Abstract: A method and system for matching an unknown facial image of an individual with an image of a celebrity using facial recognition techniques and human perception is disclosed herein. The invention provides a internet hosted system to find, compare, contrast and identify similar characteristics among two or more individuals using a digital camera, cellular telephone camera, wireless device for the purpose of returning information regarding similar faces to the user The system features classification of unknown facial images from a variety of internet accessible sources, including mobile phones, wireless camera-enabled devices, images obtained from digital cameras or scanners that are uploaded from PCs, third-party applications and databases. Once classified, the matching person's name, image and associated meta-data is sent back to the user. The method and system uses human perception techniques to weight the feature vectors.

Abstract: Joint video deblurring and stabilization techniques are described. In one or more implementations, a deblurring and stabilization module is configured to jointly deblur and stabilize a video by grouping video frames into spatial-neighboring frame clusters, and building local mesh homographies for video frames in each spatial-neighboring frame cluster.

Abstract: An image processing apparatus includes a receiving unit, a specifying unit, a controlling unit, and an outputting unit. The receiving unit receives image data. The specifying unit specifies a correction amount of the image data for keystone correction processing. The controlling unit controls, based on the correction amount specified by the specifying unit, the keystone correction processing, filter processing for reducing a predetermined high frequency component, and edge enhancement processing. The outputting unit outputs processed image data which is processed based on the controlling by the controlling unit.

Abstract: Systems and methods for correction of user identified artifacts in light field images are disclosed. One embodiment of the invention is a method for correcting artifacts in a light field image rendered from a light field obtained by capturing a set of images from different viewpoints and initial depth estimates for pixels within the light field using a processor configured by an image processing application, where the method includes: receiving a user input indicating the location of an artifact within said light field image; selecting a region of the light field image containing the indicated artifact; generating updated depth estimates for pixels within the selected region; and re-rendering at least a portion of the light field image using the updated depth estimates for the pixels within the selected region.

Abstract: A system for determining a high resolution output image that includes receiving a low resolution image and determining an intermediate high resolution image. The system detects semantic features based upon the input image and selects corresponding semantic components from a database based upon the detected semantic features. The first intermediate high resolution image is modified based upon information from the corresponding semantic components to determine the high resolution output image.

Abstract: Methods and systems are provided to reduce noise in thermal images. In one example, a method includes receiving an image frame comprising a plurality of pixels arranged in a plurality of rows and columns. The pixels comprise thermal image data associated with a scene and noise introduced by an infrared imaging device. The image frame may be processed to determine a plurality of column correction terms, each associated with a corresponding one of the columns and determined based on relative relationships between the pixels of the corresponding column and the pixels of a neighborhood of columns. In another example, the image frame may be processed to determine a plurality of non-uniformity correction terms, each associated with a corresponding one of the pixels and determined based on relative relationships between the corresponding one of the pixels and associated neighborhood pixels within a selected distance.

Abstract: Hint-based spot healing techniques are described. In one or more implementations, techniques are described in which a user may provide input as a hint used to automatically determine features in an image to process for application of a selected image editing operation. The user may select a feature in an image exposed for editing using touch input or another input technique. The image is then processed based on the hint to identify additional features that match a spot pattern of the user selected feature. A visual representation of feature set that includes the selected feature and the additional features is presented and an option to designate (e.g., de-select or select) features on an individual basis is provided to refine the feature set. The image editing operation is then applied to the designated features in the feature set.

Abstract: An image processing device includes an extraction unit, a judgment unit, a restoration unit and a specification unit. The extraction unit specifies a first same-color area having a color similar to a color of a pointer in a pre-pointed image of a subject not overlapped by the pointer to extract a pointer portion from a being-pointed image of the subject overlapped by the pointer on the basis of the first same-color area. The restoration unit restores a dividing portion of the pointer portion using a surrounding image of the dividing portion when the judgment unit judges that the pointer portion is divided. The specification unit specifies a pointed position pointed with the pointer on the subject on the basis of a shape of the restored pointer portion.

Abstract: Provided are an input device and an image processing method thereof. The image processing method of the input device having a scan function includes acquiring a first image frame and a second image frame to detect coordinates of the acquired first image frame and coordinates of the acquired second image frame; dividing an overlap region between the first image frame and the second image frame into a plurality of sub overlap regions by using the detected coordinates of the first and second image frames; dividing each of the sub overlap regions into unit regions; setting a reference feature point of a plurality of feature points within the divided unit regions; and extracting corresponding points by using the set reference feature point.

Abstract: An image processing apparatus is an image processing apparatus which derives an angle of inclination of an image and includes: an edge angle calculation unit which calculates a plurality of edge angles corresponding to a plurality of pixels in the image by calculating, in each of the pixels, an edge angle that is an angle of an edge; a use angle identification unit which identifies one or more use angles that are each the edge angle and are each a candidate for the angle of inclination, using the edge angles and a plurality of depth values that correspond to the pixels and each indicate a depth of a corresponding one of the pixels; and an inclination angle derivation unit which derives the angle of inclination from the one or more use angles.

