Abstract: One embodiment disclosed relates to the use of object motion estimation to interlace a progressive video sequence. One of a plurality of consecutive frames is segmented and motion vectors for each segment are determined though object motion estimation. Interpolated motion vectors are used to construct at least one intermediate frame, and interlaced fields are extracted from the new sequence of frames that includes intermediate frames. An interlaced sequence with smooth, incremental motion is thus constructed from a progressive video sequence.

Abstract: Various embodiments create a source image from a web page and then process the source image effective to remove left and/or right border areas so that a reduced-size web page image created from the source image has a better chance of capturing relevant content for a viewer. In at least some embodiments, image processing techniques are utilized to identify repeating patterns of pixels along left and/or right border areas of a source image. The image processing techniques can process individual rows of pixels looking for patterns of pixel color values. Identified patterns of pixel color values are noted and then subsequently used to remove regions of the source image in which repeating patterns occur. Having removed these regions from a source image, the source image can be reduced in a manner directed to improving information density contained in a reduced-size web page image created from the source image.

Abstract: A CAD/GIS system that dynamically updates planar topologies through incremental updating techniques. Rather than batch processing all of the changes to every geometrical feature in a given site map, the changes are made in incremental fashion and only enclosures or faces/parcels that are affected by changes are updated.

Abstract: Systems and methods are provided for performing diffusion-based image extrusion. According to one embodiment, a three dimensional model is created by polygonizing an input image to produce an inflatable image. The input image may be either a 2D image or icon or a 3D image or icon. The set of pixels making up the input image are represented as a plurality of polygons. Then, an initial value is assigned to a z-coordinate of each pixel in the set of pixels. After polygonizing the input image to create the inflatable image, the inflatable image is extruded by applying a biased image-based diffusion process to generate appropriate z-coordinate values for a reference point associated with each polygon of the plurality of polygons. In various embodiments, an end-user may be provided with the ability to interactively change one or more parameters associated with the inflatable image and/or the diffusion process.

Abstract: Image data to be recovered having a loss part is input into an image processing apparatus. The image processing apparatus generates restoration data with the loss part corrected. The image processing apparatus includes a thinning processing unit, an end-point extraction unit, a pair-of-connection-end-point extraction unit and a connection unit. The thinning processing unit executes thinning processing with respect to the image data to be recovered having the loss part. The end-point extraction unit executes finding end points of thinned lines of the image data generated by the thinning processing unit. The pair-of-connection-end-point extraction unit extracts a pair of connection end points to be connected from the end points extracted by the end-point extraction unit. The connection unit connects the pair of connection end points extracted by the pair-of-connection-end-point extraction unit.

Abstract: This disclosure describes techniques for correcting artifacts that occur along a boundary of a substitute video unit generated using video unit substitution, e.g., motion-compensated video unit interpolation or extrapolation. In accordance with the techniques described in this disclosure, a frame substitution unit identifies first locations within a substitute video unit that correspond with a boundary that exists within a reference video unit and should exist within the substitute video unit, and corrects boundary artifacts in the first locations using a first boundary artifact correction technique. The frame substitution unit also identifies second locations within the substitute video unit that correspond with a boundary that exists within the substitute video unit and does not exist within the reference video unit and corrects boundary artifacts in the second locations using a second boundary artifact correction technique.

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 method of designing filters for filtering digitized images includes constructing a set of difference-of-Gaussian (DoG) filters that partition a frequency space, forming a linear combination of said DoG filters to form a trial filter, convolving said trial filter with a training image to obtain a trial image, summing a square difference of said trial image and a target image, wherein if said sum is a minimum, outputting said trial filter as a final filter, and using a singular value decomposition on said final filter wherein an eigenvector corresponding to the largest eigenvalue of the final filter is obtained.

Abstract: A method of generating pixel data of a missing block in an image frame is disclosed. Edge points are detected from neighboring image side adjacent to the missing block. A direction is calculated for each edge point. Edge lines are formed from edge points based on the direction thereof to partition the missing block into a plurality of missing regions. Data for missing pixels in each missing region are then calculated using reference pixels from neighboring image sides adjacent to the missing region.

