Abstract: The invention is directed to an image processing device and a processing method thereof. The image processing device comprises an image calibration module estimating multiple local motions and global motions of unselected images relative to a target image and performing multiple motions calibrations so as to generate multiple calibrated images, a moving-object detection module determining if a difference value between each of the local motions and the corresponding global motions is greater than a threshold value and if a pixel difference value between each pixel point of the target image and each pixel point of the calibrated images is greater than a predetermined difference value so as to generate multiple object motion pointers, and an image blending module performing a calculation on each pixel point of the target and calibrated images based on the object motion pointers so as to generate a super-resolution image.

Abstract: A pixel interpolation process is based on detection of a potential edge in proximity to a pixel being estimated, and the angle thereof. The potential edge and its angle is determined based on filtering of offset or overlapping sets of lines from a pixel window centered around the pixel being estimated and then cross-correlating the filter results. The highest value in the correlation result values represents a potential edge in proximity to the pixel being estimated and the index of the highest value represents the angle of the potential edge. This information is used in conjunction with other information from the cross-correlation and analysis of the differences between pixels in proximity to verify the validity of the potential edge. If determined to be valid, a diagonal interpolation based on the edge and its angle is used to estimate the pixel value of the pixel. Otherwise, an alternate interpolation process, such as vertical interpolation, is used to estimate the pixel value for the pixel.

Abstract: Methods and a processing device are provided for reducing purple fringing artifacts appearing in a digital image. A linear filter may be applied to a digital image to identify purplish candidate regions of pixels. Ones of pixels that are in any of the purplish candidate regions and are within a predefined distance of a high gradient/high contrast region may be identified as damaged pixels. A map of the damaged pixels may then be created, or formed. The damaged pixels may be reconstructed based on interpolation of values from undamaged pixels on a fringe boundary with guidance from a green channel. In various embodiments, the damaged pixels may be reconstructed based on a Poisson blending approach, an approximated Poisson blending approach, or a variety of approaches based on interpolation of values from undamaged pixels on a fringe boundary, with guidance from a green channel.

Abstract: An image processing apparatus includes a data supply node to receive line data scanned in a main scan direction of an image, an image enlargement unit coupled to the data supply node to apply to the line data an enlargement process for enlarging the image by an enlargement factor equal to an integer so as to produce enlarged data at an output node, and an image reduction unit coupled to the output node of the image enlargement unit to apply to the enlarged data a reduction process for reducing the enlarged image by a desired reduction factor so as to produce reduced data at an output node.

Abstract: An image forming apparatus includes a resolution converting unit, an address generating unit, a density determining unit, and an image path selector. The resolution converting unit converts a resolution of image data into a higher resolution. The address generating unit performs a position determining process of determining a position of an additional pixel on the basis of main-scanning directional positions of pixels composing the converted image data and respective shift amounts of the pixels shifted to a sub-scanning direction. The density determining unit determines a density of the additional pixel on the basis of a density of a pixel located at a position corresponding to the determined position in the image data. The image path selector scales the image data up or down by controlling the address generating unit while adding the additional pixel having the determined density to the determined position.

Abstract: Methods and apparatuses use a pixel-adaptive interpolation algorithm to provide image upscaling. For each pixel location, the algorithm determines whether to use a high quality scaler algorithm (such as a polyphase filter, for example) or a directional interpolator to determine the pixel value. The determination of the appropriate interpolation algorithm is based on whether the pixel is determined to be an edge. If the pixel is determined to be an edge, the pixel-adaptive interpolation algorithm may use the directional interpolator to process the pixel; otherwise, the pixel is processed using a scaler algorithm.

Abstract: Disclosed herein are a bilinear interpolation circuit for an image and a method thereof. The bilinear interpolation method for ran image according to an exemplary embodiment of the present invention includes: increasing an input clock of a camera two times by a PLL; reading a plurality of reference pixels to be interpolated from the memory while storing input images (pixels) in the memory by the memory control unit, matching a clock timing increased two times; calculating pixel values to be corrected by an arithmetic operation by the data interpolation unit based on the read pixel (image) data; and outputting the calculated pixel values to be corrected by the output format conversion unit, matching an original clock speed.

