Abstract: An image transmitting apparatus includes a region detecting unit detecting, in an image, a region of interest matching a predetermined condition; a resolution converting unit selecting, for reducing resolution of the image, an image passed through a low-pass filter as an image outside the detected region of interest and an image not passed through the low-pass filter as an image inside the region of interest; and a transmitting unit transmitting the image with reduced resolution and positional information of the region of interest. An image receiving apparatus includes a resolution restoring unit performing image quality improvement processing on the region of interest obtained from the positional information and included in the image transmitted from the image transmitting apparatus so as to increase resolution in the region of interest; and a combining unit combining the image inside the processed region of interest with the image outside the region of interest.

Abstract: A method for generating an image is provided. The method includes estimating a high resolution image from a plurality of low resolution images and downsampling the estimated high resolution image to obtain estimates of a plurality of low resolution images. The method also includes generating a desired high resolution image based upon comparison of the downsampled low resolution images and the plurality of low resolution images.

Abstract: An image processing apparatus includes a determination unit that determines a type of a provided object, a resolution conversion unit that converts a resolution of the object determined by the determination unit as an image into a resolution of an output image, an object processing unit that performs a spatial frequency processing for the object after the resolution conversion by the resolution conversion unit depending on a ratio between a resolution of the object before the resolution conversion and a resolution of the output image, and a generating unit that generates the output image based on the object subjected to the spatial frequency processing in the object processing unit.

Abstract: The object of the present invention is to provide an imaging and display apparatus and method for providing small and reasonable apparatus while the imaging frame rate of the imaging element can be high without decreasing the resolution of the display image. For this object, an imaging and display apparatus comprises an imaging element 12 for performing photo electric conversion on an optical image formed by an optical system 11, a display element 20 for displaying image information, a readout control section 14 for sequentially reading out the image information from the imaging element 12, and a image selection section 17 for selecting image information to be displayed on the display element 20 from the image information sequentially read out of the imaging element 12 by the readout control section 14.

Abstract: An imaging apparatus has an intermediate image generating section to generate a second structure component and a second texture component by magnifying each of a first structure component and a first texture component separated from an original image by an intermediate magnification ratio. The second structure component and the second texture component are synthesized to generate an intermediately magnified image. A final image generating section generates a finally magnified image by synthesizing a finally magnified structure component generated by magnifying a third structure component separated from the intermediately magnified image by a final magnification ratio, and a finally magnified texture component generated by magnifying the first texture component by the final magnification ratio.

Abstract: An image processing apparatus includes a storage unit in which regression coefficient data is stored for each class on the basis of a tap in which a linear feature amount corresponding to a pixel of interest of first image data and a non-linear feature amount determined from the image data are used as elements; a classification unit configured to classify each of linear feature amounts of a plurality of items of input data of the input first image into a predetermined class; a reading unit configured to read the regression coefficient data; and a data generation unit configured to generate data of a second image obtained by making the first image have higher quality by performing a product-sum computation process by using the regression coefficient data read from the reading unit and elements of the tap of each of the plurality of items of input data of the input first image.

Abstract: A method for resizing an input digital image having input pixel values to produce an output digital image having output pixel values, wherein the output digital image has a lower resolution and wherein single pixel width details in the input digital image are preserved, the method being performed by a processor and comprising: determining an output pixel value for the output digital image by interpolating within a corresponding neighborhood of image pixels in the input digital image; detecting whether the input digital image contains a fine detail within the corresponding neighborhood of image pixels; adjusting the output pixel value when a fine detail is detected; and repeating steps a)-c) for a plurality of output pixels.

Abstract: Super-resolution images may be produced by dividing a higher resolution image into a set of non-overlapping rectangular tiles of substantially the same size. Then, each pixel in each lower resolution image is mapped to the higher resolution image and it is determined which tiles are mapped to which lower resolution image pixels. A continuous buffer may be allocated for each tile and the relevant lower resolution pixels may be stored, together with optical flow vectors, in that continuous buffer. Then, the determination of gradients may use the information now stored in the buffer to facilitate symmetric multiprocessing using multi-core processors.