Abstract: Efficient image display on a display screen (e.g., in terms of number, space, resolution, and/or distortion) is facilitated by implementing one or more specialized select and pack routines for images. That is, representative images are selected from an image database, based on desired resolution and distortion, then resized and packed into a display arrangement that enhances use of display screen space. This allows, for example, images to be sent to a user from an image database more quickly, with more desirable resolution, and less distortion than traditional display techniques.

Abstract: The invention relates to a method for the transmission of additional information when using a method for compressing data by means of a prioritizing pixel transmission, said data consisting of individual pixel groups, each of which comprises a positional value within an image array and at least one pixel value. The minimum size of the image array is defined by the height (h) and the width (b) of an image, expressed in pixels. The invention is characterized by the fact that positional values which do not occur in the actual data but lie outside the range of the image array are used during the transmission of additional information.

Abstract: An image processing method includes the steps of extracting edges from each of a plurality of original images, thereby obtaining edge images; extracting straight lines from the edge images, thereby obtaining line images; assuming extensions of the straight lines constituting the line images and setting vanishing points on the basis of the extensions; and trimming the plurality of original images so that positions of the vanishing points in the respective original images mutually match, thereby obtaining final images.

Abstract: Provided is a method and apparatus for inpainting a depth image and a color image seen from one viewpoint by using a depth image and a color image inpainted from another viewpoint. The method includes detecting an edge on the basis of a difference between depth values of pixels in a first image seen from a view viewpoint and inpainting depth values of pixels in an occlusion region that is shown in a second image seen from a second viewpoint but not shown in the first image, in a direction from pixels in a region having high depth values among regions forming the edge to pixels in a region having low depth values.

Abstract: The boundaries of a scanned digital document are determined by identifying the largest connected component in the received digital document and assigning the boundaries of the largest connected component as the boundaries of the received digital document or by using a row by row and column by column analysis of the received digital document to identify horizontal and vertical bands in the digital image having pixels with a value opposite to the value of pixels of a background of the received digital document and assigning the horizontal and vertical bands to be the boundaries of the received digital document. These processes may be performed in series or parallel by a processor associated with a scanner that creates the digital document.

Abstract: A method, apparatus, and article of manufacture provide the ability to update a drawing surface in a CAD/GIS computer application. First, a drawing surface is displayed in a CAD/GIS application. A surface edit operation is then performed on the drawing surface. The CAD/GIS application then determines if an automatic rebuild option is active. If the rebuild option is active, the drawing surface is dynamically and automatically rebuilt to reflect the surface edit operation. Alternatively, if the automatic rebuild option is inactive (e.g., toggled off), the drawing surface is flagged as out-of-date.

Abstract: A method for analyzing a three-dimensional (3D) image representative of an initial volume of interest (VOI) containing a lesion is disclosed. The 3D image has an associated binary map having voxels associated with a thresholded variance map of the initial VOI. The initial VOI has boundaries that may be defined by a cube. A final VOI is determined that is less than the initial VOI, where the final VOI is a function of the number of transitions from a boundary voxel to a filtered voxel at an outer boundary of the lesion. The final VOI is then analyzed to determine a nodule consistency class, classified based upon the computed nodule consistency class by applying a voxel-clustering algorithm, and displayed with respect to three classifications of tissue.

Abstract: An example-based filling system identifies appropriate filling material to replace a destination region in an image and fills the destination region using this material, thereby alleviating or minimizing the amount of manual editing required to fill a destination region in image. Tiles of image data are borrowed from the proximity of the destination region or some other source to generate new image data to fill in the region. Destination regions may be designated by user input (e.g., selection of an image region by a user) or by other means (e.g., specification of a color or feature to be replaced). In addition, the order in which the destination region is filled by example tiles may be configured to emphasize the continuity of linear structures and composite textures using a type of isophote-driven image-sampling process.

