Abstract: An information processing apparatus includes a designation unit which designates an object, a sensing unit which senses a change which exceeds a threshold value in at least a part of the object when a user zooms in on the object, and a zoom unit which zooms in on the object at the zoom rate which is just less than that when there is a change that exceeds the threshold value in at least a part of the object if there is a change that exceeds the threshold value in at least a part of the object when the user zooms in on the object at the designated zoom rate, and which zooms in on the object if there is no change that exceeds the threshold value in at least a part of the object even when the user zooms in on the object at the designated zoom rate.

Abstract: In some instances, an image may have dimensions that do not correspond to a slot to display the image. For example, an image content item may have dimensions that do not correspond to a content item slot. The image may be resized using seam carving to add or remove pixels of the image. A saliency map for the image may be used having saliency scores for each pixel of the image. Evaluation metrics may be used before, during, and after, seam carving to determine whether salient content is affected by the seam carving. In some instances, a seam cost threshold value may be used for adaptive step size during the seam carving. The resized image may then be outputted, such as for an image content item to be served with a resource.

Abstract: An image processing apparatus for processing image data by a plurality of pipeline-connected processing modules is provided. The apparatus includes a first pipeline processing unit configured to include a plurality of processing modules including a processing module which processes image data for every first size; and a second pipeline processing unit configured to be branched from the first pipeline processing unit and include a plurality of processing modules including a processing module which processes image data for every second size different from the first size. The second pipeline processing unit includes, at a start, a change unit configured to acquire partial image data of the first size from the first pipeline processing unit and change the partial image data of the first size into partial image data of the second size.

Abstract: Methods, systems, and media for image processing using hierarchical expansion are provided. More particularly, the hierarchical expansion can include a merge expansion and/or a refine expansion. In some embodiments, a method for image processing, comprising: receiving a plurality of images, wherein each of the plurality of images has one of a plurality of resolutions; for a first image from the plurality of images that has a first resolution, determining a first set of labels corresponding to each pixel of the first image; and for a second image from the plurality of images that has a second resolution, generating a second set of labels corresponding to each pixel of the second image based on the first set of labels.

Abstract: A method includes receiving an indication of a set of image regions identified in image data. The method further includes, selecting image regions from the set of image regions for text extraction at least partially based on image region stability.

Abstract: Disclosed is an image processing apparatus which (i) determines whether or not characters to be subjected to a character recognition process in image data have a size larger than a predetermined size, (ii) in a case where the characters is determined as larger than the predetermined size, reduces at least a region including the characters so that the size of the characters fits within the predetermined size, and (iii) performs a character recognition process of the characters with use of the reduced image data.

Abstract: An apparatus, system, and method are disclosed for simulating physical movement of a digital image. The apparatus includes an input receiving module, a calculation module, and a output module. The input receiving module is configured to receive a position input identifying a physical unit of measure. The calculation module is configured to correlate the physical unit of measurement to a position of a image positioning coordinate. The output module is configured to output the position of the image positioning coordinate.

Abstract: An image registration method is disclosed for processing a distorted image into a registered image that is aligned with reference to an original image. Distortions from the original image may include scaling, rotation, and noise. The method is based on correlating Radon transforms of both images to determine the rotation angle, and the scaling factor is determined by dividing averages of the overall luminance of each image on the assumption that any added noise will cancel. The Fast Fourier Transform (FFT) is used to estimate global spatial shifts. In one embodiment, the distorted image is first scaled to the size of the original image before being rotated. In another embodiment, the original image is first scaled to the size of the distorted image before rotating the distorted image, and finally scaling it to match the original image. A corresponding system for image registration is also provided.

Abstract: Method and apparatus for compressed sensing yields acceptable quality reconstructions of an object from reduced numbers of measurements. A component x of a signal or image is represented as a vector having m entries. Measurements y, comprising a vector with n entries, where n is less than m, are made. An approximate reconstruction of the m-vector x is made from y. Special measurement matrices allow measurements y=Ax+z, where y is the measured m-vector, x the desired n-vector and z an m-vector representing noise. “A” is an n by m matrix, i.e. an array with fewer rows than columns. “A” enables delivery of an approximate reconstruction, x#, of x. An embodiment discloses approximate reconstruction of x from the reduced-dimensionality measurement y. Given y, and the matrix A, approximate reconstruction x# of x is possible. This embodiment is driven by the goal of promoting the approximate sparsity of x#.

