Abstract: A region of the eyes in an image of the face photographed by a camera 1 and input to an image input means 2 is specified by an eye-region determining means 8. The image of the eyes in the eye region is binarized by an eye-image binarizing means 9. The coordinates of the binarized image are rotated by a coordinate rotating means 10 to obtain an adequate correlation coefficient. The image of the eyes, the coordinates of which have been rotated, is used in a calculation which is performed by a correlation calculating means 11. In accordance with an obtained correlation coefficient, an opening/closing determining means 12 determines whether the eyes are opened or closed.

Abstract: During the printing process, print skew can result from skewed delivery of paper or other sheet media to the print engine or print cartridge. Skew can include a left-right translation component and a rotational component. For example, the leading left comer may be translated to the right and the document rotated counterclockwise about that comer. To solve this problem, a sensor array identifies the left-right translation of a leading comer of the print media, and determines a degree of rotation of the print media about that comer by measuring the leading edge. Using this information, an algorithm maps the print information to compensate for the skew. The mapped print information results in resampled print information, as indicated by the print media's translation and rotation. Accordingly, the print engine prints text and other print images that are not skewed with respect to the print media.

Abstract: The size and orientation of a document are detected by determining the length in the horizontal scanning direction and the length in the vertical scanning direction of the document to be read through a reader. According to the detection result, it is determined whether the image of the document needs to be rotated or not so as to satisfy a condition where a shortest dimension among the transmittable widths in the horizontal scanning direction, at which no part of the image is missing, occurs and the dimension in the vertical scanning direction is minimized. According to the determination result, the document image which has been read through the reader is registered in an image memory and the registered image data is read out to transmit it to a receiver through a telephone line.

Abstract: A method for automatically cropping, rotating, and scaling a scanned image to ensure that a printed copy of the scanned image is the same size as the original, when possible. The method attempts to honor the default or operator designated orientation of the printed image, but will automatically rotate the image if that will eliminate unnecessary image reduction. Optimal orientation and scaling factors are automatically determined based on the target page size and the size and shape of the information of interest in the original image (not the boundaries of the original document). The operator selects a desired printed orientation (or accepts a default orientation) and selects a desired printed paper size (or accepts a default printed paper size). If an image will fit within the printable margins without rotation or cropping, the image is simply printed without modification. If the image will fit without rotation by cropping white space, then white space is cropped.

Abstract: A method of stabilizing and registering a video image in multiple video fields of a video sequence provides accurate determination of the image change in magnification, rotation and translation between video fields, so that the video fields may be accurately corrected for these changes in the image in the video sequence. In a described embodiment, a key area of a key video field is selected which contains an image which it is desired to stabilize in a video sequence. The key area is subdivided into nested pixel blocks and the translation of each of the pixel blocks from the key video field to a new video field is determined as a precursor to determining change in magnification, rotation and translation of the image from the key video field to the new video field.

Abstract: A column address is decoded by each column decoder, and an arrangement of pixels to be written to a memory cell array is rotated by a rotation circuit. The rotation result is written to the memory cell array in accordance with the decoding result of the column address. Then, the column address is decoded by each column decoder to a decoding result which is different from the decoding result of the column address at the time of writing. In accordance with the decoding result, pixels stored in the memory cell array are read. The arrangement of the read pixels is rotated by the rotation circuit and then outputted. Thus, rearrangement of pixels constituting an image can be carried out quickly while avoiding any increase in the size of the device.

Abstract: The present invention concerns a method for evaluating a scale factor and a rotation angle in image processing and more particularly digital image processing. The method includes the steps of first providing an input image, and then reducing the input image to provide a smaller image. The smaller image is scaled according to a plurality of factors to produce a plurality of scaled images and is also rotated according to a plurality of factors to produce a plurality of rotated images. The scaled images in the rotated images are then placed into a mosaic which is arranged by scale and rotation. A referenced template is provided and the referenced template is correlated with the mosaic of scaled and rotated images to provide a scale factor and a rotation angle based on the position in the mosaic of the high score relation value between the reference template and the scaled and rotated images. The method is more efficient in that it reduces the amount of computations required to obtain useful results.