Abstract: A method of detecting displacement with sub-pixel accuracy includes the steps of: capturing a first array image and a second array image; interpolating the first array image to form a reference image; interpolating the second array image to form a comparison image; comparing the reference image with the comparison image so as to obtain a displacement. The present invention also provides an apparatus for detecting displacement with sub-pixel accuracy.

Abstract: Systems and methods of determining motion vectors, such as for video encoding, are disclosed. In one example, motion vectors are determined for a current frame, using sampled pixel information from a reference frame. Sampled pixel information is obtained using a sampling pattern. The sampling pattern, in one example, includes subsampling pixels at different rates for horizontal and vertical directions. The subsampling rate can differ, based on an amount of motion represented by a matching block (e.g., the farther a match is found away from an origin of the block, the more subsampling can be done). In another example, a full pixel resolution is maintained proximal an original location of the block; as distance increases in one or more directions, subsampling can begin and/or increase. Sampled pixels can be stored. Interpolation of the sampled pixels can be performed and the sampled and resulting interpolated pixels can be used for comparison.

Abstract: A method and device identify from plural sets of pixels of a digital image, a set of pixels whose values are to be used in image processing to determine a target-pixel value. The method and device: obtain a pixel set comprising solely the target pixel and first and second pixel subsets extending along only first and second directions, respectively, each pixel of the pixel set being contiguous with another pixel of the set; obtaining first and second measures being, respectively, measures of an angle difference between the first direction and the gradient of a pixel of the first subset, and of an angle difference between the second direction and the gradient of a pixel of the second subset; and determining whether the obtained set of pixels is the pixel set whose values determine the value of the target pixel, in accordance with the first and second measures.

Abstract: A map editing system for processing map data in order to reduce discrepancies between geometric objects in the map data through the use of a cost function. The system selects a polygon shaped object (e.g., a park) for processing. The polygon may be located close to several polyline objects (e.g., streets) or other polygon objects so that discrepancies, such as open spaces, appear between the objects when displayed together in a map. To eliminate these discrepancies while maintaining the overall appearance of the polygon, the system repeatedly adjusts the border of the polygon until the attributes of the polygon minimize a cost function.

Abstract: Apparatus for interpolating or dispersing effects over a video frame, useful for chroma keying of an image comprising a foreground including a part to remove, such as a background or spill from the background. The apparatus handles pixels of the image one by one and includes an interpolation unit for applying an interpolation of attributes at a respective pixel and then applies a function based on the attributes. For example in chroma keying an opaqueness assigner may compare the local color with a color of the part to remove using the interpolation. Based on the comparison, keying is used to set at the respective pixel a level of opaqueness for the pixel.

Abstract: A computer-implemented method for invariant-based normal estimation. The method includes calculating a set of measured invariants for a point associated with a surface of an object, where the set of measured invariants is based on pixel information that includes lighting information, calculating one or more sets of estimated invariants for the point associated with the surface of the object, where each set of estimated invariants is based on a known lighting environment for the object and a different normal for the point associated with the surface of the object, and determining a first normal for the point associated with the surface of the object that results in the set of measured invariants corresponding to a first set of estimated invariants.

Abstract: A method, including calculating a first distance matrix for a first binary image and a second distance matrix for a second binary image, and calculating a first gradient matrix for the first distance matrix and a second gradient matrix for the second distance matrix. Using the calculated distance and gradient matrices, a displacement matrix is calculated that defines a change in position between elements in the first distance matrix and corresponding elements in the second distance matrix. Outlier elements are identified including elements in the displacement matrix satisfying at least one predetermined criterion, and the identified outlier are replaced with calculated interpolated values.

Abstract: A method of determining interpolation coefficients (607, 609, 610, 611) of a symmetric interpolation kernel (608) is disclosed. The method comprises determining a first interpolation coefficient (611) from the symmetric interpolation kernel (608) and storing the first interpolation coefficient in a memory (506). The method then determines the value of an intermediate function (310) from symmetrically opposed segments (201, 204) of the kernel, and determines a subsequent interpolation coefficient dependent upon the first interpolation coefficient and the value of the intermediate function.