Abstract: An image processing apparatus includes an extraction unit, a counting unit and an information embedding unit. The extraction unit extracts a circumscribed figure of a pixel block in an image. The counting unit counts contact portions between the circumscribed figure extracted by the extraction unit and the pixel block. The information embedding unit embeds information to be embedded by adjusting a number of the contact portions between the pixel block and the circumscribed figure extracted by the extraction unit based on the number of contact portions counted by the counting unit and the information to be embedded.

Abstract: Image object adjustment is achieved without lookup tables or templates. Cross sections of image objects are modeled. Parameters of the modeled cross-section are adjusted in accord with a desired effect. For example, a width of the modeled cross section is change. The changed cross section model is sampled to determine a new value for a target pixel. For instance, vector windows are applied to a target pixel. If a candidate image object is included in the vector window, a cross section thereof is modeled as a rectangle. A parameter of the model, such as a width, is adjusted. Area sampling of the adjusted model can be used to determine a new value for the target pixel. Accuracy can be increased by blending information associated with a plurality of vector windows.

Abstract: A method and system for making information available of a computer system and compensating information owners or creators for access to said information. In various aspects, the invention provides a mechanism for giving users meaningful access to information via a computer system and network while protecting the interests of publishers and creators in information. The invention provides a solution for information including, but not limited to: text, graphics, photos, executable files, data tables, audio, video, and three dimensional data. In a further aspect, the invention comprises a new method for allowing a user to review a document while connected to a network but prevents the user from downloading, printing, or copying the document unless a fee is paid. In a further aspect, the invention comprises a new method for allowing a user to review documents at a first cost basis (which may be free), but only provides other access to documents, such as copying, printing, or downloading on a second cost basis.

Abstract: Representing high-resolution media content in a lower resolution system is disclosed. For a first portion of a high-resolution media content which is associated with a content boundary that does not align with an interval boundary of the lower resolution system, a new media content file that includes at least said first portion of the high-resolution media content is created. The new media content file and a second file comprising at least a second portion of the original media content file, which second portion begins at a first interval boundary and ends at a second interval boundary of the lower resolution system, are provided to the lower resolution system.

Abstract: A method of enhancing an image, comprising providing an image having luminescence and at least one boundary, determining locations each of the at least one boundary in the image, computing an image enhancement technique having a gain for application to the image, and adjusting the gain of the image enhancement based on the luminescence values of the image near the boundary locations.

Abstract: The present invention relates to method, apparatus and storage medium for enhancing document image, and method, apparatus and storage medium for character recognition. For enhancing the document image especially half-tone block image and improving the recognition ratio thereof, the block image is segmented into line images, which are subject to noise reduction. Then, based on the connected component densities, the noise-reduced line images are sorted into three types including normal line image, broken-stroke line image and hollow-stroke line image. Based on their types and other properties, the noise-reduced line images are enhanced, generating enhanced line images, which as a whole constitutes an enhanced block image.

Abstract: The present invention concerns the blending of plural x-ray images to form a blended composite image wherein in blending the images, a stitching boundary adjustment is determined for use in adjusting boundary pixels of the composite image, and an adjustment for other pixels that are located at some distance from the boundary is determined, wherein the adjustment for the other pixels depends on the stitching boundary adjustment and on values of the boundary pixels.

Abstract: Embodiments of the invention may process an input image using phase symmetry methods and use the resulting processing results to determine an object in the image. The object may be suppressed, if desired.

Abstract: An object based boundary refinement method for object segmentation in digital images receives an image and a single initial object region of interest and performs refinement zone definition using the initial object regions of interest to generate refinement zones output. A directional edge enhancement is performed using the input image and the refinement zones to generate directional enhanced region of interest output. A radial detection is performed using the input image the refinement zones and the directional enhanced region of interest to generate radial detection mask output. In addition, a final shaping is performed using the radial detection mask having single object region output.

