Abstract: A device, system, and method for displaying seismic image data may include computing, from a wide-azimuth data set, a discrete data set associated with an image function at a seismic image point. The discrete data set may be mapped onto a continuous curved three-dimensional surface. The mapped data set may be projected onto a continuous planar surface. The projected data may be displayed as a planar disk. A plurality of continuous planar surfaces, each representing a single image point, may be assembled to form a three-dimensional body, representing a seismic gather of image points. The three-dimensional body may be displayed. Other embodiments are described and claimed.

Abstract: The present invention relates to methods and systems for automatic image cropping. An automatic image cropping system includes a downsampling system, a saliency analyzer, a spatial scatter, and a face detector configured to detecting one or more faces within the image. The saliency value of each pixel not associated with a detected face within the image is adjusted if one or more faces within the image are detected. A search system defines a saliency region based on a total value of saliency values within the saliency region and on a parameter, where the parameter value is based on a relative importance of a false positive pixel to a false negative pixel. The search system also defines a crop region using an aspect ratio that includes the saliency region and determines a position of the crop region based the saliency values within the crop region by performing a one dimensional search.

Abstract: An image processing apparatus for detecting paragraphs in a textual image includes an input component for receiving an input image in which textual lines and words have been identified and a page classification component for classifying the input image as a first or second page type. The apparatus also includes a paragraph detection component for classifying all textual lines on the input image as a beginning paragraph line or a continuation paragraph line. The apparatus is also provided with a paragraph creation component for creating paragraphs that include textual lines between two successive beginning paragraph lines, including a first of the two successive beginning paragraph lines. The paragraphs that have been identified may be classified by the type of alignment they exhibit. For instance, paragraphs may be classified according to whether they are left aligned, right aligned, center aligned or justified.

Abstract: An image processing device extracts additional information from image data and includes an input unit to input a plurality of image data items, an additional information extracting unit to extract an additional information item from each image data item, and a determining unit to determine a process to be performed for each image data item based on the extracted additional information item. The determining unit is configured to determine a process to be performed for an image-data group containing the plurality of image data items, based on a plurality of additional information items extracted from the plurality of image data items, and determine a process to be performed for each image data item based on one of the plurality of additional information items.

Abstract: An apparatus for detecting movement of an object captured by an imaging device, the apparatus includes a moving object detection unit, that is (1) operable to detect movement of an object based on a first moving object detecting process, and (2) operable to detect movement of the object based on a second moving object detecting process. The apparatus also includes an output unit operable to generate an output based on the detection by the moving object detection unit based on at least one of the first and second moving object detecting processes.

Abstract: A system and method which determines an adaptive vertical search range used to provide motion estimation in digital video content are disclosed. In some embodiments, a fixed-size vertical search range for the motion estimation is defined and utilized. A reference frame and target frame are stored in memory, and a block in the reference frame is selected for consideration. An offset value is determined which is indicative of a directional shift of the fixed-size vertical search range and the vertical search range is shifted based on the offset value. A motion vector is then estimated using the shifted vertical search range.

Abstract: The invention relates to a device and a method for testing systems or devices with visual output and at least one mechanical input element. The device comprises an input unit for the automated mechanical actuation of the at least one input element of the device, an image analysis unit, which acquires and analyzes the visual output of the device, and a control unit, which controls the input unit and image analysis unit, and automatically determines a test result based on predetermined desired outputs and the findings of the image analysis unit.

Abstract: A method for generating a multi scale representation of an input image, the method comprising the procedures of: estimating a scale factor corresponding to said input image; determining a set of Gaussian difference kernels according to said estimated scale factor, and according to a predetermined set of Gaussian kernels; and generating a multi-scale representation of said input image by applying each of said set of Gaussian difference kernels on said input image.

Abstract: A method apparatus and computer product for imaging a human breast to map the breast ductal tree is disclosed. First, a breast is diffusion tensor imaged with high spatial resolution. Then the breast ductal tree is tracked using a protocol for breast based on echo-planar imaging (EPI) diffusion designed for optimizing diffusion weightings (b values), number of non-collinear directions for tensor calculations, diffusion, echo and repetition times, spatial resolution, signal to noise, scanning time and a sequence for fat suppression. The diffusion tensor is calculated by a non-linear best fit algorithm and then diagonalized with principal component analysis to three eigen vectors and their corresponding eigen values. A vector field map is obtained for tracking of breast ducts of the ductal trees along the direction of the 1st eigenvector v1 and the ductal tree is displayed on a voxel by voxel basis in parametric images using color coding and vector pointing.

Abstract: A system dynamically improves quality of medical images using at least one processing device including an image analyzer, a correction processor and a message generator. The image analyzer automatically parses and analyzes data representing an image of a particular anatomical feature of a patient acquired by a medical image acquisition device to identify defects in the image by examining the data representing the image for predetermined patterns associated with image defects. The correction processor uses a predetermined information map associating image defects with corresponding corrective image acquisition parameters to determine corrected image acquisition parameters for use in re-acquiring an image using the image acquisition device in response to an identified defect. The message generator generates a message for presentation to a user indicating an identified defect and suggesting use of the corrected image acquisition parameters for re-acquiring an image.