Abstract: An image processing apparatus for scaling an image including: an operation position determining section for determining a pixel operation position, which is either a pixel inserting or deleting position, based on a scaling ratio; an inserting/deleting section for inserting/deleting a pixel to/from the pixel operation position determined by the operation position determining section; an error calculating section for calculating a density difference as an error between densities in a vicinity of the inserted/deleted pixel via the inserting/deleting section, before and after the insertion or deletion; and an error allocating section for allocating the error, calculated by the error calculating section, to the inserted pixel and pixels in a vicinity of the inserted or deleted pixel, so that a pixel value, after allocation, of a pixel of an allocation destination, falls within an allowable range estimated from a pixel value of a pixel near the pixel of allocation destination.

Abstract: The methods and systems of this invention allow for independent adaptive control of ringing and overshoot effects in 2-dimensional array interpolation processes, including in image and video rescaling and analysis. The methods and systems can use either a column-wise or a row-wise interpolation, or a combination thereof. Each uses a respective preliminary interpolation of data, followed by ringing and/or overshoot control. Controllable parameters allow variability in the amount of ringing and/or overshoot retained in the interpolated data. The ringing and overshoot controls apply a local analysis of the data to adjust the preliminary interpolation results. The methods may be repeated iteratively, for example, to obtain a desired rescaling of an image data array.

Abstract: An image processing device may include detection means for detecting a motion vector of an input image signal which is an input time-series image signal; interpolation means for interpolating, based on the motion vector, a signal between input image signals which is an image signal at an arbitrary time between the input image signal and a previous input image signal immediately preceding the input image signal, the interpolation means for further outputting an interpolated signal; acquisition means for acquiring superimposition information which indicates the position, in the input image signal, of a predetermined image signal to be superimposed on the input image signal; and specification means for specifying, based on the superimposition information, at least one non-interpolation region of the signal between input image signals in which the interpolation is not performed.

Abstract: The present invention discloses a character display method and apparatus. The method includes: obtaining a display color value of a character; obtaining a background color value of the character according to a position of the character; obtaining a difference between the display color value and the background color value; obtaining an outline of the character when the difference is smaller than a preset threshold; and displaying the character that has the outline. By adopting the present invention, the character may be clearly displayed in a background without changing a color of the character and a color of the background.

Abstract: An image taking system including: (a) a CMOS or CCD image sensor; (b) an interest-region setter configured to set regions of interest within an image taking area of the image sensor; (c) an acquiring-condition determiner configured to determine an image-data acquiring condition required for acquiring at least two image data generated in at least two of the regions of interest; and (d) an image-data acquirer configured to acquire the at least two image data. The acquiring-condition determiner includes an exposure-time determining portion configured to determine, as the image-data acquiring conditions, at least two different exposure times required for acquiring the at least two image data generated in the at least two regions of interest. The image-data acquirer includes an exposure-time-based-image-data acquiring portion configured to acquire the at least two image data, such that the acquired at least two image data are based on the at least two different exposure times.

Abstract: An interpolation computation unit (3B) treats, as positions of interest, positions where pixels within a high-resolution image (D30) occupy when the high-resolution image (D30) is superimposed on a low-resolution image (D01), and for each position of interest, obtains a pixel value for a pixel assumed to exist at the position of interest by performing an interpolation computation using pixel values of a plurality of pixels within the low-resolution image (D01). An interpolation coefficient calculation unit (3A) obtains interpolation coefficients (D3A) having values that increase with increasing strength of correlation of the pixels in the plurality of pixels in the low-resolution image with the pixel of interest, and outputs the interpolation coefficients to the interpolation computation unit (3B). Angles of edges and shapes of edges are not classified into any predetermined patterns; therefore, it is possible to perform suitable interpolation computations regardless of edge shape.

Abstract: One or more derived versions of image content may be obtained by interpolating two or more source versions of the same image content. A derived version may be targeted for a class of displays that differs from classes of displays targeted by the source versions. Source images in a source version may have been color graded in a creative process by a content creator/colorist. Interpolation of the source versions may be performed with interpolation parameters having two or more different values in two or more different clusters in at least one of the source images. A normalized version may be used to allow efficient distribution of multiple versions of the same content to a variety of downstream media processing devices, and to preserve or restore image details otherwise lost in one or more of the source versions.