Abstract: The present invention provides gradient preservation of an input image. A method of providing gradient preservation of an input image, comprises the steps of: computing gradient fields of the input image; computing gradient fields of a remapped image, wherein the remapped image is the input image remapped; comparing a gradient of the remapped image to a predefined range of acceptable values, wherein the acceptable values depend on the input gradient; changing values of the gradient of the remapped image if the values of the gradient of the remapped image are not within the predefined range of acceptable values depending on the input gradient, resulting in x and y components of a modified gradient; and reconstructing the input image using the x and y components of the modified gradient.

Abstract: An image-capturing device and method for removing strangers from an image are described. First, a first image is input. Then, a control module determines if an unwanted object processing step is needed, and obtains a result. If the result is no, the first image is directly sent to an output module. If the result is yes, an image-identifying module begins to identify the target-image and the unwanted object in the first image, and then, an unwanted object processing module starts the step to process unwanted images. The unwanted object processing step can remove the unwanted object from an image and fill the left lacuna region. Afterwards, a second image is produced and sent to the output module.

Abstract: According to an embodiment of the present invention, there is provided a picture reproducing and displaying apparatus which displays a compression-encoded picture on a display section. A first memory stores input encoded picture data. A decoding section decodes the input encoded picture data stored in the first memory. A second memory in which one of a first development area whose size larger than that of a display area of a display picture and a second development area whose size smaller than that of the first development area is capable of being set in the second memory. A second memory stores a picture decoded by the decoding section. A display section displays a picture developed in the second memory. A control section controls the decoding section and the second memory according to one of a picture quality priority mode and a speed priority mode.

Abstract: The device has flexure correcting means for operating to rotate a first eccentric cam provided at a central part of a first side of a reflecting mirror, thereby moving up and down the central part of the first side to correct the flexure of the reflecting mirror, torsion correcting means for operating to rotate a second eccentric cam or/and a third eccentric cam provided at the ends of a second side opposed to the first side of the reflecting mirror, thereby moving up and down both ends of the second side of the reflecting mirror to correct the torsion of the reflecting mirror, and a rotation operation portion provided at each of extended ends of camshafts provided at the eccentric cams to correct the flexure and torsion of the reflecting mirror.

Abstract: An object activity modeling method which can efficiently model complex objects such as a human body is provided. The object activity modeling method includes the steps of (a) obtaining an optical flow vector from a video sequence; (b) obtaining the probability distribution of the feature vector for a plurality of video frames, using the optical flow vector; (c) modeling states, using the probability distribution of the feature vector; and (d) expressing the activity of the object in the video sequence based on state transition. According to the modeling method, in video indexing and recognition field, complex activities such as human activities can be efficiently modeled and recognized without segmenting objects.

Abstract: A system and method for improving both coding efficiency and decoding accuracy in scalable video coding involving discardable lower layer adaptations, where applications can omit transmission of unused data for inter-layer prediction for all layers below an operation point of receivers. Indicator flags are utilized to avoid transmitting syntax elements that must be set to fixed values. In addition, padding algorithms or additional encoding constraints are applied to the encoding process.

Abstract: We propose local watershed operators for the segmentation of structures, such as medical structures, from an image. A watershed transform is a technique for partitioning an image into many regions while substantially retaining edge information. The proposed watershed operators are a computationally efficient local implementation of watersheds, which can be used as an operator in other segmentation techniques, such as seeded region growing, region competition and markers-based watershed segmentation.

Abstract: Image processing methods, image management systems, and articles of manufacture are described. According to one embodiment, an image processing method includes accessing image data of a plurality of images, defining a plurality of regions in individual ones of the images, wherein the regions individually comprise a plurality of image forming elements having a common characteristic, comparing a region of one of the images with respect to regions of a plurality of others of the images, and providing information indicative of similarities of the one image relative to the others of the images using results of the comparing.

Abstract: Methods and apparatus for antialiasing images that contain one or more image objects such as colored text, line art, and graphical objects, such that the edge pixels of an antialiased image object will exhibit relatively uniform values, and the appearance of the image object is thereby improved. In one embodiment, an improved antialiasing filter is employed to detect at least one region within the received image. Upon detecting a region containing a background image level that adjoins an image object having pixel values in a range other than a range of limit values, the antialiasing filter sets the pixel values of the edge or border pixels of the image object to substantially the same value. Selection among a logical filter operation and an averaging filter operation may be adaptively employed in the antialiasing filter in order to obtain the desired uniformity of pixel values.