Abstract: An image processing apparatus which enables to suppress coloring in an image after image recovery processing, and a control method for the image processing apparatus are disclosed. After the chromatic difference of magnification of an optical imaging system is corrected, a first value relating to coloring is obtained before application of an image recovery filter. Then, an image recovery filter which, preferably, does not correct a chromatic difference of magnification and is based on a function indicating the aberrations of the optical imaging system is applied. A second value associated with coloring is obtained from the image after application of the image recovery filter. According to the difference between the first and second values obtained before and after application of the image recovery filter respectively, pixel value correction for correcting coloring is performed.

Abstract: An apparatus for mapping a gaze point of a subject on a scene image to a gaze point in a reference image, wherein said scene image and said reference image have been taken by a camera from a different position, said apparatus comprising: A module for executing a feature detection algorithm on said reference image to identify a plurality of characteristic features and their locations in said reference image; a module for executing said feature detection algorithm on said scene image to re-identify said plurality of characteristic features and their locations in said scene image; a module for determining a point transfer mapping that transforms point positions between said scene image and said reference image based on the locations of said plurality of characteristic features detected in said reference image and said scene image; a module for using said point transfer mapping to map a gaze point which has been determined in said scene image to its corresponding point in said reference image.

Abstract: Apparatuses and methods for adjusting coefficients for use in video encoding are described. An example apparatus may include an encoder that may be configured to receive transform coefficients and adjust selected ones of the transform coefficients (e.g. reset the selected ones to zero) based on a comparison with a threshold. The adjusted coefficients may then be quantized, which may result in effectively increasing a QP range of the encoder.

Abstract: A digital camera system for super resolution image processing is provided. The digital camera system includes a resolution enhancement module configured to receive at least a portion of an image, to increase the resolution of the received image, and to output a resolution enhanced image and an edge extraction module configured to receive the resolution enhanced image, to extract at least one edge of the resolution enhanced image, and to output the extracted at least one edge of the resolution enhanced image, the at least one edge being a set of contiguous pixels where an abrupt change in pixel values occur. The digital camera system also includes an edge enhancement module configured to receive the resolution enhanced image and the extracted at least one edge, and to combine the extracted at least one edge or a derivation of the extracted at least one edge with the resolution enhanced image.

Abstract: The image coding method includes: determining a context for a current block to be processed, from among a plurality of contexts; and performing arithmetic coding on the control parameter for the current block to generate a bitstream corresponding to the current block, wherein in the determining: the context is determined under a condition that control parameters of neighboring blocks of the current block are used, when the signal type is a first type, the neighboring blocks being a left block and an upper block of the current block; and the context is determined under a condition that the control parameter of the upper block is not used, when the signal type is a second type, and the second type is one of “mvd_l0” and “mvd_l1”.

Abstract: Feature extraction of image data using feature extraction modules. The feature extraction modules may be provided in an architecture that allows for modular, decoupled generation and/or operation of the feature extraction modules to generate feature data corresponding to image data. In this regard, the feature extraction modules may communicate with a file system storing image data and feature data by way of a common interface format. Accordingly, regardless of the nature of the execution of the feature extraction module, each feature extraction module may be communicative by way of the common interface format, thereby providing a modular approach that is highly scalable, flexible, and adaptive.

Abstract: The present invention provides an apparatus for processing image data obtained by reading a document and a background image outside the document, and method of controlling the apparatus. The apparatus determines a degree of similarity between a color of the background image and a color of a marginal region of the document from the image data, sets a region extraction parameter based on the determined degree of similarity, and determines a document region by using the region extraction parameter from the image data.

Abstract: An apparatus and method are provided for performing detail enhancement. The apparatus includes an edge detector that detects an edge pixel from contents based on a luminance component of the contents, a histogram analyzer that generates at least one histogram with respect to the edge pixel and determines a gain variable value of the edge pixel based on the at least one histogram, and a gain regulator that determines a gain corresponding to the gain variable value of the edge pixel.

Abstract: An image processing apparatus, which correctly extracts specular reflected light components of reflected light from an object, and accurately estimates a light source color, is provided. The image processing apparatus calculates a pixel value difference distribution by repeating, for respective pixels, to calculate pixel value differences between a pixel of interest and adjacent pixels in an input image and to calculate similarities between pixel value differences. A light source estimation unit estimates a color of a light source which illuminates an object in the input image based on the calculated distribution.

Abstract: Techniques are disclosed herein that enable digital images to be segmented based on a user's semantic input. In other words, given an input image of a person walking a dog adjacent to a tree, a user can simply provide the semantic input “dog” and the system will segment the dog from the other elements in the image. If the user provides other semantic input, such as “person” or “tree”, the system will segment the person or the tree, respectively, from the same image. Using semantic input advantageously eliminates any need for a user to directly interact with the input image through a tedious process of painting brush strokes, tracing boundaries, clicking target points, and/or drawing bounding boxes. Thus semantic input represents an easier and more intuitive way for users to interact with an image segmentation interface, thereby enabling novice users to take advantage of advanced image segmentation techniques.