Abstract: A method and system is provided for aligning a geometric object model with a pixel image. A geometric object model representing an object is obtained first. Using the geometric object model of the object, a revised geometric object model is created. An alignment tool is then trained based on the revised geometric object model. The alignment model can be applied to a pixel image of the object so that the pose of the object can be computed by aligning the revised geometric object model with the image.

Abstract: A mass spectrometry apparatus uses image processing of output signals of a camera in a mass spectrometer to provide feedback for directing the laser. The present invention provides for the determination of where samples have actually been deposited on a plate, and for the selection of different points for each sample, based on its structure, at which to aim a laser, during the cycle period of the mass spectrometer. Such feedback information increases the likelihood that the laser impinges samples and provides useful data.

Abstract: A business form handling system includes an image reading device for reading a business form and a terminal apparatus installed at the window for discriminatively deciding whether a read image corresponds to a first species of business form by referencing form species identifying definition information stored previously in a file. When the read image corresponds to the first species of business form, the terminal apparatus cuts an image from a field corresponding to a format inherent to the first species of business form to thereby recognize contents of statement from the cut image and executes processing in accordance with result of the recognition. Unless the read image corresponds to the first species of business form, the terminal apparatus decides discriminatively whether the read image corresponds to a second species of business form by referencing the form species identifying definition information.

Abstract: A method of extracting a section of a page from a portable document format file (“pdf”): The method includes receiving indication of a user-defined region on a pdf file page, designating an extraction region including all elements determined to be within the user-defined region, and placing the extraction region into a new file. The method may also include determining if one or more elements on the pdf page are within the user-defined region by applying inclusion rules based on whether an element's bounding box is within or intersects the user-defined region. The method may also include verifying the accuracy of the extraction by converting the user-defined region in the original pdf document and the extracted region to bitmap images and comparing the two bitmap images, bit by bit.

Abstract: An image recording apparatus for recording image data of an inspection object and inspection data corresponding to inspection results outputted at their own respective timings from an inspection apparatus which judges quality by an image recognition process is equipped with a temporary storage portion for temporarily storing the image data and the inspection data, a storage device, and a control portion for synchronizing the image data and the inspection data and storing the synchronized image data and inspection data in the storage device based on relative position data from a prescribed signal sent from the inspection apparatus, wherein the control portion accesses the temporary storage portion to acquire previous data for at least the prescribed signal.

Abstract: A method and system of merging a pair of images to form a seamless panoramic image including the following steps. A set of feature points are extracted along the edges of the images, each feature point defining an edge orientation. A set of registration parameters is obtained by determining an initial set of feature points from a first one of the images which matches a set of feature points of a second one of the images. A seamless panoramic image is rendered using the first and second images with the set of registration parameters.

Abstract: According to the present invention, it is designed in such manner that a designation minimum unit for designating a position of an effective region of an image transmitted from a camera and a designation minimum unit for designating a size of the effective region are set independently from each other so that a restriction on one of them is not extended or applied to the other. Apart from designation minimum units (C, D) for determining the extent of an image region to be transmitted (effective region), designation minimum units (I, J) for determining position of the effective region are set to values irrelevant to the designation minimum units for determining the extent of the effective region. As a result, even when there is a restriction on the setting of one of the designation minimum units, i.e.

Abstract: A system and method of pointed position detection, a presentation system, and a program that make it possible to detect a pointed position accurately. The system of the present invention which detects a position of a light spot that has been projected into an image display region by using an infrared pointer comprises: a CCD camera that picks up an image of this image display region; a pointing coordinate detection section that is position detection means which detects a pointed position of the light spot within the image display region; and a receiver section which receive a state signal that is transmitted from the infrared pointer during a pointer operation by that infrared pointer. The pointing coordinate detection section detects a position of the light spot as the pointed position on the image display region, based on the reception timing of the state signal.

Abstract: A method and apparatus for creating an image is disclosed. The image is formed by rendering at least a plurality of graphical objects to be composited according to a compositing expression. Each object has a predetermined outline. The method comprises the following steps. Firstly, dividing a space in which the outlines are defined into a plurality of mutually exclusive regions wherein each of the regions is defined by a region outline substantially following at least one of the predetermined outlines or parts thereof. Secondly, examining each of the regions to determine those objects which contribute to the regions. Thirdly, modifying the compositing expression on the basis of the contribution of each of the objects within the region to form an optimized compositing expression for each region. Fourthly, compositing the image using each of the optimized compositing expressions.

Abstract: A tone correction system, method and interface is described in which a digital image is initially filtered to obtain a corresponding locally averaged value for each pixel value of the image. The image is optimally filtered using a cone-type filter having a small filter radius and which favorably weights the center pixel values of the radius. Shadow and highlight values are obtained from selected shadow and highlight functions, respectively, using the locally averaged values. A tone function is derived from each of the shadow an highlight values for each pixel. Each pixel value of the image is then remapped according to its derived shadow and highlight tone functions. The tone corrected image can be reinteratively corrected by adjusting parameters of the shadow and highlight functions and remapping the image data until a desired image quality is achieved.