Abstract: An image processing apparatus includes a first storage section and a second storage section, a storage control section, and a computation section. The storage control section sequentially acquires block images obtained as a result of dividing an input image, and stores the block image as a target block image in the first storage section, while storing, in the second storage section, image data of, in a region of the target block image, a region abutting un-inputted block images in the input image, as image data of an abuttal region. The computation section implements a resizing process for changing the size of the target block image by performing an interpolation calculation using image data of the target block image stored in the first storage section and the image data of the abuttal region stored in the second storage section.

Abstract: A method and system for enabling interaction with unmodified 3D graphics applications using face-tracking. The method includes determining a position of a viewer using face-tracking component and transforming a viewer's position to application coordinates. The application coordinates are passed to a wrapper library around a 3D graphics application's library. The 3D graphic application's instruction stream is altered to display 3D graphics on a display with scenes rendered as seen from the viewer's position. The 3D graphics application is forced to load a wrapper library which overloads functions of the underlying 3D graphics application library. In this way, the 3D graphics application can be an existing unmodified 3D graphics application provided on a computer system.

Abstract: Software for supervised learning extracts a set of pixel-level features from each source image in collection of source images. Each of the source images is associated with a thumbnail created by an editor. The software also generates a collection of unique bounding boxes for each source image. And the software calculates a set of region-level features for each bounding box. Each region-level feature results from the aggregation of pixel values for one of the pixel-level features. The software learns a regression model, using the calculated region-level features and the thumbnail associated with the source image. Then the software chooses a thumbnail from a collection of unique bounding boxes in a new image, based on application of the regression model.

Abstract: An image processing apparatus comprising a storage unit configured to store image data; a readout unit configured to read out the image data stored in the storage unit; a detection unit configured to detect a target object from the image data read out by the readout unit; a conversion unit configured to convert a resolution of the image data read out by the readout unit; and a write unit configured to write the image data having the resolution converted by the conversion unit in the storage unit, wherein the readout unit outputs the readout image data in parallel to the detection unit and the conversion unit.

Abstract: Disclosed are various embodiments directed to transcoding a bit stream in parallel. A bit stream may be divided into a plurality of segments, where a plurality of transcoders encode at least a portion of the segments in parallel. If encoding is performed using variable bit rate (BR) encoding, each encoder may encode a segment and vary a BR for the segment. A measured average BR is compared with a target average BR to determine whether to adjust a video quality level (VQL) or any other encoder parameter. A relatively constant subjective quality may be maintained using variable BR encoding while achieving a target average BR. When using constant BR encoding, a VQL or other encoder parameter is used by encoders to achieve relatively constant subjective quality. For example, a relatively continuous quantization parameter between adjacent encoded segments may be achieved.

Abstract: A set of images is processed to modify and register the images to a reference image in preparation for blending the images to create a high-dynamic range image. To modify and register a source image to a reference image, a processing unit generates correspondence information for the source image based on a global correspondence algorithm, generates a warped source image based on the correspondence information, estimates one or more color transfer functions for the source image, and fills the holes in the warped source image. The holes in the warped source image are filled based on either a rigid transformation of a corresponding region of the source image or a transformation of the reference image based on the color transfer functions.

Abstract: An image scaling processor includes a coefficient table storing interpolation coefficients, a multiplier that multiplies each of pieces of pixel data constituting input image data and each of the interpolation coefficients stored in the coefficient table, an adder that repeatedly adds pieces of multiplied data output from the multiplier and obtains a total sum of the pieces of multiplied data for a predetermined number of the pieces of pixel data, a selector that outputs a total sum of the pieces of multiplied data at a timing at which the total sum of the pieces of multiplied data is obtained for the predetermined number of the pieces of pixel data, and a shift circuit that shifts an output of the selector to adjust a bit count of the output image data to a bit count of the input image data.

