier system, one tier can recognize predetermined groups of linked letters that are connected based on joining rules of a language associated with the text, and another tier dissects (and recognizes) such linked letters to respective constituent letters that form the predetermined group of linked letters. Various classifiers and artificial intelligence components can further facilitate text recognition at each level.

Abstract: A method and apparatus for recognition of handwritten symbols. A plurality of strokes is received at a common input region of an electronic device, wherein the plurality of strokes in combination defines a plurality of symbols. Sequential combinations of the plurality of strokes are analyzed with a plurality of symbol recognition engines to determine at least one possible symbol of the plurality of symbols defined by the plurality of strokes, wherein at least one of the plurality of symbol recognition engines is configured to identify symbols comprising a particular number of strokes.

Abstract: A method for converting image data coded with run lengths to the format of a page description language, such as PostScript or PDF, the run lengths identifying how many image points of one color follow one another in an image row, includes utilizing the run lengths of the same color that overlap in successive image rows to form an object, and describing the object with operators from the page description language. Objects of the same color can be combined to form one object. An object is described in the page description language by the image mask operator and an associated bitmap, or by a polygon train that connects reference points on the edge of the object.

Abstract: A coordinate detection device is provided, which device includes an input unit which has a surface thereof to which a coordinate value is input by an input means, a calculation unit which calculates a difference between previous and current coordinate values input by the input unit, and a setting unit which sets, in the calculation unit, a coordinate value input last before the input means is detached from the surface of said input unit as the previous coordinate value to a coordinate value input first after the input means is detached from the surface of the input unit.

Abstract: Ink strokes of cursive writing are segmented to make the cursive writing more like print writing, particularly with respect to the number of strokes of a character. A stroke-segmentation module first finds the local extrema points on a stroke of input ink. Then the local extrema points are stepped through, two (or three) at a time. The stroke-segmentation module may compare the three (or four) ink segments that are adjacent to the two (or three) local extrema points to a set of predefined stroke-segmentation patterns to find a closest matching pattern. Strokes are then segmented based on a stroke-segmentation rule that corresponds to the closest matching pattern. Additional stroke segmentation may be performed based on the change of curvature of the segmented ink strokes. Then, a character-recognition module performs character recognition processing by comparing the segmented ink strokes to prototype samples at least some of which have been similarly segmented.

Abstract: Aspects of the present invention relate to the creation of an ink font. Based on characteristics of handwritten characters, the collection of characters may be scaled so as to adjust the size of the font to match predefined size values or relationships.

Abstract: A method and apparatus include referencing a phonetic language database that includes double-byte font entries and associated phonetic representations of the double-byte font entries. At least one of the double-byte font entries is used to obtain a phonetic representation of the used at least one double-byte font. The phonetic representation is displayed on a display device.

Abstract: A method of creating font format data from source font data includes analyzing the source font data to obtain glyph data for a plurality of glyphs, dissecting the glyph data, extracting midline data from the dissected glyph data, classifying the midline data as unique element data and common element data, associating unique element data and common element data to each glyph of the plurality of glyphs.

Abstract: A Chinese text entry system and method is provided to allow users to enter a character to a device such as a cellular phone or a PDA by adding a first few strokes required for the character using a joystick or its equivalent. By simply moving the joystick to add one or more strokes which are used to start writing a character, or in some case even before any stroke is added, a user can find a desired character from a displayed selection list. The selection list is context sensitive, varying depending on the last character entered, so that the user can be provided with the most possible candidates of the desired character.

Abstract: A system for distinguishing names of persons in Chinese, which includes a computer. The computer includes at least an input, an output, a processor, and a memory and storage arrangement. Data is accessible by the processor, including at least names presently being used in Chinese, and name indicators and non-name indicators that respectively indicate probable presence and non-presence of a name. The system also includes software for performing computer processing including identifying names in Chinese text that has been input to the computer for names corresponding to names in the data for names presently being used in Chinese, name indicators, and non-name indicators. The processing includes comparing the location in the Chinese text of identified name indicators and non-name indicators relative to identified names in the text, and if predefined conditions are met, affirming that that an identified name is being used as a name in the text.

Abstract: A method for entering ZhuYin symbols and tone marks into electronic text is provided. The method comprises receiving an input symbol and providing a candidate list comprising the input symbol and the Chinese characters associated with the input symbol. After the selection of the input symbol from the candidate list, the selected input symbol is entered to the electronic text, and the tone marks of the ZhuYin symbol set are provided. After the selection of a tone mark, the selected tone mark is entered to the electronic text.

Abstract: A character recognition apparatus which performs character recognition with increased accuracy on a document image including plural languages. A re-recognition range is set based on the result of recognition using a first recognition unit, and character recognition by a second recognition unit is performed within the set range. In the re-recognition range, if a similarity of the result of re-recognition is higher than that by the first recognition unit, the result of recognition by the first recognition unit is replaced with the result of recognition by the second recognition unit.

Abstract: A character recognition device to recognize characters in a text image read by an image scanner having a first recognition device to recognize the characters in the text image using a first character recognition method and a second recognition device to recognize the characters in the text image using a second character recognition method different from the first character recognition method. An extraction device extracts locations of recognized characters in the text image wherein the recognition results of the first recognition device do not coincide with the recognition results of the second recognition device. An output device outputs character recognition results designating the non-coinciding locations extracted by the extraction device.

Abstract: Systems and methods are described for intelligent default selection of characters to be entered via an on-screen keyboard. Based on one to several criteria, a character most likely to be selected for entry via the on-screen keyboard during a search request is determined and a selector is positioned at that particular character. If that character is indeed the character the user wishes to enter, the user does not have to execute any navigation steps to enter the character, but can—with a single actuation—enter that character. In many instances, the user will only have to enter the selection without first having to navigate to the selection. As a result, the number of times buttons need to be actuated by the user to enter a character string can be significantly reduced.

Abstract: A method and system for context-based sorting of character strings. A first sorting weight of a current character of a character string is determined from a first table. The first sorting weight is stored. Provided the current character is a predetermined character, a second table is accessed. A second sorting weight of the current character is determined from the location of a preceding character within the second table. The first sorting weight is replaced with the second sorting weight for the current character. Embodiments of the present invention provide an efficient method of context-based sorting in languages, such as Japanese, where the sorting weight of a character can be altered by the preceding character.

Abstract: A Chinese text entry system and method is provided to allow users to enter a character to a device such as a cellular phone or a PDA by adding a first few strokes required for the character using a joystick or its equivalent. By simply moving the joystick to add one or more strokes which are used to start writing a character, or in some case even before any stroke is added, a user can find a desired character from a displayed selection list. The selection list is context sensitive, varying depending on the last character entered, so that the user can be provided with the most possible candidates of the desired character.

Abstract: Every Chinese character belongs to a small graphic form group which is created with respect to the radical of the character instead of character components. Every small graphic form group is incorporated into higher-level groups, i.e. medium graphic form groups, in turn every medium graphic form group is incorporated into higher-level groups, i.e. large graphic form groups. Input guidance is provided according to this hierarchy concerning graphic form. More specifically, the large groups are presented and one of them is selected by the first keystroke, the medium groups are presented and one of them is selected by the second keystroke, and the small groups are presented and one of them to which the desired character for input belongs is selected by the third keystroke. In this fashion, three keystrokes to a numeric keypad efficiently narrows down the alternative characters for conversion.