Abstract: A technique is disclosed for enhancing discrete pixel images in accordance with a desired dynamic range, such as the dynamic range of a softcopy display. Adaptive equalization is first performed on the image data to reduce overall differences between high and low intensity values, while maintaining the overall appearance of light and dark regions of the reconstructed image. Adaptive contrast boosting or enhancement is then performed on the equalized values to bring out details visible by virtue of the enhanced local contrast. The contrast enhancement may include non-linear mapping of a mid-frequency boosted image onto the dynamic range of the softcopy display.

Abstract: Image data 110 of an object is recorded in a recording medium so as to contain data 113 for a high resolution and data 112 for a low resolution. In executing a game, an image display device is discriminated, and image data conforming to the resolution of the image display device is used. Thus, an object appearing in the game is displayed using the image data suited to the image display device.

Abstract: Systems and methods for incrementally updating a first image in flash memory of a device by downloading a differences file that identifies differences between the first image and a second image and applying the differences file to the first image to create the second image in the flash memory. The updating is performed incrementally by writing portions of the second image to the flash memory, each portion being of a standard block size acceptable for writing to the flash memory.

Abstract: An input image processing apparatus includes a FIFO memory (FIFO-S) in which region selection information for specifying a selected region in an input image frame, in order to consecutively store in an image memory pixel data within a selected region in an arbitrary shape defined on the image frame. The FIFO memory provides a signal for indicating write of pixel data included in the selected region into the image memory, based on the region selection information.

Abstract: A data compression method and system that include the substitution of a substring of data characters located at a first position in a stream of data characters with a substitution code. The substitution code includes a reference to a previous position in the stream of data characters at which is located a substring of data characters that matches the substring of data characters which are being substituted located at the first position. The substitution code also includes an indication of the size of the substituted substring. The reference in the substitution code is a backwards offset to the previous position relative to the first position. According to a further aspect, Huffman encoding can be applied to the backward offsets, the substring lengths, the consecutive literal character lengths, and the literal characters themselves to reduce the data requirement size.

Abstract: A method and a system by which a document image is analyzed for the purposes of establishing a searchable data structure characterizing ground-truthed contents of the document represented by the document image operates by segmenting a document image into a set of image objects, and linking the image objects with fields that store metadata. Image objects identified by segmenting the document image are grouped into subsets. The image objects are grouped according to characteristics suggesting that the image objects may have common ground-truthed metadata. By grouping the image objects into subsets, the image objects may be indexed to facilitate the ground-truthing process. In some embodiments, the index of representative image objects is presented to the user in a table form. A database of image objects with ground-truthed metadata is formed. Interactive tools and processes facilitate ground-truthing based on paired image objects and metadata.

Abstract: A data processing technique called a Ridgelet transform is disclosed for more efficiently representing information. Original data samples (e.g., in the time domain) are received and transformed into frequency domain values provided in Cartesian coordinates. The frequency domain values provided in Cartesian coordinates are then transformed to digital polar coordinates (provided in a digital polar grid). Because the polar grid is non-uniform, the polar coordinate values can be weighted or normalized. A Wavelet transform is performed on data derived the frequency domain values provided in digital polar coordinates to generate Wavelet coefficients (or Ridgelet coefficients). Next a thresholding or filtering process can be performed on the Ridgelet coefficients to select a group of larger Wavelet coefficients and to discard the remaining Wavelet coefficients.

Abstract: A mesh is created from selected focus points having locations on a surface of interest of a sample being micro-imaged. The mesh and associated focus settings of the focus points are used to define adjacent focus facets forming a focus surface substantially coincident with the surface of interest of the sample. In micro-imaging the sample, a micro-imaged portion of the surface of interest is segmented for the purpose of acquiring tile images. A tile image focus location is used to extract a tile image focus setting from the focus surface. A tile image focus determination process selects a focus facet coincident with the tile image focus location and interpolates a tile image focus setting from focus settings associated with the focus points defining the focus facet. If a coincident focus facet is not found, the tile image focus setting is set to the focus setting of a nearest focus point. Dependence on autofocus is thus eliminated, providing faster imaging and better focused images.

Abstract: The invention provides a method and device for interpolating between a first and second pixel in a video display system, where the first pixel has a first pixel value and a first coordinate on a first axis, and the second pixel has a second pixel value and a second coordinate on the first axis. The invention provides a first intermediate coordinate in between the first and second coordinates on the first axis, and determines a weight factor for the first intermediate coordinate. The weight factor is determined by either inputting the first intermediate coordinate into a first blending function if the first intermediate coordinate is within a first domain, or by inputting the first intermediate coordinate into a second blending function if the first intermediate coordinate is within a second domain. Once the weight factor is determined, a first interpolated value is calculated from a first product of the weight factor and a function of the first pixel value and the second pixel value.

Abstract: The present invention is embodied in a system and method for automatically estimating the orientation or pose of an object, such as a human head, from any viewpoint and includes training and pose estimation modules. The training module uses known head poses for generating observations of the different types of head poses and the pose estimation module receives actual head poses of a subject and uses the training observations to estimate the actual head pose. Namely, the training module receives training data and extracts unique features of the data, projects the features onto corresponding points of a model and determines a probability density function estimation for each model point to produce a trained model.