Abstract: Super-resolution processing is regarded as a kind of intersample interpolation process and performed by using a linear interpolation filter designed according to sampled-data control theory. In an error-system model used in the process of designing the filter, a pre-filter is disposed before a sampler and a post-filter is disposed after the zero-order hold in a signal restoration system. At least either one of the characteristic Q(s) of the pre-filter or the characteristic P(s) of the post-filter is designed to be a low-pass characteristic, whereby the gain of the characteristic K(z) of a digital filter within a middle-to-high frequency range is raised. Raising the gain makes jaggies more prominent. To reduce this effect, in an actual processing system, the image to be processed is passed through a low-pass filter to reduce high-frequency components before the linear interpolation is performed.

Abstract: Conventionally, during a copy operation, certain advanced mode settings make the extraction of additional security information impossible. In order to solve this problem, the print control apparatus includes: determining unit for determining an interval between a pattern element and a pattern element adjacent to the pattern element from the received image data; and control unit for performing a control so as to scale the image at a magnification specified by a user and have the scaled image printed by a printing apparatus when the product of the magnification specified by the user and the interval determined by the determining unit falls within a predetermined range, and configured to terminate or interrupt the printing of the image by the printing apparatus when the product of the magnification specified by the user and the interval determined by the determining unit does not fall within the predetermined range.

Abstract: A method of enhancing spatial resolution of an image. An image is accessed. The image comprises a set of confident pixels and an unconfident pixel positioned adjacent to each confident pixel of the set of confident pixels. The set of confident pixels comprises four or fewer pixels and corresponds to a plurality of known depth values, the unconfident pixel comprises an unknown depth value. A best depth hypothesis for the unconfident pixel is determined using a filter module in which the plurality of known depth values are used as depth hypotheses. The unconfident pixel is updated as a confident pixel using the best depth hypothesis.

Abstract: A robotic surgical system includes a master controller with an input handle and robotic manipulator assemblies including a surgical end effector and an endoscopic camera. The input handle is translatable to provide a position and rotatable to provide an orientation. A control system couples the master controller to the first and second manipulator assemblies. The control system moves the surgical end effector in response to the position and orientation of the input handle. The control system moves the input handle to orient the input handle to correspond to an orientation of the surgical end effector from a viewpoint of the endoscopic camera during the repositioning of at least one of the input handle position, the end effector, or the endoscopic camera. The control system may move the surgical end effector only in a first mode and orients the input handle only in a second mode.

Abstract: A method and system for processing video data using multi-pixel scaling in a memory system are provided. The multi-pixel scaling may include reading pixel data for one or more data streams from the memory system into one or more scalers, wherein each of the plurality of data streams includes a plurality of pixels, scaling the pixel via the one or more scalers and outputting the scaled pixels from the one or more scalers. Pixel data may be sequential or parallel. The plurality of scalers may be in parallel, scaling sequential pixel data with independent phase control, or scaling parallel pixel data in substantially equal phase. Pixel data may be transposed, replicated, distributed and aligned prior to reading by scalers, and may be aligned merged and transposed after scaling. Scaling may include interpolation or sub sampling using pixel phase, position, step size and scaler quantities.

Abstract: A system and method for generating a second reduced size digital image from a first digital image, the method including iteratively compressing the first digital image to an extent determined by a quality measure comprising at least a blockiness measure quantifying added artifactual edges along coding block boundaries of the second image and/or use of a quantization matrix generated by computing a weighted average of the quantization matrix of the first digital image and a scaled second quantization matrix.

Abstract: An electronic device may have a camera module and a host subsystem. The camera module may include a camera sensor and associated image processing and data formatting circuitry. The image processing and data formatting circuitry may include an image processor that produces unscaled images frames using data from the camera sensor. Unscaled image frames may be processed in multiple paths between the image processor and the host subsystem such as a path that includes an image compression circuit block, a parallel path that includes a preview scaler, and a parallel path that includes a multiframe scaler and a frame buffer and multiframe image processor circuitry. The multiframe scaler may scale unscaled frames for buffering and processing by the frame buffer and multiframe image processor circuitry to produce analysis results. The analysis results may be appended to compressed unscaled image frames sent to the host subsystem.

Abstract: Methods, computer devices, and computer readable media containing instructions for executing such methods are provided for the modification of digital images having a plurality of visual elements.

