Abstract: An eigenprojection matrix (#14) is generated by a projection computation (#12) using a local relationship from a studying image group (#10) including a pair of a high quality image and a low quality image to create a projection core tensor (#16) defining a correspondence between the low quality image and an intermediate eigenspace and a correspondence between the high quality image and the intermediate eigenspace. A first sub-core tensor is created (#24) from the projection core tensor based on a first setting, and an inputted low quality image (#20) is projected (#30) based on the eigenprojection matrix and the first sub-core tensor to calculate a coefficient vector in the intermediate eigenspace. The coefficient vector is projected (#34) based on a second sub-core tensor (#26) created by a second setting from the projection core tensor and based on the eigenprojection matrix to obtain a high quality image (#36).

Abstract: Disparity in a stereoscopic image is converted, according to features of a configuration element of an image that influences depth perception of a stereoscopic image. A disparity detecting unit 110 detects disparity from a left image L and right image R of an input image, and generates a disparity map dM. A disparity correction unit 150 corrects the disparity in the disparity map dM and generates a corrected disparity map dM?. A correction feature setting unit 130 sets the correction features in the event of performing disparity correction in the disparity correction unit 150. The image synthesizing unit 160 synthesizes the left image L and right image R of the stereoscopic image based on the corrected disparity map dM? and outputs the stereoscopic image made up of a left image L? and right image R? as an output image. Thus, a stereoscopic image having disparity according to the set correction features is output.

Abstract: A method for motion detection is provided that includes determining a first motion measure for a pixel based on differences between first neighboring pixels of the pixel, determining a detail measure for the pixel, wherein the detail measure is indicative of an amount of detail in second neighboring pixels of the pixel, adapting a first coring threshold and a first gain of a first transfer function based on the detail measure, and using the adapted first transfer function to map the first motion measure to a first motion parameter.

Abstract: Provided is a method for controlling an image processing apparatus for generating and outputting frames different from each other in frequency component from an input frame include, detecting motion of the input frame by comparing the input frame with a frame before or after the input frame in terms of time, storing the input frame in a frame memory, and reading the input frame by a plurality of times to convert a frame rate of the input frame, generating the frames different from each other in frequency component from the frame whose frame rate has been converted, outputting the generated frames if the detected input frame is determined to be a moving image, and outputting the frame whose frame rate has been converted if the input frame is determined to be a still image.

Abstract: In an image processing device and method, program, and recording medium of the present invention, high frequency components of a low quality image and a high quality image included in a studying image set are extracted, and an eigenprojection matrix and a projection core tensor of the high frequency components are generated in a studying step. In a restoration step, a first sub-core tensor and a second sub-core tensor are generated based on the eigenprojection matrix and the projection core tensor of the high frequency components, and a tensor projection process is applied to the high frequency components of an input image to generate a high quality image of the high frequency components. The high quality image of the high frequency components is added to an enlarged image obtained by enlarging the input image to the same size as an output image.

Abstract: An image processing method and a system for processing the same are provided. The image processing method includes the following steps. A first image having several first areas and a second image having several second areas are provided. Each first area has a first feature point having the largest or the smallest grey value in the first area. Each second area has a second feature point having the largest or the smallest grey value in the second area. A first relationship between the first feature points and a second relationship between the second feature points are created. The first and the second feature points are paired by a microprocessor according to the first and the second relationship.

Abstract: A tentative eigenprojection matrix (#12-a) is provisionally generated from a studying image group (#10) including a pair of a high quality image and a low quality image, and a tentative projection core tensor (#12-b) defining a correspondence between the low quality image and an intermediate eigenspace and a correspondence between the high quality image and the intermediate eigenspace is created. A first sub-core tensor is created from the tentative projection core tensor based on a first setting (#12-c), and the studying image group is projected based on the tentative eigenprojection matrix and the first sub-core tensor (#15-a) to calculate an intermediate eigenspace coefficient vector (#15-b).

