Abstract: A method and an apparatus for character string recognition may be provided that enables prevention of a decrease in recognition accuracy for a character string even when distortion of an image appears in a direction perpendicular to a medium transfer direction.

Abstract: To handle static text and logos in stabilized images without destabilizing the static text and logos, a method of handling overlay subpictures in stabilized images includes separating an existing overlay subpicture from an input image to generate a separated overlay subpicture and a separated input image. The separated input image is stabilized to form a stabilized image. The separated overlay subpicture is then merged with the stabilized image to obtain an output image.

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: A method of segmenting images receives an image (such as a medical image) and a segment in relation to the image, displays them to an observer, receives a modification to the segment from the observer, and generates a second segment in relation to a second image, responsive to the modification. An image segmentation system includes a learning scheme or model to take input from an observer feedback interface and to communicate with a means for drawing an image segment to permit adjustment of at least one image segmentation parameter (such as a threshold value). The learning scheme is provided with a knowledge base which may initially be created by processing offline images. The learning scheme may use any scheme such as a reinforcement learning agent, a fuzzy inference system or a neural network.

Abstract: Systems and methods for character recognition by performing lateral view-based analysis on the character data and generating a feature vector based on the lateral view-based analysis.

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: Using methods, computer-readable storage media, and apparatuses for computer-implemented processing, an image of handwritten text may be segmented into a disjoint component image corresponding to individual glyphs connected by ligatures. The disjoint component image is skeletonized into a grid graph, and a connected path traversing the ligatures is determined. The disjoint component image is segmented into non-overlapping segments based on connected graphs corresponding to edges in the disjoint component image, where sets of adjacent non-overlapping segments correspond to the individual glyphs. Glyph geometry may be varied by obtaining an ensemble of glyph representations, each characterized by measurable geometric glyph properties. For each geometric glyph property, target values are obtained from ensemble-wide statistical distribution functions, and the target values are used to transform a base glyph representation into a target glyph representation.

Abstract: A printing apparatus, including a user input unit which receives a first user command to initiate a printing operation, a display unit which displays information relating to the printing operation, a printing unit which performs printing with respect to printing data, and a controller which controls the display unit to display reference information of the printing data before the printing, and which controls the printing unit to perform the printing according to a second user command.

Abstract: A handwritten character recognition system is disclosed. The system has an input device for receiving handwritten strokes, and a processor for classifying the handwritten strokes as an output character. The processor does so by calculating a degree of membership of the handwritten strokes to each of a plurality of character models. The character model that produces the highest degree of membership is selected and the handwritten strokes ate classified as the output character associated with the character model that produces the highest degree of membership.

Abstract: A visualization program, method and apparatus for determining reading order of content in a structured document. The method includes generating, for each of a plurality of elements, a directed segment; storing, in the reading order, the generated directed segments of the elements into a storage device; reading from the storage device; linking together the directed segments for the elements in accordance with the reading order; and displaying the linked directed segments overlaid on the structured document which is displayed on the screen. A computer implemented program and an apparatus for carrying out the above method are also provided.

Abstract: In accord with embodiments consistent with the present invention, a first action in recognizing text from image and video is to locate accurately the position of the text in image and video. After that, the located and possibly low resolution text can be extracted, enhanced and binarized. Finally existing OCR technology can be applied to the binarized text for recognition. This abstract is not to be considered limiting, since other embodiments may deviate from the features described in this abstract.

Abstract: An image forming device includes a main body casing, a cover configured to be openable and closable with respect to the main body casing, a sensing unit configured to sense an opening-closing operation of the cover, a forming unit configured to form an image on a sheet, a detecting unit configured to perform a detecting operation to detect a deviation of an image forming position of the image to be formed by the forming unit, an accepting unit configured to accept a print request, and a control unit configured to control the detecting unit to perform the detecting operation in response to the print request being accepted when the sensing unit senses an opening-closing operation of the cover after execution of a previous detecting operation, and thereafter to control the forming unit to form the image in the image forming position corrected to cancel the deviation detected in the detecting operation.

