Abstract: A method, a computer program product, and a computer system compare images for content consistency. The method includes receiving a first image including a first document and a second image including a second document. The method includes performing a visual classification analysis on the first image and the second image. The visual classification analysis generates an overlap of the first image with the second image. The method includes determining whether a region of the overlap is indicative of a content inconsistency. As a result of the region of the overlap being indicative of a content inconsistency, the method includes performing a character recognition analysis on a first area of the first image and a second area of the second image corresponding to the region of the overlap to verify the content inconsistency.

Abstract: In one embodiment, a system receives an image depicting a line of text. The system segments the image into two or more fragment images. For each of the two or more fragment images, the system determines a first hypothesis to segment the fragment image into a first plurality of grapheme images and a first fragmentation confidence score. The system determines a second hypothesis to segment the fragment image into a second plurality of grapheme images and a second fragmentation confidence score. The system determines that the first fragmentation confidence score is greater than the second fragmentation confidence score. The system translates the first plurality of grapheme images defined by the first hypothesis to symbols. The system assembles the symbols of each fragment image to derive the line of text.

Abstract: A method for sharing content is provided. An image of content is obtained. An address is generated based on the image using a set of predefined rules. The address is associated with the content. The content is provided to a computing device in response to the computing device accessing the address.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program and a method for rendering virtual modifications to real-world environments depicted in image content. A reference surface is detected in a three-dimensional (3D) space captured within a camera feed produced by a camera of a computing device. An image mask is applied to the reference surface within the 3D space captured within the camera feed. A visual effect is applied to the image mask corresponding to the reference surface in the 3D space. The application of the visual effect to the image mask causes a modified surface to be rendered in presenting the camera feed on a display of the computing device.

Abstract: Disclosed is an object detection method and a system thereof. The object detection method for detecting an object, the method comprising the steps of: extracting line segments from an image in which a detection target is displayed, by an object detection system, generating merged line segments on the basis of directionality of each of the extracted line segments, by the object detection system, specifying candidate outer lines corresponding to outer lines of the object on the basis of a line segment set including the generated merged line segments, by the object detection system; and specifying the candidate outer lines as the outer lines of the object on the basis of whether or not the specified candidate outer lines correspond to appearance attributes of the object, by the object detection system.

Abstract: A structured document analyzer that associates keys and values in structured documents based on key, value, and key-value container bounding boxes. A trained machine learning model analyzes images of structured documents to determine bounding boxes for keys, values, and key-value containers in the images with confidence scores for the classifications. For each image, duplicate bounding boxes are removed, and then a set of key-value containers are selected and sorted based on the confidence scores. For each key-value container, a best key and value are determined for the container based on overlap of the key and value bounding boxes with the container bounding box and the confidence scores. Optical character recognition may be performed on the image to determine text for the keys and values.

Abstract: A robust string text detection and recognition system is provided to improve the reading performance of sliding-window based OCR solutions (such as histogram of oriented gradient (HOG) OCR and convolutional neural network (CNN) OCR). A search algorithm is created that is robust enough to detect outliers and false detections. A general Text Search algorithm structure is created allows the specification of different constraints/assumptions to guide the search in multiple text lines detection and recognition.

Abstract: Disclosed are OCR-based system and method for recognizing a map image. The system for map recognition comprise a recognition unit for recognizing text on an inputted image by means of a text recognition technology; a search unit for searching, in a database comprising toponym data, for a toponym corresponding to the text; and a provision unit for providing map information comprising the toponym as a result of the recognition of the inputted image.

Abstract: Systems and methods for computationally efficient and precise transformation recovery using two image frames are provided. A key image frame and a tracked image frame are selected from a series of image frames, a plurality of points on the key image frame are selected, and the plurality of points are then projected onto the tracked image frame to produce a number of corresponding points. Then, for each corresponding point, a patch of pixels is defined centered on the corresponding point. Each pixel of the patch is reprojected back onto the key image frame to identify a reprojected pixel in that image frame. An intensity value for each reprojected pixel is determined and each patch is parameterized. A normal equation for each patch is determined and then solved for the transformation.