Abstract: An image processing apparatus may include an image frame determiner to determine one standard image frame and at least one reference image frame using light field data about a scene, a point spread function determiner to determine a point spread function based on sub-pixel displacement between the standard image frame and the at least one reference image frame, an image interpolator to interpolate the standard image frame into a high-resolution standard image frame having a higher resolution than the standard image frame, and an image restorer to restore a high-resolution image by updating the high-resolution standard image frame using the generated high-resolution standard image frame, the point spread function, and the at least one reference image frame.

Abstract: An optimal resolution imaging system comprises a resolution engine adapted to apply at least one resolution rule to at least one zone of an object to determine an optimal reduced resolution setting for the at least one zone while maintaining a predetermined quality level for the at least one zone.

Abstract: A method of pattern and image recognition and identification includes building a data store of known patterns or images having known attributes and comparing those patterns to unknown patterns. The data store and comparison processing may be distributed across processors. A digital pattern recognition engine on each of the processors has the ability to compare a known pattern from the data store and an unknown pattern and compare the two patterns to determine whether the patterns constitute a match based on match criteria. If the comparison indicates a match, the match may be communicated to the data store and added as a known pattern with detected attributes to the data store. If the comparison does not indicate a match, the pattern may be flagged, transmitted to manual recognition, or further processed using character thresholding or cutting or slicing the pattern.

Abstract: An image processing device, which performs, on image data, image quality adjustment processing and resize processing to adjust an image size to a target size, and which outputs processed image data, including: an adjustment parameter creation unit which creates adjustment parameters for the image quality adjustment processing, on the basis of original image data; a contrast information creation unit which acquires the image size of the original image data and the target size, and creates size contrast information; a resize amount detection unit which determines the resize amount in the resize processing on the basis of the size contrast information; and an adjustment parameter modification unit which modifies the adjustment parameters in accordance with the resize amount.

Abstract: An imaging system compensates for mask frame misalignment with non-mask frames in an image sequence of patient anatomy. The system includes an image data processor. The image data processor determines a compensation zoom factor for individual image frames of an image sequence of an object of interest in response to data indicating distance between the object and a radiation detector for the individual image frames. The processor then associates individual zoom factors with corresponding individual image frames of the image sequence. The individual zoom factors associated with corresponding individual image frames of the image sequence are stored in a repository. An individual determined zoom factor is applied to align an associated corresponding image frame with a mask frame to provide an aligned image frame. Data representing an image difference frame, comprising a difference between data representing the aligned image frame and a mask frame, is determined.

Abstract: A video signal can be decoded at a reduced resolution by receiving a video signal encoded at a first resolution; determining a second resolution at which the received video signal is to be decoded, wherein the second resolution is lower than the first resolution; and decoding the received video signal at the second resolution. The second resolution can be selected from a plurality of predetermined decoding resolutions. Further, the second resolution can be selected in response to an input received from a user. Decoding of the received video signal can include scaling one or more reference pictures by a first scaling factor and scaling one or more non-reference pictures by a second scaling factor. Additionally, scaling can comprise transforming a first portion of frequency coefficients associated with a block of picture information and discarding a second portion of frequency coefficients associated with the block of picture information.

Abstract: A hand-held mobile apparatus and method of quickly displaying online community friends' images applicable thereto are disclosed. The hand-held mobile apparatus includes a network communication module for linking to an online community server; a comparison module for comparing and determining whether data of a web image in the online community server matches data of a local image in a storage unit of the apparatus; a recognition module for determining an image type of the web image when the web image data is different from the local image data; a processing unit for downloading the web image of a first type in a smallest image size or the web image of a second type in an image size matching a screen resolution of the apparatus, and storing the web image in the storage unit as the local image; and a display unit for displaying the local image.

Abstract: Functionality for storing and modifying multi-resolution texture atlases is provided so that applications can expose methods to enable users to access and browse a collection that includes multiple multi-resolution images. The images are stored as thumbnails in a texture atlas having different levels of detail in which the levels are arranged in an image pyramid that includes multiple tiles that are each stored as separate files. The thumbnails are spatially storable as textures in the texture atlas using a fractal layout (which in one illustrative example is a Morton layout) that enables images to be efficiently packed in the tiles. The fractal layout ensures that no more than one tile stores less than a fully packed texture at each level of detail. The same packing order scales across each level of detail in the texture atlas so that layout information is stored for the individual images in the collection only once.