Abstract: A method of processing uniform mailpieces referred to as a “run” of mailpieces, during which method OCR is performed for recognizing certain information in a zone of interest of an image of each mailpiece, and during which method the following steps are performed: a) initializing a matrix accumulator associated with said run and including unitary accumulation elements that correspond to the pixels of the image; b) consolidating said matrix accumulator by incrementing certain unitary accumulation elements by deriving an indication of the spatial position of a block of pixels in which said certain information has been recognized unambiguously, or by using construction and local graphical correlation of blocks of image pixels to derive an optical flow map indicating local graphical movements; and c) defining, in the OCR processing, said zone of interest on the basis of the unitary accumulation elements of the consolidated matrix accumulator that present extreme accumulation values.

Abstract: A system 10 and method for searching image text documents includes a content repository 12 storing image documents having text images therein. An image text transformer 14 performs optical character recognition on the image documents to form optical character recognition results and creates a reflection repository 22 having reflection files therein corresponding to the image documents from the optical character recognition results. A search engine 38 searches the reflection files and a user device 30 displays a first reflection file from the reflection files or a first image document from the image documents in response to searching. The files are displayed on a display 32 associated with a user device 30.

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: Embodiments disclosed include methods for connected component labeling including labeling groups of raw data as one or more regions, the labeling including designating one or more data structures as containing information about the one or more regions; designating one or more of the regions as one or more subregions to expose a spatial distribution of one or more region features; and arranging at least one memory array with a 1:1 correspondence to a data array associated with the raw data to enable one or more data structures to include feature labels of the one or more subregions, the 1:1 correspondence enabling acquisition of the one or more region features with a controllable precision.

Abstract: A method for emphasizing differences in graphical appearances between an original document and a modified document is provided in accordance with an aspect of the present invention. The method includes the step of receiving a first bitmap of the modified document, and a second bitmap of the original document. The method includes deriving a set of difference points based upon a comparison of the first bitmap and the second bitmap. The method includes a step of superposing a spatial index onto the set of difference points, and generating polygon vertices from a plurality of adjacent elements of index. Each of the elements has a predetermined density of difference points. The method concludes with generating an annotation from the polygon vertices.

Abstract: Systems and methods for detecting annotation digital ink strokes and further associating annotation digital ink strokes with word digital ink strokes are presented. Ink strokes are captured on a writing surface and then classified as words or annotations. Annotations are then anchored to corresponding words. When words are relocated or edited on the writing surface, the anchored annotations are also relocated and may even be reshaped according to the changes in the anchored words.

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: 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: The present invention aims to prevent a problem that an image on a document sheet is erased due to misdetection of a line-shaped noise. A copy machine 1 compares RGB values of a target pixel with averaged RGB values (Step S103). If only one of the RGB values has a difference that is greater than a prescribed value Ref2 (Step S103: YES), the copy machine 1 extracts the target pixel as a line-shaped noise pixel, and moves to a line-shaped noise correction (Step S108) while holding the address of the target pixel in a line-shaped noise address storing area 49b. If two of the RGB values have differences (Step S103: NO, Step S104: YES) and a difference between these two of the RGB values is no greater than a prescribed value Ref3 (Step S105: YES), the copy machine 1 extracts the target pixel as a line-shaped noise pixel, and moves to the line-shaped noise correction (Step S108) while holding the address of the target pixel in the line-shaped noise address storing area 49b.

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 disclosed information processing apparatus includes an image data obtaining unit configured to obtain image data generated by scanning a confirmation/correction form on a recording medium; a workflow definition obtaining unit configured to obtain a workflow definition of a workflow that includes a workflow step corresponding to the recording medium; a form definition obtaining unit configured to obtain a form definition of the confirmation/correction form corresponding to the workflow step based on the workflow definition; a field image extracting unit configured to extract a field image of a field of the confirmation/correction form from the image data based on the form definition; and a handwriting image extracting unit configured to remove a previous handwriting image and extract a current handwriting image from the field image if the field image contains both the previous handwriting image and the current handwriting image.

