Abstract: A method of enlarging an image field of a camera by combining partial images. This method includes continuously rotating at least two refractive prisms such that an optical axis of the at least two prisms scans in a cycloidal pattern. Furthermore the method includes capturing and combining a plurality of partial images. Finally, the cycloidal pattern is formed as an astroid pattern with a plurality of vertexes. The partial images are generated at the time of the reversal movement during the scanning in the astroid pattern, which limits unsharpness in the images kept to less than the size of a pixel.

Abstract: System and method for estimating a rotational shift between a first discrete curve and a second discrete curve, where the second discrete curve is a rotationally shifted version of the first discrete curve. First and second discrete curves are received. A rotational shift between the first discrete curve and the second discrete curve is estimated based on the first discrete curve and the second discrete curve. A cumulative rotational shift is updated based on the estimated rotational shift. A rotationally shifted version of the second discrete curve is generated based on the cumulative rotational shift. The estimating, updating, and generating are performed in an iterative manner using the respective rotationally shifted discrete curve for each iteration until a stopping condition occurs, thereby determining a final estimate of the rotational shift between the first discrete curve and the second discrete curve. The final estimate may be used to perform curve matching.

Abstract: An index detection unit (110) detects the image coordinates of indices from a captured image. An index allocation information updating unit (160) calculates the position and orientation of an image capturing apparatus using the image coordinates of the indices and allocation information of each of these indices. Furthermore, the index allocation information updating unit (160) re-calibrates allocation information of an unreliable index having a reliability indicating that the allocation information is unreliable. The index allocation information updating unit (160) updates allocation information held by an allocation information holding unit (140) in association with the unreliable index to the re-calibrated allocation information and a reliability indicating that the allocation information is reliable.

Abstract: A method of printing a two-dimensional barcode by tilting the print head, which results in tilted barcode, and methods of detecting various types of attempts to forge the tilted barcode including: (i) a low level forgery that consists of a simple scan and reprint of the barcode, (ii) a low level forgery that consists of a reproduction (i.e., a read and regeneration) and subsequent printing of the barcode using a printer with a non-tilted print head by a fraudster that is not aware of the tilt in the original barcode, and (iii) a higher level forgery by a fraudster that is aware of the tilt in the original barcode and that digitally tilts/shears an image of the barcode and prints the digitally tilted/sheared image using a printer with a non-tilted print head in an effort to mimic the tilt present in the legitimate barcode.

Abstract: In accordance with an image processing method, a data region is detected from input image data. The input image data is rotated in accordance with inclination of an image. Determination is made whether the data region of rotated image data protrudes from an image area of the input image data. When detection is made of protruding, the smallest area including the data region is extracted from the rotated image data. When the data region of the rotated image data protrudes from the image area of the image data previous to rotation, the smallest region including the data region of the rotated image data is extracted from the rotated image data. Therefore, loosing information from image data subjected to rotational correction can be prevented. Also, the amount of image data subjected to rotational correction can be minimized.

Abstract: A method for processing wafers includes learning a first pattern at a de-skew site on a first wafer layer, saving the first patterns in a recipe for de-skewing wafers, learning a second pattern at the de-skew site a second wafer layer, and saving the second pattern in the same recipe for de-skewing wafers. Learning the first pattern may include determining a score of uniqueness for the first pattern. The method further includes finding the de-skew site on the second wafer layer using the first pattern before learning the second pattern. Finding the de-skew site includes determining a score of similarity between the first pattern and the second pattern. Learning the second pattern is performed when the score of similarity is less than a threshold value. A recipe for de-skewing wafers includes multiple patterns of a de-skew site of a wafer, wherein the patterns include a first pattern at the de-skew site on a first wafer layer and a second pattern at the de-skew site on a second wafer layer.

Abstract: An image processing device includes an acquiring unit that acquires, from image data, processing image data having a first resolution in a first direction and a second resolution in a second direction different from the first direction; a receiving unit that receives input of a first theoretical resolution in the first direction and a second theoretical resolution in the second direction; and a tilt detecting unit that detects tilt of the image data in accordance with the processing image data and the first theoretical resolution and the second theoretical resolution.