Abstract: System, method, and computer product embodiments for efficiently casting interactively-controlled visual content displayed on a first display screen to a second display screen. In an embodiment, the computing device sends the visual content displayed on the first display screen to a multimedia device for displaying on the second display screen. Upon receipt of an instruction that visually manipulates how the visual content is displayed on the first display screen, the computing device generates a command representative of the received instruction. The command may specify a positional relationship between the center of the first display screen and the visual content displayed on the first display screen. Then, the computing devices sends the command to the multimedia device that causes the second display screen to display the visual content according to the positional relationship.

Abstract: The present disclosure relates to a system and a method for detection of touching characters in a media, characterized by segmentation of adjoining character spaces. In the very first step, an aspect ratio is calculated for each connected component. A candidate touching position of each character is determined by calculating a threshold aspect ratio for each character. Further, a candidate cut column is determined based on a relation between column pixel densities and corresponding length thereof the column in order to segment the touching characters at the candidate cut column.

Abstract: The current application is directed to methods and systems that convert document images, which contain Arabic text and text in other languages in which symbols are joined together to produce continuous words and portions of words, into corresponding electronic documents. In one implementation, a document-image-processing method and system to which the current application is directed employs numerous techniques and features that render efficiently computable an otherwise intractable or impractical document-image-to-electronic-document conversion. These techniques and features include transformation of text-image morphemes and words into feature symbols with associated parameters, efficiently identifying similar morphemes and words in an electronic store of standard-feature-symbol-encoded morphemes and words, and identifying candidate inter-character division points and corresponding traversal paths using the similar morphemes and words identified in the word store.

Abstract: For removing connective strokes, code identifies two connective points in a contiguous written input from a written input device. Each connective point is identified in response to a connective score for the connective point exceeding a connective threshold. The code further removes a connective stroke between the two connective points from the contiguous written input.

Abstract: A font recognition section recognizes a font of characters depicted by character image data included in image data upon first character data corresponding to the character image data being acquired through character recognition. A font character recognition section compares the character image data to font character image data depicting characters in the recognized font and acquires second character data corresponding to font character image data when the font character image data matches the character image data. A recognized character determination section determines whether or not the first character data matches the second character data, and when determining that the first character data does not match the second character data, adopts the second character data, instead of the first character data, as recognized character data for the character image data.

Abstract: The present invention relates to an apparatus for recognizing a gesture in a space. In accordance with an embodiment, a spatial gesture recognition apparatus includes a pattern formation unit for radiating light onto a surface of an object required to input a gesture in a virtual air bounce, and forming a predetermined pattern on the surface of the object, an image acquisition unit for acquiring a motion image of the object, and a processing unit for recognizing a gesture input by the object based on the pattern formed on the surface of the object using the acquired image. In this way, depending on the depths of an object required to input a gesture in a space, haptic feedbacks having different intensities are provided, and thus a user can precisely input his or her desired gesture.

Abstract: A system and method for image enhancement associated with scan generators is provided. For example, a source stimulates a device under test (DUT) at electrical interconnects. An internal clock of the DUT is synchronized with the scan rate of the source to reduce the noise of the output signal and enhance a resultant image. A phase adjustment is effected to further reduce the noise in the signal. The synchronization and the phase adjustment seek to ensure that the data is collected at uniform times relative to the reference signal and thereby reduce the noise introduced into the system, by such offsets. Post-scan processing increases the signal-to-noise ratio through averaging techniques. Using a pixel overlay algorithm the averaged data is transformed into a 2-D array and the image of the DUT reconstructed.

Abstract: Provided is a table recognizing method, comprising: parsing and analyzing metadata information in an original fixed-layout document, and extracting basic elements on a page of the document; segmenting the basic elements, extracting segmented text lines on the page, and acquiring fragments; constructing an undirected graph with respect to each of the fragments; extracting an image on the page, detecting intersection points of horizontal lines and vertical lines, detecting an external bounding box of the intersection points, and taking whether the segmented text lines fall within the external bounding box as local relationship features; training a learning model according to the local relationship features, local features of the fragments, and neighborhood relationship features among the fragments, acquiring model parameters, and establishing a table recognizing model; and invoking the table recognizing model to perform table recognizing for the document, and acquiring a recognizing result.

Abstract: An image processing apparatus includes a reception unit, a determination unit, a handwriting separation unit, an image generation unit, an image recognition unit, and an output unit. The reception unit receives handwriting information. The determination unit determines whether first handwriting indicated by first handwriting information and second handwriting indicated by second handwriting information overlap each other on the basis of the handwriting information. The handwriting separation unit separates the first handwriting from the second handwriting by changing a first/second handwriting position in the first/second handwriting information when the determination unit has determined that the first and second handwriting overlap each other. The image generation unit generates an image from handwriting information obtained through the separation, and information regarding handwriting that has been determined not to overlap other handwriting. The image recognition unit recognizes the generated image.