Abstract: The invention relates to the authentication of users for a multi-function peripheral (MFP) device using handwritten signatures. Systems and methods are disclosed which relate to a MFP that conditions access to MFP operations based on an authenticating process that compares a prospective user's signature to previously saved signatures. The signatures are communicated to the MFP using the MFP's native scanning function.

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: The invention relates to a method and system for the acquisition and correlation matching of points belonging to a stereoscopic pair of images, whereby the pair is formed by a first image and a second image representing a scene. According to the invention, the two images of the pair are acquired with a single acquisition instrument (30) comprising two sensors CCD (31, 32) in the optical focal plane. The matching of the acquired stereoscopic pair consists in determining, by means of correlation, the point in the second image that is homologous to a point in the first image. Said correlation is performed for a point from the first image using an optimally-sized correlation window. When the homologous point of a point from the first image has been determined, the position deviation between the point from the first image and the homologous point thereof is entered in a table. Once all of the homologous points of the points from the first image have been found, the results table is reset barycentrically.

Abstract: In an image forming apparatus, a first document manager stores image data in an image storage device, associates the image data with a first identifier, outputs the image data via an image output device when the first identifier is specified via an operation device, and deletes the image data from the image storage device when a first condition is satisfied. A second document manager associates the image data with a second identifier, outputs the second identifier via the image output device, and outputs the image data via the image output device when the second identifier is input via an image input device. The first document manager does not delete the image data from the image storage device and prohibits the operation device from specifying the first identifier when the image data is associated with both the first and second identifiers.

Abstract: A method for classifying a handwritten input character is disclosed. Character models are used. Each character model is associated with an output character and defines a model specific segmentation scheme for that output character and an associated segment model. The model specific segmentation scheme defines a minimum length corresponding to a number of points in a stroke of the output character and a minimum length threshold. Using each of the character models, the input character is decomposed into segments and the segments are evaluated against the segment model of the respective character model to produce a score indicative of the conformity of the segments with the segment model. The character model that produced the highest score is selected and the input character is classified as the output character associated with the character model that produces the highest score.

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: A method for classifying digital ink receives digital ink comprising ink strokes. A plurality of the ink strokes can be classified. A temporal line grouping is performed on a plurality of the classified ink strokes that are grouped to form a temporal line group. The temporal line group is segmented into a cluster. The cluster can be classified.

Abstract: After markings have been placed on a pre-printed form by a user who interacted with an entity, the form is scanned to produce a scan file. The scan file is analyzed to identify whether user added markings are present on machine readable selection items. The method can take a number of automated actions, depending upon which pre-printed machine readable selection items were checked by the user. For example, in response to checkbox selections, the method can obtain (read) some form of electronically storable data relating to the entity based on which of the machine readable selection items the user checked. Alternatively, in response to other checkbox selections, the method can ignore the user added markings on the machine readable selection items. In addition, in response to the checkmarks, the system can maintain only an image of the user added handwritten text.

Abstract: A technique that provides for real-time segmentation of hand written traces during data entry into a computer. In one example embodiment, this is achieved by computing a current trace bounding contour as a function of a drawn current trace. A current selection bounding contour is then computed as a function of the drawn current trace and the current trace bounding contour. The current selection bounding contour includes one or more previously drawn traces. The computed current trace bounding contour is then compared with the computed current selection bounding contour. The hand written traces including the current trace and the one or more previously drawn traces are then dynamically segmented as a function of the comparison.

Abstract: A forward pass through a sequence of strokes representing a handwritten equation is performed from the first stroke to the last stroke in the sequence. At each stroke, a path score is determined for a plurality of symbol-relation pairs that each represents a symbol and its spatial relation to a predecessor symbol. A symbol graph having nodes and links is constructed by backtracking through the strokes from the last stroke to the first stroke and assigning scores to the links based on the path scores for the symbol-relation pairs. The symbol graph is used to recognize a mathematical expression based in part on the scores for the links and the mathematical expression is stored.