Abstract: Method embodiments herein print a test document using a multi-function printing device to produce a printed document. This printed document is examined in a first direction to determine a first skew of the printing device. The first skew comprises a combination of raster output scanner skew and media path skew. The printed document is also examined in a second direction to determine a second skew. However, this second skew only includes the media path skew of the printing device. Once these two skews are acquired, the method can subtract the media path skew from the first skew to calculate the raster output scanner skew of the printing device.

Abstract: An image distortion correcting apparatus is provided with an image input section to input an image of a flat rectangular paper surface imaged by an imaging section, as an input image, an imaging position estimating section to estimate a relative imaging position of the imaging section with respect to the paper surface from four vertexes of the rectangular paper surface within the input image, a rectangular paper surface estimating section to estimate four vertexes of the rectangular paper surface within a three-dimensional space based on the imaging position, and an image correcting section to correct a perspective transformation distortion in the paper surface within the input image based on the imaging position and the four vertexes within the three-dimensional space, so as to output an output image.

Abstract: An image reading apparatus has a data calculation unit (31,32) to calculate moving average data and second derivative data for a plurality of samples made of multivalued data, a position detection unit (41, 42) to detect first and second positions at which the moving average data and second derivative data have a predetermined relationship, a parallel region determination unit (5) to determine a parallel region based on the first and second positions, an inclination detection unit (61 to 64) to determine inclinations based on the parallel region, and an inclination detection unit (7) to correct image data based on the inclinations.

Abstract: A calligraphy/drawing camera image-captures a document and sends a resultant captured image to a personal computer (S101). The personal computer applies various image processes such as correction of various deformations including a trapezoidal deformation based on image information obtained from the captured image, a rotation process, a cut out process, etc. to the captured image (S102 to S104). The personal computer sends the processed image to a projector (S105). The projector projects the processed image on a screen (S106). Since the captured image is corrected based on the image information obtained from the captured image, not only correction of a trapezoidal deformation but also various other corrections can be done on the captured image.

Abstract: An image reading apparatus to read image of rectangle shape document set on a setting board, is supplied capable of assigning correct edge image to an output image. In the image reading apparatus, a image data storing section stores image data reading area lager than the rectangle shape document; an edge feature extracting section extracts edge feature according to the image data; a rectangle feature extracting section extracts edge feature of side regions respectively corresponding to each side of the rectangle shape document according to the edge feature; a region selecting section selects two regions from the side regions; a coordinates calculating section calculates coordinates specifying position of straight lines representing four sides through using inclination information of the selected respective two regions; and a compounded-image outputting section replaces the feature region with frame image according to the coordinates, compounds the frame image with image data, and outputs the compounded image.

Abstract: A wireless phone is equipped with a 2D optical sensor, enabling a variety of applications. For example, such a phone may also be provided with a digital watermark decoder, permitting decoding of steganographic data on imaged objects. Movement of a phone may be inferred by sensing movement of an imaged pattern across the optical sensor's field of view, allowing use of the phone as a gestural input device through which a user can signal instructions to a computer-based process. A variety of other arrangements by which electronic devices can interact with the physical world are also detailed, e.g., involving sensing and responding to digital watermarks, bar codes, RFIDs, etc. Other novel arrangements are also detailed.

Abstract: A method for aligning a modified document and an original document is provided according to an aspect of the present invention. The method includes a step of receiving a first bitmap representative of the modified document, including a first anchor. Additionally, a second bitmap representative of the original document including a second anchor is received. The method also includes the step of deriving a set of first vertex coordinates of the first anchor, and a set of second vertex coordinates of the second anchor. The method further includes the step of transforming the first bitmap to a common reference based upon the first set of vertex coordinates, and the step of transforming the second bitmap to the common reference based upon the second set of vertex coordinates.

Abstract: A method for creating a 360 degree panoramic image from multiple images includes (1) computing a gross rotation error ?R between a first image and a calculated first image rotated to be stitched to a last image, and (2) spreading the gross rotation error ?R to each pixel on the panoramic image. Spreading the gross rotation error ?R includes (1) computing a rotation angle ?0 and rotational axis n0 from the gross rotational error ?R, (2) determining an angle ? of each pixel, and (3) determining a compensation matrix Rc for each pixel using the following formula: Rc(?)=R(?/2??0).

