Abstract: A pixel processing method includes: selecting a first plurality of color component values of a first plurality of pixels within a pixel block in a buffering device, performing a first color component process upon a first target pixel in the first plurality of pixels to determine a first target color component value of the first target pixel; and selecting a second plurality of color component values of a second plurality of pixels within the pixel block at the same time as the first color component process is performed, and performing a second color component process upon a second target pixel in the second plurality of pixels according to the second plurality of color component values to determine at least one underdetermined target color component value of the second target pixel, wherein the second target pixel has been processed by the first color component process.

Abstract: An apparatus for enhancing the visibility of color images includes: a luminance value cumulative distribution calculator that calculates a cumulative distribution function of the number of pixels from a minimum value of luminance values; a baseband signal determining unit that determines baseband signal pixels having luminance values smaller than a threshold level; a luminance compensation value generator that generates luminance compensation values to apply the lower-level luminance compensation values as the pixels have higher-level luminance values, for the pixels having the luminance values larger than the threshold level; a luminance gain generator that determines a luminance gain applied to the luminance compensation values according to a mean luminance values of the input images and the level of the luminance values of the pixels to which the luminance compensation values are applied; and a luminance value enhancing unit that summing the luminance compensation values including the gain with the luminan

Abstract: Techniques are described for improving accuracy and speed of video fingerprinting and identification by using video frame color and intensity information. Multiple approaches for generating a novel signature based on video frame color information are described. One is based on spatial distribution of pixel intensities with reference to derived color groups, while another is based on thresholding a joint histogram of pixel intensity, color, and spatial coordinates. These color based signatures can be deployed either as primary video content signatures, or as hash traversal signatures used to improve speed of an initial stage of video data base search procedures. They can also be used as secondary signatures during a video signature data base search with primary video content signatures, to help disambiguate possible false positive matches, and to improve marginal matches which might not be identified otherwise.

Abstract: Provided is an image inputting apparatus wherein luminance signals having a high S/N ratio can be generated even during nighttime with a small quantity of photons. An imaging element images image components. A color signal generating section generates color signals from the image components. A color space conversion section converts the color signals into a color space that includes luminance signals and color difference signals. The color space conversion section calculates a luminance signal obtained by adding the image components, as the luminance signal of the color space to be converted.

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 color input pixels by aligning a filtering operation with a detected direction of an image feature at a pixel position to be interpolated comprises detecting image activity within respective color components of a group of input pixels around the pixel position to be interpolated; generating monochromatic test pixels by combining the color components of input pixels in relative proportions dependent upon the detected image activities; detecting the direction of an image feature in a group of the monochromatic test pixels around the pixel position to be interpolated; and interpolating an output pixel using the two-dimensional filter, according to the detected image feature direction.

Abstract: A method and system implementing the method for color pixel counting in images by determining color pixels that, upon marking, appear as visibly color or gray to the human eye by applying a 2-dimensional filter and a reverse color lookup process. An area color computation is performed on a window around each pixel of interest to determine average gray level values for output colors (C, M, Y). Gray line values for each output color are determined and the values for at least two output colors are compared to the average gray level values. If average gray level value for both colors is within a tolerance for the gray line, the pixel is determined as visibly gray. Otherwise, if at least one count is not within the tolerance, the pixel is determined as visibly color. The count of visibly color pixels can be used to determine the billable color pixel count.

Abstract: In accordance with one or more aspects of the image-based backgrounds for images, an image is analyzed in order to identify a color that represents the image. An enhanced background is generated based at least in part on the identified color, and both the image and the enhanced background are output on a screen. In addition, or alternatively, the identified color can be saved as being associated with the image in order to be used to generate an enhanced background for the image when the image is displayed.

Abstract: An apparatus for processing a raster image comprising a plurality of pixels is disclosed. The apparatus comprises a non-transitory computer readable medium for storing steps of a computer program, and a computer processor connected to the non-transitory computer readable medium for executing the steps of the computer program. A plurality of horizontal axial blobs are identified in the raster image, a plurality of vertical axial blobs are identified in the raster image, and the horizontal and vertical axial blobs are linked into a feature blob.

Abstract: A system may determine a number of floors of a building based on image data of the building. The system may determine a background color of a façade of the building shown in the image data. Using this background color, predefined deviations may then be detected that form the background color in the façade of the building. A mean number of predefined deviations in the vertical direction of the façade of the building may be determined, and the number of floors of the building based on the determined mean number of predefined deviations can be then be deduced.