Abstract: A system for line extraction in digital ink. The digital ink represents handwritten input and is comprised of a stroke sequence. The system comprises a processor configured for: receiving the digital ink from a pen device; segmenting the strokes into a sequence of substrokes; grouping substrokes about a selected substroke into a temporally preceding group of substrokes and a temporally subsequent group of substrokes; calculating a centroid for each substroke or group of substrokes; calculating angular differences between the selected substroke and its temporally neighbouring groups of substrokes; and determining positions of extrema of the angular differences. The extrema correspond to substrokes at line breaks, thereby enabling line extraction in the stroke sequence.

Abstract: A method identifying a ligature within a scanned document, the ligature including two or more touching characters. The two or more touching characters of the ligature are then compared to a plurality of prototypes to identify two or more matched prototypes. A synthetic ligature is then created based on the two or more matched prototypes.

Abstract: A method for recognition of a handwritten pattern comprising one or more curves is presented. The method comprises a step of receiving sample data representing the handwritten pattern. The method further comprises a step of segmenting the handwritten pattern by detecting segmentation points on each curve, and by dividing the handwritten pattern into segments. Further, the method comprises a step of comparing the handwritten pattern to templates wherein the comparing comprises a step of normalizing said segments according to a scheme which is independent of the templates to which the segments are to be compared, and a step of determining matching measures for selecting at least one sequence of templates representing a recognintion candidate of the handwritten pattern.

Abstract: A method for recognizing a character string on a static document is disclosed. The character string is extracted from the static document. The character string is converted into a representative character string graph. The common embedded isomorphic graphs are extracted from the representative character string graph. Each of the common embedded isomorphic graphs extracted are converted into digital ink files. The character string associated with each of the digital ink files are identified using a dynamic recognition system.

Abstract: Embodiments include a method, a manual device, a handheld manual device, a handheld writing device, a system, and an apparatus. An embodiment provides an apparatus. The apparatus includes a writing element having a first portion operable to discharge a first marking substance on a surface in response to a movement of the writing element over the surface and a second portion operable to discharge a second marking substance on the surface in response to a controller. The apparatus also includes the controller operable to encode information corresponding to a context of the apparatus by regulating the discharge of the second marking substance.

Abstract: Embodiments include a method, a manual device, a handheld manual device, a handheld writing device, a system, and an apparatus. An embodiment provides a manual device operable in a context. The manual device includes a writing element operable to form a mark on a surface in response to a movement of the writing element with respect to the surface. The manual device also includes a controller operable to encode information corresponding to the context of the manual device by regulating the formation of the mark.

Abstract: A system for line extraction in digital ink. The digital ink represents handwritten input and is comprised of a stroke sequence. The system comprises a processor configured for: receiving the digital ink from a pen device; segmenting the strokes into a sequence of substrokes; grouping substrokes about a selected substroke into a temporally preceding group of substrokes and a temporally subsequent group of substrokes; calculating a centroid for each substroke or group of substrokes; calculating angular differences between the selected substroke and its temporally neighbouring groups of substrokes; and determining positions of extrema of the angular differences. The extrema correspond to substrokes at line breaks, thereby enabling line extraction in the stroke sequence.

Abstract: A method aligns a character to a sampling grid of an image, where an outline of the character is specified by input pen commands. Points and contours of the input pen commands are determined. An orientation of each contour is determined. A first directed acyclic graph (DAG) is constructed indicating a hierarchical relationship of related contours. Radicals are determined using the first DAG. Simple segments of the contours are determined and merged independently for each radical. Segment pairs and their hinted coordinates are determined. The segment pairs are sorted and a second DAG is constructed for the sorted segment pairs. Collisions between the segment pairs are resolved using the second DAG. The segments pairs, x-free points, and y-free points are fitted to the sampling grid independently for each radical and a result of the fitting is stored in output pen commands.

Abstract: A handwriting recognition system interprets handwritten text and produces a typed interpretation of that text. When the initial interpretation of the handwritten text is inaccurate, the handwriting recognition system alters the initial recognition by reinterpreting the handwritten text in view of a correction made by a user and constraints (e.g., derived by assumptions in user behavior). The handwriting recognition system intelligently reinterprets and renews its text recognition each time the user implements a correction. In effect, a single correction can trigger multiple adjustments to the text recognition. Therefore, with the use of a reinterpretation algorithm, the handwriting recognition system helps the user obtain the desired result in fewer correction steps.

