Abstract: Methods and systems for creating three-dimensional models from two-dimensional images are provided. According to one embodiment, a method of creating an inflatable icon involves a vectorizing module polygonizing an input image to produce an inflatable image by representing a set of pixels making up the input image as polygons. The inflatable image is then extruded by an extrusion module by generating appropriate z-coordinate values for a reference point associated with each polygon of the inflatable image based upon a biased diffusion process. End-user controlled pressure modulation is supported by an interface module by (i) adjusting one or more modulation functions employed by the biased diffusion process based upon end-user input regarding relative modulation bias for a selected set of one or more pixels associated with the inflatable image or (ii) applying the biased diffusion process to only the selected set of one or more pixels.

Abstract: An image processing system includes a wavefront coding element that codes a wavefront forming an optical image, a detector for converting the optical image to a data stream and an image processor for processing the data stream with a reduced set filter kernel to reverse effects of wavefront coding and generate a final image. The reduced set filter kernel may include a reduced set distributive filter kernel. An image processing method includes wavefront coding a wavefront that forms an optical image, converting the optical image to a data stream, and processing the data stream with a reduced set filter kernel to reverse effects of wavefront coding and generate a final image. The processing consists of processing the image, for each pixel, with filter tap logic consisting of a shifter.

Abstract: Processing for judging whether a face is included in a frame is performed, in a predetermined interval, on each of frames included in a moving image of a subject, displayed on a monitor, until the judgment becomes positive. If it is judged that a face is included in a frame, the facial position is detected in the frame, and stored. Then, judgment is made as to whether a face is included in the next frame after predetermined time. If the judgment is positive, the facial position is detected. The previously stored facial position is replaced by the newly detected facial position, and the newly detected facial position is stored. These processes are repeated until photographing operation is performed by operating a release unit.

Abstract: An image information-inputting unit inputs image information including position information indicating a position where an image was captured. A reference distance-calculating unit calculates a reference distance from a predetermined reference position utilizing the image information. An image information-classifying unit classifies the image information based on the reference distance.

Abstract: A method, system and computer program product that involves receiving and initializing a digital image. Quantization is preformed on the digital image using at least two multiplication operations. Finally, a compressed version of the digital image is presented for viewing and/or storage or transport.

Abstract: Embodiments of the invention are directed toward reversible/invertible and lossless, image data hiding that can imperceptibly hide data into digital images and can reconstruct the original image without any distortion after the hidden data have been extracted in various digital image formats including, but not limited to Joint Photographic Experts Group (JPEG). In particular, embodiments of the invention provide a lossless data hiding technique for JPEG images based on histogram pairs. that embeds data into the JPEG quantized 8×8 block DCT coefficients and achieves good performance in terms of peak signal-to-noise ratio (PSNR) versus payload through manipulating histogram pairs with optimum threshold and optimum region of the JPEG DCT coefficients. Furthermore, the invented technology is expected to be able to apply to the I-frame of Motion Picture Experts Group (MPEG) video for various applications including annotation, authentication, and forensics.

Abstract: Systems and methods using an unstructured pattern for three-dimensional model construction, such as may be used for processing images of documents are disclosed. The method generally includes projecting an unstructured infrared pattern onto a target object, capturing a pair of stereoscopic images of the pattern projected onto the target object, such as with infrared cameras, performing signal processing on the pair of stereoscopic images to cross-correlate portions of the stereoscopic images in order to identify corresponding portions in the stereoscopic images, and constructing a three-dimensional model of the target object. The three-dimensional model can be utilized to rectify, e.g., de-warp, an image of the target object, e.g., a page or both facing pages of a bound document.

Abstract: This invention consists in an image processing method in which the similarity between a first pixel and a second pixel constituting an image is numerically given by statistical testing, and the values of the first and second pixels are averaged when the similarity numerically given is high, whereas the first and second pixel values are not averaged when the determined similarity is low, whereby an image with noises suppressed is obtained without spoiling a spatial resolution as well as a temporal resolution.

Abstract: A method of testing a mask pattern, includes applying optical proximity-effect compensation to a first pattern to be tested and to be formed onto a mask layer, to thereby form a mask pattern of the mask layer, dividing the first pattern into a plurality of areas in accordance with a second pattern to be formed onto another mask layer, determining sampling points on an edge of the first pattern, determining a test standard for each of the areas, simulating a resist pattern formed on a resist by exposing the resist to a light through the mask pattern, and checking whether a dimensional gap between the first pattern and the resist pattern at each of the sampling points is within a test standard associated with an area to which each of the sampling points belongs, wherein test standards for first and second areas among the areas are different from each other.

Abstract: Secure stamping of multimedia document collections is disclosed. In one embodiment, the method comprises adding an image to a collection of media objects, and producing a visual representation of the collection that includes the image, where the visual representation has an identifier to identify the collection and graphical content representing the media objects.