Abstract: This invention makes it possible to obtain an enlarged image while suppressing noise and maintaining the sharpness of an original image only by setting a simple enlargement ratio without no special knowledge. Original image data (Ia) is enlarged in accordance with a set enlargement ratio (E) to generate an enlarged image (IA). The enlarged image (IA) is smoothed by using a smoothing filter with a size depending on the enlargement ratio (E) to generate smoothed image data (IB). Difference image data (IC) is generated by calculating the difference between the enlarged image data (IA) and the smoothed image data (IB). The generated difference image data is multiplied by an emphasis coefficient. The product is added to the enlarged image data, thereby obtaining image data (IS) that has undergone enlargement/unsharp masking.

Abstract: Even when vector data contains resolution dependent data, the vector data is generated at a resolution of quality without deterioration even if the vector data is output from any device on a network. When spooling the vector data, an MFP 1, receiving PDL data containing resolution information on a data processing resolution from a PC 2, analyzes the resolution information, and determines a processing resolution used at a time when an image forming device executes resolution dependent processing. After that, when the resolution dependent processing is necessary to generate the vector data, the MFP 1 executes the resolution dependent processing in accordance with the determined processing resolution.

Abstract: Described is a technology in which a low resolution image is processed into a high-resolution image, including by a two interpolation passes. In the first pass, missing in-block pixels, which are the pixels within a block formed by four neighboring original pixels, are given values by gradient diffusion based upon interpolation of the surrounding original pixels. In the second interpolation pass, missing on-block pixels, which are the pixels on a block edge formed by two adjacent original pixels, are given values by gradient diffusion based upon interpolation of the values of those adjacent original pixels and the previously interpolated values of their adjacent in-block pixels. Also described is a difference projection process that varies the values of the interpolated pixels according to a computed difference projection.

Abstract: A method resizes input images by first constructing a grid graph. The grid graph includes one node for each pixel in the input image, and adjacent nodes in the grid graph are connected by arcs. Each arc is directed and has an associated cost. A cut is applied to the arcs of the grid graph using a cost function. A seam of pixels is determined from the cut so that coordinates of the pixels in the seam enforce monotonicity and connectivity constraints. Then, the input image is resized according to the seam to produce an output image while minimizing a change of energy in the output image when compared with the input image.

Abstract: Upon enabling an automatic cropping feature, a computer-implemented method for cropping a plurality of images retrieves a number of images to process among the plurality of images, and selects an image from the plurality of images to determine a set of crop values for the image until the set of crop values for each image have been determined. Determining a set of crop values for an image includes scanning the image from a first side to an opposing side to determine for each scan line of the image an amount representing a degree of color variation among the pixels for that scan line. The amount determined for each scan line is then compared to a threshold value until a crop value for a first area of the image can be determined.

Abstract: Systems and methods for interactive image compositing may integrate image searching using visual search criteria (e.g., color, composition, tonal distribution, or lighting effects), non-destructive image compositing, and high-performance rendering using a fast gradient solver to provide an efficient workflow for users. An image compositing application, executable by a CPU and/or GPU, may employ a sketch-and-refine approach, whereby a user draws a rough perimeter around an object of interest in an image and (following an initial application of the fast gradient solver to a lower-resolution version of the image) receives a preview of how it would fit into a composition. The fast gradient solver may differentiate between the object and its background by applying artificial intelligence techniques and/or dependent on user-supplied hints.

Abstract: An image processing device includes a storage section, an estimation calculation section, and an image output section. A pixel is sequentially shifted so that overlap occurs to acquire a light-receiving value of the pixel as a low-resolution frame image. The storage section stores the low-resolution frame image. The estimation calculation section estimates estimated pixel values at a pixel pitch smaller than the pixel pitch of the low-resolution frame image. The image output section outputs a high-resolution frame image that has a resolution higher than that of the low-resolution frame image based on the estimated pixel values. The estimation calculation section calculates the difference between the light-receiving value of the pixel set at a first position and the light-receiving value of the pixel set at a second position, and estimates the estimated pixel values based on the difference.