Abstract: Adaptive filtering techniques are set forth that improve video playback performance. A color similarity metric is computed for source pixels undergoing an image transform operation to determine color values of a target pixel location. The value of the color similarity metric defines what algorithm is used to determine the color values of the target pixel location from the source pixels. While the computation of the color similarity metric introduces additional instructions for each pixel, going against conventional wisdom, enormous performance savings by avoiding unnecessarily complex sets of interpolation instructions where a simpler instruction set suffices, outweighs any such cost from additional instructions.

Abstract: An image data converting device of at least one embodiment of the present invention for converting, by linear interpolation, input image data having a predetermined resolution into delta arrangement image data having a resolution that is smaller than the predetermined resolution, the image data converting device includes: an even line pixel value converting section for converting a value of each pixel in each even line in the input image data into a value of each pixel in each even line in the delta arrangement image data, by using a predetermined initial value for even lines; and an odd line pixel value converting section for converting a value of each pixel in each odd line in the input image data into a value of each pixel in each odd line in the delta arrangement image data, by using a predetermined initial value for odd lines, the predetermined initial value for odd lines being (1±?)/2(0???0.5) of the initial value for the even lines.

Abstract: An image processing device that, even when a degradation model differs from a real degradation process of an obtained low-resolution image, generates a high-resolution image while restricting noises from occurring due to differences between the degradation model and the real degradation process.

Abstract: The present invention provides an apparatus for interpolation which is able to process input data with multiple video standards without sacrificing chip area. The interpolation unit comprises: a first interpolation unit for interpolating input data; a second interpolation unit for interpolating input data; a filter indicator for providing information to the first interpolation unit and the second interpolation unit; and an output unit for multiplexing and averaging output from the first interpolation unit and the second interpolation unit. The present invention also provides a motion compensation unit and a decoder for processing multiple video standards.

Abstract: A method of pixel interpolation in which a two-dimensional digital filter is arranged so as to interpolate an output pixel from a two-dimensional array of input pixels comprises detecting the direction of an image feature at a pixel position to be interpolated; applying a shear transformation to the digital filter and/or to the array of input pixels so as to map the operation of the filter to the detected image feature direction in respect of at least a first one of two axes of the two dimensional filter; and applying the digital filter to obtain the output pixels.

Abstract: Input pixel values associated with input pixel positions having a first spacing along a direction are received and processed to determine output pixel values associated with output pixel positions having a second spacing along the direction, from respective combinations of input pixel values weighted by coefficients given by an interpolation function. In a downscaling operation, the second spacing is larger than the first spacing, and the weighting coefficients represent values of the interpolation function expanded spatially by an expansion factor equal to the ratio of the second spacing to the first spacing.

Abstract: An image display device includes: an external light measurement unit measuring the illuminance of an external light a plurality of times, and generating a measurement value indicating the illuminance; a storage unit storing history data which shows the measurement values, and color mode data which shows a correspondence between the illuminance and a color mode; a determination unit, based on the history data, determining whether or not it is a changed condition wherein the illuminance changes upward or downward, or the illuminance fluctuates; and an adjustment unit, in the event that it is not the changed condition, determining the color mode to be applied based on the measurement values and the color mode data, and adjusting the color or brightness of an image in accordance with the color mode, and in the event that it is the changed condition, continuing the adjustment currently being applied as the image adjustment.

Abstract: To obtain a high resolution image from two or more low resolution images, positional offsets among the low resolution images are determined and the low resolution images are mapped onto a common plane according to the positional offsets. Pixel values in the high resolution image are calculated by weighted interpolation from the pixel values of the low resolution images, using interpolation coefficients that increases with increasing correlation with the pixel of interest. Correlation is determined by taking horizontal and vertical first and second derivatives of the pixel values in one low resolution image to find a direction of strong correlation. Appropriate interpolation is thereby obtained even near edges and other abrupt changes in the image.

Abstract: An image processing apparatus includes: a representative value calculation unit calculating a representative value from an input first image signal; an interpolation unit interpolating the representative value calculated by the representative value calculation unit using a second image signal input after the first image signal; and an adjustment processing unit blending the interpolated image signal and the second image signal so that an output ratio of the image signal interpolated by the interpolation unit is smaller when a variation amount of an image corresponding to the second image signal with respect to an image corresponding to the first image signal is large in comparison to a case when the variation amount is small.