Abstract: The invention relates to upscaling of images such as upscaling of video images from standard definition to high definition. An input image is upscaled to a resolution enhanced image (207) by weighting pixel values in the input image depending on a match metric combining two match metrics. A first image generator (103) generates a blurred version of the input image and a second image generator (103) generates an upscaled interpolated version. The first metric is generated by comparing pixel sets of the blurred image and the upscaled interpolated image. A second metric is generated by comparing pixel sets of the input image and already synthesized pixel values of the resolution enhanced image (207). For each location in a search area, a resolution enhancement processor (107) generates the combined match metric and uses this to weigh the pixel value of that location when generating the unknown pixel value of the resolution enhanced image (207).

Abstract: A method and apparatus for improving stability of histogram correlation based image and video processing algorithms. The method includes computing a histogram for target signal and reference signal for generating a target histogram and a reference histogram, performing low pass filtering of the input signal and the reference signal and producing smoothed histograms, and performing correlation on the smoothed histograms for improving stability of histogram correlation.

Abstract: The image processing device includes: a storage unit (211) holding intensity gradient vectors Vr, position vectors Rr, and voting vectors Ur of a reference image; an intensity gradient vector calculation unit (212) which calculates intensity gradient vectors Vs of a search image; and a position determination unit (213) which determines a position of the reference image in the search image. The position determination unit (213) includes: a sampling unit (214) which thins out a part of the intensity gradient vectors Vs and/or the voting vectors Ur; an origin position estimation unit (215) which locates voting vectors Ur at each starting position of intensity gradient vectors Vs and estimates ending positions of the voting vectors Ur as candidate points; and a re-verification unit (216) which locates the position vectors Rr at each candidate point and determines a candidate point having most intensity gradient vectors Vs at ending positions of the position vectors Rr as an origin position.

Abstract: A subject tracking apparatus which performs subject tracking based on the degree of correlation between a reference image and an input image is disclosed. The degree of correlation between each of a plurality of reference images based on images input at different times, and the input image is obtained. If the maximum degree of correlation between a reference image based on a first input image among the plurality of reference images and the input image is equal to or higher than a threshold, a region with a maximum degree of correlation with a first reference image is determined as a subject region. Otherwise, a region with a maximum degree of correlation with a reference image based on an image input later than the first input image is determined as a subject region.

Abstract: The method operates by estimating the differential movement of the scene picked up by a vertically-oriented camera. Estimation includes periodically and continuously updating a multiresolution representation of the pyramid of images type modeling a given picked-up image of the scene at different, successively-decreasing resolutions. For each new picked-up image, an iterative algorithm of the optical flow type is applied to said representation. The method also provides responding to the data produced by the optical-flow algorithm to obtain at least one texturing parameter representative of the level of microcontrasts in the picked-up scene and obtaining an approximation of the speed, to which parameters a battery of predetermined criteria are subsequently applied. If the battery of criteria is satisfied, then the system switches from the optical-flow algorithm to an algorithm of the corner detector type.

Abstract: An eye tracker device (200) comprises a diffractive beam expander (207) to provide two substantially collimated illuminating light beams (B11, B12). The collimated light beams (B11, B12) provide two reflection spots (G1, G2) appearing in the image of the eye. The gaze direction (GZD) is calculated from the positions of the reflection spots (G1, G2) with respect to the pupil (P) of the eye (E1). The two illuminating beams (B11, B12) are provided by splitting an infrared laser beam (B4) into two in-coupled beams (B5, B6), which propagate in different directions in the substrate (7) of the beams expander. The in-coupled beams (B5, B6) are expanded and their light is subsequently coupled out of the substrate (7) by an out-coupling grating (230) to illuminate the eye (E1). The same substrate (7) may also be used to implement a virtual display device (100) for displaying virtual images to said eye (E1).

Abstract: A method controls a projection of a projector. The method predetermines hand gestures, and assigns an operation function of an input device to each of the predetermined hand gestures. When an electronic file is projected onto a screen, the projector receives an image of a speaker captured by an image-capturing device connected to the projector. The projector identifies whether a hand gesture of the speaker matches one of the predetermined hand gestures. If the hand gesture matches one of the hand gestures, the projector may execute a corresponding assigned operation function.

Abstract: For monitoring an image transformation such as aspect ratio conversion, an image feature is defined by identifying a position in the image having a local spatial maximum value and then identifying four other positions in the image having local spatial minimum values such that the four minimum value positions surround the position of the maximum, a first pair of the minimums lie on a first line passing through maximum and a second pair of the minimums lie on a second line passing through the maximum.