Abstract: A method for scaling two-dimensional structures, which is especially usable for resizing digital 2D images with a rational scaling factor, is based on efficient implementation of a diamond-shaped filter. The conventional “1”-diamond matrices of variable size are replaced by a (m×n) coefficient matrix. For any given rational scaling factor, the computational load for calculating an output pixel is reduced to filtering (m×n) input pixels with a corresponding (m×n) filter matrix. The coefficients of this filter matrix depend from the phase of the output pixel to be calculated and the factor of interpolation, but are always integer numbers. The coefficients may be stored in lookup tables (LUT), which leads to a very efficient implementation of the inventive method. In one embodiment, a (3×3) coefficient matrix has been found to be advantageous.

Abstract: An information processing apparatus includes an image acquisition unit for acquiring a real-world image, a space analysis unit for analyzing a three-dimensional space structure of the real-world image, a scale reference detection unit for detecting a length, in a three-dimensional space, of an object to be a scale reference that is included in the real-world image, and a scale determination unit for determining, from the length of the object detected by the scale reference detection unit, a scale of the three-dimensional space.

Abstract: System for storing and retrieving tiled image data. System and method store a record in an image file for each tile at a zoom level, create a lookup table for the record, store a null value in the lookup table when there are no tile records at the row and the column of the lookup table, omit a row from the lookup table when there are no tile records in the table row, create an index file having a null value for each omitted rows, and retrieve an address for a specific tile by seeking the row associated with the record in the index file, reading a value, positioning the lookup table according to the index value if the value is non-null, seeking the column associated with the record, reading an address associated with the record, and retrieving the tile associated with the record at the address.

Abstract: The present disclosure includes systems and techniques relating to processing of high resolution images, such as digital painting on high resolution images. In general, one aspect of the subject matter described in this specification can be embodied in a method that includes receiving input defining a modification to a target image; determining, at a first processor, a low resolution proxy result of the modification applied to the target image; determining, at a second processor, a higher resolution result of the modification applied to the target image; displaying the low resolution proxy result before completion of the determining at the second processor; and updating the displayed low resolution proxy result with the higher resolution result. Other embodiments of this aspect include corresponding systems, apparatus, and computer program products.

Abstract: A method of operating a three-dimensional (3D) map system including: receiving an image and a geo-location tag of the image; determining a building model for a physical building corresponding to an object captured in the image based on the geo-location tag; mapping, on a region-by-region basis, the image to a stored facade of the building model; and mapping, on a pixel-by-pixel basis, the image to the stored facade of the building model for displaying the image as a new facade of the building.

Abstract: An image processing apparatus of the present disclosure includes: a step detecting unit which detects a first step pixel and a second step pixel in the binary image and step directions of the first step pixel and the second step pixel; and an enlargement processing unit which inverts pixel values of pixels from the first pixel value to the second pixel value in a pixel area corresponding to the first step pixel in the enlarged image, and inverts pixel values of pixels from the second pixel value to the first pixel value in a pixel area corresponding to the second step pixel. The pixels of which pixel values are inverted are located at positions corresponding to its step direction. The number of the pixels of which pixel values are inverted corresponds to its step length in the binary image.

Abstract: A method and apparatus for restoring a resolution of a low resolution view image from a multi-view image. In the resolution restoration method, detailed information may be generated using a reference image neighboring a criterion image, and a resolution of the criterion image may be restored using the detailed information.

Abstract: In some instances, an image may have dimensions that do not correspond to a slot to display the image. For example, an image content item may have dimensions that do not correspond to a content item slot. The image may be resized using seam carving to add or remove pixels of the image. A saliency map for the image may be used having saliency scores for each pixel of the image. Evaluation metrics may be used before, during, and after, seam carving to determine whether salient content is affected by the seam carving. In some instances, a seam cost threshold value may be used for adaptive step size during the seam carving. The resized image may then be outputted, such as for an image content item to be served with a resource.

Abstract: A reading machine that operates in various modes includes image correction processing is described. The reading device pre-processes an image for optical character recognition by receiving the image and determining whether text in the image is too large or small for optical character recognition processing by determining that text height falls outside of a range in which optical character recognition software will recognize text in a digitized image. If necessary the image is resized according to whether the text is too large or too small.