Abstract: An apparatus for color interpolation using an adjustable threshold is disclosed. The color interpolation apparatus calculates the difference between the maximum value and the minimum value of the elements of the image data and determines the color interpolation method of the image data depending on the difference to perform the corresponding color interpolation. With the present invention, the improved image quality can be provided because the color interpolation can be performed as a user desires.

Abstract: A segmentation unit included an assignment unit configured to assign a first pixel of a first image of a sequence of images to a segment comprises an assignment unit, and to assign a first homogeneity value to the first pixel on basis of the first image. An averaging unit is configured to calculate an average homogeneity value for the first pixel by averaging the first homogeneity value and a second homogeneity value being determined for a second pixel of a second image of the sequence of images. The first and second pixels are related by a motion vector. A comparing unit is configured to compare the average homogeneity value with a threshold in order to assign the first pixel to the segment.

Abstract: An image processing device includes: a transformation ratio calculation unit which calculates transformation ratio of an image after transformation, the image after transformation being obtained by transforming an original image under predetermined rule; a filter coefficient calculation unit which calculates filter coefficients based on the transformation ratio; and a pixel value calculation unit which calculates the pixel value of each pixel in the image after transformation using the filter coefficients and outputs the pixel value of the image after transformation as image data after transformation.

Abstract: A system, a method and computer-readable media for processing raw image data with a graphics processing unit (GPU). Raw image data generated by an imaging sensor is received. A set of instructions for demosaicing the raw image data is communicated to the GPU. The GPU is enabled to demosaic the raw image data by executing the set of instructions.

Abstract: The described embodiments comprise a system that adjusts pixel values to produce visual effects in a frame to be displayed. During operation, the system receives coordinates and pixel-adjustment values for one or more control points within the frame. Next, the system calculates pixel-adjustment values for pixels in the frame based on the coordinates and the pixel-adjustment values for the one or more control points. The system then applies the pixel-adjustment values to the pixels within the frame and displays the frame.

Abstract: An apparatus and method for efficiently interpolating and rendering transformed images on mobile devices are provided. The method includes obtaining a plurality of super pixels by virtually increasing a resolution of the original image, determining a sampling position of a target image pixel under transformation, selecting the nearest super pixel from the plurality of super pixels for the target image pixel, and determining a characteristic of the selected nearest super pixel for the target image pixel. The apparatus and method render a transformed image having image quality comparable to that achieved by bilinear interpolation method while significantly reducing the necessary calculation cost.

Abstract: A forward interpolation approach is disclosed for enabling a second version of an image to be constructed from a first version of the image. According to one implementation, an input pixel from the first version of the image is forward mapped to the second version of the image to determine a set of candidate pixels that may be affected by the input pixel. Each candidate pixel is then backward mapped to the first version of the image to determine whether they are actually affected by the input pixel. For each candidate pixel that is actually affected by the input pixel, a pixel value is determined for that candidate pixel based at least in part upon the pixel value of the input pixel. By using this forward and backward mapping technique, forward interpolation can be implemented quickly and efficiently.

Abstract: Processing of a digital image that has been recorded through an optical system is described, the image being in a raw format matrix of picture elements and comprising a plurality of subsets of picture elements, each subset corresponding to a color component. The method comprises analyzing values of picture elements of the color components in terms of spatial features, resulting in at least one calculated parameter that is representative of aberration caused by the optical system, and performing demosaicing of the digital image by, for each picture element under consideration, defining a kernel comprising picture elements that are to be considered during the demosaicing, the definition of the kernel being dependent on the at least one parameter that is representative of the aberration.

Abstract: The present invention relates to generation of an appropriate high-resolution image with respect to a plurality of input images. An image processing apparatus including a unit for acquiring a relative movement amount for each first image between a reference image selected from a plurality of first images and the first images; a unit for generating a fourth image having a first resolution for each first image in accordance with a third image having a second resolution, the relative movement amounts, and image capture characteristics of an image capture device; a unit for acquiring, for each fourth image, an evaluation value indicating a difference between the fourth image and the first image corresponding to the fourth image; and a unit for generating a second image having the second resolution by updating the third image using an update value that is determined using the fourth images in accordance with the evaluation values.

Abstract: Embodiments described herein facilitate or enhance the implementation of image recognition processes which can perform recognition on images to identify objects and/or faces by class or by people.