Abstract: There is disclosed an image processing device capable of receiving an image file having a first texture representation in rotation variant format and converting the texture representation to a modified texture representation in a rotation invariant format. The image processing device comprises an image processor for analyzing rotation variant texture parameters in the first texture representation and converting them to 1) rotation invariant texture parameters disposed in circular rings about a selected pixel; or 2)rotation invariant texture parameters disposed along radial lines extending through the selected pixel. In the second embodiment, the image processor can use the angular separation of the radial lines to determine the angular rotation of a rotated version of the image file.

Abstract: A region extraction apparatus for extracting a desired region from a moving image, includes a region specifying unit for specifying contour points of a region which is to be extracted, a template creating unit for creating a template of the region which is to be extracted based on the contour points of the region specified by the region specifying unit, a template matching unit for matching the template created by the template creating unit and the moving image, and a template correcting unit for correcting the template depending on a matching result obtained by the template matching unit.

Abstract: A method of image processing is provided, the method including acquiring a digital image having a three-dimensional shadow, determining a boundary of the three-dimensional shadow, and lightening the three-dimensional shadow within the boundary.

Abstract: Image rotations of 90°, 180° and 270° and horizontal and vertical mirroring image transformations are performed losslessly and with greatly enhanced speed by processing orthogonal transform coefficients in a zig-zag order with direct storage of S (size) values, reassociated R (run of zero valued coefficients) from an adjacent coded orthogonal transform value and a non-zero valued transformation coefficient in reverse zig-zag order. Cache misses are avoided by processing values which are not widely separated in the coded data and other features of the technique and memory accesses are reduced to accelerate processing while extremely little computation is required. These effects are substantially augmented when intermediate codes having certain attributes including coding of zero valued coefficients and flagging certain code features are employed.

Abstract: Methods are provided for use with a computing device and an image scanning device. One method includes performing a scan to produce a preview scanned image, selecting a portion of the preview scanned image for final scanning, and scanning the selected portion of the preview scanned image to produce a final scanned image. Performing the scan to produce the preview scanned image may include performing an autocrop process and a deskew process before displaying the preview scanned image to the user. Once the preview scanned image is displayed, then the user may decide to selectively rotate the preview scanned image, for example, about an anchor point that was used in the deskew process. The user may also select a portion of interest within the image. Once the user is satisfied with the user selected rotation, if any, and the user selected portion of interest, then a final scan will be performed. As part of the final scan process, the method includes calculating an effective portion of the preview scanned image.

Abstract: A method for deskewing a scanned text image is disclosed. The method comprises the steps of: a) determining a first intensity level for each line of the image with the image in an original position; b) determining which of the lines has a highest intensity level and which of the lines has a lowest intensity level; c) adding a relaxation factor to the lowest intensity level to establish a lower threshold; d) subtracting the relaxation factor from the highest intensity level to establish an upper threshold; e) determining a first value equal to a sum of lines having a first intensity level above the upper threshold and lines having a first intensity level below the lower threshold; f) rotating the image by a first amount in a first direction to a first position; In one embodiment, the relaxation factor is ten percent.

Abstract: A system for generating a warped contone image that compensates for beam scan trajectory distortions. The system includes an image buffer for storing a portion of a received contone image. An interpolation coefficient generator provides interpolation coefficients associated with a warped pixel within the warped contone image in response to an input identifying the warped pixel. A pixel interpolator is coupled to the image buffer and the interpolation coefficient generator and provides an output signal that identifies the warped pixel within the warped contone image. The pixel interpolator further retrieves pixels from the contone image stored in the image buffer using the interpolation coefficients and generates the warped pixel by combining the retrieved pixels into a single pixel value.

Abstract: An image is rotated in opponent color space, such as L*a*b* or Y CB CR color space, by inputting the opponent color space image data, subsampling the opponent color space image data, and addressing the subsampled opponent color space image data into an output configuration corresponding to a specified rotation angle. For 90° and 270° rotation, the opponent color space image data is scaled before being addressed. This eliminates distortion of the rotated image, while allowing real-time rotation of the image in hardware.

