Abstract: A method for generating a positron emission tomography (PET) attenuation correction map from magnetic resonance (MR) images includes segmenting a 3-dimensional (3D) magnetic resonance (MR) whole-body image of a patient into low-signal regions, fat regions, and soft tissue regions; classifying the low-signal regions as either lungs, bones, or air by identifying lungs, identifying an abdominal station, and identifying a lower body station; and generating an attenuation map from the segmentation result by replacing the segmentation labels with corresponding representative attenuation coefficients.

Abstract: A method of detecting one or more errors in a series of electronically processed, multi-pixel images, the pixels of which correspond from one image to the next, the method including monitoring the reflectance of one or more of the corresponding pixels during sequential processing of each image of the series and, if the reflectance value of a pixel is invariant or substantially invariant in more than a predetermined number of consecutive said images, and identifying an error.

Abstract: A moving object detecting device measures a congestion degree of a space and utilizes the congestion degree for tracking. In performing the tracking, a direction measured by a laser range sensor is heavily weighted when the congestion degree is low. When the congestion degree is high, a sensor fusion is performed by heavily weighting a direction measured by a image processing on a captured image to obtain a moving object estimating direction, and obtains a distance by the laser range sensor in the moving object estimating direction.

Abstract: A technique is provided for computing an atomic number of materials forming an object imaged by a radiological modality. The method includes accessing a first monochromatic image and a second monochromatic image of the object, the first monochromatic image acquired at a first energy level and the second monochromatic image acquired at a second energy level. A ratio of the mass attenuation coefficients between the first monochromatic image and the second monochromatic image may be obtained. The atomic number for a material of the object may be computed based upon the ratio of mass attenuation coefficients.

Abstract: Motion blur periods (bf) are detected (14) from gradation differences (g1) between a first image signal (d1) and a second image signal (d2), gradation differences (g2) between the second image signal (d2) and a third image signal (d3), and results of the detection of transition periods (h) in the gradations of the second image signal (d2), and the second image signal (d2) is corrected (3) only during the detected motion blur periods (bf). Transition periods (h) are deemed to occur when, for example, the absolute value of a gradation change in the second image signal is greater than a first predetermined threshold value (S1) and less than a second predetermined threshold value S2 (<S2). Motion blur in the image signal can be detected without increased circuit size, and accordingly, the detected motion blur can be reduced.

Abstract: Stored documents can be recognized and identified by evaluation of their attributes from an image file to obtain a document specification that can be compared to stored data about the document. The image file is analyzed using a processor in order to discern image attributes. The image attributes form a specification for the document in the image. This specification can then be compared to the stored criteria using the processor, and the result of the comparison can be stored. An embodiment of the invention can be used in a check processing system for a financial institution. In such a case, the corresponding data comprises MICR data and the image attributes can, for example, indicate whether the document is a check in a carrier, as opposed a paper check by itself.

Abstract: A method for synthesizing an image with multi-view images includes inputting multiple images, wherein each of the reference images is corresponding to a reference viewing-angle for photographing; synthesizing an image corresponding to a viewpoint and an intended viewing-angle; segmenting the intended synthesized image to obtain a plurality of meshes and a plurality of vertices of the meshes. Each of the vertices and the viewpoint respectively establish a viewing-angle, and the method further includes searching a plurality of neighboring images among the reference images referring to the viewing-angle. If at least one of the neighboring images falls within an adjacent region of the vertex, a first mode is adopted without interpolation to synthesize the intended synthesized image; when none of the neighboring images falls within the adjacent region of the vertex, a second mode is adopted, where a weighting-based interpolation mechanism is used for synthesizing the intended synthesized image.

Abstract: An image processing apparatus such as a monitor system for executing image processing to present a suspicious object effectively. An object detecting unit detects an object contained in an image, an associating unit associates a plurality of objects detected with the object detecting unit, with each other, and an evaluating unit evaluates (e.g., evaluation as being suspicious) an object detected by the object detecting unit, and an association evaluating unit evaluates another object associated by the associating unit with the object evaluated by the evaluating unit, in accordance with the evaluation made by the evaluating unit.

Abstract: A system and method of contrast enhancement is disclosed. A contrast enhancement unit processes an input pixel to generate a contrast-enhanced pixel, and a delta unit subtracts the input pixel from the contrast-enhanced pixel, thereby resulting in a difference value. Multiple delayed difference values generated by a delay unit are low-pass filtered to generate a refined difference value. An adding unit adds back the refined difference value to the input pixel, thereby resulting in an output pixel that is contrast-enhanced without noise boost.

Abstract: A driving support system with plural dimension processing units (DPUs) for indicating a condition of a surrounding area is disclosed. The driving support system of a vehicle includes plural image capturing devices disposed around the vehicle; at least a dimension processing unit (DPU) connected with the plural image capturing devices for receiving images from the plural image capturing devices and then producing plural related depth maps; a controller connected with the DPU for receiving the plural related depth maps and then producing an indicating data; and a display device connected with the controller for displaying the indicating data around the vehicle in a vertical view.

Abstract: Frame images captured in a continuous manner are acquired, and temporarily stored. Characteristic points of faces in the acquired frame images are extracted. A sum (expression change amount) of distances between characteristic points of the face (face parts) in a current frame and the characteristic points of a preceding frame is calculated. The target frame image in which the expression change amount is largest, and m frame images preceding and following the target frame image in which the expression change amount is largest are extracted as best image candidates. A best shot image is extracted from the best image candidates and stored in a storage medium. Thus, only an image (best shot image) which contains a face which a user wishes to record can be efficiently extracted from among images captured in a continuous manner, and stored.