Abstract: A projector includes an image projection section, a sensor that senses a projected first calibration image at a low resolution and generates first sensing information, senses the first calibration image at a high resolution and generates third sensing information, and senses a second calibration image at a high resolution and generates second sensing information, a projection area detection section that generates projection area information, based on the first and second sensing information, a projection-target area detection section that generates projection-target area information, based on the first, second, and third sensing information, and an image distortion correction section that corrects distortion of an image projected by the image projection section, based on the projection area information and the projection-target area information.

Abstract: An automatic method for the registration of prone and supine computed tomographic colonography data is provided. The method improves the radiologist's overall interpretation efficiency as well as provides a basis for combining supine/prone computer-aided detection results automatically. The method includes determining (centralized) paths or axes of the colon from which relatively stationary points of the colon are matched for both supine and prone positions. Stretching and/or shrinking of either the supine or prone path perform registration of these points. The matching and registration occurs in an iterative and recursive manner and is considered finished based on one or more decision criteria.

Abstract: A system and method for detecting edge locations where intercolor bleeding would likely be a problem, and reducing the amount of ink printed at those locations. The method operates on image data including a set of pixels with each pixel having multiple separation values. Upon receipt of the image data, the data is analyzed to identify those pixels located at an edge. A coverage value is computed from the separation values for those pixels identified as being located at an edge. Based on the coverage value, a reduction factor is determined. The reduction factor is used to multiply the separation values for the pixels located at the edge to yield reduced pixel values.

Abstract: An inspection system includes a plurality of models are applied in a way that enhances the effectiveness of each type of model. In one embodiment, a printed circuit board inspection system includes an image model, a structural model and a geometric model to inspect objects. The image model is first applied to an object being inspected to identify objects which look alike. After the image model is applied, a structural model is applied to determine whether the object exists in the image that has the same structure and is used to decide if the image model has truly found a part in the image. Lastly, a geometric model is applied and uses the approximate positional data provided by the previous two models to determine precisely the location of the object being inspected. Also described are techniques for learning and updating the plurality of models.

Abstract: A first image enlargement processing section enlarges an original image to a specified size to generate an initial enlarged image. A domain block extraction section extracts a domain block image from the original image. A range block extraction section extracts a range block image from the neighborhood of the correspondence part of the domain block image in the initial enlarged image. A reduced range block preparation section reduces the range block image to the domain size to generate a reduced range block image. An enlarged range block preparation section enlarges the most similar range block image having the highest degree of similarity to an enlargement size to generate an enlarged pseudo domain block image. An enlarged image acquisition section 676 uses each enlarged pseudo domain block image to generate an enlarged image of the original image.

Abstract: A method for scaling a digital picture to generate a scaled picture including following steps:(a) scaling a portion of the digital picture instead of the whole digital picture in a first direction; (b) scaling part of the data produced in step (a) in a second direction; and (c) repeating steps (a) and (b) to form the scaled picture.

Abstract: A printing system simultaneously prints both images and related information which is recorded together with the images. The print output may be unsuitable for use, depending on the combination of the image layout and positions where the related information is printed. To obviate this problem, an image processing apparatus lays out, on a recording medium, a plurality of images and information related to each of the images. The image processing apparatus has an image layout changing unit and an image layout controlling unit. The image layout changing unit changes a layout method for laying out the plurality of images. The image layout controlling unit determines, in accordance with the layout method changed by the layout changing unit, whether the related information is to be located within or outside areas of the associated images.

Abstract: Systems and methods are provided for constructing a composite image having an extended depth of focus from a plurality of spatially congruent source images of lesser depth of focus. The systems and methods are relatively fast, preserve detail, provide robust results on a variety of unpredictable workpiece features and configurations, and tend to suppress or reduce out-of-focus artifacts. The composite image is constructed by edge and/or boundary analysis to identify well-focused edges or boundaries in the source images. Each particular edge or boundary in the composite image is determined based on the source image containing the best-focused instance of each particular edge or boundary. The composite image is constructed outside of the previously constructed portions by surface analysis to identify well-focused surfaces in the source images, Each particular surface portion in the composite image is determined based on the source image with the best-focused instance of each particular surface portion.