Abstract: A system and method for accurately mapping between camera coordinates and geo-coordinates, called geo-spatial registration. The system utilizes the imagery and terrain information contained in the geo-spatial database to precisely align geographically calibrated reference imagery with an input image, e.g., dynamically generated video images, and thus achieve a high accuracy identification of locations within the scene. When a sensor, such as a video camera, images a scene contained in the geo-spatial database, the system recalls a reference image pertaining to the imaged scene. This reference image is aligned very accurately with the sensor's images using a parametric transformation. Thereafter, other information that is associated with the reference image can easily be overlaid upon or otherwise associated with the sensor imagery.

Abstract: The present invention includes a system and method for the correction of user induced inadvertent orientation errors in captured digital images before the digital image is saved to a storage media or memory. A system of the present invention checks a user-selectable input to determine if the orientation correction has been enabled, enables a tilt determining mechanism which senses orientation errors when the feature is enabled, corrects the orientation errors in the viewed image, displays a corrected digital image to the user and allows the user to store a digital representation of the corrected image into a memory. The method of the present invention includes receiving a digital representation of an image, identifying vertical or horizontal lines contained within the image, determining an orientation error, rotating the digital representation of the image to reduce the orientation error and displaying a corrected digital image.

Abstract: An image processing of an object to be detected in bonding system for manufacturing, for instance, semiconductor devices including a step of calculation of a difference value between a reference image inputted beforehand and a rotated image obtained by rotating the reference image for a plurality of reference points within the reference image, a step of mask pattern production based upon the difference values for the plurality of reference points, and a step of position detection for a position of an object of detection by pattern matching by way of using an image of the object of detection obtained by imaging the object of detection, the reference image and the mask pattern.

Abstract: The present invention is a method and apparatus for improving the appearance of electronic images, and more specifically, to the efficient use of template rotation within a template matching process to enhance such images. The invention reduces the number of entries that are stored in a look up table by eliminating identical patterns that differ only by the angle at which they are output. The appropriate templates are then rotated it by the required angle for output subsequent to their retrieval from the lookup table.

Abstract: When a storage memory becomes full during processing of printing out of image data read from a page memory and transferred to both a storage memory and a printing portion at the same time for a first copy, a function of an image rotating portion is not effected for copies subsequent to the first copy, and, also, for pages of image data which are stored in the storage memory are printed out, and a page of image data processed at the time the storage memory became full is transferred from the page memory to the printing portion and is printed out.

Abstract: CPU of a sheet processing apparatus reads a sheet by a scanner, stores the image of the sheet in an image memory, checks to determine whether expanding, reducing, rotating, synthesizing or other editing operations have been performed for the sheet image stored in the image memory and performs processing for converting the image to a recognizable size and rotating an image before recognizing the read sheet image when determining that editing has been performed. CPU further recognizes sheet ID information contained in the sheet image stored in the image memory by means of a character recognizing section, selects an unrecorded sheet image corresponding to the sheet ID information from a hard disk, stores the image in the image memory and prints out by way of a printer. Thus, sheets synthesized, expanded/reduced, rotated or edited in other ways can be recognized and high image quality of clean and unrecorded sheets can always be provided, thereby maintaining a good recognition rate.

Abstract: A prescreen filtering method and algorithm based upon Attributed Relational Graph (ARG) techniques are employed in a node-by-node matching to individually determine a best alignment of the sets of minutia of a pair of search and file fingerprints. First, the directional components of each and every different pair of minutia from the two sets are compared to ensure that they are within a given angular tolerance, which is selected to allow for a reasonable variation in possible rotational misalignments. After this directional alignment tolerance criteria has been passed, a Distance Matrix (DM) score is generated for each passed [u,v] minutia pair by performing a virtual alignment of the [u,v] minutia pair in location and direction, and then by comparing the distances and relative orientations between each of four pairs of minutia neighbors in each of the four local quadrants, which represents how well each different [u,v] minutia pair match each other.

Abstract: A digital copier and method of processing images in which the images are manipulated and processed utilizing smaller blocks of the image. By working with smaller blocks, the image processing may begin before an entire image is scanned or before the entire image is loaded into a memory or buffer. Further, when printing, the start of the printing process may begin as soon as a row of the smaller blocks is completed without waiting for the generation of the entire manipulated image. The blocks are preferably an integral multiple of the size of a size of a direct memory access buffer, or alternatively, are of a size which may be divided into the size of the direct memory access buffer an integral number of times or are a multiple of the size of the direct memory access buffer.