Abstract: An image interpolating method and apparatus, in which horizontal and vertical Differences of Absolute Inter-channel Differences (DAIDs) are calculated from a color filter array (CFA) image, and an unknown pixel is interpolated in horizontal and vertical directions estimated in consideration of the DAIDs of R, G, and B pixels. Therefore, the image interpolating method and apparatus provide a large Peak Signal and Noise Ratio (PSNR), a Structural Similarity (SSIM), and high visual quality images.

Abstract: A set of even interpolated sub-pixels is formed based on a pixel window and a tap coefficient register having a tap coefficient set, the pixel window is shifted and, applying the tap coefficient register a set of odd interpolated pixels is formed. The set of even interpolated sub-pixels and the set of odd interpolated sub-pixels are accumulated, repeatedly, until a termination condition is let. In the accumulating, the tap coefficient register is updated with another tap coefficient set, the pixel window is shifted, and the even interpolated pixels are incremented, the pixel window is then shifted again and the odd interpolated pixels are incremented.

Abstract: An image processing apparatus characterized by including; an area sensor unit that reads from an original document image a plurality of frames of image data having a shift of less than one pixel, an output resolution acquisition unit that obtains an output image resolution at which resolution the original document image read by the area sensor unit is output, an acquisition frame number control unit that controls a number of frames read by the area sensor unit according to a result of the output resolution acquisition unit, a correction unit that corrects an inclination of the frames of image data controlled by the acquisition frame number control unit, and a high resolution conversion unit that performs an interpolation processing using the plurality of frames of image data whose inclination is corrected by the correction unit to obtain image data in a resolution higher than a resolution during reading.

Abstract: The invention relates to a method for generating a motion vector field for an intermediate image disposed between a first and a second image.

Abstract: The claimed subject matter relates to an architecture that can facilitate more efficient free view generation in Ray-Space by way of a Radon transform. The architecture can render virtual views based upon original image data by employing Ray-Space interpolation techniques. In particular, the architecture can apply the Radon transform to a feature epipolar plane image (FEPI) to extract more suitable slope or direction candidates. In addition, the architecture can facilitate improved block-based matching techniques in order to determine an optimal linear interpretation direction.

Abstract: An image interpolation method obtains an image line pixel value between two adjacent image lines. The method acquires a luminance change of pixels of two image lines and decides a region of two image lines where only one portion similar to a part of the luminance change of one of the image lines exists in the luminance change of the other image line in the vicinity of the image to be interpolated. Then, among pixel sets located at the symmetric positions about the object image to be interpolated with respect to the pixel within the region, the set having the highest similarity is selected. By using the pixel value of the selected set, the pixel value of the pixel to be interpolated is decided.

Abstract: A radioactive emission probe in communication with a position tracking system and the use thereof in a variety of systems and methods of medical imaging and procedures, are provided. Specifically, wide aperture collimation—deconvolution algorithms are provided, for obtaining a high-efficiency, high resolution image of a radioactivity emitting source, by scanning the radioactivity emitting source with a probe of a wide-aperture collimator, and at the same time, monitoring the position of the radioactive emission probe, at very fine time intervals, to obtain the equivalence of fine-aperture collimation. The blurring effect of the wide aperture is then corrected mathematically. Furthermore, an imaging method by depth calculations is provided, based on the attenuation of photons of different energies, which are emitted from the same source, coupled with position monitoring.

Abstract: A method and system for interpolating video pixels is described, in which the value of a first fractional pixel is calculated based on the values of the first set of integer pixels, while the value of a second fractional pixel is calculated based on the values of the second set of integer pixels. The first set of integer pixels is not equal to the second set of integer pixels. For example, the first and second set may contain different integer pixels and may contain different numbers of integer pixels.

Abstract: A pixel interpolating device includes a cycle calculation unit and an interpolating unit. The cycle calculation unit calculates a cycle in change of pixel values of pixels in a document image obtained by reading a document by first and second photoelectric conversion element arrays each having a plurality of photoelectric conversion elements. The interpolating unit extracts from the pixels such pixels that an interval between each pixel and an interpolated pixel corresponding to a position between the first and second photoelectric conversion element arrays corresponds to the cycle calculated by the cycle calculation unit. The interpolating unit interpolates a pixel value of the interpolated pixel based on pixel values of the extracted pixels.