Abstract: A post-processing circuit for processing an image signal according to frequency components of an image signal includes: a low-frequency extracting unit outputting a low-frequency image component of the image signal as a low-frequency signal; a high-frequency extracting unit multiplying a high-frequency image component of the image signal by a first gain and outputting the multiplication product as a high-frequency signal; an intermediate-frequency extracting unit multiplying an intermediate-frequency image component of the image signal by a second gain and outputting the multiplication product as an intermediate-frequency signal; and an adder adding the low-frequency signal, the high-frequency signal, and the intermediate-frequency signal and outputting the addition sum as a post-processed signal, wherein the first gain and the second gain are differently set according to a pixel location in a spatial domain.

Abstract: An image processing apparatus has an enlargement processing function of displaying an image on an image display unit at a designated enlargement magnification, and a color conversion processing function of changing a designated conversion source color to a conversion destination color. This image processing apparatus determines at least one of the conversion source color and conversion destination color by acquiring color information from a predetermined area in the displayed image. Upon determining one of the conversion source color and conversion destination color, control according to the enlargement magnification of the enlargement processing function is made so as to assure an amount, which is equal to or larger than a predetermined value, of color information included in the predetermined area.

Abstract: A binary image is generated by binarizing a multilevel image. An edge image is generated by extracting an edge component in the multilevel image. The binary image is segmented into a plurality of regions with different attributes. An outline candidate of a halftone region is extracted from the edge image. A second region segmentation result is output on the basis of the information of the outline candidate and information of the region segmentation result.

Abstract: Methods and systems for incorporating handwritten information into a text or graphics document as text data, image data or command cues received through a positional input digitizing recognizer, such as a digitizer pad. In a data entry mode, a unit of data is inserted and accepted for placement at a designated location. In a recognition mode, the data is recognized as legible text with optional embedded edit or other commands, or it is recognized as graphics and accepted into an associated image frame. Information interpreted as commands can be executed as editing commands to control addition, deletion or movement of text within the document, as well as font or type size change or color change and the like. The invention may take advantage of features native to the particular application.

Abstract: A method and system for scaling an original image into a scaled image is disclosed. Rather than using the corresponding position in the original image to generate the pixels values of a current pixel in the scaled image, image scalers in accordance with the present invention, calculate a high frequency adjusted position based on the high frequency components of pixels near the corresponding position. Pixel values based on the high frequency adjusted position provide better picture quality for the scaled image than pixel values based on the corresponding position. Furthermore, some embodiments of the present invention also use sharpness compensation to further improve the picture quality of the scaled image.

Abstract: Image-based searching for information on a network is provided in response to an image query sent by a user. The image query includes an image captured using a mobile communications device with a camera. The image is processed to detect any text present in the image, and any detected text can be analyzed using a process such as optical character recognition (OCR). The analyzed text is used to search for matches in at least one corresponding domain database, selected from various domain databases present in the network. Thereafter, one or more selected matches and any additional related information can be sent to the user as one or more results for the submitted image query.

Abstract: An image processing unit for computing a sequence of output images on basis of a sequence of input images, comprises: a motion estimation unit for computing a motion vector field on basis of the input images; a quality measurement unit for computing a value of a quality measure for the motion vector field; an interpolation unit for computing the output images by means of interpolation of pixel values of the input images, on basis of the motion vector field; and control means to control the interpolation unit on basis of the quality measure. The quality measurement unit is arranged to compute the value of the quality measure on basis of a maximum difference between neighboring motion vectors. If the value of the quality measure is lower than a predetermined threshold, then a motion compensated interpolation is performed, else a non-motion compensated interpolation is performed.

Abstract: A line segment detector comprises a vertical line detecting part, a horizontal line detecting part, a left-to-right downward slanting line detecting part, a left-to-right upward slanting line detecting part, and a line-segment detecting/synthesizing section that calculates OR operation of output values from the vertical line detecting part, the horizontal line detecting part, the left-to-right downward slanting line detecting part, and the left-to-right upward slanting line detecting part. The line segment detector further comprises a re-determining unit comprising a second line-segment detecting part that sets a window to the detection result near the target pixel, counts the number of pixels whose detection result is determined as the line segment in the set window, determines, when the counted value is not smaller than a predetermined threshold value, that the pixel is a line segment.

Abstract: Methods and systems for cropping images of book pages are disclosed according to one embodiment of the invention. A method may include identifying reference images and receiving cropping rectangles for the reference images. These cropping rectangles associated with reference images may then be used to generate cropping rectangles for images of book pages between the reference images. The cropping rectangles may be generated based on a linear interpolation of the cropping rectangles associated with the reference images and the number of pages between images. The method may also display one or more images of book pages with the associated one or more cropping rectangles superimposed thereon. A user may then have the opportunity to make adjustments to the position and/or size of the cropping rectangles.

Abstract: A method for illumination-independent change detection in a pair of original registered gray images based on blob extraction. Blobs are extracted from the two original images and their negatives, using an enhanced blob extraction algorithm based on connectivity analysis along gray-levels. Blobs extracted from the first original and negative images are compared with blobs extracted from the second original and negative images to determine whether each blob has a corresponding blob, i.e. whether it is a matched or unmatched blob. All unmatched blobs are tested for significance as “blobs of change” using a fitness measure based on either a ratio of saliency gradients, or a product of this ratio and a gradient distribution measure.