Abstract: A computer-implemented method for method for detecting features in an image, comprising, receiving a first image at a GPU, wherein the GPU comprises a plurality of memory units and wherein the first image is stored in a first memory unit of the plurality of memory units, processing a second image stored in a second memory unit, of the plurality of memory units, to detect one or more features within the second image and writing one or more processed portions of the second image to a third memory unit of the plurality of memory units. In certain aspects, the method further comprises steps for outputting a third image stored in a fourth memory unit of the plurality of memory units. A mobile computing device and GPU are also provided.

Abstract: Certain embodiments of the invention provide a method and apparatus for DRAM 2D video word formatting. In one aspect of the invention, words of data in a DRAM may be arranged for optimal DRAM operating efficiency. The data organization may utilize a 2-dimensional array of samples, for example. In one embodiment of the invention, a 128-bit or 16-byte word or GWord of DRAM may include an 8×2 array of luma samples, comprising 8 horizontal samples and 2 vertical samples from one field, for example. In this regard, either both may be even lines or both may be odd lines. Various other 2-dimensional arrangements may be chosen according to the demands of the video format being processed in accordance with various embodiments of the invention.

Abstract: A color management system is described herein. Various embodiments of a method described herein can include receiving source color content that is associated with a source device, and transforming the source color content into destination color content for rendering on one or more destination devices. Various embodiments of an apparatus described herein can include a color infrastructure transformation engine that further includes a sequential transform component, which is adapted to receive source color content and to create a transform to facilitate mapping the source color content to destination color content. The color infrastructure transformation engine can also include a transform optimization component that is adapted to receive the transform and to create an optimized transform table based on the transform, and a transform execution component that is adapted to receive the optimized transform table and to generate the destination color content based thereon.

Abstract: A system, method, and computer program product for improving digital images and video by reducing or eliminating artifacts created by sensor binning, i.e. channel displacement of downscaled image pixels. Red and blue pixels are shifted to corresponding ideal pixel locations using for example bi-linear interpolation for each color. Green pixels are shifted to corresponding ideal pixel locations using one-dimensional cubic interpolation along a diagonal direction in which the green pixels are aligned. Pixel values are replaced by weighted pixel value averages of groups of pixels, preferably four, and the weights used vary inversely with shifted distances. Cubic interpolation results may be separately weighted pairwise among pixels with a weighting parameter favoring pixels near the ideal pixel location. The embodiments noticeably improve image and video quality, particularly by treatment of jagged edges of diagonal image features without compromising image sharpness or creating false colors along edges.

Abstract: An apparatus for matching colors between various image devices includes a characterization model generation unit configured to generate characterization models for color conversion using gamut information on the image shooting device and the output imaging device; a color conversion unit configured to convert all colors corresponding to a gamut of the image shooting device into colors corresponding to a gamut of the output imaging device using the characterization models; a lookup table generation unit configured to generate a lookup table between the image shooting device and the output imaging device based on color conversion information of the colors corresponding to the gamut of the image shooting device; and an image conversion unit configured to generate an output image of the output imaging device, of which the colors are matched with those of the image inputted from the image shooting device, using the lookup table.

Abstract: A system and method for modeling a region segmented image is described. Aspects of the present invention may include the generation of a computer model that models the region segmented image, the computer model comprising one or more nodes, wherein each node in the one or more nodes represents an arbitrarily shaped region present in the region segmented image, and each of the arbitrarily shaped regions comprises an image segment wherein the image segment is an indivisible partition in the region segmented image. The model may additionally comprise one or more logical nodes, wherein each logical node represents an image region formed by the union of two or more arbitrarily shaped image regions in the region segmented image that exhibit at least one type of spatial relationship and a hierarchical graph representation of the region segmented image. Types of spatial relationships may include hierarchical, adjacent and cohesive spatial relationships.

Abstract: An object of the present invention is to provide a scanning electron microscope for reducing a process concerning inspection positioning or an input operation, thereby functioning with high precision at high speed. To accomplish the above object, the present invention provides a scanning electron microscope having a function for identifying a desired position on the basis of a pattern registered beforehand, which includes a means for setting information concerning the pattern kind, the interval between a plurality of parts constituting the pattern, and the size of parts constituting the pattern and a means for forming a pattern image composed of a plurality of parts on the basis of the information obtained by the concerned means.