Abstract: The present application relates to a method, apparatus and programmable product for uniquely identifying a document. More specifically, the application allows for the identification of the document through collection of minutiae data at various points throughout the document's lifecycle without reliance upon or requirement for any unique identification characters, barcodes and/or objects that were added to the document specifically for the purpose of identification.

Abstract: Embodiments of a system and method are described that automate processes to reconstruct models from two-dimensional images. In one embodiment, the systems comprise an apparatus that can acquire a plurality of images of an object and automatedly form a boundary about the object in each of the images. The boundary highlights a portion of the image that will form the basis for the model. The apparatus can also select a primary image from the images, wherein the boundary in the primary image is narrowest relative to an axis that is common to each of the images. In one example, the apparatus can select a secondary image, which is perpendicular to the primary image, and reconstruct the primary image and the second image to generate the model.

Abstract: A system and method for motion estimation involves obtaining input image frames, where the input image frames correspond to different instances in time, and performing motion estimation on the input image frames using depth information from the input image frames, where the depth information from an input image frame indicates how far a pixel in the input image frame is located from a surface of a three dimensional space.

Abstract: A determination is made for each of multiple regions in multiple images of how good that region is perceived as being. A base image is identified, and a combined image is generated from the multiple images by automatically replacing each region of the base image with a corresponding region of another image if the corresponding region has been determined as being better than the region of the base image. The generating of the combined image can include automatically selecting from one of the multiple images a region in which an object that is present in one or more corresponding regions of other images is absent. Additionally, for a particular region of the base image, corresponding regions of the other images can be displayed, and the particular region replaced with a user-selected one of the corresponding regions of the other images.

Abstract: When a mobile is detected using an imaging device installed in the mobile, the image of a partial area is enlarged/reduced depending on variation in distance to the detection object mobile and then it is compared under a fixed scale thus causing increase in computation cost. In order to eliminate the need for an enlargement/reduction processing or a deformation correction processing every time when collation is performed, an input image is converted into a virtual plane image having a size or a shape on the image of a detection object mobile which does not vary depending on the distance between the mobiles. Using a pair of virtual plane images obtained at two different times, points are made to correspond and the mobile is detected based on the gap of corresponding points.

Abstract: A process for checking the quality of logs, each log having a front surface (2), a rear surface (6) and a lateral surface (3). In the process, the quality check being carried out by means of a visual examination of the outer appearance of the logs (1). The process also comprising the operating steps of obtaining a first flat photographic representation (7) which represents the flat extension of the lateral surface (3) of the log (1), and if necessary a second flat photographic representation (4) which represents the front surface (2) of the log (1), and a third flat photographic representation (5), representing a rear surface (6) of the log (1). Finally, the quality of the log (1) is evaluated by means of an examination of the photographic representations (4), (5), (7).

Abstract: The present invention relate generally to digital watermarking and data hiding. One claim recites a method including: obtaining a first color channel and a second color channel, the first color channel and the second color channel are components of a color image signal or color video signal; obtaining a digital watermark orientation pattern, the orientation pattern serving to facilitate detection of a watermark message; separating the digital watermark orientation pattern into first frequency components and second frequency components; utilizing a programmed electronic processor or electronic processing circuitry, transforming the first color channel by steganographically embedding the first frequency components therein; and utilizing a programmed electronic processor or electronic processing circuitry, transforming the second color channel by steganographically embedding the second frequency components therein. Of course, other combinations and claims are provided too.

Abstract: An image processing device for dividing an image imaged by imaging means into multiple regions includes: processing means for grouping, when difference of the pieces of image data between a single pixel within the image and a pixel adjacent thereto is less than a predetermined threshold, the single pixel and the adjacent pixel, and dividing the image into multiple regions with finally obtained each group as each region of the image; and average-value calculating means for calculating the average value of the image data within the group including the single pixel; with the processing means comparing the image data of the single pixel, and the average value calculated at the average-value calculating means regarding the group to which the adjacent pixel belongs; and when the difference thereof is equal to or greater than a predetermined second threshold, doing not group the single pixel and the adjacent pixel.

Abstract: A method of verifying a registration of a digital image includes receiving a reference image and a moving image registered to the reference image representing the same object, selecting one or more landmarks in the images, defining a neighborhood in the domain of each image near each selected landmark, extracting feature sets from the neighborhoods for the reference image and the registered moving image, calculating a total quality measure of the registration of the moving image from a distance metric applied to the feature sets extracted from the neighborhoods of the reference image and the registered moving image, comparing the total quality measure to a threshold determined from a reference atlas for the object represented in the image, and determining whether to accept or reject the registration of the moving image based on the comparison result.

Abstract: An image processing device includes: a coordinate conversion unit (142) which calculates a corresponding sampling coordinate on a color mosaic image corresponding to a pixel position of a color image when a deformation process is performed, according to the pixel position of the color image; a sampling unit (143); a sampling unit (143) which interpolates-generates a pixel value in a sampling coordinate for each of color planes obtained by decomposing the color mosaic image; and a color generation unit (144) which generates a color image by synthesizing interpolation values of the respective color planes. Each pixel value of a color image subjected to a deformation process is obtained as a pixel value of the sampling coordinate from the color mosaic image by interpolation calculation, thereby realizing the color interpolation process for generating a color image from the color mosaic image and a deformation process of the color image by one interpolation calculation.