Abstract: A method of stabilizing and registering a video image in multiple video fields of a video sequence provides accurate determination of the image change in magnification, rotation and translation between video fields, so that the video fields may be accurately corrected for these changes in the image in the video sequence. In a described embodiment, a key area of a key video field is selected which contains an image which it is desired to stabilize in a video sequence. The key area is subdivided into nested pixel blocks and the translation of each of the pixel blocks from the key video field to a new video field is determined as a precursor to determining change in magnification, rotation and translation of the image from the key video field to the new video field.

Abstract: A method for selecting and arranging digital images to be printed from a group of thumbnail images is disclosed. The method comprises the steps of displaying the group of thumbnail images; selecting, from the group of thumbnail images, the number of images to be printed per page and the images which are to be printed on each page; automatically arranging the selected images for each page to be printed; and printing the arranged images.

Abstract: A method for matching images includes the step of providing a template image and an input image. A Laplacian-of-Gaussian filtered log (LOG-log) image function is computed with respect to the template image and the input image to obtain a Laplacian-of-Gaussian filtered template image and a Laplacian-of-Gaussian filtered input image, respectively. An energy function is minimized to determine estimated geometric transformation parameters and estimated photometric parameters for the input image with respect to the template image. The energy function is formed by weighting non-linear least squared differences of data constraints corresponding to locations of both the Laplacian-of-Gaussian filtered template image and the Laplacian-of-Gaussian filtered input image. The estimated geometric transformation parameters and the estimated photometric parameters are output for further processing. The method allows for image matching under non-uniform illumination variations.

Abstract: The present invention provides an image processing system for scanning a rectangular document. The system comprises a scanner with a scanning module and a computer. The computer has a memory, a processor, a scanner control program, and an image processing program. Depression of a start button generates a start signal that prompts the image processing system to rotate the document image from the scanned rectangular document by a tilting angle as well as to correct the image shape based on angle variation. This produces a straight and rectangular document image.

Abstract: This invention proposes to transcode the compressed image, that may be in the JPEG format for example, to an intermediate format that allows pseudo-random access. Such a pseudo-random access would that allow efficient image transformation. By using this format, in most cases a pixel is decoded only once in the entire image transformation process. This is certainly true for the most common transformation operations such as rotation by 90, 180 and 270 degrees. This transcoding would enable image transformations in printers whose memory is insufficient to store the entire decompressed image.

Abstract: This invention is a method and apparatus for processing compressed digital images. More particularly, this invention relates to methods and apparatus which accomplish rotation in conjunction with a variable-length decompression operation. A small amount of auxiliary information consisting of pointers to the starts of the scanlines is stored along with the DC coefficients in the decompressor, instead of the compressed image, to reduce the memory requirements for orthogonally rotating an image.

Abstract: The present invention is a method and apparatus for improving the appearance of electronic images, and more specifically, to the efficient use of template rotation within a template matching process to enhance such images. The invention reduces the number of entries that are stored in a look up table by eliminating identical patterns that differ only by the angle at which they are output. The appropriate templates are then rotated it by the required angle for output subsequent to their retrieval from the lookup table.

Abstract: In an image processing apparatus, an image reading unit reads a document put on a platen glass to generate image data, and a detector in the image reading unit detects offset, tilt angle and document area of the document put on the platen glass. A rotation angle is set based on the image data of a document. The entire document area is determined based on a portion of the document which exists within the image reading area when the document extends beyond the image reading area. The document area can be detected even if a document is not rectangular. For example, a slope of the document is determined based on the detected longest segment. In order to solve the unequal reading pitch, the longest segment is selected in the segments having a slope smaller than a predetermined angle relative to the subscan direction. Then, the image data are corrected according to the above result.

Abstract: An image forming apparatus for inputting an original image and forming an image on a recording medium, includes an image direction detection unit for detecting the image direction of an original image, and a control unit for controlling image forming device to perform predetermined image forming processing in accordance with the detection result of the image direction detection unit. The image direction detection unit outputs a degree of determination as the detection result of the image direction, and a level for determining whether or not the predetermined image processing is done is set for the degree of determination.