Abstract: A method for inspecting a diced object that comprises multiple dies, the method includes: acquiring multiple images of multiple portions of the diced object, starting from a first portion that comprises an alignment area and continuing through adjacent portions of the diced object; assigning a die index to each die of the multiple dies of the diced object, starting from a die of the first portion and continuing through adjacent portions of the diced object; associating between dies of the diced object and a dies of a reference object in response to the assigned indexes and locations of the dies of the diced object; wherein the reference object is not diced; and comparing between a die of the diced object and another die while taking into account an association between the die of the diced object and a reference object die.

Abstract: There is disclosed an image resolution adjustment method comprising the steps of: performing a predetermined selection rule to select one of scaling modes based on a source resolution Vi and a display resolution Vo to generate a scaling value set for outputting a scaled image; and determining whether a smoothing process to determine whether or not the scaled image is smoothed based on application requirements, wherein the scaling modes comprises a first scaling mode, a second scaling mode and a third scaling mode to generate each of the corresponding scaling value set, respectively. The scaling value set is provided to generate replicated pixels or lines for each pixel or line of the source image during a horizontal or vertical scaling period, and the replicated pixels or lines are arranged in horizontal or vertical symmetry in relation to its central region of the source image.

Abstract: A low cost image quality enhancement method to be utilized in an ordinary consumer camera and for post processing of an existing image database is described herein. The quality enhancement is transferred into an adaptive intensity stretching process in the YUV domain. A different enhancement process is designed for a luminance (Y) channel and chrominance (UV) channel. The parameters in the enhancement process are estimated based on the contents of the image. After the stretching-based enhancement, an adaptive unsharp masking process is applied to the luminance data. The quality is significantly improved for the images shot under unfavorable conditions.

Abstract: A method of image compressing is provided. During compressing, color intensity of the image is considered. When the color intensity of the image is relatively high, lower bits used for representing the image are dropped. When the color intensity of the image is relatively low, upper bits used for representing the image are dropped. By this, the image is compressed according to color intensity of the image. Therefore, the images with different color intensities are compressed dynamically. Correspondingly, a method of image decompressing is provided. Moreover, a compressing apparatus and a decompressing apparatus are also provided.

Abstract: A method and system is provided for segmenting scanned image data in accordance with mixed raster content processing for more efficient processing of non-uniform color touching objects. The scanned data is segmented to background and foreground layers wherein the foreground layer is comprised of a plurality of objects such as text characters. At least one of the plurality of objects is identified as being non-uniform in color. The non-uniform color object is partitioned into a plurality of sub-objects of predetermined size pixel blocks. The sub-objects are then clustered by uniform color and coded with a binary compression algorithm as a foreground layer segment. Non-uniform color sub-objects are alternatively discarded for compression with the background layer algorithm, or processed for determination of a particular color based upon the color of a plurality of pixels within the sub-object.

Abstract: A method for a computer system includes receiving a first camera image of a 3D object having sensor markers, captured from a first location, at a first instance, receiving a second camera image of the 3D object from a second location, at a different instance, determining points from the first camera image representing sensor markers of the 3D object, determining points from the second camera image representing sensor markers of the 3D object, determining approximate correspondence between points from the first camera image and points from the second camera image, determining approximate 3D locations some sensor markers of the 3D object, and rendering an image including the 3D object in response to the approximate 3D locations.

Abstract: A computing device may select a source tile from a source image. From the source tile, the computing device may select a first rectangular feature and a second rectangular feature. Based on the first and second rectangular features, the computing device may calculate a source feature vector. The computing device may also select a search area of a target image, and a target tile within the within the search area. Based on the target tile, the computing device may calculate a target feature vector. The computing device may determine that a difference between the source feature vector and the target feature vector is below an error threshold, and based on this determination, further determine a mapping between the source image and the target image. The computing device may then apply the mapping to the source image to produce a transformed source image.

Abstract: An image processing apparatus and an image processing method. The image processing apparatus includes a first convolution unit, a weight generator, a second convolution unit, an arithmetic unit and an outputting unit. The first convolution unit performs a convolution to output edge strength according to an original image signal and a high pass filter mask. The weight generator chooses a weight coefficient according to the edge strength. The second convolution unit performs a convolution to output an unsharp image signal according to the original image signal and a low pass filter mask. The arithmetic unit outputs a first sharpening signal according to the original image signal, the unsharp image signal and the weight coefficient. The outputting unit outputs a processed image signal according to the original image signal and the first sharpening signal.

Abstract: Systems, methods, and apparatuses, including computer program products, are provided for re-layout of composite images. In some implementations, a method includes identifying geometric transformations corresponding to multiple images from a collection of images, where a geometric transformation reorients a corresponding image in relation to a common reference frame when applied and identifying a reference image for the multiple images in the collection of images. The method also includes determining overlapping image regions for the multiple images starting from the reference image, the determining based on the identified geometric transformations, determining additional transformations of a specified type for the multiple images based on the overlapping image regions, where an additional transformation lays out a corresponding image in relation to the reference image when applied, and making the additional transformations available for further processing and output with respect to the collection of images.