Abstract: A method of recognizing and generating a structure of a table included in an image is provided. The method includes extracting lines forming the table from among connection components forming an image, determining line intersections by using crossing functions matched with the lines, determining one of a plurality of crossing models identified based on a plurality of crossing shapes, in correspondence with each of the line intersections, and generating data about the table, which includes at least one cell determined using the determined crossing model.

Abstract: A system and methods for progressive feature evaluation of an electronic document image to identify user supplied elements is disclosed. The system includes a controller in communication with a storage device configured to receive and accessibly store a generated plurality of candidate images. The controller is operable to analyze the electronic document image to identify a first feature set and a second feature set, wherein each of the first and second feature sets represents a different form feature, compare the first feature set to the second feature set, and define a third feature set based on the intersection of the first and second feature sets, wherein the third feature set represents the user provided elements.

Abstract: An inkjet printing apparatus which performs printing by performing scanning using a print head has a problem in that quality of an image of a ruled line is degraded when ink is not ejected for a certain period of time. To address this problem, control is performed such that power for driving the print head for unit regions including pixels having a ruled-line attribute becomes higher than power for driving the print head for unit regions which do not include the pixels having the ruled-line attribute. By this, a high-quality ruled-line image may be printed.

Abstract: A city directory, having a listing of names and associated information of residents in a city (or similar location), is digitized. Zones of text having information not useful to users of the digitized directory are removed, and lines of information corresponding to residents are reconstructed, to make the digitized directory more easily accessed and reviewed.

Abstract: The present disclosure relates to a system and a method for detection of touching characters in a media, characterized by segmentation of adjoining character spaces. In the very first step, an aspect ratio is calculated for each connected component. A candidate touching position of each character is determined by calculating a threshold aspect ratio for each character. Further, a candidate cut column is determined based on a relation between column pixel densities and corresponding length thereof the column in order to segment the touching characters at the candidate cut column.

Abstract: According to one embodiment, an electronic apparatus includes a display processor, and a correction calculator. The display processor is configured to display strokes corresponding to coordinates of loci of contact points on a display. The correction calculator is configured to calculate a correction direction and a correction quantity to correct a coordinate, by using a position of a first handwritten character recognizable from the strokes and a position of a second handwritten character recognizable from the strokes.

Abstract: A printer driver for generating print job data to be transferred to a printer in response to a drawing instruction determines, based on combining condition, whether the received drawing instruction can be combined with another drawing instruction. If the printer driver determines that the received drawing instruction can be combined, the printer driver stores the received drawing instruction as intermediate data. If the printer driver determines that the received drawing instruction cannot be combined, the printer driver combines intermediate data of already stored drawing instructions into a single item of print job data and outputs the print job data to the printer. The combining condition is that the received drawing instruction meets all of three conditions.

Abstract: A graphics or image rendering system, such as a map image rendering system, receives image data from an image database in the form of vector data that defines various image objects, such as roads, geographical boundaries, etc., and textures defining text strings to be displayed on the image to provide, for example, labels for the image objects. The imaging rendering system renders the images such that the individual characters of the text strings are placed on the image following a multi-segmented or curved line. This rendering system enables text strings to be placed on a map image so that the text follows the center line of a curved or angled road or other image feature without knowing the specifics of the curvature of the line along which the text will be placed when creating the texture that stores the text string information.

Abstract: In one embodiment, a method is disclosed for performing a video processing. The method can extract one or more common video segments. The method can select a common summarization segment based on a first summarization score. The method can extract one or more individual video segments in which the number of segments included therein is not more than a third threshold value that is less than a second threshold value. The method can select an individual summarization segment based on a second summarization score. In addition, the method can integrate the common summarization segment and the individual summarization segment to create the summary video.

Abstract: An image processing apparatus extracts a line segment included in an image, and includes a density gradient direction determining section that determines a direction, in which density changes, of each processing unit composed of a predetermined number of pixels of an image, and an line segment extracting section that regards a couple of processing units whose density gradient direction are opposite each other as a processing unit pair and extracts a processing unit group including a plurality of processing unit pairs allocated in a row in a direction perpendicular to the density gradient directions as a line segment.