Abstract: An image processing apparatus and method wherein consecutive image data is input, the image data is divided into blocks each constituted of a plurality of pixels, a motion vector of each block is detected, a border block is judged in accordance with the detected motion vector, the border block forming a boundary area between an object area and a background area corresponding to a background of the object area, and image data in the object area is extracted in accordance with the judged border block.

Abstract: The present invention concerns the blending of plural x-ray images to form a blended composite image wherein in blending the images, a stitching boundary adjustment is determined for use in adjusting boundary pixels of the composite image, and an adjustment for other pixels that are located at some distance from the boundary is determined, wherein the adjustment for the other pixels depends on the stitching boundary adjustment and on values of the boundary pixels.

Abstract: We disclose quantitative geometrical analysis enabling the measurement of several features of images of tissues including perimeter, area, and other metrics. Automation of feature extraction creates a high throughput capability that enables analysis of serial sections for more accurate measurement of tissue dimensions. Measurement results are input into a relational database where they can be statistically analyzed and compared across studies. As part of the integrated process, results are also imprinted on the images themselves to facilitate auditing of the results. The analysis is fast, repeatable and accurate while allowing the pathologist to control the measurement process.

Abstract: Segmentation of pulmonary nodules from digital volumetric image includes segmenting, automatically, the pulmonary nodule from attached anatomical structures by analyzing a structure of interest, and providing a template according to an analyzed structure of interest, wherein the template displays a segmentation of a volume of interest including an object of interest. The template can be adjusted according to a one or more adjustable parameters. The method stores values of the parameters according to the object of interest, and stores a segmentation of the object of interest according to the values of the parameters. The segmentation is refined by extracting and labeling surrounding anatomical structures, defining each structure touching a boundary of a volume of interest as an elongated object, determining a size and shape for each structure, and determining a distance of a current structure to the segmentation result, upon determining the distance to be small compared to a threshold.

Abstract: The invention relates to a method for changing the image size of video images, in which a decimation of video image signals (V) by an integral decimation factor (MHD, MVD) is carried out, and the decimated video image signals are subsequently read into an image memory for buffering. In order to achieve better possibilities of adjusting the image reduction with a relatively low outlay and high image quality, a fine decimation of the video image signals (V) is additionally carried out before buffering by a fine decimation factor (SHS, SVS) which can be adjusted to non-integral values, and a total decimation factor (MH, MV) relevant to the decimation of the video image signals (V) is formed from the integral decimation factor (MHD, MVD) and the fine decimation factor (SHS, SVS).

Abstract: A method and apparatus for reducing three-dimensional shape data, includes calculating estimation values for portions to be deformed by converging two or more vertices of a polygon model, and reducing the number of data for the polygon model by converging two or more vertices of the polygon model when the estimation values are equal to or below the predetermined permissible value. Estimation values for surfaces to be deformed by shrinking edges or surfaces are calculated based on distances between the respective surfaces and all the original vertices involved in the surface deformation. Before each data reduction, the portion having been involved in all the previous data reductions is defined as a reduction prohibition area, and a succeeding data reduction is applied to a portion other than the reduction prohibition area.

Abstract: A scanning system and method for locating a point within a region. The method may: 1) determine or locate a region of interest in the region; 2) determine one or more characteristics of the region of interest within the region, wherein the region of interest includes the point of interest; 3) determine a continuous trajectory based on the one or more characteristics of the region of interest; 4) measure the region of interest at a plurality of points along the continuous trajectory to generate a sample data set; 5) perform a surface fit of the sample data set using the approximate model to generate a parameterized surface; and 6) calculate a location of the point of interest based on the parameterized surface. The method may include measuring the region at and/or near the calculated location to confirm the solution, and may also include generating output comprising the results.