Abstract: A method and apparatus to providing higher resolution images on an embedded device by performing a super resolution technique on a compressed image sequence and one or more motion vectors are described. In one example, the method includes compressing an image sequence using a video compression technique, wherein the image sequence comprises a plurality of lower resolution images and applying a super resolution technique to the compressed image sequence to generate a higher resolution image.

Abstract: In super-resolution processing in which a plurality of low resolution images are synthesized to generate a high resolution image, a high-quality high-resolution image is to be generated with suppression of the noise ascribable to motion estimation error. Motion estimating means 11 estimates motion of pixels between a basis image selected out of plural low resolution images and remaining reference images, and outputs a result of motion estimation. Motion estimation reliability evaluating means 12 evaluates reliability of the result of motion estimation output from the motion estimating means 11, based on such as analogy in luminance of pixels, correlated by the results of the motion estimation, and outputs a motion estimation reliability value indicating the degree of reliability.

Abstract: A virtual image is synthesized from a reduced resolution depth image storing depth values at each pixel location. The reduced resolution depth image is scaled up to produce an up-scaled depth image. Then, at least one filter is applied to the up-scaled depth image to produce a reconstructed depth image, and the virtual image is synthesized using the reconstructed depth image.

Abstract: A printing processing device that includes an analyzing unit that analyzes the components of print data. Based on the analysis results, a first raster processing unit performs raster processing at a first resolution for the print data of a portion of the components of the print data other than an optically read printing portion. Similarly, based on the analysis results, a second raster processing unit that performs raster processing at a second resolution higher than the first resolution, for the print data of the optically read printing portion of the components of the print data. Further, the printing processing device includes a resolution conversion unit that converts the print data that has been processed by the first raster processing unit into the second resolution and a synthesizing unit that synthesizes the print data that has been converted into the second resolution by the resolution conversion unit and the print data that has been processed by the second raster processing unit.

Abstract: Methods and systems for a regression-based learning model in image upscaling are disclosed. In one embodiment, a set of image patch pairs for each of a set of images is generated. Each of the image patch pairs contains a natural image and a corresponding downscaled lower-resolution image. A regression model based at least in part on the set of image patch pairs is defined. The regression model represents a gradient of a function of the downscaled lower-resolution image. An image is upscaled based at least in part on the regression model.

Abstract: An image processing apparatus includes an image correction processing unit configured to correct an input image so as to generate a corrected image and a super-resolution processing unit configured to receive the corrected image generated by the image correction processing unit and increase a resolution of the corrected image through super-resolution processing so as to generate a high-resolution image. The image correction processing unit performs at least one of a time-direction noise removal process, a space-direction noise removal process, a compression noise removal process, and an aperture control correction process.

Abstract: Systems and methods for upsampling input images may evaluate potential upsampling solutions with respect to an objective function that is dependent on a sparse derivative prior on second derivative(s) of the potential upsampling solutions to identify an acceptable higher-resolution output image. The objective function may also be dependent on fidelity term(s) and/or sparse derivative prior(s) on first derivative(s) of potential upsampling solutions. The methods may include applying the iteratively re-weighted least squares procedure in minimizing the objective function and generating improved candidate solutions from an initial solution. The identified solution may be stored as a higher-resolution version of the input image in memory, and made available to subsequent operations in an image editing application or other graphics application. The methods may produce sharp results that are also smooth along edges.

Abstract: Imaging devices and techniques that utilize multiple optical detectors are described and, in particular, imaging geometries for imaging devices that include three or more optical detectors with overlapping fields of regard. The imaging geometries are determined and provided in consideration of one or more performance criteria evaluated over multiple different operating conditions for a process of generating a reconstructed image from the captured images. Imaging systems and methods utilizing the imaging geometries are also described.

Abstract: An embodiment provides a method for image upscaling. The method includes anti-aliasing an input image and downsampling the input image to create a lower resolution image. The method also includes interpolating the lower resolution image to obtain a higher resolution image and creating a filter map from the input image and the higher resolution image. The method also includes upsampling the input image using the filter map to create a high-resolution image.