Abstract: A method and apparatus for encoding an image is provided. An image coding unit, including a region that deviates from a boundary of a current picture, is divided to obtain a coding unit having a smaller size than the size of the image coding unit, and encoding is performed only in a region that does not deviate from the boundary of the current picture. A method and apparatus for decoding an image encoded by the method and apparatus for encoding an image is also provided.

Abstract: Disclosed is a character recognition preprocessing method and apparatus for correcting a nonlinear character string into a linear character string. A binarized character string region is divided into character regions on a character-by-character basis. Upper and lower feature points of each character region are derived, and an upper boundary line, which is a curve connecting the upper feature points of the character regions, and a lower boundary line, which is a curve connecting the lower feature points of the character regions, are generated by applying cubic spline interpolation. Nonlinearity is corrected through adaptive region enlargement by using the maximum horizontal length and the maximum height of the divided character regions.

Abstract: A computer implemented that, in various aspects, transforms a grayscale image into an OCR image by applying a combination of steps to the grayscale image is disclosed herein. The grayscale image may include one or more alphanumeric characters. The grayscale image may includes visual content displayed upon a computer screen, so that the grayscale image may have a resolution generally equivalent to a screen resolution of the computer screen prior to application of the combination of steps thereto. The resultant OCR image, in various implementations, is of sufficient resolution and quality that an OCR engine can generally recognize alphanumeric characters imbedded within the OCR image.

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: Systems, methods and computer program products on storage devices for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process. The output of an OCR process is classified into a plurality of clusters of clip images and a representative image for each cluster is generated to identify clusters whose clip images were incorrectly assigned character codes by the OCR process.

Abstract: Before page description data are input to a raster image processor (RIPa) that plots an overprint of a shading object in process colors in the nonzero overprint mode, the page description data are converted into robustized page description data wherein minimum values of process colors are replaced with small values which are not of 0. The robustized page description data are input to the RIPa.

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

Abstract: An image processing apparatus is provided that includes a character chopper component that segments words into individual characters in a bitmap of a textual image undergoing an OCR process. The Character chopper component is configured to produce a set of (possibly curved) chop-lines which divide a bitmap of any given word into its individual character or glyph candidates. Cases where an input bitmap contains two separate words are handled by marking a place where those words should be split. The character segmentation algorithm computes the set of vertically oriented, curved chop-lines by considering glyph and background colors in a given word bitmap. The set is filtered afterwards using various heuristics, in order to preserve those lines that indeed do separate a word's glyphs and minimize the number of those that do not.

Abstract: When generating outline data, the contour pixels of the binarized image data are first extracted. Based on the extracted contour pixels, the contour of the image data is approximated to a straight line. In the straight-line approximation process, the distance between adjacent contour pixels among the extracted contour pixels is calculated. It is determined based on the result of the comparison between the length of the first straight line and the length of the second straight line whether the first straight line is used as a contour of the image data. The first straight line connects the first contour pixel and the second contour pixel adjacent to the first contour pixel. The second straight line connects the second contour pixel and the third contour pixel adjacent to the second contour pixel.

Abstract: A touch sensing system including a touch input interface and a capacitance sensing circuit is provided. The touch input interface includes a plurality of sensing capacitors for outputting a capacitance under test and a reference capacitance. The capacitance sensing circuit includes a first sensing channel, a second sensing channel, and a difference comparing unit. During a first period of the sensing period, the first sensing channel senses the capacitance under test, and the second sensing channel senses the reference capacitance. During a second period of the sensing period, the first sensing channel senses the reference capacitance, and the second sensing channel senses the capacitance under test. The difference comparing unit outputs a difference according to the capacitance under test and the reference capacitance. Additionally, a capacitance sensing method is also provided.

Abstract: A method and system for preprocessing an image, wherein the image includes a plurality of columns, or regions, of text is disclosed. A plurality of components associated with the text is determined. On determining the plurality of components, a line height and a column spacing is determined for the components. The components are then associated with a column based on the line height and the column spacing. A set of characteristic parameters are calculated for each column and the plurality of components of each column are merged based on the characteristic parameters to form sub-words and words. A first plurality of words and/or subwords is merged and processed as a first region and a second plurality of words and/or subwords is merged and processed as a second region wherein at least a portion of the second region vertically overlaps at least a portion of the first region.