Abstract: A method and system for performing a 2D transform is disclosed. The 2D transform may include a row transform and/or a column transform. When performing the row or column transform, it may be determined whether each of different subsets of the data values including a partition of a row or column includes at least one zero value, whether each of different subsets of a first subset of the partition includes at least one zero value, and whether each of different subsets of at least one other subset of the partition includes at least one zero value. When performing the row or column transform, at least one transformation operation on at least one zero value may be bypassed or performed in a reduced-power manner, where such transformation operation would otherwise be performed in a manner consuming full power if the zero value were a non-zero value.

Abstract: The different illustrative embodiments provide a method, computer program product, and apparatus for managing an image. A determination is made whether an object is present in a subset of a plurality of images using an identification of the object. A determination is made whether the object is permitted to be present in the subset of the plurality of images using the policy for the user associated with the object responsive to a determination that the object is present in the subset of the plurality of images using a policy for a user associated with the object. A removal action of the object is performed on the subset of the plurality of images responsive to an absence of a determination that the object is permitted to be present in the subset of the plurality of images using the policy.

Abstract: Scaleable video sequence processing with various filtering rules is applied to extract dominant features, and generate unique set of signatures based on video content. Video sequence structuring and subsequent video sequence characterization is performed by tracking statistical changes in the content of a succession of video frames and selecting suitable frames for further treatment by region based intra-frame segmentation and contour tracing and description. Compact representative signatures are generated on the video sequence structural level as well as on the selected video frame level, resulting in an efficient video database formation and search.

Abstract: Methods, devices, and systems for determining feature descriptors are provided. An example includes defining a plurality of anchor points within a patch of pixels in a particular area that includes a detected feature in an image, defining a first set of subpatches and calculating an intensity of each of the first set of subpatches, defining a second set of subpatches and calculating an intensity of each of the second set of subpatches, comparing the intensity of each of the second set of subpatches to the intensity of each of the first set of subpatches and if the intensity of a second set subpatch is higher than the intensity of a first set subpatch assign a binary value, otherwise assign an alternative binary value, and concatenating all the assigned binary values into a binary feature descriptor.

Abstract: It is provided a computer system for matching between images/graphs comprising a processing unit, a storage unit, an input unit and a data recording unit, wherein the computer system includes a feature pattern generating unit for generating a set of feature patterns of the image and the graph from the received image and the received graph, segmenting each of the image and the graph into a plurality of regions centered on a sample point, and determining characteristics of the plurality of regions; a correspondence computing unit for computing correspondence between the image and the graph to be matched by comparing the generated feature patterns; a transform unit for transforming a coordinate system of at least one of the image and the graph to be matched; and a combination unit for combining the image and the graph that have been subjected to the transform of the coordinate system.

Abstract: A periodicity determining unit determines whether an image region including a target pixel is a periodic region in which pixel values vary periodically. A first generating unit generates a pixel value using a first interpolation method. A second generating unit generates a pixel value using a second interpolation method. A control unit determines, based on the determination result of the periodicity determining unit, which one of the first and second generating units is to be used for generating a pixel value of the target pixel. A pixel value inserting unit inserts the generated pixel value to the target pixel. The periodicity determining unit includes a cycle estimating unit to estimate, using pixel values of pixels within the image region, a variation cycle of the pixel values, and/or a determining unit to determine whether each region positioned at left and right sides of the target pixel is the periodic region.

Abstract: Input image data may be subjected to a spatial convolution to produce a plurality of different filter matrices or kernels. Thus, a single system may be capable of producing a plurality of different filter sizes which may be selected based on particular circumstances, uses and described precision. Thus, a single system may provide variable spatial filtering. By reducing the input data matrix size and by reusing components, in some cases, the computational complexity of producing a plurality of symmetrical filters is not significantly greater than that involved in producing only a single filter.

Abstract: Interest points are markers anchored to a specific position in a digital image of an object. They are mathematically extracted in such a way that, in another image of the object, they will appear in the same position on the object, even though the object may be presented at a different position in the image, a different orientation, a different distance or under different lighting conditions. The goal is to match interest points in one image with corresponding interest points in another image. Typically, this involves the construction of a descriptor, which is both computationally expensive and resource-intensive. Methods and devices are described that match interest points without the construction of conventional descriptors and that permit the use of spatial coherency information to increase the accuracy of the match.