Abstract: An angle de-skew device and the method thereof are used in an image processing system to rotate a skewed image with respect to a reference point as a rotated center. First and second accumulator circuits respectively are used to accumulate first and second offsets for the X coordinates and Y coordinates of the first pixel in the skewed image, and respectively output the sums into the image processing system. A counter is connected to the two accumulator circuits to control the number of accumulation times.

Abstract: An apparatus and method for processing a captured image and, more particularly, for processing a captured image comprising a document. In one embodiment, an apparatus comprising a camera to capture documents is described. In another embodiment, a method for processing a captured image that includes a document comprises the steps of distinguishing an imaged document from its background, adjusting the captured image to reduce distortions created from use of a camera and properly orienting the document is described.

Abstract: Image data having a total number of pixels being H×V is written in SDRAM having an enough number of recording domains capable of storing all the pixel data of the image data and the number of Column addresses set therein at 2n (4?n) in the order of lines after the implementation of a first image rotation processing at a rotation angle of 90°×m (0?m?3) to the image data and read from the SDRAM in the order of the lines after the implementation of a second image rotation processing at a rotation angle of 90°×p (0?p?3). In doing so, the recording domains of the SDRAM are divided into a plurality of recording blocks 21-s having the number of the Column addresses set therein at 2q (2?q?(n?2) and capable of storing groups of the pixels for one line in the image data after the implementation of the first image rotation processing. The groups of the pixels for one line in the image data in an image direction after the implementation of the first image rotation processing are written in the recording blocks 21-s.

Abstract: A method of auto-deskewing a titled original image is provided. Frist, obtain an original image by scanning to acquire values of pixels in the original image. Next subject the original image to a binarization process. And, set a datum line in the original image. Then determine a tilting angle on the basis of the datum line. Finally, adjust the original image on the basis of the tilting angle. Therefore, the tilting angle of the original image may be acquired to adjust.

Abstract: A method for rotating and scaling at least a portion of an image is provided. The method consists of determining symbolically an inverse matrix of a rotation and scaling matrix, using one or more entries in the inverse matrix as variables in a scaling and rotation routine, evaluating the variables with an angle factor and a scaling factor, and using the evaluated variables to specify a location of a screen pixel corresponding to the portion of the image.

Abstract: A rotation angle detection apparatus which detects a rotation angle with respect to a reference disposition position of an object included in a detection subject image, includes: a plurality of kinds of pixel extraction pattern for extracting a plurality of pixels which detect an image feature amount from pixels configuring the detection subject image; a feature amount detector which detects, for each pixel extraction pattern, an image feature amount of the extracted plurality of pixels; a likelihood memory which stores a likelihood of the rotation angle, correlated in advance to the image feature amount, for each pixel extraction pattern; and a rotation angle determiner which determines a rotation angle which has a greatest likelihood, based on the image feature amount corresponding to each pixel extraction pattern and on the likelihood, as the rotation angle of the object.

Abstract: A method for adjusting an image projected onto a warped surface is provided. The method initiates with capturing calibration points within a calibration image projected onto the warped surface. The method includes analyzing the calibration points to determine relative locations among the calibration points. In one embodiment, the method utilizes a pseudo origin for locating beginning points for successive rows of calibration points. The calibration points are ordered according to the relative locations. The ordered calibration points may be applied to alter the image data prior to projection of the image data onto the warped surface. A system for calibrating points so that an image projected onto a warped surface does not appear as distorted is also provided.

Abstract: Methods and apparatuses for determining a skew angle of text relative to an axis are disclosed herein. One exemplary embodiment of the method comprises locating a first portion of the text that has a spatial frequency greater than a first preselected value. The method continues with locating a second portion of the text that has a spatial frequency greater than a second preselected value. A line is fitted between the first portion of the text and the second portion of the text. The angle between the line and the axis is measured, wherein the angle corresponding to the skew angle.

Abstract: A method for identifying a projection view and an orientation of a chest radiograph. The method includes the steps of: providing an input digital image of the chest radiograph; preprocessing the input digital radiographic image; classifying the view of the input digital radiographic image; and determining the orientation of the input digital radiographic image.

Abstract: The present invention is operative to determine the angular pose of an assumed object. A series of projection sums are calculated from a sample image of the known object where the known object has an assumed pose. The projection sums are calculated for a range of angles and organized into a two dimensional array coined a projection image. An image of the known object is provided where the known object has an unknown pose. A projection sum is calculated across the image of the known object with the unknown pose preferably at the perpendicular. This projection sum is correlated against the projection image and the angle corresponding to the best correlation is determined to be the angular pose of the known object.