Abstract: An image generation method for generating image information of an image C by using an image A and an image B having a resolution higher than that of image A. Image C having the same resolution as image B is generated by enlarging image A; presence or absence of a point in image B corresponding to each pixel position of image C and the position of the relevant corresponding point are estimated; and to each pixel position in image C for which it is estimated that there is a corresponding point, image information of the corresponding position in image B is assigned. It is possible to generate image information at each pixel position in image C for which it is estimated in the corresponding point estimation that there is no corresponding point, by using the image information assigned according to an estimation result that there is a corresponding point.

Abstract: There is provided an image determining device including a frequency band signal detecting unit for dividing an image into a plurality of local regions and detecting for each local region signals of a plurality of frequency bands from the image signal; an average value calculating unit for calculating an average value of a characteristic value corresponding to an amplitude, for each local region and for each signal of the plurality of frequency bands; a local region selecting unit for selecting at least one local region based on image information; an average value selecting unit for selecting the average value corresponding to the selected local region; a relative value calculating unit for calculating a relative value of one average value with respect to another average value both of the average values being of the selected average values; and an image determining unit for determining an image based on the relative value.

Abstract: An image processing apparatus includes a region determination unit detecting attributes of image data generated by a reading unit; an image modification unit generating attribute data based on the results of the determination performed by the region determination unit; an image conversion processing circuit performing resolution conversion processing on the image data of a pixel of interest; and an attribute conversion processing circuit performing resolution conversion processing on the attribute data of the pixel of interest.

Abstract: Provided is an image processing device including a model-based processing portion that generates an estimated low resolution image from a high resolution image, using an observation model that performs motion compensation processing and down-sampling processing, a feature amount calculation portion that calculates a feature amount of at least one of a spatial feature amount and a temporal feature amount from one of an observed low resolution image, which is a low resolution image that is actually observed, and the high resolution image, and a prediction operation portion that predicts and generates an image with higher image quality based on the high resolution image, using a parameter which corresponds to the calculated feature amount and which is obtained from the observed low resolution image, from the estimated low resolution image and from learning that is performed in advance.

Abstract: An image generation method for generating image information of an image C by using an image A and an image B having a bit depth higher than that of image A. Image C having the same bit depth as image B is generated by increasing the bit depth of image A by means of tone mapping; presence or absence of a point in image B corresponding to each pixel position of image C and the position of the relevant corresponding point are estimated; and to each pixel position in image C for which it is estimated that there is a corresponding point, image information of the corresponding position in image B is assigned. It is possible to generate image information at each pixel position in image C for which it is estimated in the corresponding point estimation that there is no corresponding point, by using the image information assigned according to an estimation result that there is a corresponding point.

Abstract: The present invention relates to a data conversion apparatus and a learning device in which an image can be converted into a higher-quality image. A class-tap generating circuit (2) and a predictive-tap generating circuit (3) respectively generate from an SD image a class tap for classifying a specified pixel of an HD image and a predictive tap for determining the specified pixel. A classification circuit (4) classifies the specified pixel based on the class tap. A coefficient RAM (5) obtains a tap coefficient for the class of the specified pixel from tap coefficients obtained by using supervisor pixels and learner pixels and by learning the relationship between the supervisor pixels and the learner pixels for each of at least one class while applying weighting to the supervisor pixels and the learner pixels based on the activity of the predictive tap generated from the learner pixels. A predictive-computation circuit (6) determines the specified pixel by using the tap coefficient and the predictive tap.

Abstract: A method and apparatus for bit resolution enhancement and edge enhancement in an electronic device are provided. The method includes determining a Contour Counter (CC) and determining a type of each region of the input image, determining a Bit Resolution Enhancement (BRE) parameter and an edge enhancement parameter of each region according to the determined region type, determining a first weight for each region of the image and enhancing a bit resolution of the input image, and determining a second weight for each region of the image and performing edge enhancement for the image.

Abstract: An image processing apparatus includes a plurality of addition means and an image processing means. The addition means performs addition processing of adding pixels of a differential image at a second resolution representing a difference between an inputted image at a first resolution and an image at the second resolution higher than the first resolution as pixels of an inputted image at the second resolution. The image processing means is configured to perform second and subsequent addition processing, and generate an image of the second resolution as a processing result by performing the addition processing for a predetermined number of times. The addition processing is performed with inputs of an image at the first resolution and an image at the second resolution obtained by an immediately preceding addition processing, which are different from each other.