Abstract: In an apparatus for displaying reference images of patients and slices to be measured in a displayed reference image for assisting the positioning of slices in preparation for a slice-by-slice measurement and a computer software product and corresponding method, a storage device stores at least one measured reference image of a current patient, a display screen displays a stored reference image, an input device allows entry of commands for displaying and positioning slices to be measured in a displayed reference image, and a processing device processes the entered commands and correspondingly controls the display of the reference image and the slices. The processing device, depending on the entry of commands via the input device by a user, generates a rotated representation of the reference image and a spatial representation—corresponding to the rotation of the reference image—of the slices and displays them on the screen.

Abstract: Rotating image data ninety degrees is disclosed. In one embodiment of the invention, the computerized system includes an operating system providing a graphics interface library, and a graphics interface buffer maintained by the graphics interface library. The graphics interface buffer contains image data comprising a first screen image. The system also includes a graphics device driver that implements a method to rotate an area within the image data by dividing the area into a plurality of square pixel regions, rotating each of the squares, and writing the squares to an image data buffer comprising a display buffer maintained by the graphics device driver.

Abstract: A method and an apparatus for registering frames of imaging data using Fourier phase matching. Successive image frames of pixel data are processed using an image registration algorithm. Either image frames or the frames after edge detection are transformed into polar-logarithmic coordinates in the frequency domain and the phases of the Fourier transform of the resulting image representations, after inverse Fast Fourier transformation, are matched. The coordinates at the maximum phase difference are used to determine the scaling and rotation parameters needed for image frame registration. The frequency domain representation of one of the image frames is then scaled and rotated using an anti-aliasing algorithm in accordance with those parameters. The phase of the result is matched with the phase of the frequency domain representation of the other image frame to determine the translation parameters needed for image frame registration.

Abstract: Determining a skew angle of a bitmap image comprising of background and image pixels and de-skewing the bitmap image by the determined skew angle. The bitmap image skew angle is determined by calculating plural estimates of the skew angle with corresponding reliability indicators and thereafter selecting the estimate skew angle with the best reliability indicator as the bitmap image skew angle and then de-skew the bitmap image by the determined skew angle. Thereafter, auto-cropping the de-skewed image around a rectangle defined by a first and last column and first and last row of pixels which are not all white.

Abstract: Disclosed is an image forming apparatus capable of performing image formation by automatically discriminating and correcting the direction of an original without sorting originals including both portrait and landscape ones. Image data is read, and the direction of the read image is discriminated. In accordance with the discrimination result, a synthesis image to be synthesized suited to the direction of the image is selected. The synthesis image is rotated, where necessary, so that the synthesis image points in the same direction as the read image, and the two images having the same direction are synthesized and output.

Abstract: The invention aims at providing personal identification in environments where non-contact is required, with high accuracy even though using a finger vein pattern images unclear and susceptible to positional deviations, wherein it has: a means for acquiring finger vein patterns without contact; a means for carrying out rotational correction using the outline of a finger as a method of taking out a vein pattern contained in the acquired image; a means for normalizing the position of the finger image with reference to the fingertip; a means for acquiring an overall vein pattern statistically by repetitively tracking regions of dark luminance intensities for a desired length from a desired position in the image; a matching means for comparing regions where vein patterns manifest vivid features; and a means for independent matching of subregions and evaluating positional deviations where matching is recognized.

Abstract: A computer-assisted diagnosis method for assisting diagnosis of anatomical structures in a digital volumetric medical image of at least one lung includes identifying an anatomical structure of interest in the volumetric digital medical image. The anatomical structure of interest is automatically segmented, in real-time, in a predefined volume of interest (VOI). Quantitative measurements of the anatomical structure of interest are automatically computed, real-time. A result of the segmenting step and a result of the computing step are displayed, in real-time. A likelihood that the anatomical structure of interest corresponds to a disease or an area warranting further investigation is estimating, in real-time, based on predefined criteria and the quantitative measurements. A warning is generated, in realtime, when the likelihood is above a predefined threshold.

Abstract: This invention is a method and apparatus for processing compressed digital images. More particularly, this invention relates to methods and apparatus which accomplish rotation in conjunction with a variable-length decompression operation. A small amount of auxiliary information consisting of pointers to the starts of the scanlines is stored along with the DC coefficients in the decompressor, instead of the compressed image, to reduce the memory requirements for orthogonally rotating an image.