Abstract: Systems, methods and computer program products on storage devices for shape clustering and applications in processing various documents, including an output of an optical character recognition (OCR) process. The output of an OCR process is classified into a plurality of clusters of clip images and a representative image for each cluster is generated to identify clusters whose clip images were incorrectly assigned character codes by the OCR process.

Abstract: A method and apparatus for detecting an object are provided. The method calculates a feature value based on features extracted from an input image by using a classifier of an ith stage, compares the calculated feature value with a first threshold value of the ith stage, compares the feature value with a second threshold value of the ith stage according to a result of the comparison between the feature value and the first threshold value of the ith stage, and jumps to a classifier of an i+2th stage according to a result of the comparison between the feature value and the second threshold value of the ith stage. By doing so, the method can avoid repeated calculations and can rapidly detect the object in the input image.

Abstract: Recognition target area images are sequentially clipped out from an input image. Each of the clipped-out recognition target area images is recognized as or not as an image related to an object by referring to each of a plurality of dictionary data items stored in advance for recognizing the object. Based on the recognition result for a recognition target area image, the order in which each of the plurality of dictionary data items is referred to for a partial image in the neighborhood of the recognition target area image is determined. Thus, the time required for recognizing the object is reduced.

Abstract: The invention is related to encoding an image block of an image using a partitioned block transform. The inventors recognized that applying a texture-pattern associated invertible mapping to the pixels of a first partition, said first partition resulting from partitioning said image block according to a current texture pattern with which said texture-pattern associated invertible mapping is associated, allows for limiting the maximum number of required first 1-D transforms to not exceeding a number of columns in the image block as well as limiting the maximum number of required second 1-D transforms to not exceeding a number of rows in the image block, also. Achieving limitation of maximum required 1-D transforms enables more efficient implementation on hardware and improves encoding performance but also allows for further partitions according to texture patterns which comprise at least one of multiple strips, texture patterns with highly unsymmetrical pixel distribution and non-directional texture patterns.

Abstract: A processing system, such as typically a CPU, is used for converting a digital signal organized in pixels, such as a video signal, between a first format and a second multiple-description format. The system comprises at least one input register and at least one output register, and is configured via instructions, that can be constituted at least in part by instructions of a SIMD type, so as to: order the pixels of the signal to be converted in a set of input registers; and take selectively the pixels from the aforesaid set of input registers and place them in an orderly way in at least one output register.

Abstract: A picture encoding apparatus divides an input picture into a plurality of regions and produces quantized transform coefficients of one of the regions. A zero/non-zero coefficient information encoding unit included in the picture encoding apparatus encodes information representing the respective quantized transform coefficients of the one region as either a zero coefficient or a non-zero coefficient. A non-zero coefficient encoding unit included in the picture encoding apparatus encodes non-zero quantized transform coefficient included among the quantized transform coefficients of the one region. The non-zero coefficient encoding unit is configured to select, from a probability model composed of a plurality of estimated probabilities, an estimated probability used to encode an absolute value of a next non-zero quantized transform coefficient of the one region.

Abstract: Compressed sensing can be mapped to a more general set of problems in computer graphics and computer imaging. Representation of a rendered scene in the formulation y=A{circumflex over (x)} produces higher-quality rendering with less samples than previous approaches. A filter formulation ? makes point samples compatible with wavelet and therefore allows reconstruction of 2-D images from a set of measured pixels (point samples).

Abstract: The present invention facilitates efficient and effective detection of pixel alteration. In one embodiment a pixel alteration analysis system includes a difference summing multiple engine component and a control component. The difference summing multiple engine component determines the sum of differences between pixel values in a plurality of pixels. The control component determines an indication of motion based upon said relationship of said pixels in said plurality of pixels. In one exemplary implementation, the difference in values corresponds to a relationship between values of pixels in a block of pixels at different frames. The number and configuration of pixels in a block partition can be flexibly changed.

Abstract: The present invention relates to a method for generating a thumbnail image for a video image, and more particularly, to a method for generating a thumbnail image for a video image that includes directly computing a DC coefficient of a prediction block for the video block constituting a video image from a prediction reference pixel of the video block of a spatial domain, and computing a DC coefficient of the video block from the computed DC coefficient of the prediction block and from a DC coefficient of an residual block for the video block. The method for generating a thumbnail image according to the present invention directly computes a DC coefficient of the video block from the DC coefficient of the residual block for the video block and the DC coefficient of the prediction block for the video block, thus generating a thumbnail image for a video image of the H.