Abstract: Embodiments of the present invention are directed to an image processing system. The image processing system may comprise a content detection module having an input to receive a sequence of input pixels and configured to generate an adjustable parameter based on detected differences between adjacent pairs of input pixels, and a digital filter having an input for the sequence of input pixels and a control input coupled to an output of the content detection module. The digital filter may adjust filtering coefficients according to the parameter.

Abstract: A computer readable medium storing a program causing a computer to execute a process for document processing, the process includes: receiving image data obtained by, with an image reading apparatus, reading a document of a predetermined format in which contents of an electronic document stored in a storage portion while being associated with identification information, the identification information, and an entry for additional information are arranged; extracting entered additional information from the entry area of the received image data; and correlating the extracted additional information with an electronic document associated with the identification information.

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: Disclosed is an image processing apparatus that is capable of effectively generating a high-resolution image with high image quality from multiple low-resolution images having displacements by an iterative reconstruction processing based on a reconstruction-based super-resolution processing method.

Abstract: A method for reducing image artifacts in an image that includes a number of pixels each of which includes at least one video information value, includes generating a plurality of filter coefficients for at least some of the pixels of the image, on the basis of which the video information values of the pixels can be reconstructed. Artifact detection is performed to detect artifact regions within the image. At least some filter coefficients of those pixels that lie within the artifact regions are modified to generate modified filter coefficients. The video information values are synthesized using the filter coefficients, the modified filter coefficients being employed for the synthesis for pixels lying within the artifact regions.

Abstract: Systems and methods are disclosed for processing a low resolution image by performing a high resolution edge segment extraction on the low resolution image; performing an image super resolution on each edge segment; performing reconstruction constraint reinforcement; and generating a high quality image from the low quality image.

Abstract: A method for vision field computing may comprise the following steps of: forming a sampling system for a multi-view dynamic scene; controlling cameras in the sampling system for the multi-view dynamic scene to perform spatial interleaved sampling, temporal interleaved exposure sampling and exposure-variant sampling; performing spatial intersection to the sampling information in the view subspace of the dynamic scene and temporal intersection to the sampling information in the time subspace of the dynamic scene to reconstruct a dynamic scene geometry model; performing silhouette back projection based on the dynamic scene geometry model to obtain silhouette motion constraints for the view angles of the cameras; performing temporal decoupling for motion de-blurring with the silhouette motion constraints; and reconstructing a dynamic scene 3D model with a resolution larger than nominal resolution of each camera by a 3D reconstructing algorithm.

Abstract: An image processing method for boundary resolution enhancement is disclosed. Firstly, an image is transferred into an image layer. Noise of the image layer is removed by a bilateral filter and crisp edges are retained at the same time. Moreover, the image layer is interpolated by an interpolation filter for resolution enhancement. The image processing method of the present invention can lower the image blur degree substantially, enhance the image resolution and be widely implemented in all sorts of image/video processing hardware devices.

Abstract: A method and apparatus for converting a resolution of a block-based image. The method includes: dividing a low resolution image frame into a plurality of blocks, each block having a predetermined size; performing motion prediction in a sub-pixel unit of each of the divided blocks and determining a motion vector in the sub-pixel unit; dividing the motion vector of the sub-pixel unit into a first motion vector having an integer pixel unit and a second motion vector having the sub-pixel unit; determining at least one low resolution reference block corresponding to each of the divided blocks by using the first motion vector having the integer pixel unit; converting each of the divided blocks into high resolution block by using the second motion vector having the sub-pixel unit and the one low resolution reference block; and generating a high resolution image frame by using each of the converted high resolution blocks.

Abstract: It is possible to provide an image processing device, a method, and a program which can prevent image degradation which occurs when modifying the image magnification. The image processing device includes: an image input unit (10) which performs an image input; an edge direction calculation unit (24) which detects the edge direction contained in an image inputted by the image input unit (10); and an interpolation position decision unit (26), an interpolation object pixel decision unit (28), a first direction interpolation unit (30), and a second direction interpolation unit (32) which perform an interpolation process in the edge direction detected by the edge direction calculation unit (24) on the image inputted by the image input unit (10).