Abstract: A reference posture and a reference position of the imaginary sphere and an arbitrary position are set. The relationship between three-dimensional coordinates and two-dimensional coordinates is derived by using a photographing means. Positions of marks given to the imaginary sphere formed at the coordinates in the three-dimensional space are converted into positions on a two-dimensional image. An operation of displacing a posture of the imaginary sphere relative to the reference posture and the reference position is performed in such a way that the coordinate values of the two-dimensional imaginary marks and the coordinate values of the marks present on the two-dimensional images of the sphere are coincident with each other. The rotational and flight characteristics of the sphere are computed, according to the three-dimensional posture and position at one time and the three-dimensional posture and position thereof at another time.

Abstract: A device and method for correcting a skew of an object in an image. The device and method comprises an input part for receiving an image; a binarization part for binarizing pixels of the image into pixels having brightness values for character pixels and background pixels; a candidate stripe generation part for generating candidate stripes by performing dilation on character regions of the binarized image. The device and method further comprises a stripe classification part for classifying candidate stripes having a predetermined eccentricity and blob size among the candidate stripes, as valid stripes; a skew angle decision part for calculating direction angles of the classified stripes, and determining a direction angle having the largest count value as a skew angle; and a skew correction part for correcting a skew of an image by rotating the mage by the skew angle.

Abstract: A method for extracting a subset of data from an ordered set of bi-dimensional matrices (data arrays) such as a sequence of pictures or a multi-dimensional matrix, for instance, is implemented by dedicated hardware that may be used each time it is necessary to extract a subset of data from a data array. For each matrix of data, the method calculates very quickly row and column indices of border data of the portion to be extracted, which are obtained by arithmetical operations among row and column indices of vertices of a closed area of interest. The method is implemented in a device for selectively transferring a data stream sampled at a certain bit-rate to a microprocessor unit or to a memory receiving the data stream at a different rate.

Abstract: An apparatus and a concomitant method for detecting and recognizing text information in a captured imagery. The present method transforms the image of the text to a normalized coordinate system before performing OCR, thereby yielding more robust recognition performance. The present invention also combines OCR results from multiple frames, in a manner that takes the best recognition results from each frame and forms a single result that can be more accurate than the results from any of the individual frames.

Abstract: Image data is scaled, rotated and/or otherwise manipulated. Diffusive effects of associated interpolation and/or re-sampling are compensated for, or corrected, by applying an adaptive packing form of error diffusion to output data of one or more manipulating transforms. For example, rank order error diffusion is applied to output data of a manipulating transform, thereby restoring compaction to otherwise diffuse halftone structures (e.g., halftone dots, lines, etc), saturated text and/or other small, high contrast image elements.

Abstract: An apparatus and method for processing a captured image and, more particularly, for processing a captured image comprising a document. In one embodiment, an apparatus comprising a camera to capture documents is described. In another embodiment, a method for processing a captured image that includes a document comprises the steps of distinguishing an imaged document from its background, adjusting the captured image to reduce distortions created from use of a camera and properly orienting the document is described.

Abstract: A construction is used in which a plurality of sets of frame information are acquired from video information, rotation amount information that expresses the rotational deviation among the images expressed by the abovementioned plurality of sets of frame information is acquired on the basis of the acquired plurality of sets of frame information, conversion processing is performed in which at least one of the abovementioned plurality of sets of frame information is converted by rotating at least one of the respective images expressed by the plurality of sets of frame information on the basis of the acquired rotation amount information so that the rotational deviation among the images is reduced, and image data that expresses images in halftones using numerous pixels is produced by synthesizing a plurality of sets of frame information on which conversion processing has been performed.

Abstract: System and method for estimating a rotational shift between a first discrete curve and a second discrete curve, where the second discrete curve is a rotationally shifted version of the first discrete curve. First and second discrete curves are received. A rotational shift between the first discrete curve and the second discrete curve is estimated based on the first discrete curve and the second discrete curve. A cumulative rotational shift is updated based on the estimated rotational shift. A rotationally shifted version of the second discrete curve is generated based on the cumulative rotational shift. The estimating, updating, and generating are performed in an iterative manner using the respective rotationally shifted discrete curve for each iteration until a stopping condition occurs, thereby determining a final estimate of the rotational shift between the first discrete curve and the second discrete curve. The final estimate may be used to perform curve matching.