Abstract: Various technologies and techniques are disclosed for improving handwriting recognition using a neural network by allowing a user to provide samples. A recognition operation is performed on the user's handwritten input, and the user is not satisfied with the recognition result. The user selects an option to train the neural network on one or more characters to improve the recognition results. The user is prompted to specify samples for the certain character, word, or phrase, and the neural network is adjusted for the certain character, word, or phrase. Handwritten input is later received from the user. A recognition operation is performed on the handwritten input using the neural network that was adjusted for the certain character or characters.

Abstract: In certain embodiments, a method for generating fees using a receiving device, involves distributing censored video from a distributor video to a receiving device; and uncensoring the censored video using the receiving device upon payment of a fee. The receiving device uses overlay data received from the distributor to uncensor the censored video by overlaying the overlay data over the censored video using a video overlay frame to overlay a video frame containing the censored video data in accordance with boundaries determined by an alpha plane within the receiving device. This abstract should not be considered limiting since embodiments consistent with the present invention may involve more, different or fewer elements.

Abstract: A wordspotting system and method are disclosed for processing candidate word images extracted from handwritten documents. In response to a user inputting a selected query string, such as a word to be searched in one or more of the handwritten documents, the system automatically generates at least one computer-generated image based on the query string in a selected font or fonts. A model is trained on the computer-generated image(s) and is thereafter used in the scoring the candidate handwritten word images. The candidate or candidates with the highest scores and/or documents containing them can be presented to the user, tagged, or otherwise processed differently from other candidate word images/documents.

Abstract: A character recognition apparatus generates each character candidate from a character string written in a plurality of character entry boxes written on a sheet of paper such as a business form, and performs character recognition. A row image separating unit acquires an image containing a plurality of character entry boxes and the character string. A character extraction processing unit detects each point at which a plurality of lines are in contact with each other and intersect in the character string contained in the image, determines a point at which the character string should be cut or recombined on the basis of the placement relationship between the point and the corresponding character entry box, and generates each character candidate constituting the character string. A character recognition unit performs character recognition for each character candidate generated by the character extraction processing unit.

Abstract: Computer-readable media having computer-executable instructions and apparatuses detect a structured handwritten object is detected in a handwritten document. A primitive structure, which is associated with a set of component objects, is formed. A candidate handwritten object is identified by detecting a corresponding logical structure. A classifier for the candidate handwritten object is determined. Consequently, the candidate handwritten object is validated from the classifier.

Abstract: A method and system of line extraction in a digital ink sequence of handwritten text data points is provided in which a stroke sequence comprised of a sequence of strokes is obtained, the strokes are segmented into a sequence of substrokes by applying a stroke segmentation algorithm, angular differences between neighboring groups of substrokes, in the sequence of substrokes, are calculated, and the positions of the extrema of the angular differences are determined, thereby identifying the substrokes at line breaks and enabling line extraction.

Abstract: Systems and methods are disclosed that facilitate normalizing and beautifying digitally generated handwriting, such as can be generated on a tablet PC or via scanning a handwritten document. A classifier can identify extrema in the digital handwriting and label such extrema according to predefined categories (e.g., bottom, baseline, midline, top, other, . . . ). Multi-linear regression, polynomial regression, etc., can be performed to align labeled extrema to respective and corresponding desired points as indicated by the labels. Additionally, displacement techniques can be applied to the regressed handwriting to optimize legibility for reading by a human viewer and/or for character recognition by a handwriting recognition application. The displacement techniques can comprise a “rubber sheet” displacement algorithm in conjunction with a “rubber rod” displacement algorithm, which can collectively preserve spatial features of the handwriting during warping thereof.

Abstract: Computer-readable media having computer-executable instructions and apparatuses detect a table in a handwritten document. Line segments are derived from drawing strokes so that a bounding frame of a candidate table is obtained. An associated table structure is consequently recognized from the bounding frame, lines segments within the bounding frame, and their intersection points. A classifier that reflects at least one table characteristic is determined, and the candidate table is consequently validated or rejected.