Abstract: There is disclosed a method and system for resizing a digital image wherein a RGB image is converted into an YCbCr image (Y, Cb, Cr planes). Thereafter, a discrete cosine transform (DCT), followed by a specific inverse cosine transform (IDCT) is performed on each row/column of the Y, Cb, Cr planes. The mentioned specific operation corresponds to a type of homothetic matrix, which dimensions are defined by a scaling factor. In order to produce a scaled image, the scaled Y, Cb, Cr images are transformed to an RGB image for display.

Abstract: A system and method of resizing an image on a mobile communication device prior to transmitting to an online image repository is disclosed. In accordance with one embodiment, the method comprises: determining a size of an original image; determining whether there are any default file sizes to which the original image may be resized; when a default file size does not exist, receiving a custom image size, resizing the original image in accordance with the received custom image size to create a resized image, and transmitting the resized image to the online image repository.

Abstract: Provided is an image processing apparatus, including an enlargement ratio setting section which sets a region of data in an original image, including a designated position designated as an object to be enlarged within the original image, as a region to be enlarged, and sets an enlargement ratio to the region to be enlarged, based on an image feature amount showing complexity of an image of the region to be enlarged, and an enlarged image generation section which generates enlarged image data for the data of the original image, by applying an enlargement process by the enlargement ratio set by the enlargement ratio setting section.

Abstract: A dust detection system, comprising a receiver, a dust extraction block, a memory and an image correction block, is provided. The receiver receives an image signal. The dust extraction block generates a dust image signal on the basis of the image signal. The memory stores an intrinsic-flaw image signal corresponding to an intrinsic-flaw image including sub-images of dust that the dust extraction block extracts in initializing. The image correction block generates a corrected dust-image signal on the basis of the intrinsic-flaw image signal and a normal dust-image signal. The normal dust-image signal corresponds to a normal dust image including sub-image of dust that the dust extraction block extracts after initializing. The corrected dust image is the normal dust image that sub-images of dust in the intrinsic-flaw image are deleted from.

Abstract: An image processing apparatus comprises a processing unit for computing displacement amounts between a basis image and each reference image, a processing unit for generating multiple deformed images based on the displacement amounts, the basis image and multiple reference images, a processing unit for setting a threshold of a parameter, a processing unit for selecting image information from the reference image by the threshold, a processing unit for generating composed images and weighted images based on the basis image, the displacement amounts and the image information, a processing unit for generating high-resolution grid images by dividing the composed image by the weighted image, a processing unit for generating simplified interpolation images based on high-resolution grid images, a processing unit for generating assistance images, a display unit for displaying the assistance images and a control unit that controls the necessary processing as necessary.

Abstract: A method for embedding an image in a video sequence for a mobile terminal. Preferably, the mobile terminal is a tablet or smartphone. The method comprises the steps of choosing an image to be embedded, reading the video sequence, displaying a frame, and determining the presence of an embedding zone in the frame. The embedding zone having been previously identified or deduced according to a predefined algorithm. The method further comprises the step of applying a deformation to the image to be embedded such that the image to be embedded coincides with the form of the embedding zone. The image combining the frame and the image to be embedded is displayed/disposed in place of the embedding zone.

Abstract: High depth grayscale images, (e.g. <8 bits per pixel) are losslessly cross channel encoded to multi-channel image formats for transformation and display by display devices not capable of displaying high depth grayscale. DICOM and other images may be encoded and provided to web browser based client image viewers that leverage native code for handling multi-channel images. Transformations are applied to reconstitute the high depth grayscale images.

Abstract: An image processing apparatus includes a superimposition processing unit that performs a blending process for a plurality of continuously captured images, wherein the superimposition processing unit is configured to selectively input luminance signal information of a RAW image or a full color image as a processing target image and perform a superimposition process, and performs a process for sequentially updating data that is stored in a memory for storing two image frames so as to enable superimposition of any desired number of images.

Abstract: Disclosed are various embodiments for systems and methods for image processing. A resizing template may be generated having one or more image sizes of an original image based at least in part on resize settings. A preview may then be generated of preview images of the original image based at least in part on the resizing template and the resize settings. The resize settings may be further adjusted via the preview. Upon approval of the preview and the adjusted resize settings, the original image is processed to generate final resized images according to the template and the modified resize settings.