Abstract: An image read controller for extracting an original portion from an image read by an image reader. The image read controller includes means for extracting a rectangular area containing the area in which the original exists from the read image, inclination detection means for detecting the inclination of the rectangular area, inclination correction means for correcting the inclination of the rectangle in response to the detected inclination, cut width setting means for setting the cut width of each side of the rectangle in response to the detected inclination, and cutting means for cutting the margins of the rectangular area based on the setup cut width of each side to extract the original image.

Abstract: A three-dimensional image data is formulated and saved in a memory for indicating a three-dimensional shape of an object and reflectivity or color at every point of the object. For each of multiple pose candidates, an image space is created for representing brightness values of a set of two-dimensional images of the object which is placed in the same position and orientation as the each pose candidate. The brightness values are those which would be obtained if the object is illuminated under varying lighting conditions. For each pose candidate, an image candidate is detected within the image space using the 3D model data and a distance from the image candidate to an input image is determined. Corresponding to the image candidate whose distance is smallest, one of the pose candidates is selected. The image space is preferably created from each of a set of pose variants of each pose candidate.

Abstract: Systems and methods for automatically extracting form information (document structure, elements, format, etc.) from electronic documents such as raster-based passive documents, and storing such form information in a file in accordance with a predetermined DTD (document type definition).

Abstract: The camera includes a sensor for sensing the photographer's iris image and registering the image in advance. The iris image is recorded in the image of a subject by a digital MCU at a timing different from that at which the image of the subject is captured. The recording timing is that at which the camera power supply is turned off, that at which a recording medium is ejected from the camera or that at which the iris image to be recorded is changed to the registered iris image of another photographer. The recording of the iris image is achieved by embedding it as a watermark or by appending it to metadata.

Abstract: The present invention includes a method to use a phase modulating micromirror array to create an intensity image that has high image fidelity, good stability through focus and good x-y symmetry. Particular aspects of the present invention are described in the claims, specification and drawings.

Abstract: A method of determining the orientation of text is disclosed herein. An embodiment of the method may comprise measuring the contrasts associated with an upper edge of the text relative to a background. A first length of the upper edge of text having contrasts that are at least a first preselected value is measured. In addition to measuring the contrasts associated with the upper edge of the text, contrasts associated with a lower edge of the text are measured relative to the background. A second length of the lower edge of text having contrasts that are at least the first preselected value is then measured. The first length is compared to the second length, wherein the text is improperly oriented if the first length is greater than the second length.

Abstract: The present invention relates to a method for determining the orientation of text, so that the text can be correctly read. In one embodiment, the method analyzes the “open” portions of text characters to determine in which direction the open portions face. By determining the respective densities of characters opening in each direction (e.g., right or left), the method can establish in which direction the text as a whole is orientated. The present invention may be adapted for use in automated mail processing, to determine the orientation of checks in automated teller machine envelopes, or the orientation of scanned or copied documents, or documents sent via facsimile, or to determine the orientation of digital photographs that include text (e.g., road signs, business cards, driver's licenses, etc.), among other applications. A fast, substantially automatic determination of text orientation according to the present invention will reduce the labor expense and processing delay required for manual orientation.

Abstract: The present invention relates to an imaging system for obtaining an image correctable for the presence of a gravity induced image error. The imaging system includes an imager to obtain an image of an object and a position measurement device to obtain position data indicative of a gravity-induced deformation of the imager. The position data may include gravity vector data indicative of an orientation of a gravity vector.

Abstract: Skew angle in a document image is estimated using operators known from mathematical morphology. Skew angle in a document image (A) is estimated by run-length smoothing the image and then producing a plurality of eroded run-length-smoothed images. The run-length-smoothed image (RLSA(A)) is eroded using a linear structuring element (k2L?) oriented at each of a plurality of different angles (?). The angle of the linear structuring element which produces an eroded image having the greatest surface area is designated as the skew angle. A plurality of run-length-smoothed images (RLSA?(A)) may be produced, each generated by smoothing the document image using a linear structuring element (k1L?) oriented at a respective different angle (?i). Then each run-length smoothed image (RLSA?(A)) is eroded using a linear structuring element oriented at the corresponding angle (?i).