Abstract: An electronic document producing device has a correcting unit for correcting distortion of a first image to obtain a correction image, and a character recognition unit for executing character recognition processing on a plurality of character images contained in the correction image to obtain text data. The device also has a unit for finding a base line of each character row in the first image, and a unit for finding a relative position from the base line in regard to each character image in the first image. The device also includes a producing unit for producing an electronic document including the text data and the first image, wherein a position of the text data is described based on the relative position from the base line.

Abstract: An image processing apparatus for performing image processing for a plurality of band areas obtained by dividing image data is provided. The apparatus includes a dividing unit configured to divide the image data such that each of the plurality of band areas has an area overlapping an adjacent band area, and an image processing unit configured to perform the image processing for the band areas with respect to each of a plurality of planes that constitute the image data. A processing range within a band area used in the image processing by the image processing unit differs between at least two planes among the plurality of planes.

Abstract: An image generating device and a method thereof are disclosed in the present invention. The image generating device and method may find out true motion for static text strings. The image generating device and method detect static text angles from consecutive frames and use a 3D-static text filter to recover correct motion vector fields. After our Static Text Detector fixing, the static text strings like subtitles can get more accurate motion vector and improve video quality.

Abstract: Method for converting at least one image of a first spectrum into an image of a second spectrum, comprising: —recording at least one first-spectrum reference image (NRI) of at least one reference scene (RS) with a first-spectrum recording apparatus (1), the first-spectrum reference image (NRI) comprising first image portions with corresponding first-spectrum sensor reference data (b1, b2); —providing corresponding second-spectrum reference information (RGB); —providing at least one set of reference data (T1, T2) from at least part of the first-spectrum sensor reference data (b1, b2) relating to the reference scene (RS), and at least a corresponding part of the second-spectrum information (RGB) relating to that reference scene (RS); —providing at least one target first-spectrum image (NTI) or target second-spectrum image; and —converting each target first-spectrum image (NTI) or target second-spectrum image into a respective second-spectrum image (CI) or first-spectrum image, respectively, using the set of ref

Abstract: A method of identifying stricken-out characters in handwriting, comprising parsing a scanned image into regions and objects, defining objects containing handwritten characters, applying structural or feature classifiers for primary character recognition, applying one or more supplemental feature classifiers preliminarily trained by strike-out characters, and identifying a stricken-out character if any. The stricken-out character may be further examined by special procedures, either automated or manual.

Abstract: Methods and systems for processing an image to create an object model are disclosed. In accordance with one embodiment, each segment of the image is assigned to a respective bin of a bounding box. For each bin of the bounding box, the value of a feature for the bin is computed based on the values of that feature for each of the segments assigned to the bin. An object model is then created based on the values of the feature for the bin.

Abstract: A method is provided for authenticating an image printed at a predefined print resolution or in accordance with a predetermined print grid. The method includes the steps of scanning the image to produce digital data and segmenting the data into first and second groups corresponding, respectively, to first and second predefined sections of the image. Next, a determination is made concerning the anticipated spatial position of select columns of digital data from each of the first and second groups of data. By examining the data, differences may be identified between the anticipated and actual spatial position of the columns, to determine the authenticity of the image. The identified differences which may include (i) a rotary/linear displacement in the actual spatial position of the select columns. (ii) a change in beat frequency between sections of the image, and/or (iii) a phase shift in a beat frequency.

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: A graphics or image rendering system, such as a map image rendering system, receives image data from an image database in the form of vector data that defines various image objects, such as roads, geographical boundaries, etc., and textures defining text strings to be displayed on the image to provide, for example, labels for the image objects. The imaging rendering system renders the images such that the individual characters of the text strings are placed on the image following a multi-segmented or curved line.

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 font reproduction in electronic documents are provided. The method includes: receiving an image of a printed document; extracting pairs of consecutive characters from the image of the printed document; storing the extracted pairs as images of the characters; and reproducing the printed document as an electronic document with text of overlapping extracted character pair images. Extracting pairs of consecutive characters includes extracting adjacent horizontal characters, extracting spaced horizontal characters, and extracting spaced vertical characters. Reproducing the printed document as an electronic document includes reproducing the spacing between words and between lines using the spaced horizontal characters and the spaced vertical characters as anchors in the reproduced document.