Abstract: Several quality-aware transcoding systems and methods are described, in which the impact of both quality factor (QF) and scaling parameter choices on the quality of transcoded images are considered in combination. A basic transcoding system is enhanced by the addition of a quality prediction look-up table, and a method of generating such a table is also shown.

Abstract: Systems, methods, and processor executable code for high quality wide-range multi-layer image compression of a sequence of video images. A non-transient electronic storage media stores the processor executable code configured and is capable of causing one or more processors to compress a sequence of digitized video images. The method includes generating a hierarchy of processed images from a digitized video image, determining a plurality of regions within each processed image, each region being selected based on lossless coding efficiency; and applying a lossless variable-length coding independently to each such region.

Abstract: A first aspect of the invention relates to a method for creating a binary mask image from an a inputted digital image of a scanned document, comprising the steps of creating a binarized image by binarizing the inputted digital image, detecting first text regions representing light text on a dark background, and inverting the first text regions, such that the inverted first text regions are interpretable in the same way as dark text on a light background. A second aspect of the invention relates to a method for comparing in a binary image a first pixel blob with a second pixel blob to determine whether they represent matching symbols, comprising the steps of detecting a line in one blob not present in the other and/or determining if one of the blobs represents an italicized symbol where the other does not.

Abstract: A high dynamic range (HDR) video can be compressed using inter-frame or intra-frame compression. The compression results in multiple encoded macroblocks and associated residual images. The residual images can be lossy compressed by mapping floating point image data values of the residual image from a light linear space to a perceptually linear space using a first non-linear mapping function. A value in the light linear space is proportionate to the power of a light source, and a value in the perceptually linear space is proportionate to a visual perceived brightness. Floating point discrete cosine transform (DCT) frequency coefficients of the floating point image data values of the residual image are determined. The floating point DCT frequency coefficients are quantized. The quantized floating point DCT frequency coefficients are compressed. The compression of the quantized floating point DCT frequency coefficients is lossless. The compressed quantized floating point DCT frequency coefficients are stored.

Abstract: An image reproduction apparatus decompresses and outputs compressed data, and includes: a reproduction unit which reads, per predetermined unit of processing, the compressed data as unit compressed data from a recording medium; a decompression unit which decompresses the unit compressed data, so as to generate unit decompressed data; a display processing unit which outputs decompressed data including the unit decompressed data; an error management unit which detects, per unit compressed data, an error caused in either the reproduction unit or the decompression unit; and a control unit which determines whether or not to output the decompressed data when the error is detected, and when it is determined to output the decompressed data, the control unit complements, with implement image data, unit decompressed data corresponding to the unit compressed data in which the error has been detected, and the display processing unit outputs decompressed data including the complement image data.

Abstract: A computer-implemented method for identifying the edges of web media transported on a movable transport surface includes sensing, using a linear array sensor positioned along a process path of a web, the web media and the movable transport surface to obtain image data representative of variations in optical textural properties of the web media and variations in optical textural properties of the movable transport surface, wherein the variations in the optical textural properties of the movable transport surface are different from the variations in the optical textural properties of the web media; and processing the image data to determine differences between the variations in the optical textural properties of the web media and the variations in the optical textural properties of the movable transport surface to identify an edge of the web media.

Abstract: An image filter and method of smoothing pixel values. A pixel value of a pixel to be smoothed is compared with block average pixel values of each of a plurality of pixel blocks. The pixel to be smoothed may be downstream from each of the pixel blocks. If the difference between the pixel value and each of the block average pixel values is less than a corresponding sigma threshold value for each of the pixel blocks, a first sigma filter utilizing the block average pixel values is applied to the pixel to be smoothed. If the difference between the pixel value and any one of the block average pixel values is not less than a corresponding sigma threshold value, a second sigma filter is applied to the pixel to be smoothed.

Abstract: The system and method of use are provided for correcting digital images based on the notions of local black points. The system and method are based on determining local black points in a digital image and correcting the intensities of nearby pixels so as to remove bias in the image introduced by atmospheric conditions. By sampling only localized land imagery the claimed method computes black points that are more robust against the localized effects of atmospheric and land reflection effects than black points computed from wider areas. The result of the method is that images corrected by this method are robust to atmospheric conditions that vary with time and viewing angle.