Abstract: Method for partitioning a digital image into two or more regions where each region is defined using a portion of the digital image. In addition, margin pixels for each region are defined as pixels that correspond to a top margin, a bottom margin, a left margin, and a right margin of each region of the digital image. Margin pixels are generated by using various techniques such as on-the-fly generation, using data information of neighboring pixels to each region, using data information of pixels within each region, or using predetermined data information for a color including black. The pixels of each region are processed with its margin pixels to create a new processed region of the digital image. The processing may include scaling of each region from a first resolution to a second resolution. The data information of each processed region can be displayed using a portion of an electronic display panel, or a monitor having with multiple display regions.

Abstract: Method and apparatus for compressed sensing yields acceptable quality reconstructions of an object from reduced numbers of measurements. A component x of a signal or image is represented as a vector having m entries. Measurements y, comprising a vector with n entries, where n is less than m, are made. An approximate reconstruction of the m-vector x is made from y. Special measurement matrices allow measurements y=Ax+z, where y is the measured m-vector, x the desired n-vector and z an m-vector representing noise. “A” is an n by m matrix, i.e. an array with fewer rows than columns. “A” enables delivery of an approximate reconstruction, x#? of x. An embodiment discloses approximate reconstruction of x from the reduced-dimensionality measurement y. Given y, and the matrix A, approximate reconstruction x# of x is possible. This embodiment is driven by the goal of promoting the approximate sparsity of x#.

Abstract: An image processing apparatus includes: an acquisition unit configured to acquire original image data expressing an original image that comprises a first type pixel and a second type pixel; and an enlargement processing unit configured to execute enlargement processing for the original image data to generate enlarged image data expressing an enlarged image that is obtained by enlarging the original image in a first direction. The enlargement processing unit includes: a pixel group selection unit configured to select a pixel group extending in a second direction intersecting with the first direction in the enlarge image when a specific pattern configured by the first type pixel and the second type pixel is included in the original image; and a setting unit configured to set a pixel configuring the pixel group in the enlarged image as the second type pixel.

Abstract: To detect non-uniform spatial scaling of an image in the horizontal direction (for example in 4:3 to 16:9 aspect ratio conversion) the image is divided into regions, for example a middle region and two side regions. A measure of horizontal spatial frequency energy is taken in each region by for example subtracting the values of horizontally adjacent pixels and a comparison is made between measures of horizontal spatial frequency energy for the different regions.

Abstract: According to an embodiment, an image processing apparatus includes: a reading unit, a magnification change processing unit, a wait time acquiring unit, and a signal output unit. The reading unit reads image data from the memory line by line. The magnification change processing unit performs a magnification change process on the image data and outputs. The wait time acquiring unit acquires wait time information on a value corresponding to a wait time from when a synchronous signal, representing a start of read of the image data for each line, falls to when the magnification change process starts. The signal output unit outputs, to the reading unit, a permission signal indicating whether read of image data of a next line is permitted or denied based on the wait time information while the magnification change processing unit is outputting the image data.

Abstract: The present invention provides an image processing apparatus which can simply and appropriately analyze an image, an image processing method, and a storage medium. The present invention reduces an original image and enlarges a reduced image obtained by the reduction. The present invention enlarges the original image. The present invention analyzes the original image by comparing a first enlarged image obtained by enlargement of the reduced image with a second enlarged image obtained by enlargement of the original image.

Abstract: A device for processing data includes a first input port for receiving color image data from a first image sensor and a second input port for receiving depth-related image data from a second image sensor. Processing circuitry generates a depth map using the depth-related image data. At least one output port conveys the depth map and the color image data to a host computer.

Abstract: Methods for reducing dimensionality of hyperspectral image data having a number of spatial pixels, each associated with a number of spectral dimensions, include receiving sets of coefficients associated with each pixel of the hyperspectral image data, a set of basis vectors utilized to generate the sets of coefficients, and either a maximum error value or a maximum data size. The methods also include calculating, using a processor, a first set of errors for each pixel associated with the set of basis vectors, and one or more additional sets of errors for each pixel associated with one or more subsets of the set of basis vectors. Utilizing such errors calculations, an optimum size of the set of basis vectors may be ascertained, allowing for either a minimum amount of error within the maximum data size, or a minimum data size within the maximum error value.