Abstract: The image processing apparatus transforms orthogonal transform coefficients into a predetermined number of bits for each spatial frequency, rearranges quantized data for each spatial frequency to an arrangement with spatial frequency band portions, thereby generates bit serial data that the quantized data of the same spatial frequency band exists successively over adjacent blocks, and compresses the bit serial data.

Abstract: A method of generating a bitmap representative of an original image.

Abstract: An image collation apparatus includes a collation unit, minimum coincidence ratio extraction unit, and determination unit. The collation unit obtains a coincidence ratio between first and second images within a printing element range for each collation unit by collating the first and second images with each other. The minimum coincidence ratio extraction unit obtains a minimum coincidence ratio from coincidence ratios obtained from the collation unit. The determination unit determines that the first and second images are identical, if the extracted minimum coincidence ratio is smaller than a predetermined threshold. An image collation method is also disclosed.

Abstract: An original image is held in the image holder 11, and displayed on the image display 12 to be viewed by the operator. The operator inputs the angle of rotation and ratio of compression of an focal point of the original image for observing ridges more clearly. A perspective transforming unit 14 generates a result image according to corresponding perspective transformation (i.e., affine transformations), and a perspective transformed image display 15 displays the result image to the user. The operator does operations of manual plotting and manual tracing with reference to the result image. The result of the operations is inputted to and recorded in the manual input unit 16, and transformed in a feature data transforming unit 17 to feature data.

Abstract: The invention is a system and method for determining alignment parameters (rotation angle and translation vector) between two images of scene based on the attributes of segments associated with a pair of corresponding points, each point extracted from each of the images.

Abstract: A method and apparatus for assisting in the rotation of digital images is described. The digital image is divided by a separate process into image blocks which are rotated through a predetermined angle. Data moving hardware then processes the image blocks to determine the proper placement of each block in a frame buffer to create a properly rotated image. A set of predetermined values based on characteristics of the input image and the predetermined output image format is provided to the data moving hardware from a value processor. The data moving hardware performs only additions and subtractions. The only multiplication necessary for the method is performed by the processor prior to placement of the rotated image blocks in an output frame buffer. Thus the rate of processing the rotated image blocks is significantly improved.

Abstract: Image rotation systems and methods optimally rotate high addressability binary images in a compact manner. High addressability bit pixels are clustered to form multi-bit pixels. The multi-bit pixel image is rotated +/−90°. A pixel mapping method is employed that realigns high addressability pixels within each target group of pixels in a manner that maintains edge integrity, maintains density, and does not introduce additional false contours. Information regarding neighboring pixel values is used to determine edge information about a given high addressability target pixel group. The edge information includes an edge slope and edge location of the high addressability target pixel group. Based on the rotation angle and the edge information of the pixel group, the target high addressability pixel group is mapped to a preferred pattern. After mapping to a preferred pattern, the high addressability pixel group is rotated.

Abstract: An image processor performs a high accuracy orientation determination process on a color image. A color component analyzer determines a frequency of appearance of each color component based on color image data of an input original document, and an orientation determining block determines the orientation of the original document by a character recognition process based on the frequency of appearance result. The color image data is then subjected to a predetermined editing in accordance with the determination results, and the edited image data is output.

Abstract: The invention corrects for rotational misalignment of images having a prominent periodic structure in a preferred direction, particularly imaged text pages. It preferably also finds the degree of correlation between different images. First the rotational misalignment of an imaged page is detected and corrected, bringing the page into alignment with an axis. The angle of rotation of the page is detected by performing a linear regression analysis on filtered, two-dimensional power spectral density distribution of the page, to find the angular orientation of the periodic components. In the preferred embodiment, two imaged pages are then cross-correlated, preferably by an optical correlator, to find the degree of correlation between the pages.

Abstract: This invention is a method and apparatus for processing compressed digital images. More particularly, this invention relates to methods and apparatus which accomplish rotation in conjunction with a variable-length decompression operation. A small amount of auxiliary information consisting of pointers to the starts of the scanlines is stored along with the DC coefficients in the decompressor, instead of the compressed image, to reduce the memory requirements for orthogonally rotating an image.