Abstract:
A multi-lens based capturing apparatus and method are provided. The capturing apparatus includes a lens array including lenses and a sensor including sensing pixels, wherein at least a portion of sensing pixels in the sensor may generate sensing information based on light entering through different lenses in the lens array, and light incident on each sensing pixel, among the portion of the plurality of sensing pixels may correspond to different combinations of viewpoints.
Abstract:
A method and apparatus for correcting an image error in a naked-eye three-dimensional (3D) display may include controlling a flat-panel display displaying a stripe image, calculating a raster parameter of the naked-eye 3D display based on a captured stripe image, and correcting a stereoscopic image displayed on the naked-eye 3D display based on the calculated raster parameter, wherein the naked-eye 3D display includes the flat-panel display and the raster.
Abstract:
A method and apparatus for matching stereo images including calculating a data cost of at least one image, calculating a smoothness cost of the image, and matching pixels among pixels of a plurality of images based on the data cost and the smoothness cost.
Abstract:
Provided are a biometric image processing method and an apparatus including the same. The biometric image processing method includes acquiring a biometric image from a biometric sensor, evaluating image quality of the biometric image by calculating an evaluation score with respect to each of a plurality of evaluation items corresponding to the biometric image, determining at least one of an improvement algorithm corresponding to an evaluation result and a weight of the improvement algorithm by using an image quality improvement table including an improvement degree of image quality, and correcting the biometric image according to the at least one of the improvement algorithm and determined weight of the improvement algorithm.
Abstract:
An image processing apparatus and a method implemented by the image process apparatus generates a vertical disparity map through regression analysis, based on a difference between vertical coordinate values from feature correspondence information of left and right source images. A geometric difference through image warping is calibrated before depth information is restored through depth estimation. Thus, a process of optimizing a camera model may not have to be performed, and occurrence of black areas that may be caused by image rotation may be reduced.
Abstract:
A computing apparatus for providing a three-dimensional (3D) interactive user experience (UX) is provided. The computing apparatus may include an object position estimator configured to calculate first coordinates recognized by a user as a position of a first point of an object in a stereoscopic image. The computing apparatus may include a pointing determiner configured to determine whether the user points to the first point based on the first coordinates and second coordinates, the second coordinates representing a pointing position of the user.