Abstract: In methods, systems, and computer program products for locating a regularly configured object within a digital image, a plurality of primary rotated integral images of the digital image are computed. Each primary rotated integral image has a different in-plane rotation. A set of secondary rotated integral images are derived from each of the primary rotated integral images. The secondary rotated integral images have further in-plane rotations relative to the respective primary rotated integral image. A window is defined within the digital image and corresponding windows of the rotated integral images. The values of convolution sums of a predetermined set of feature boxes within the window, in each of the rotated integral images are extracted. The dimensionality of the convolution sums is reduced to provide a set of reduced sums. A probability model is applied to the reduced sums to provide a best estimated derotated image of the window.

Abstract: A first direction determining unit determines, with respect to each of directions in image data corresponding to an image that contains text, a degree of certainty that the direction corresponds to a predetermined direction of the image to obtain a first direction with the highest degree of certainty and a second direction with the second-highest degree of certainty. When the first direction is opposite to the second direction, a second direction determining unit determines whether the predetermined direction corresponds to the first direction or the second direction based on a position of a text line extracted from the image data.

Abstract: The image processing apparatus extracts edge pixels of an input image, connects the edge pixels so as to extract a segment, extracts an inclination angle of the image based on the segment, corrects an inclination of the image based on the angle, determines that correction has ended when the corrected inclination is equal to or less than a predetermined threshold value, and repeats inclination extraction, inclination correction and end determination using an output image obtained after the inclination correction as a new input image until it is determined that correction has ended.

Abstract: In an image stitcher for arranging a plurality of images to be stitched in m rows and n columns (both m and n are natural numbers) on a monitor screen such that their respective arrangement positions conform to an actual relative positional relationship, to stitch all the images utilizing information related to the arrangement position of each of the images, the image stitcher comprises means for displaying on the monitor screen an image arrangement pattern selection screen including a plurality of types of image arrangement patterns for arranging the plurality of images to be stitched in m rows and n columns on the monitor screen, means for causing a user to select one of the plurality of types of image arrangement patterns on the image arrangement pattern selection screen, and means for arranging the plurality of images to be stitched in m rows and n columns on the monitor screen in accordance with the image arrangement pattern selected by the user.

Abstract: A projector includes a projection section which projects an all-white image and an all-black image onto a screen, a sensor which generates first sensing information by sensing the all-white image and generates second sensing information by sensing the all-black image, a differential image generation section which generates a differential image based on the first and second sensing information, an external light effect removal section, and a projection target area detection section which generates projection target area information on the position of a projection target area corresponding to the screen in the sensing area of the sensor based on the differential image from which the external light effect is removed.

Abstract: A three-dimensional image data is formulated and saved in a memory for indicating a three-dimensional shape of an object and reflectivity or color at every point of the object. For each of multiple pose candidates, an image space is created for representing brightness values of a set of two-dimensional images of the object which is placed in the same position and orientation as the each pose candidate. The brightness values are those which would be obtained if the object is illuminated under varying lighting conditions. For each pose candidate, an image candidate is detected within the image space using the 3D model data and a distance from the image candidate to an input image is determined. Corresponding to the image candidate whose distance is smallest, one of the pose candidates is selected. The image space is preferably created from each of a set of pose variants of each pose candidate.

Abstract: A method for determining the orientation of a digital image, includes the steps of: employing a semantic object detection method to detect the presence and orientation of a semantic object; employing a scene layout detection method to detect the orientation of a scene layout; and employing an arbitration method to produce an estimate of the image orientation from the orientation of the detected semantic object and the detected orientation of the scene layout.

Abstract: A method and apparatus for correcting for a distortion in a mammogram. The method comprises classifying pixels as either likely fat or likely not-fat. The method further comprises identifying a candidate distortion and calculating a histogram of the likely fat and the likely not-fat pixels at the candidate distortion. The method further comprises evaluating a quality of the candidate distortion based on features of the histograms of pixel values in the fat and dense tissue classes. The distortion may be a two dimensional tilt of the plates or a three dimensional deformation of the plates as in a bend.