Abstract: Systems and methods for generating an image determine scene information based on a first image of a scene, the first image including an image of a subject at a first position in the scene, and the first image information including a first field of view of the first image and a first capture location where the first image was captured, acquire a second image of the scene from a repository storing a plurality of images based on the scene information, the second image having a second field of view similar to the first field of view and a second capture location similar to the first capture location, adjust light parameters of the image of the subject based on the light parameters of the second image, and generate a combined image based on the second image and the image of the subject, the combined image including at least part of the second image, and the adjusted image of the subject at a position in the scene similar to the first position in the scene.

Abstract: A video processing apparatus and method is provided. The video processing apparatus divides video data and then processes a current divided area of the divided video data by referring to pixels in an adjacent divided area while processing the current divided area, thereby minimizing artifacts generation along a boundary between divided areas when the processed divided areas are subsequently merged.

Abstract: Geometric method of transforming a first two-dimensional image into a second two-dimensional image through an image processing applied to the first images or to the second image. In this method, one of said first and second images is divided into several surfaces, each of the surfaces of the divided image is transformed by a bilinear transformation specific to each surface, and the transformed surfaces are grouped together.

Abstract: Systems, methods, and computer-readable storage media for editing the frequency content of an image may provide an intuitive interface for examining and/or modifying the frequency content. The methods may include accessing image data, performing a wavelet transform of the image data (or another MRA technique) to produce a time-frequency representation (TFR) of the image representing frequency content in multiple frequency bands, and displaying an indication of the frequency content of the image by displaying a sub-image of the TFR or numerical data representing the frequency content at selected pixels. In response to receiving input specifying a desired frequency content modification, the methods may include performing a Fourier transform of the image data to produce frequency content data, modifying the frequency content data, and performing an inverse transformation of the modified data to produce modified image data. The modification may be applied globally or to a selected portion of the image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for graphical overlay object translation. One of the methods includes receiving a first plurality of first feature points, each first feature point being associated with a plurality of feature descriptors and a respective location on the first digital image. The method includes receiving a second plurality of second feature points, each second feature point being associated with a plurality of feature descriptors and a respective location on the second digital image. The method includes determining the translation offset for the second digital image from the first digital image by matching locations of the first feature points with locations of the second feature points without regard to the feature descriptors.

Abstract: A method and system for improving picture quality of color images by combing the content of a plurality of frames of the same subject; comprising: at least one processor; the at least one processor comprising a memory for storing a plurality of frames of a subject; the at least one processor operating to combine the content of plurality of frames of the subject into a combined color image by performing: a process in which at least two multicolored frames are converted to monochromatic predetermined color frames; a gross shift process in which the gross shift translation of one monochromatic predetermined color frame is determined relative to a reference monochromatic predetermined color frame; a subpixel shift process utilizing a correlation method to determine the translational and/or rotational differences of one monochromatic predetermined color frame to the reference monochromatic predetermined color frame to estimate sub-pixel shifts and/or rotations between the frames; and an error reduction process to

Abstract: A diagnosis image generation apparatus is provided. The diagnosis image generation apparatus includes a low resolution image signal synthesis unit configured to synthesize each of a plurality of low resolution image signals by using a signal reflected from a subject, a weight calculation unit configured to calculate a weight, which is used to synthesize a high resolution image signal, with a signal value which corresponds to each of positions of some pixels among a plurality of signal values corresponding to respective positions of a plurality of pixels forming each of the synthesized low resolution image signals, and a high resolution image signal synthesis unit configured to synthesize the high resolution image signal by applying the calculated weight to each of the low resolution image signals.

Abstract: A system and method for mapping interpersonal relationships, the method including processing a multiplicity of images and contextual information relating thereto including creating and prioritizing a list of a plurality of candidate persons having at least a predetermined relationship with at least one person connected to at least one image, using multi-dimensional information including visually sensible information in the multiplicity of images and contextual information relating thereto and searching the list of a plurality of candidate persons based at least in part on the prioritizing to select at least one of the candidate persons as having at least a predetermined relationship with the at least one person.

Abstract: An image is displayed on a touch screen. A user's underline gesture on the displayed image is detected. The area of the image touched by the underline gesture and a surrounding region approximate to the touched area are identified. Skew for text in the surrounding region is determined and compensated. A text region including the text is identified in the surrounding region and cropped from the image. The cropped image is transmitted to an optical character recognition (OCR) engine, which processes the cropped image and returns OCR'ed text. The OCR'ed text is outputted.